If you've received it, then you either subscribed or someone forwarded it to you. If the latter is the case, subscribe by pressing this button:

Subscribe now

This issue is sponsored by Intelligencia AI

Webinar Invite: How Causal Inference Can Increase the Probability of Success in Clinical Trials

The mantra “Correlation does not equal causation” is well known. However, causal inference, a new set of statistical techniques, can identify causal relationships and even derive experimental results and counterfactuals from historical data. 

In this webinar, the expert speakers from GSK and Intelligencia AI will introduce causal inference and apply it to ten years of oncological clinical trial data, seeking opportunities to optimize trial design decision-making. 

What if there was a proven process to identify trade-offs that could save precious resources when designing trials with the greatest probability of success?

Speakers will present results from studying patient selection biomarkers, which focus a trial on a subset of patients, possibly increasing the trial’s PoS. Conversely, this focus can reduce the patient population for which regulators approve a drug. To help companies consider this trade-off, the analysis provides unbiased, precise estimates of how much the focus increases a trial’s PoS. This analysis can help identify opportunities for underutilized biomarkers that can significantly impact PoS or where they are overutilized and their use offers little benefit in terms of PoS, unnecessarily reducing the target population.

The findings shared will empower sponsors to understand the impact of their choices better, de-risk pipelines and make more informed decisions regarding their clinical development strategies.

Attendees will learn: 

• How to use causal inference to understand the impact of clinical design decisions, specifically focusing on biomarkers inclusion criterion and clinical trial success

• The importance of combining quality data with the proper methodologies for more informed decisions

• How to apply state-of-the-art methodologies to clinical trials to uncover underlying causal relationships that can optimize decision-making

• The correlation between biomarkers and the probability of technical and regulatory success

Register for this webinar today to learn how causal inference can revolutionize clinical trial design decision-making.

Now, let’s get to this week’s topic!

Insights from ASCO 2024: What AI-Driven PTRS Assessments Unveil

(This guest post is authored by: Andreas Dimakakos, PhD, MBA, Director of Scientific Insights at Intelligencia AI and Elena Hilario Martinez, MSc, Customer Success Associate at Intelligencia AI).

The American Society of Clinical Oncology (ASCO) Annual Meeting ranks as one of the largest and most impactful oncology conferences. The content published during the annual meeting can change established practices, and many of the trends identified reflect the current or future industry landscape in oncology. 

In this blog, we’ll showcase trends from ASCO 2023 vs. 2024, highlight our time-stamped pre- and post-ASCO predictions, and discuss the business implications this data and analysis have on de-risking clinical development and augmenting decision-making. This is particularly relevant for professionals responsible for identifying in- and out-licensing opportunities, assessing the acquisition potential and driving portfolio strategy in pharmaceutical companies.

A Comparative Analysis: ASCO 2023 vs 2024

Data always has a story to tell, and we can learn a lot from comparing data year over year, identifying trends and gathering actionable insights. We ran a comparative analysis between ASCO 2023 and ASCO 2024 abstracts. 

Here are some of the inferred observations. 

• Based on the number of high-impact abstracts, different indications pulled the majority of the conference’s interest. At ASCO 2024, the focus on bladder, liver and prostate cancer significantly increased. On the other hand, the focus on myeloma, renal and colorectal cancer decreased compared to 2023.

• Lung cancer, the leading cause of cancer-related deaths worldwide, retained the highest indication-specific focus. 

• Bladder, liver and prostate cancer only had a limited number of approvals in the past five years, which signifies an unmet need and justifies an increased industry interest. 

• Myeloma, renal cancer and colorectal cancer, on the other hand, have received numerous approvals (21 for myeloma, 9 for renal and 10 for colorectal since 2020) in the past few years, so market saturation is higher.

• Going deeper into the data, specifically on the targets of the assets described in the abstracts, interest in Kirsten rat sarcoma virus (KRAS), vascular endothelial growth factor (VEGF) and hepatocyte growth factor (HGF) rose significantly in ASCO 2024.

  • Due to some recent approvals, KRAS has proven to be a very promising target in non-small cell lung cancer (NSCLC). Therefore, the industry has shifted its focus towards producing more KRAS-targeting drugs. 

  • On the other hand, the epidermal growth factor receptor (EGFR) showed a significant reduction in focus. EGFR has mostly been targeted in NSCLC, and in the past few years, interest has shifted towards other mutations, like ALK, TP53 or the previously mentioned KRAS.

• The heat map below (Figure 3) demonstrates that antibody-drug conjugates (ADCs) have been at the cutting edge of oncology research for the past few years. They gained significant traction between 2023 and 2024 (a 10% increase in Phase 3 ADC-focused trials) when several high-profile acquisitions of ADC-focused companies occurred. Conversely, there was a significant drop in monoclonal antibody (mAb) focus, showing signs of saturation and the start of a paradigm shift towards more targeted therapies.

ASCO Predictions at the Program Level

Identifying industry trends and keeping your finger on the pulse is undoubtedly a requirement for decision-making, but on its own, it leaves significant room for uncertainty and interpretation. It might be clear that a specific modality or target is trending. However, there will still be questions about the ideal indication, trial phase(s) and actual trial design. Information provided at the clinical program level significantly reduces that uncertainty. 

By our definition, a program (also known as clinical pipeline or drug pipeline) is the clinical development of a drug (or a set of drugs in case of combination therapies) by a pharmaceutical company (alone or in collaboration with other partners) for an indication. A program consists of a set of clinical trials with the ultimate goal of marketing approval. Each program has unique and specific parameters that can justify a separate regulatory approval. Specifically, the definition of a clinical program is one of unique drug(s), drug dosage, mode of administration, adjuvant state, indication, sponsor, disease severity (e.g., stage of disease), line of treatment and biomarker information used as inclusion criteria.

Intelligencia AI’s solutions aim to reduce uncertainty and de-risk decision-making in pharma and financial market industries by providing an accurate probability of technical and regulatory success (PTRS) for each active clinical program in the entire oncology therapeutic area. The predictive performance of our algorithms in forecasting FDA approvals for Phase 2 oncology programs boasts a prospectively validated accuracy of 83%*and 90% when measured retrospectively.

Leave a comment

To showcase the accuracy and robustness of our leading AI-driven PTRS assessments, we identified high-impact ASCO 2024 abstracts, measured the PTRS before and immediately after abstract publication, and time-stamped our predictions. 

Let’s take the IBI343 clinical program in pancreatic cancer as an example. Before ASCO 2024, it was in the top PTRS quartile compared to peer programs (same phase and indication); the announcement of positive outcomes (40% ORR) boosted its PTRS by 37%. 

Similarly, in the case of Abemaciclib in human epidermal growth factor receptor 2 negative (HER2-) breast cancer, the announcement of positive outcomes (primary endpoint met with PFS of 5.6 months) boosted its PTRS by 24%

Our PTRS algorithm’s accurate prediction of positive outcomes presented at ASCO 2024 highlights its reliability and precision. The high initial PTRS scores for these programs, even before the conference, demonstrate the algorithm’s strong predictive capability. Plus, the post-ASCO increase in PTRS scores for these programs confirms the algorithm’s sensitivity and ability to provide timely updates. This level of precision is crucial for high-stakes decisions such as go/no-go determinations, investment choices, and acquisition strategies. 

The sponsor’s portfolio strategists could use this information to prioritize funding for this program. In the case of a positive prediction, this might include starting to prepare for subsequent trial(s) early to gain a significant time-to-market advantage. In the case of negative predictions, they might discontinue the program as early as possible and divert funds to more promising assets in the pipeline.

A Look at Our Data and Methodology  

Two different datasets were leveraged for the analysis. The first used in the comparative analysis captured the entirety of ASCO abstracts corresponding to industry-led, interventional, FDA-track trials. For the second data set for the PTRS analysis, only Late Breaking Abstracts (LBAs) and those that drew the most attention by being showcased in specific ASCO sessions or pharma news sources were included. As per ASCO, LBAs include original research studies that highlight novel and high-impact research with practice-changing implications.

Our methodology provides a PTRS assessment for each clinical program. This significantly differs from other solution providers, who generally provide it at the drug-indication level. Clinical program-level assessments allow users to compare combinations, monotherapies, and even different administration modes in the same drug-indication. Combining that with Intelligencia AI’s capability to provide PTRS explainability and evolution over time results in an unprecedented level of data granularity that can be leveraged to de-risk decision-making further.

One limitation of the comparative analysis is that only two ASCO meetings were considered. However, the number of abstracts is significant enough to provide a reasonable level of reliability. As data from subsequent meetings are incorporated, the validity of the insights derived will further improve.

Share

Applicability of ASCO Insights and AI-Driven PTRS Assessments 

Our focus with this analysis differs from the traditional approach of simply highlighting relevant abstracts. We aim to generate valuable insights that optimize the pharma industry’s search and evaluation practices and portfolio strategy. 

Access to the abstracts is public information, but what sets us apart is how we capture and utilize the relevant data. Our dedicated team of therapeutic area experts meticulously analyzes and assesses the abstracts. Combined with our proprietary data-capturing tools, which harmonize the information using custom ontologies, timely updates and expert QA throughout, we deliver a level of insights that allows us to predict the success or failure of individual programs with high accuracy and distinguish us from the competition.

In addition to identifying specific programs that show the most promise, either for investment or competitive intelligence reasons, search and evaluation professionals and portfolio strategists can test their strategic approach and assumptions against this combination of insights and predictions. With our time-stamped PTRS assessments and detailed documentation of their evolution, organizations can compare past strategic decisions with the predictions available at that time. 

Understanding which trends and programs are currently most critical allows for the potential to pursue (or not) new clinical trials or continue (or end) current ones while maximizing the likelihood of successful transitions or approvals.

Conclusion

ASCO serves as an accurate representation of the industry’s direction. Due to the methodical process and deep granularity in our data, we’re uniquely positioned to help pharmaceutical companies dive even deeper. Combining that extensive knowledge with a robust, validated and time-stamped PTRS decreases the uncertainty indecision-making based on powerful AI and expertly curated clinical data. Using our approach, search and evaluation professionals can identify promising assets and test their strategies and decisions against past and current data. At the same time, portfolio strategists can prioritize the most promising assets among their pipelines.

**Based on Intelligencia AI predictions as of May 2022 for oncology programs with definite announcements in 2023.

If you've received it, then you either subscribed or someone forwarded it to you. If the latter is the case, subscribe by pressing this button:

Subscribe now

This newsletter is sponsored by Intelligencia AI, a provider of AI-powered solutions that support data-driven decision-making in drug development.

They lead the way in leveraging proprietary data, biomedical expertise and artificial intelligence (AI) with its patented technology to address significant challenges in the pharmaceutical industry. Its suite of AI-powered solutions delivers actionable insights crucial in mitigating risks and enhancing decision-making associated with drug development by providing an accurate, unbiased assessment of a drug's probability of success. Founded in 2017, Intelligencia AI is headquartered in New York, NY, with offices in Athens, Greece, and employs 110 individuals globally.

Visit intelligencia.ai to discover more and request a demo.

Now, let’s get to this week’s topic!

Many of us know Moore’s Law, which, in short, says that the number of computer transistors (a measure of performance) doubles every two years while prices fall. So, over time, we get more computing power at a lower cost.

Few people know the opposite of Moore’s Law—aptly named Eroom’s Law—which states that drug discovery is becoming slower and exponentially more expensive over time despite technological improvements.

Significant effort and resources are being invested in reversing that trend. Artificial intelligence (AI) is one of the latest tools deployed to reduce costs and increase drug discovery and development productivity.

The reason why the hopes for AI are high lies in the ability of machine learning (ML) algorithms to detect patterns and learn similar to the way humans learn, just much faster and paired with the ability to ingest vast amounts of data in a short period of time. This is a critical feature as the amount of data available continues to multiply rapidly.

AI is already used at many stages in drug discovery and development, including target identification, virtual screening and optimization of compounds, prediction of drug response on cells and the efficacy of drug-target interaction, and after approval for the reporting of adverse effects, to name but a few. 

AI is now also being applied to additional critical decision points in drug development, such as assessing the probability that a drug in development will successfully complete clinical trials and receive approval from regulatory authorities, known as the probability of technical and regulatory success (PTRS).

What is PTRS? How is it used, and why is it so important?

The probability of technical and regulatory success (PTRS) is a quantitative assessment of the inherent risk a drug development program bears. This metric estimates the likelihood that a pharmaceutical or biotech product will successfully meet the technical (scientific and clinical) and regulatory (health authorities) requirements from development to market approval.  

PTRS assessments of clinical programs occur at various stages during drug development to support decision-making at critical stage gates. In particular, encoding a program’s inherent risk into a PTRS score helps biopharma companies decide whether to continue investing in a drug candidate or discontinue development. Consequently, this informs asset prioritization at the portfolio level, long-range planning and revenue forecasting, and resource allocation decisions.

Both decisions bear risks. Investing in a drug that ultimately fails wastes significant resources that could have been invested in another candidate. The earlier drug developers know a drug is unlikely to succeed, the better. “Failing early” saves potentially 10s or even 100s of millions of dollars in development costs. In addition, failing early also avoids subjecting volunteers and patients to unnecessary treatments.

The flip side of this risk is discontinuing a drug that would have been approved, which results in a missed opportunity to bring a novel therapy to market and provide patients with more treatment options.

The more accurately the probability of success can be assessed, the more informed drug developers’ go/no go and resource allocation decisions become. This improves the efficiency of the drug development process by enabling companies to prioritize programs that are more likely to succeed. Greater efficiency contributes to reversing Eroom’s Law and ultimately benefiting patients.

What are some of the common approaches to calculating PTRS in pharma?

PTRS assessments in pharma are an integral part of pharmaceutical decision-making. Companies have long been trying to evaluate the chances a drug will make it to the market. While the actual process varies from company to company, industry benchmarks are traditionally used as the starting point, adjusted by experts in their respective fields, and supplemented with statistical analysis.

This PTRS approach comes with challenges and limitations:

• Industry benchmarks are inconsistent; some are based on just a few program characteristics, and others are based on many. Also, reliable, comprehensive industry-wide benchmarks are challenging to obtain and lack granularity.

• Adjustments to these benchmarks are not often based on objective data and can be liable to overestimate the probability of success. Human bias comes into play, both cognitive and motivational. 

• Statistical analysis, such as regression analysis of large data sets, is challenging and often static because new data cannot be incorporated into the analysis in a timely fashion, impacting the conclusion one can draw from the non-updated data sets.

Given these shortcomings, drug development has long needed a more objective, data-driven approach capable of analyzing vast amounts of data and seamlessly ingesting new data.

How can artificial intelligence (AI) improve PTRS assessments?

Large amounts of continuously updated data, complex interdependencies and subtle patterns are the conditions under which AI surpasses all other approaches.

AI, specifically the machine learning (ML) sub-discipline, has demonstrated that it can outperform drug developers and physicians when assessing the probability of success.

Machine Learning is defined as the use and development of computer systems that can learn and adapt without following explicit instructions by using algorithms and statistical models to analyze and draw inferences from patterns in data.

 ML has several significant advantages over traditional approaches:

• The algorithms can ingest broader and much larger sets of input data

• Sophisticated algorithms can identify inferences that analysts cannot spot by traditional means

• Data from hundreds of disparate sources – both structured and unstructured datasets – can be integrated into structured ontologies for a single source of truth.

These rich data sources and superior analyses yield objective probability assessments throughout the drug development pipeline.

An additional feature, namely AI explainability, addresses the concern around the “Black Box” nature of these algorithms. AI explainability provides insights into the relative contributions of various features (e.g., drug biology, clinical trial design, regulatory designations, and outcomes) to the final PTRS prediction. It makes it easier for the user to trust AI-generated probabilities of success.

Benefits of AI-driven probability assessments in clinical development

PTRS predictions have long been used to help make consequential decisions in drug development. 

AI is a powerful tool to augment current methods and base drug approval and phase transition predictions on a highly objective, data-driven foundation that aids informed decision-making at critical decision points. 

The accurate assessment of the likelihood of clinical trials to succeed helps:

• Improve the efficiency of drug development by giving companies an edge in identifying therapeutic programs that are more likely to succeed in clinical trials and should, therefore, be prioritized.

• Companies fail drugs with little chance of success early on, potentially saving 10s of millions of dollars and years of effort. These resources can be redirected to more promising drug candidates.

• Business development and licensing (BD&L) decisions allow acquirers to better establish the value of a drug candidate they are interested in buying and sellers to better understand the value of their assets. 

We need to leave the detrimental dynamics of Eroom’s Law behind and enter into a new era of efficient and more affordable drug development. Artificial intelligence is a powerful tool in this process. Applying it to support decision-making at critical points will benefit pharmaceutical and biotech companies and, most importantly, patients.

Share

Patented AI Platform Identifies Promising Early-Stage BioPharma Assets and Companies

Fierce competition. Thin pipelines. Patent cliffs. The stakes are sky-high for pharmaceutical companies and investors alike. With biotech firms often going public before generating revenue, valuations hinge on the potential for FDA approval of their assets. Herein lies the power of artificial intelligence (AI): by predicting the likelihood of success for these assets, we can uncover undervalued companies, offering a strategic edge not only to hedge funds and VCs but also to big pharma companies considering acquisitions. In this dynamic landscape, projected to see M&A activities reaching as high as $275B in 2024, the ability to discern and invest in promising biotech assets early is crucial.

At Intelligencia AI, our methodology offers a clear edge by delivering superior, real-time insights into the probability of success (PoS) for Phase 1 and Phase 2 assets gaining FDA approval. We used our predictions to create a virtual portfolio that generated 60% returns in one year and 3 out of the top 10 companies we highlighted were acquired.

This advanced predictive capability is pivotal for stakeholders to identify promising acquisition and in-licensing opportunities with a higher degree of accuracy and confidence. Our methodology has proven to be highly effective as a standalone strategy and can also complement established approaches.

Achieving Results: A Glimpse Behind the Curtain

At Intelligencia AI, we used our proprietary, patented probability of success (PoS) prediction technology to create our own virtual portfolio* of publicly traded biotech companies. Our portfolio was constructed with early-stage, pre-proof-of-concept biotech companies with oncology pipelines and a market capitalization between $100M and $1B.

Our investment strategy focused on ranking companies based on predicted overperformance against historic benchmarks and selecting the top percentile of ranked companies. The ranked list discussed here was produced algorithmically. Overall, results can be further qualified and prioritized by our team of expert analysts when further dimensions may be relevant to our partners.

Biotech companies ranked by their expected overperformance.

Intelligencia AI’s approach has been prospectively validated with time-stamped predictions from April 21, 2023. By March 21, 2024, Intelligencia AI’s portfolio of top 40 ranked biotechs achieved a 60% return and a Sharpe Ratio of 1.83. In comparison, similar market cap companies had a 25% return, while the biotech market benchmark index (XBI-ETF) saw a 17% return, underscoring the strategy's effectiveness. This approach has also been back-tested over a 5-year period.

Performance of Intelligencia AI portfolio of top 40 ranked biotechs compared to the rest of the biotech market.

The same methodology can be applied continuously incorporating the latest information to construct the most up-to-date portfolios. We continued to construct such time-stamped profiles. Below we highlight one constructed in late November 2023 displaying top ten picks from that portfolio. Highlights include multiple recently acquired early-stage biotechs.

Highlights from Intelligencia AI’s portfolio of top 10 ranked biotechs on November 28, 2023.

Harpoon Therapeutics (HARP), which has developed a portfolio of novel T-cell engagers, entered into a definitive agreement with Merck (MSD) on January 8, 2024.

We singled out Harpoon Therapeutics’ assets in clinical development as standing out from competitive products. Both the lead candidate, HPN328 targeting T-cell engager, and HPN217 targeting B-cell maturation antigen (BCMA), were included in the acquisition.

PoS distribution of ongoing assets similar to Harpoon’s candidate HPN217 targets B-cell maturation antigen (BCMA). Harpoon’s candidate had been outperforming most development programs within the same indication and stage of development, belonging to the top quartile.

Ambrx (AMAM), an early-stage biotech with proprietary Antibody Drug Conjugate (ADC) technology, entered into a definitive agreement with Johnson & Johnson on January 8, 2024.

We singled out two of the programs currently in early-stage clinical development as highly promising. Both novel ADC candidates, ARX788 and ARX517, were part of the acquisition.

Kinnate Biopharma Inc. (KNTE), a clinical-stage precision oncology company, entered into a definitive agreement with XOMA Corporation on February 16, 2024.

We highlighted two of their programs, Exarafenib and KIN-3248 treating melanoma and intrahepatic cholangiocarcinoma respectively, which had probabilities of success that far exceeded their expected historical benchmarks.

Better Predictions, Better Investment and Clinical Development Decisions With Validated PoS Assessments

The ability to create the above-described composite biotech scores on the basis of PoS is driven by highly accurate, prospectively validated PoS predictions for specific programs. Built on a unique, proprietary database, Intelligencia AI’s platform brings together expertly curated and harmonized clinical development, biological and regulatory data, which feeds our AI algorithms to assess drug approval and phase transition probabilities.

Our algorithms show an 83%** accuracy in predicting FDA approvals for Phase 2 oncology programs, reaching 90% retrospectively. We achieve this performance by using standard calibration techniques and continuously validating our predictions against real FDA outcomes.

In conducting a 4-year, ongoing prospective study, we demonstrate the high accuracy of our algorithms for early-stage development programs. In 2019, we collaborated with a leading pharmaceutical company to assess PoS for all FDA-track, industry-led, interventional Phase 1 and Phase 2 non-small cell lung cancer (NSCLC) and melanoma programs.

We have been monitoring these programs since then, with 140 failures and 6 approvals. Our platform accurately predicted approval for four drugs, including novel ones and three receiving accelerated approvals: Amivantamab, Tepotinib, Tebentafusp, and Selpercatinib. Our PoS predictions for these programs were significantly higher than for those of similar-stage peers, even with relatively limited information at the time. Also, by time stamping the PoS assessments, we show that the accuracy of the PoS predictions has further improved in later releases of our algorithms.

The graphs show the distribution of approved and failed programs, based on the PoS assigned by Intelligencia AI. Our algorithms have consistently assigned a significantly higher PoS to programs that moved on to approval and lower probability to programs that eventually failed. Importantly, our accuracy has improved over time, as the comparison between 2019 (left panel) and 2022 (right panel) shows.

Conclusion and Future Outlook

Our AI-driven approach in assessing biotech companies based on the risk of their development portfolio constitutes an innovative approach to identify assets for acquisition and in-licensing. The returns realized with our approach highlight its accuracy and demonstrate its capability to guide timely, informed and impactful decisions. These capabilities allow us to help our partners quickly pinpoint overlooked opportunities and realize superior returns.

As we continue optimizing the use of AI for risk assessment in drug development, we are committed to supporting life science companies in bringing groundbreaking therapies to the market and transforming patients’ lives.

Visit intelligencia.ai to discover more and request a demo.

* This material is provided for informational purposes only, and it is not, and may not be relied on in any manner as investment advice or as an offer to sell or a solicitation of an offer to buy an interest in any fund or investment vehicle managed by Intelligencia AI or any other Intelligencia entity. The information and data are as of the publication date unless otherwise noted, and Intelligencia has no obligation to update such information or data. Certain information contained herein has been obtained from third-party sources. Although such content is believed to be reliable, it has not been independently verified as to its accuracy or completeness and cannot be guaranteed.

** Based on Intelligencia AI predictions as of May 2022 for oncology programs with definite announcements in 2023.

If you've received it, then you either subscribed or someone forwarded it to you. If the latter is the case, subscribe by pressing this button:

Subscribe now

This newsletter is sponsored by LatchBio, a provider of next-generation cloud infrastructure for biology research.

Hundreds of biotechs use Latch to make data analysis faster, cheaper, more accessible, and instantly accelerate their R&D milestones.

To learn more about Latch’s complete production solution for kit, assay, and solution providers, sign up for a free 7-day trial here.

Now, let’s get to this week’s topic!

Enabling Data Infrastructure for Biology

The advent of artificial intelligence (AI) in drug discovery and biotech is remarkable. But the foundational premise for any major success in this area is high-quality biological and medical data, properly managed, curated, and accessible to various parties involved in the R&D work.

That's why I believe we should talk a bit less about cutting edge AI algorithms, and more about the following categories of companies:

• companies building ways to get novel data (analytical tools and instruments, scientific methods, research kit providers, robotic labs as a service, etc)

• data providers (biobanks, EHRs, etc)

• companies helping manage and analyze big biological data in machine learning-friendly ways

So, below is a nuanced take on various aspects of building a strong data foundation for biology research, especially relevant to assay, kit, and solution providers within the life sciences industry.

As biology advances exponentially, new multi-omic technologies to read, write, and edit cells (genome, proteome, metabolome, or epigenome) emerge every week, rapidly increasing the level of complexity. Techniques that would have made the cover of Nature Biotech ten years ago are now standard in experimental protocols. Skills that once required an entire PhD and postdoc to master are now routinely expected from a first-year research associate.

How are we supposed to keep exploring the farthest boundaries of biological possibilities if even the most basic discoveries depend on such complex and rapidly changing multi-omic technologies?

Enter biological solutions providers. They play a crucial role in transforming cutting-edge biology into accessible solutions by abstracting these complex but essential tools into services, kits, or instruments. 

The Struggle for Meaningful Results

Getting raw assay data into a state that is easily accessible and understandable for customers is often impossible. 

As kits push the scale and resolution at which we are able to interrogate biology (more cells, more reads, etc.), downstream analysis suffers from uniquely large computing and storage pain. 

Take the example of AtlasXOmics, which offers a comprehensive solution to map the spatial epigenome at a cellular resolution. 

Despite AtlasXOmics’ novel DBiT-seq technology, customers were initially unable to grasp the biological insights they would derive from these assays:

• Each kit can produce terabytes worth of raw data for kit providers, making it challenging to share with customers. 

• The bioinformatics pipelines required to process these datasets require parallelization of multiple computers and several hours to finish. They often point customers to an existing GitHub repository requiring advanced bioinformatics expertise to self-serve. There’s no guarantee that customers can run the pipeline successfully and achieve the final insight themselves. 

• Once the data has been processed, it is often delivered as text files or CSVs that are not readily digestible by scientific teams. HTML reports or RShiny applications and dashboards are viable workarounds, but they often require internal efforts to customize and deliver on a customer-by-customer basis.

These computational challenges are not unique to AtlasXOmics. Many kit and assay providers experience a frustrating disconnect because customers purchase the kit not solely for the kit but for the scientific questions it enables them to explore. 

Customer Journey Suffers

Due to the compute-intensive nature of high-throughput sequencing data, the journey from assay to insights can be long and arduous for customers, often spanning weeks or even months. 

Many kit providers are considering building an in-house, customer-facing bioinformatics solution. However, they also worry about the opportunity cost & time sunk into making such a solution production-ready, not to mention the resources required to maintain such a solution long-term. 

The Status Quo

As a result, many shy away from a differentiated offering with dynamic reports & visualizations, sticking with the tried-and-true status quo: no complementary analyses at all (reducing potential revenue) or sending static reports and zipped data folders over email (reducing insight into whether customers find these outputs useful). 

There must be a more straightforward way to ensure every customer experiences that magical "Aha" moment right from day one, immediately after using your kit.

LatchBio has built close partnerships with CROs and kit manufacturers across markets to design a white-labeled, purpose-built bioinformatics platform to deliver analyses to customers quickly.

Latch is the First Bioinformatics Delivery Platform Focused on the Assay, Kit, and Solutions Provider Market

Latch offers bioinformatics delivery to assay, kit, and solution providers, empowering them to deliver a delightful, white-labeled web portal to their customers on day 1. 

How it works:

From a kit/assay/solution provider point-of-view:

• A kit provider can log into the Latch platform and create an internal workspace for their team. With a Latch workspace, they can:

• Mount data from various sources (local computer, BaseSpace, AWS, Google Cloud), and have a central, intuitive file system in Latch Data.

  

• Organize samples with contextual metadata in the Latch Registry. 

• Publish existing Nextflow and Snakemake to their private workspace on Latch while automatically receiving user-friendly, no-code GUI and scalable infrastructure using the Latch SDK. 

• Create shareable visualization applications inside Latch Pods. 

• Within the provider’s Latch workspace, they can iterate on pipeline and application development internally and assemble an “analysis package” to send to customers. 

• Providers can also create customer workspaces, dispatch an analysis package (with portions from Latch Data, Workflows, Pods, and Registry), and ship it to a customer workspace in just a few clicks. 

• Like AWS, Latch is a usage-based platform, so as customers store data, run workflows, or use visualization applications, they show up as Latch credits (1 credit = $1). The kit provider has complete visibility into the number of credits incurred for every customer workspace via an Admin Dashboard. They can also quickly transfer credits to a customer. Monitoring credit usage yields valuable insights, helping quantify customer engagement, revealing which aspects of the analysis package are most beneficial, and spurring innovative business models to generate new revenue streams.

• Additionally, providers can subscribe to alerts for failed customer workflows, enabling rapid response and proactive customer support.

From a customer of a kit/assay/solution provider point-of-view:

• They log into a beautiful, easy-to-use platform with the kit provider’s branding. 

• They are welcomed with a workspace curated for their specific assays. They only see the test data and workflow that they need. Customers can run bioinformatics pipelines themselves or, with a simple click on Latch Pods, access interactive visualizations through an intuitive application.

• The entire process, from raw data to final insights, is streamlined, empowering them to achieve results in just one day.

Key Benefits of a Bioinformatics Delivery Solution

If you've received it, then you either subscribed or someone forwarded it to you. If the latter is the case, subscribe by pressing this button:

Subscribe now

Now, let’s get to this week’s topics!

Weekly tech+bio highlights

💰 Regeneron announces venture investing plans, committing $100 million annually for five years to fund therapeutics, medical devices, and health tech tools, as it continues to showcase its entrepreneurial spirit with a market cap near $100 billion.

🚀 Novo Nordisk launches a new AI research facility in London's Knowledge Quarter, focusing on integrating Artificial Intelligence and Machine Learning into drug discovery. This Digital R&D Hub aims to accelerate target identification, molecule design, and clinical outcome predictions through AI, enhancing their drug development process.

🚀 BenevolentAI, a pioneering AI biotech with a recent history of setbacks, announces a significant boardroom reshuffle effective May 2, following founder Kenneth Mulvany's plans to rejoin as deputy chair alongside new independent directors, aiming to enhance governance and future value creation.

🚀 Nvelop Therapeutics launches with $100M in seed funding, introducing two innovative in vivo delivery approaches for gene therapy, developed by gene editing experts David R. Liu and J. Keith Joung. These platforms aim to safely and effectively deliver genetic medicines, potentially transforming treatments for currently unreachable patient populations.

💰 US-based Canaan Partners boosts its biotech investment pool by $100 million, following an $850 million fund last year, with plans to focus on early biopharma company formation and venture series rounds. The firm also welcomes Pfizer veteran Uwe Schoenbeck as a venture partner to strengthen its biotech investment strategy.

🔬 Aspen Neuroscience announces the dosing of the first patient in the ASPIRO Phase 1/2a trial, evaluating ANPD001, an autologous dopaminergic neuron cell replacement therapy for moderate to severe Parkinson's disease, marking a step in personalized regenerative neurologic therapies.

💰 Bruker acquires NanoString Technologies, a spatial biology company, for $392.6 million. NanoString, known for its RNA and protein analysis technology, filed for bankruptcy in February before the acquisition.

💰 23andMe CEO Anne Wojcicki plans to take the company private, as revealed in a recent securities filing. Despite the company's struggles with its dual role in consumer genetics and drug development since its 2021 SPAC public offering, Wojcicki is exploring financing options and is not considering alternative transactions.

💰 Corner Therapeutics raises $54 million in Series A funding to advance new immunotherapies for cancer and infectious diseases, led by healthcare veteran Steve Altschuler. The startup plans to enter the clinic with programs targeting influenza and HIV, focusing on novel dendritic cell activation platforms.

🔬 Insilico Medicine discovers a new class of orally bioavailable Polθ inhibitors for BRCA-deficient cancers, using generative AI for precise molecular modifications. Demonstrating robust potency and promising druglike properties, this breakthrough, published in Bioorganic & Medicinal Chemistry,

Share Where Tech Meets Bio

An AI Model to Predict RNA Expression in Whole Slide Images

I’d like to highlight today HE2RNA, an innovative AI model that predicts RNA expression from whole slide digital images. This tool is built by the Paris- and New York-based AI company Owkin.

Designed for interpretability, HE2RNA serves as a virtual spatialization tool, generating heatmaps to visualize the expression of any gene.

This AI model is adept at predicting tumor immune infiltration, detailing the spatial expression of RNA, and identifying treatment-relevant mutations in diseases.

Unlocking Interoperability with AI: How This Company is Building a New Framework for Clinical Trials

(Disclaimer: this interview is sponsored by Trialize)

In an industry as critical as clinical trials, where efficient data management and swift processes are paramount, outdated tech methods often create organizational barriers. Digital tools, data management systems, and analytical dashboards are generally ways to improve clinical trial design and operational efficiency. 

In fact, statistical surveys reveal tangible advancements in efficiency and technological integration within clinical trials. The rapid adoption of digital tools, including electronic Investigator Site Files (eISF) and electronic consent (eConsent), has increased markedly, with usage climbing from 61% in 2020 to 89% by 2022 among clinical trial sites and sponsors.

Additionally, 74% of sponsors surveyed in that study were shown to utilize remote monitoring, anticipating this to reach 91% by the end of 2022, highlighting a substantial shift towards digital oversight​. 

However, the unprecedented advent of large language models over the last couple years presented novel opportunities to improve clinical trial design.

That's why I sat down with Leo Stoianov, CEO of Trialize, a company at the forefront of redefining clinical trials through innovative technology.

We discussed the still substantial challenges that clinical trials face today and how Trialize is addressing these through automation and artificial intelligence, transforming months-long preparations into a matter of days.

Leonid shared insights into how their integrated platform not only speeds up processes but also enhances data integrity and simplifies the user experience across various functionalities such as EDC, ePRO, and more.

This conversation delves into the promise of new technologies in making clinical trials more efficient, accessible, and ultimately more successful in delivering timely medical innovations.

Leonid, could you share the journey that brought technology and clinical trials together for you? What sparked the idea to innovate in a field known for its cautious pace of change?

I've learned the need the hard way. During my time managing a software engineering department in a CRO, we had many sleepless nights trying to integrate various e-clinical systems, EHRs, LIMs, and BI. We did a lot by introducing cutting-edge MetaData Repositories and Statistical Computing Environments, but eventually, I realized we weren't addressing the root cause, but rather trying to duct-tape what was broken by definition. The industry had solutions built for a different reality, with a different mindset, where the term "interoperability" sounded like a voodoo chant. Meanwhile, a groundbreaking change was happening in healthcare with the introduction of HL7 FHIR.

I realized we had to reimagine and re-engineer the entire process, from designing the data model in a standard but flexible way, to capturing data both clinical and directly from patients, to monitoring and, finally, to analysis. As a software architect, I understood the importance of the concept "don’t break things," especially in our industry.

This led to the creation of Trialize, an integrated platform built atop a new paradigm where the system itself acts more like an opinionated framework rather than a "black box," where AI-enhanced process automation and data models rule, allowing for maximum flexibility while bringing full control over the data and processes.

AI is dramatically reshaping the landscape of many industries, including clinical trials. How do you see AI, particularly through advancements like Large Language Models, transforming clinical trial processes? And could you simplify how these technologies are making an impact for those not deeply familiar with AI?

Absolutely. Imagine your Case Report Forms. Once created, they can be reused from study to study with minor changes. That's what MDRs are used for. LLMs take this further by adding an additional level of "smartness" to the process by producing even better, already adapted CRFs; you just need to "confirm" or "tweak" the remainders.

Imagine EditChecks, which ensure the quality of captured data. That's code. Previously, you had to adapt or rewrite them manually for each study. Now, the process is semi-automatic and AI-assisted; you can generate as AI "interprets" the model you're working on.

Imagine Verification, where previously, people had to do it for each field, or a predefined set of fields for targeted SDV. Now, the system automatically highlights the elements of interest.

Imagine Queries, now systems automatically produce them with loosely defined logic (not hard-coded), as LLMs allow you to identify discrepancies more easily.

Imagine Medical Coding. AutoCoders previously matched with simple logic, like if verbatim + A, B, C was coded to Term X, then other verbatims should be coded alike. LLMs elevate this further by allowing you to find candidate terms for a group of verbatim even if those are not identical.

Imagine Monitoring. Previously, you had to visit sites regularly. Now, you can mix tele-visits with traditional visits and expect a significant overall reduction in the number of visits. How? By getting real-time insights on the processes and data quality happening on sites. You don’t need to wait weeks to produce intel, LLMs could help generate intel for you by writing relevant SQL and building charts. Just prompt in human language what you want to know, what’s important to the success of your trial, and voila, you have what you need at your fingertips, immediately.

Imagine Medical Writing. LLMs are proven to be a good assistant in this exercise by significantly reducing the time needed to produce documents.

And that’s only the tip of the iceberg. The cumulative gains on productivity provided by tailored LLMs are now easy to quantify, which is described in our latest case study here on BPT.

The management of sensitive data within clinical trials is paramount. From your vantage point, what are the cutting-edge strategies or technologies that are enhancing data security and integrity in the face of increasing automation?

So, there are strategies I think are essential for data security reasons: 

• Do not use general-purpose LLM APIs which you cannot validate or ensure compliance with.

• Implement validation policies tailored to address LLM specifics - you might want to update your TQLC and SDLC SOPs to address this.

• Keep it in-house within your VPC or work with preferred partners who can ensure industry-specific compliance requirements and share responsibility with you.

• Implement an LLM-focused red team system with guards to ensure automated safety and security assessments.

• Do not allow LLM to "write" data, instead use it to propose metadata and algorithms by reading what's already there.

The adoption of Agile methodologies marks a significant evolution in clinical trials. What effects do you anticipate this shift having on drug development’s speed and efficiency? Can you point to any instances where this approach has already shown its effectiveness?

Given my technical background, I’ve seen various interpretations of the “Agile” theme. Most misconceptions start to emerge as people realize that Agile is not about “ship it fast, fix issues later”. In our industry, the quality of data directly affects analysis outcomes and whether you’ll receive approval from regulatory bodies. Being “agile” is about being “flexible” and “adaptive”. It involves starting small, having shorter validation cycles, making incremental improvements, and establishing instant feedback loops to inform and embrace change. 

This requires a change in systems, processes, and people’s mindsets. Constant change is a painful process as it requires regular mental exercise, consumes energy, and brings a feeling of "uncertainty.” It necessitates a focus on reduction—“less is more”—and a battle to discern what’s essential at the moment while always keeping the long-term goal in sight. Legacy systems were not built to be "flexible.”

Speaking of processes, imagine retraining 1,000 people on new or revised SOPs. That’s why I believe Agile should not be imposed top-down, but rather embraced bottom-up—create a dedicated business unit that encompasses all necessary elements to deliver end-to-end, think of it as an internal enterprise startup, and give them the flexibility to innovate.

Then gradually scale up their success and best practices to the entire organization. To become truly "agile," the entire organization must adopt an entrepreneurial mindset, which is challenging to instill.

Technology adoption in clinical trials isn't just about the data or algorithms; it's deeply influenced by human factors. Could you recount a situation where the human element—whether it's collaboration among teams, relationships between sponsors and CROs, or patient interaction—played a pivotal role in the success or insight gained from a trial?

People always play a pivotal role. They are the ultimate decision-makers and outcome influencers. Systems and processes can only support or hinder their efforts. It’s a matter of mental energy consumption. If you’re constantly battling with the system or process, it diminishes your chances of success. The best process is the one you hardly notice because it functions so seamlessly. To keep people motivated, the system should focus on reducing everything, especially repetitive tasks, while providing a pleasant user experience. If everything goes smoothly, you’ll rarely even mention it; it’s taken for granted.

As we look to the future, what do you believe are the next big technological breakthroughs or trends that will further revolutionize the clinical trials space? How might organizations, possibly including your own initiatives, need to adapt to stay at the forefront of these changes?

We are still unable to test on digital twins effectively: the quality data isn’t there yet, and the models are far from perfect. We can’t automatically produce Statistical Analysis Plans (SAPs) out of clinical protocols, just assist in writing them. While we’ve made significant progress with SDTM generation from raw data, generating ADaM datasets is still a far reach. QA/QC tracks, while being AI-assisted, still require considerable improvement. The ultimate breakthrough will occur when we can conduct a completely “synthetic trial” to predict outcomes before starting the actual study on humans.

Innovating within highly regulated sectors like clinical trials comes with its own set of challenges. Reflecting on your journey, what obstacles have you encountered, and what key lessons would you share with those looking to bring new technologies into this space?

Throughout the long history of industry maturation, many best practices and established processes have emerged. Along with these, we've inherited significant inefficiencies, concerning levels of bureaucracy, and internal politics that consume precious resources and slow down the industry. The focus has shifted from delivering innovative treatments to battling internal demons. That’s why most innovation now comes from acquiring startups rather than fostering in-house development.

It's essential to maintain enthusiasm and productivity in a professional environment burdened by excessive meetings and paperwork. We have studies that are at various stages of automation, including one that is close to what we jokingly call “automation singularity,” where a very small team at a CRO successfully managed a complex multi-site Phase II trial that was originally failing so badly the sponsor considered canceling it.

The key is mutual willingness from both sponsors and CROs. Sponsors need to be aware of modern approaches, and CROs need to embrace the newfound flexibility provided by emerging technologies.

Read Trialize’s technical case study: How AI and Automation Reduced Study Build Time from Months to Days

Share

A Landscape of AI-discovered Molecules and Target Novelty Analysis

We have recently launched a report, “It’s Been a Decade of AI in the Drug Discovery Race. What’s Next?” where we gathered historical data about drug pipeline progression over the years for the selected AI-driven drug discovery platforms.

Those included BenevolentAI, Exscientia, Insitro, Insilico Medicine, Recursion, Relay Therapeutics, Schrödinger, Verge Genomics, and Valo Health.

Now, we’ve gone a step further and attempted to analyze novelties of targets that the above companies are pursuing for their leading drug programs.

Some of the targets were highly novel and even AI-discovered, like in the case of Insilico Medicine, Recursion Pharmaceuticals, Schrodinger, and Verge Genomics.

In other cases, targets were moderately novel, or even very old and well-known.

This target novelty evaluation is an ongoing study, so we might be further adjusting the novelty evaluation methodology for the upcoming research paper. 

• The Excel file with the data for the target novelty and AI-discovered programs is available for download below (for paid subscribers). 

• Next up: Notable Trends and Companies to Follow in Neuroscience

Download an Excel file with the pipeline analysis of 9 AI platforms, and a preliminary evaluation of target novelty.

Notable Trends and Companies to Follow in Neuroscience

(Article written by Irina Bilous, contributor at BiopharmaTrend)

Historically, the approval rate for medicines treating central nervous system (CNS) disorders was low. By 2022, the success rate for CNS assets from phase 1 through to regulatory submission was only 5–6%.

The failure of pharmaceutical companies to bring CNS medications to the market can be attributed to factors such as a limited understanding of disease mechanisms and challenges in delivering drugs across the blood-brain barrier. Nevertheless, recent technological advancements and an improved understanding of disease pathophysiology led to expanding the CNS pipeline.

A recent report shows that the CNS pipeline has grown by 31%, constituting 14% of the overall industry R&D pipeline. Moreover, the approval of the first drug for spinal muscular atrophy (SMA) developed by Ionis Pharma and Biogen was a significant stride that revitalized interest in the field and demonstrated the ability of innovative treatments to address complex neurological disorders.

Hot Deals of 2023 Involving Modulators of Muscarinic Receptors

In December 2023, Bristol Myers Squibb expanded its neuroscience portfolio by acquiring Karuna Therapeutics for $14.0 billion. Karuna’s leading candidate, KarXT (xanomeline-trospium), has a dual action on M1 and M4 muscarinic receptors without affecting the dopaminergic pathway.

KarXT is efficient in patients with schizophrenia as it reduces both positive and negative symptoms of the condition, which affects about 24 million people worldwide. When the FDA approves KarXT, it will become the first novel treatment for schizophrenia in decades. 

The same month, AbbVie boosted its neurological and psychiatric disorder pipeline by purchasing Cerevel Therapeutics for $8.7 billion. This move will advance AbbVie's capabilities in addressing Alzheimer's, Parkinson's, psychosis, epilepsy, and panic disorders.

Cerevel's promising drug, emraclidine, is in the Phase 2 trial for schizophrenia. Emraclidine acts on M4 receptors, and similar to KarXT, it doesn’t directly affect dopamine D2 receptors, which hypothetically will prevent adverse effects that are common for available antipsychotic drugs. 

Muscarinic receptors are part of the cholinergic pathway in the brain. Therefore, drugs targeting this pathway affect brain chemistry differently from currently available medicines that act on receptors of dopamine or serotonin, the two other well-known neuromediators. Because dopamine is essential for multiple functions in the brain, e.g., motor control, dampening D2 receptors leads to adverse effects. 

The market for schizophrenia treatments targeting muscarinic receptors alone is estimated at $10 billion. With the acquisition mentioned, AbbVie and BMS strive to take leading positions in the market for muscarinic receptor drugs. Other companies in this space include Neurocrine Biosciences, Sosei Heptares, Neumora Therapeutics, MapLight Therapeutics, and Anavex Life Science.

Companies Bringing Innovations to Improve the Psychiatric and Mental Health 

In September 2023, Otsuka acquired  Mindset Pharma for $59.1 million to accelerate the development of the new generation of serotonin 5-HT2A receptor agonists to treat treatment-resistant depression and post-traumatic stress disorder (PTSD). 

Another acquisition of a brain chemistry modifying asset was accomplished by AbbVie in 2022 when the pharma giant purchased Syndesi. ABBV-552 is a small molecule that acts upon targeting synaptic vesicle glycoprotein 2A (SV2A), which enhances synaptic transmission. It’s currently in Phase 2 clinical trials for Alzheimer’s disease (AD), with the potential to improve cognitive impairments and other symptoms concurrent with AD.

Alto Neuroscience, which recently went public, focuses on applying machine learning to identify brain-based biomarkers based on EEG data. Its most advanced programs are being evaluated in ongoing Phase 2b trials in major depressive disorder (MDD).

Known Since Aztechs, Psychedelics are in Clinical Trials Today

Algernon Pharmaceuticals is developing a psychedelic that can be naturally synthesized in the human brain to treat traumatic brain injury (TBI) and stroke. The compound DMT is believed to promote neuritogenesis and neuroplasticity by upregulating the expression of brain-derived neurotrophic factor (BDNF). Phase 1 is currently underway in the Netherlands. 

Psilocybin has been known since ancient times and is used for spiritual and religious purposes. Today, it is recognized as a potential medicinal agent for treatment-resistant major depressive disorder. PurMinds™ is developing botanical psilocybin, hoping to bring positive changes in the lives of patients for whom standard antidepressants failed to improve their conditions. 

Major Developments in the Areas of Neurological Indications

In the neuroscience market, the mental health pipeline accounts for only 20%, whereas the rest is attributed to neurological disorders. The incidence of some devastating neurological conditions is high. For example, every year, around 5 million people are diagnosed with Alzheimer's disease (AD). AD affects memory and cognitive functions, depersonalizes, and brings enormous emotional and financial burdens to the families of patients. 

The FDA approves Biogen’s Second Antibody to Treat Alzheimer’s.

Leqembi is a monoclonal antibody developed by Elisay and Biogen that became the first therapy that proved to clear beta-amyloid plaques and simultaneously slow down the progression of cognitive decline in AD patients.

The antibody received its full FDA approval in the summer of 2023, finally proving the amyloid hypothesis, which has not successfully produced drugs that slow disease progression and cognitive decline over 16 years of research. Alongside approval in China, Lequembi is generating $1.5 million in weekly sales.

Additionally, Biogen expanded its Central Nervous System (CNS) portfolio by acquiring Reata Pharmaceuticals in August 2023 for $7.3 billion, gaining access to Skyclarys, the only approved drug for Friedreich's Ataxia. Furthermore, Biogen entered into a $51 million collaboration with Alcyone Therapeutics to develop the ThecaFlex DRx™ System, an implantable device for the routine subcutaneous administration of antisense oligonucleotide (ASO) therapies to the cerebrospinal fluid. This development aims to support the marketing of Spinraza and other ASO therapies.

Small Biotech Companies Drive Innovations in the Market of CNS Medicines

Small biotech companies’ unique science is often a source of innovations. For example, Caraway Therapeutics is researching cellular waste disposal mechanisms. Caraway's leading projects focus on the TRPML1 ion channel, crucial for removing lysosomal waste. The company is investigating the potential of targeting this protein to address Parkinson’s disease associated with GBA gene mutations, alongside other rare diseases outside the central nervous system. Recently, Merck has acquired Caraway Therapeutics for $610 million. This acquisition follows Merck's prior investment in the TRPML1 pathway, demonstrated by its 2019 purchase of Calporta Therapeutics for $576 million, a small biotech specializing in TRPML1-targeting compounds.

NRG Therapeutics focuses on mitochondrial dysfunction to create therapeutics that can slow the progression of neurodegenerative disorders like PD and Amyotrophic Lateral Sclerosis (ALS, also called motor neuron disease). Now, the company is working on the preclinical development of small molecule assets that target and inhibit the mitochondrial permeability transition pore (mPTP) via a new mechanism of action.

Companies Focusing on Preventing Neuroinflammation

Muna Therapeutics is a company that focuses on preventing neuroinflammation to protect adequate brain functions and prevent memory loss. Muna’s drug discovery platform focuses on discovering and validating small molecules that target microglia, the most prominent immune cells of the CNS.

Muna’s two drug discovery programs approach the opposite roles of microglia in CNS pathologies. The first and most advanced program is a TREM2 agonist to boost brain clearance. TREM2 is expressed in microglia cells, and variation of this gene is associated with a higher risk of developing neurodegenerative diseases. The second program is a blocker of a Kv1.3, a potassium channel expressed in microglia, that is involved in inflammatory mechanisms of action of microglia that often lead to neural damage. 

Immunic, another company targeting neuroinflammation, has a drug in Phase 3 clinical study to improve the lives of patients with multiple sclerosis (MS). Their lead drug, vidofludimus calcium, activates the neuroprotective transcription factor Nurr1 with direct neuroprotective properties.

The compound is also known as an inhibitor of the dihydroorotate dehydrogenase (DHODH), which keeps T-cells and B-cells overactive.  Vidofludimus calcium is also efficient in relapsing-remitting MS; it reduces lesions and serum neurofilament light chain levels, or NfL, a biomarker for axonal damage.

Arialys emerged in 2021 and was named one of the most innovative start-ups in 2023. The company focuses on the treatment of NDMA receptor encephalitis (ANRE), an autoimmune condition that prevents the transmission of glutamate and causes seizures and psychosis. ART5803, a single-arm antibody, rescues ANRE by binding and hiding an epitope of NDMA receptor from auto-reactive antibodies. The asset was acquired from Astellas Pharma in 2022. In 2023, Arialys raised $58 million to continue the development of ART5803.

Schrodinger, an AI-powered drug discovery leader, also addressed neuroinflammation by targeting LRRK2, a potential target for treating PD. Variants of LRRK2 might drive microglia to acquire pro-inflammatory functions, exacerbating neurodegeneration. Schrodinger successfully generated the cryo-microscopy structure of the LRRK2 after acquiring XTAL BioStructures, which specializes in X-ray crystallography for protein mapping. Generation of the 3D model allows Schrodinger to discover efficient inhibitors of LRRK2. Furthermore, the company has entered a multi-part agreement with Otsuka Pharmaceutical and its subsidiary Astex Pharmaceuticals, including discovery initiatives aimed at an emerging Central Nervous System (CNS) disease target.

Companies Combating Neural Nyperexcitability

QurAlis is a clinical-stage company that addresses amyotrophic lateral sclerosis (ALS),  frontotemporal dementia (FTD), and other neurodegenerative diseases. Their selective Kv7.2/7.3 ion channel opener is in a Phase 1 clinical study for treating hyperexcitability-induced disease progression in ALS.

Previously, a drug targeting this channel demonstrated promising results in patients with epilepsy, but its marketing was terminated due to side effects.  Quaralis's QRL-101 can decrease motor neuron hyperexcitability-induced excitotoxicity, preventing ALS's progression.

Companies Leveraging RNA and Gene Therapies to Target CNS

Novartis has acquired DTx Pharma for an upfront payment of $500 million, securing the FALCON platform to enhance its neuroscience endeavors. This investment allows Novartis to develop therapies for unmet medical needs, including a preclinical therapy for Charcot-Marie-Tooth disease type 1A (CMT1A), a neuromuscular disorder with no approved treatments.

The acquisition also encompasses two additional preclinical programs addressing neuromuscular and central nervous system disorders. Through this acquisition, valued at potentially $1 billion with milestone payments, Novartis aims to bolster its RNA-based therapeutic capabilities, focusing on advancing treatments for conditions like CMT1A.

AviadoBio, specializing in CNS gene therapy, is focused on developing innovative treatments to slow or halt neurodegenerative diseases by targeting their genetic causes. The company's platforms include gene-supplement and gene-silencing technologies, along with advanced surgical delivery methods to enhance treatment distribution.

AviadoBio's portfolio features therapies and devices to treat frontotemporal dementia (FTD) and ALS. FTD is early-onset dementia that affects personality and behavior. AVB-101 is AviadoBio’s lead candidate for FTD linked to mutations in the progranulin (GRN) gene (FTD-GRN).

This therapy involves a one-time infusion of the GRN gene directly into the thalamus, aiming to restore GRN protein production and distribution across the brain, potentially stopping FTD progression.

If you've received it, then you either subscribed or someone forwarded it to you. If the latter is the case, subscribe by pressing this button:

Subscribe now

In today’s newsletter:

• Weekly tech+bio highlights;

• Seed Health Invests in AI-Driven Biology Platform to Enhance Microbiome Science;

• Novel Gen AI Platform for Preclinical Research;

• This Company's ML Model Predicts KRAS Inhibitor's Clinical Benefit in Patients with >80% Accuracy (paid);

• Model Medicines Advances AI Drug Discovery in Antiviral and Oncology Fields (paid);

• A Novel Quantum-assisted Approach to Designing Drugs From Fragments (paid);

• Cancer Vaccines: insights from #AACR24

• Mapping AI-driven drug candidates and targets (infographic)

This week’s sponsor: Trialize

In the realm of clinical trials, efficient data management and monitoring are crucial yet often hampered by outdated and time-consuming practices.

Trialize's innovative approach to automating study builds and leveraging artificial intelligence (AI) for data analysis significantly reduced the time from protocol to trial, transforming the process from a traditionally months-long undertaking into a matter of days.

Trialize’s architecture offers a comprehensive, integrated solution covering all aspects of clinical trial management, from Electronic Data Capture (EDC) and Electronic Patient-Reported Outcomes (ePRO) to TeleVisits, eConsents, and Analytics. Its interface is designed to be intuitive and user-friendly, drastically reducing the learning curve for study teams.

Read Trialize’s case study Revolutionizing Clinical Trials: How AI and Automation Reduced Study Build Time from Months to Days, explaining the unique technical capacity of Trialize’s platform.

Now, let’s get to this week’s topics!

Weekly tech+bio highlights

💰 Vertex Pharmaceuticals acquires Alpine Immune Sciences for $4.9 billion, marking the largest biopharma acquisition of the year. This strategic move strengthens Vertex's position in immunology, with plans to further develop Alpine's lead asset, povetacicept, for IgA nephropathy and other autoimmune conditions.

🔬 Ginkgo Bioworks introduces Lab Data as a Service, offering rapid, scalable data generation for biotech R&D. With services like Enzyme Performance and Antibody Developability, customers can access extensive data in weeks, starting at prices like $78,000 for enzymes and $48,000 for antibodies, enhancing machine learning model training and design testing.

💰 e-therapeutics plans to delist from the London Stock Exchange and potentially relist on Nasdaq, following a £29m fundraise to invest in its AI-driven drug discovery platform. Despite strong backing from major shareholders, the UK investor response has been underwhelming, prompting the move to seek better valuation in the US market.

🔬 Ginkgo Bioworks and Novo Nordisk expand their strategic partnership, aiming to enhance the R&D and manufacturing processes for Novo Nordisk's chronic disease medications, including those for diabetes and obesity. The collaboration, set to last at least five years, will focus on leveraging Ginkgo's synthetic biology platform across the entire R&D pipeline.

🔬 Google and Bayer team up to develop AI-driven technologies for radiologists, integrating Google's cloud and AI capabilities with Bayer's expertise in radiology and clinical data. This collaboration will focus on creating a platform to ease radiologists' workloads and accelerate innovation in medical imaging, with plans for a first release in the EU and U.S. later this year.

🔬 Neurotech startup Neurovalens secures FDA clearance for a noninvasive anxiety treatment device, further expanding its portfolio which also includes an FDA-cleared device for insomnia.

💰 ADC-focused German biotech Tubulis secures an upsized $138 million Series B2 funding round, led by EQT Life Sciences and Nextech Invest. The funds will advance Tubulis' pipeline of antibody-drug conjugates targeting solid tumors and support the establishment of a U.S. subsidiary.

🚀NFX launches a $20 million ultra-fast investment track for Israeli AI and biotech startups, offering Seed and pre-Seed funds with a commitment to respond within nine days and transfer funds in three weeks, streamlining investment with SAFE agreements to reduce bureaucracy.

💰 Copenhagen-based startup Reshape Biotech secures $20M in Series A funding to expand its AI and robotics lab automation technologies to the US, enhancing R&D in biotech, agriculture, and food industries. Investors include Y Combinator and Astanor Ventures.

🔬 Children's Tumor Foundation invests in Healx to progress treatments for Neurofibromatosis Type 1, supporting the advancement of Healx's AI-powered drug discovery platform and lead compound, HLX-1502, into Phase 2 trials. This partnership emphasizes a patient-centric approach to address the significant unmet needs of the estimated 3 million global NF1 patients.

🔬 Charles River Laboratories and Deciphex launch Patholytix Foresight, an AI-powered decision support tool for toxicologic pathology, enhancing the efficiency and accuracy of histopathological assessments.

💰 DeepCure secures $24M in Series A-1 funding led by IAG Capital Partners to enhance its AI and automation capabilities in small molecule drug discovery, focusing on advancing its immunology and inflammation programs towards clinical trials

Share Where Tech Meets Bio

Seed Health Invests in AI-Driven Biology Platform to Enhance Microbiome Science

A 2015-founded life sciences startup, Seed Health has unveiled CODA, a new computational biology platform designed to leverage the expansive Human Phenotype Project data, managed by Professor Eran Segal at the Weizmann Institute of Science.

This initiative aims to foster the development of precision probiotics and other microbiome-directed interventions, enhancing the understanding of the intricate relationships between the microbiome and various health outcomes.

CODA will initially focus on advancing research in areas such as cardiometabolic health, brain health, menopause, and longevity.

The CODA platform integrates over three million phenotypic data points from more than 13,000 individuals, encompassing 40,000 cumulative subject years.

This robust dataset merges microbiome analysis with genetic, immune, metabolomic, and proteomic data, offering a holistic view of human health influences—biological, environmental, dietary, and lifestyle factors, along with medical histories.

This comprehensive approach aims to elucidate the complex interactions between the microbiome and host health.

The CODA platform's depth allows for the analysis of the microbiome’s interaction with various biological systems, such as the gut-brain and gut-heart axes.

Notable achievements include the development of organ-specific clocks that can differentiate between biological and chronological aging across different organs, highlighting the microbiome's potential as a target for health interventions.

Professor Segal’s research has been instrumental in identifying microbial genes and their network effects, which are critical for understanding health and disease mechanisms.

This research has led to discoveries such as the linkage between microbial genes and body composition, as well as the diet’s effect on metabolic parameters through microbiome modulation.

Leave a comment

Novel Gen AI Platform for Preclinical Research

I’ve been following Toronto-based BenchSci for years, and I remember they started as an AI-search engine for finding reagents online with a focus on antibodies, including protocols for designing experiments.

And now, years later, the platform has kind of pivoted into a new realm: building a generative AI-powered drug discovery engine called Ascend.

Ascend utilizes multimodal AI to analyze and interpret complex biological data from public and private sources, including text and figures, with a focus on scientific accuracy and explainability.

By integrating and processing diverse datasets securely, Ascend supports preclinical R&D workflows, facilitating better experimental design, target identification, and drug discovery.

This company's ML model predicts KRAS inhibitor's clinical benefit in patients with >80% accuracy

Recently, Rafael Rosengarten pointed me to a research poster by Genialis introducing 𝗚𝗲𝗻𝗶𝗮𝗹𝗶𝘀™ 𝗸𝗿𝗮𝘀𝗜𝗗: a new AI/ML classifier that accurately predicts KRAS outcomes in lung cancer patients.

Most biomarkers in the KRAS space measure only KRAS mutation status, which may be necessary to receive the drug but is insufficient to predict response or to inform further therapeutic interventions.

Genialis krasID works better because it is built differently.

By using high-dimensional gene expression data and a ML algorithm comprising numerous biologic signatures, it captures a more complete view of the underlying biology 𝘂𝗻𝗶𝗾𝘂𝗲 𝘁𝗼 𝗲𝗮𝗰𝗵 𝗶𝗻𝗱𝗶𝘃𝗶𝗱𝘂𝗮𝗹 𝗽𝗮𝘁𝗶𝗲𝗻𝘁.

Because the model incorporates biology aspects that are intrinsic to KRAS function in the tumor and extrinsic to the surrounding tumor milieu, this biomarker is able to perform well for different drugs across KRAS-driven cancers.

The results, presented at hashtag#AACR24, outline performance of Genialis krasID in predicting clinical benefit in a real-world cohort of patients who received sotorasib, a KRAS inhibitor currently approved for KRAS G12C non-small cell lung cancers. 💊

Today’s initial results demonstrate that the Genialis krasID classifier can predict response:

✅ with >𝟵𝟰% 𝗮𝗰𝗰𝘂𝗿𝗮𝗰𝘆 across multiple different KRASi in preclinical models and
✅ with >𝟴𝟬% 𝗮𝗰𝗰𝘂𝗿𝗮𝗰𝘆 in real world patients.

The company announced the launch of an 𝗲𝗮𝗿𝗹𝘆 𝗮𝗰𝗰𝗲𝘀𝘀 𝗽𝗿𝗼𝗴𝗿𝗮𝗺 for Genialis krasID, where members will gain the opportunity to test drive the biomarker model on their data and establish a foundation for implementing the biomarker within their translational workflows.

Share

Model Medicines Advances AI Drug Discovery in Antiviral and Oncology Fields

What? Model Medicines has introduced new methodologies in drug discovery through two preprint papers, demonstrating significant advancements in targeting antiviral and oncology diseases using artificial intelligence.

The first paper focuses on identifying the RdRp Thumb-1 site as a new target for broad-spectrum antivirals and introduces MDL-001, a compound showing promise as an orally bioavailable broad-spectrum antiviral.

The second paper discusses the ChemPrint deep learning model, part of the GALILEO AI platform, which excels in predicting molecular properties and has successfully identified novel inhibitors for previously "undruggable" oncology targets AXL and BRD4.

Why? The development of these AI-driven methodologies is crucial for addressing the challenges in conventional drug discovery processes, which are often slow and have high failure rates. By leveraging AI, Model Medicines aims to enhance the speed and efficiency of discovering novel therapeutics for diseases that have high unmet medical needs, such as various viral infections and cancer. The GALILEO AI platform enables the exploration of deeper chemical spaces and the prediction of promising compounds more accurately, potentially leading to more effective treatments.

Takeaways

• Novel Targets and Compounds: The discovery of the RdRp Thumb-1 site and the development of MDL-001 signify a new direction in broad-spectrum antiviral research, showing effective in vitro and in vivo results.

• ChemPrint Model Efficiency: The ChemPrint model has outperformed traditional AI approaches in a prospective study, achieving a 45.5% hit rate in identifying inhibitors for challenging oncology targets, thereby expanding the possibilities in drug development against tough diseases.

A Novel Quantum-assisted Approach to Designing Drugs From Fragments

A new algorithm called Quantum-assisted Fragment-based Automated Structure Generator (QFASG) from a team of researchers at clinical stage artificial intelligence (AI)-driven biotech company Insilico Medicine offers a meaningful step forward in automated drug design.

QFASG utilizes advanced chemoinformatic techniques to construct novel small-molecule structures from a library of molecular fragments.

To demonstrate its effectiveness, the researchers successfully applied QFASG to generate new small-molecule inhibitors of two pharmacological targets involved in cancer pathogenesis. The findings were published in Frontiers in Chemistry. 

In recent years, AI-assisted generative chemistry platforms such as Insilico’s Chemistry42 engine – a software platform for de novo small molecule design and optimization that integrates AI techniques with computational and medicinal chemistry methodologies – have demonstrated the possibility of designing novel drug candidates from scratch using generative AI. Now, driven by advances in quantum computing and chemoinformatic techniques, researchers can explore vast chemical spaces with new speed and efficiency, allowing them to design new compounds from virtual fragments. 

"QFASG generates new drug-like structures using a medicinal chemistry approach," says Sergei Evteev, a lead researcher on the project. "By leveraging molecular fragments and advanced algorithms, we can design compounds that interact specifically with target proteins, potentially leading to detection of new promising chemotypes."

One of the key features of QFASG is its fully automated pipeline, which streamlines the process of structure generation and optimization.

The algorithm employs a two-part approach: first, probes are strategically placed within target binding sites, and then structural growth occurs through iterative modules, resulting in the generation of diverse compound libraries.

"Our goal with QFASG is to provide researchers with a powerful tool for generating primary hit compounds," says Alex Zhavoronkov, PhD, founder and CEO of Insilico Medicine and a member of the research team. "These initial structures can serve as starting points for further optimization and development, ultimately accelerating the drug discovery process."

To demonstrate the effectiveness of QFASG, the researchers used the algorithm to design inhibitors for two proteins that hold promise as targets for new cancer treatments: ATM and CAMKK2 kinases. ATM kinase is involved in DNA damage response and repair and is a promising target for the treatment of solid tumors, glioblastoma, sarcoma, lung, prostate and colorectal cancer and other pathologies. CAMKK2 plays a significant role in various physiological and pathological processes, including cancer cell growth and is overexpressed in multiple tumor types, including prostate, breast, ovarian, gastric and hepatic cancers 

In order to test the capabilities of QFASG, the researchers performed insilico validation by reproducing binding poses of known protein ligands and in vitro evaluation of structures generated for ATM and CAMKK2. In both cases, three unique structures designed by the algorithm were selected for synthesis and testing and several compounds demonstrated low micromolar activity against the desired targets. 

Early cancer vaccine data breathe new life into the field, but many questions remain: #AACR24

An insightful report from AACR24 by Endpoints News sheds some light on the emerging field of cancer vaccination.

What: At the recent American Association for Cancer Research (AACR) conference in San Diego, a diverse array of experimental cancer vaccines was introduced. These range from "off-the-shelf" options to personalized vaccines designed to align with the specific genetic mutations of a patient's tumor.

Why: The development of cancer vaccines has been pursued for decades, but only recently have technological advancements in mRNA and other genetic delivery systems enabled more effective formulations. These vaccines aim to train the immune system to recognize and fight cancer cells by targeting neoantigens unique to individual tumors.

Takeaway: Early trials, though small, have shown promising results in preventing the recurrence of certain cancers, such as pancreatic and head and neck cancers. This reinvigorated research interest highlights a shift towards using vaccines at strategic points in cancer treatment, potentially offering a more targeted and effective approach to cancer management. The ongoing debate and research are focusing on optimizing the immune response either through customized or off-the-shelf vaccines. This could pave the way for more effective therapies and, ultimately, more hopeful outcomes for patients facing various forms of cancer.

Mapping AI-driven drug candidates and targets (infographic)

Recently, we launched a report, “It’s Been a Decade of AI in the Drug Discovery Race. What’s Next?“ where we profiled the historical progress of the internal drug discovery pipelines of 9 leading AI platforms.

Here, we are continuing this study with this infographic (still in process), where we estimate the novelty of targets for some of the candidates in development:

If you've received it, then you either subscribed or someone forwarded it to you. If the latter is the case, subscribe by pressing this button:

Subscribe now

This week’s sponsor: Trialize

In the realm of clinical trials, efficient data management and monitoring are crucial yet often hampered by outdated and time-consuming practices.

Trialize's innovative approach to automating study builds and leveraging artificial intelligence (AI) for data analysis significantly reduced the time from protocol to trial, transforming the process from a traditionally months-long undertaking into a matter of days.

When inputting the study protocol, Trialize's AI analyses it to extract essential information, such as visit schedules, relevant forms, eCOA scales, and even drafts initial Informed Consent Forms (ICFs).

Trialize’s architecture offers a comprehensive, integrated solution covering all aspects of clinical trial management – from Electronic Data Capture (EDC) and Electronic Patient-Reported Outcomes (ePRO) to TeleVisits, eConsents, and Analytics. Its interface is designed to be intuitive and user-friendly, drastically reducing the learning curve for study teams.

Read Trialize’s case study Revolutionizing Clinical Trials: How AI and Automation Reduced Study Build Time from Months to Days, explaining the unique technical capacity of Trialize’s platform.

Now, let’s get to this week’s topics!

Share Where Tech Meets Bio

It’s Been a Decade of AI in the Drug Discovery Race. What’s Next?

I am excited to announce that BioPharmaTrend.com released a new study, called It’s Been a Decade of AI in the Drug Discovery Race. What’s Next?, which looks at the historical progress of AI in the pharma industry and the “apple-to-apple” comparison of 9 leading AI platforms.

A cool feature, I think, is that we tracked a historical progression of AI-designed drug candidates for the following companies: BenevolentAI, Exscientia, Insilico Medicine, insitro, Recursion, Relay Therapeutics, Schrödinger, Verge Genomics, and Valo Health.

It means, we found archived pipeline screenshots or company filing information and tracked each pipeline molecule from drug discovery all the way to where it is now (including setbacks and abandoned programs).

What it shows is the dynamics of how companies grew their programs from nothing to clinical pipelines. It is clear that the dynamics is way faster than ‘traditional’ companies, so AI seems to be helping accelerate the process.

Along with some financial analysis of AI companies, the report includes an overview of key M&A deals in 2018–2023, highlighting more than 30 significant deals mapped year by year.

It is clear the AI sector is consolidating and the entry barrier for new AI startups is growing.

One of the reasons is that newcomers just don’t have enough proprietary data to really compete with established players.

Big Pharma is also shifting toward partnering with well-established AI platforms for large and more strategic deals, compared to typical pilot collaborations some 5-7 years ago.

There is also an increasing role for infrastructure providers such as NVIDIA, Google, and Microsoft. They are expanding into drug discovery and can even compete with drug companies directly. (Read one of my previous newsletters where we discussed NVIDIA microservices.).

The report features basic financial analysis and revenue trends for the leading AI platforms, for those who are into balance sheets and P&Ls.

I hope the report can be a decent reference point for discussing AI in drug discovery!

Below, I am copying one of the chapters:

AI in Drug Discovery Sector Keeps Consolidating

The AI in the drug discovery and development race has been going for more than a decade now, and today we see all signs of the sector’s consolidation. 

Over the last 6 years, there have been more than 30 merger and acquisition events in this space.

According to the BiopharmaTrend report some of the AI-focused deals in drug discovery, biotech, and clinical trials space included:

• 2018 acquisition of Flatiron Health by Roche for $1.9 billion;

• 2019 acquisition of Numerate by Valo Health;

• 2020 acquisition of Haystack Biosciences by Insitro;

• 2021 acquisition of Prescient Design by Genentech;

• 2022 acquisition of Zymergen by Ginkgo Bioworks for $300 million;

• 2023 acquisition of InstaDeep by BioNtech for $549 million

• double acquisition of Cyclica and Valence Labs by Recursion Pharmaceuticals for around $90 million combined, to name just a few. 

Some of the notable deals are summarized in the figure below:

Another driver of consolidation is expansion of “big tech” giants into the life sciences, including NVIDIA, Alphabet, Microsoft and others. They leverage their cutting edge resources in artificial intelligence research, world-class tech infrastructures (software, cloud, computational power) and flexible business models. 

Famous successes include Alphabet subsidiary DeepMind in protein modeling space, Isomorphic Labs’ recent partnerships with Eli Lilly and Novartis, the advent of NVIDIA’s AI-based Clara Discovery platform for everything from drug design to healthcare research, and Microsoft Cloud for life sciences.

As Dr. Alex Zhavoronkov writes in his Forbes article: “In 2024, I predict NVIDIA will come out big with its healthcare platform so that the need for new AI in drug discovery (AIDD) companies will go away. Drug discovery players will be able to use NVIDIA tools in their cloud, on Amazon, or on massive clusters of NVIDIA GPUs locally. 

It is unlikely to hurt established AIDD players with end-to-end AIDD platforms and significant validation, but it will inhibit the formation of startups with little or now differentiation, and it will add more credibility to the field.”  

Dr. Zhavoronkov continues about Microsoft: “In 2024, we should expect to see massive growth in LLMs in pharma and biotech, with Microsoft being the main provider. Even when some LLM startups achieve superior performance in benchmarks and come up with new models, they do not stand a chance in big pharma. 

Pharma is very conservative; there are too many compliance and legal challenges to deploying generative AI from a new vendor. Microsoft made it easy to use the latest OpenAI models on Azure Cloud and to implement sophisticated AI platform architectures. And Microsoft works all over the world. I predict many internal-external LLM architectures will be built on the Microsoft platform”.

Next, according to the BiopharmaTrend report, venture capital firms are increasingly prioritizing smaller numbers of established AI in drug discovery players over new platform companies, which is a sign of consolidation. 

Finally, ‘big pharma’ and leading biotech corporations are increasingly shifting from external partnerships towards building their own AI muscle, effectively diminishing opportunities for novel startups to win R&D dollars.

Big Pharma is increasingly choosing well-established technology vendors and validated AI for drug discovery engines. 

The consolidation of AI in the drug discovery sector naturally led to the formation of a distinct group of AI frontrunners—companies that managed to build sufficient AI capabilities, robust business models, and win major clients. From Table 2 below, one can see that several companies, including Insilico Medicine, Recursion Pharmaceuticals, Schodinger, and XtalPi, demonstrate strong financials, compared to some of the peers in this space.

> > > read full report.

Share

Why This Quantum Computing/Gen AI Company Stock Sank After Debut

I’ve been following Zapata Computing ever since I had an interview with the company’s CEO, Dr. Christopher Savoie (watch here), where he explained the promises, opportunities and hype around quantum computing, including pharma/biotech applications.

Zapata Computing Holdings Inc., a Boston-based company known for its work in artificial intelligence and quantum computing, experienced a significant downturn during its first day on NASDAQ under the ticker ZPTA.

A 2023 collaborative study involving Zapata Computing, Insilico Medicine, Foxconn, and the University of Toronto has demonstrated the potential of hybrid quantum-classical generative adversarial networks (GANs) for the discovery of small molecules with pharmaceutical applications.

By integrating variational quantum circuits (VQCs) into the GAN framework, the research team successfully generated small molecules with superior physicochemical properties compared to those produced by purely classical GANs, indicating a significant advancement in the efficiency and effectiveness of drug discovery processes.

Zapata went public via the Special Purpose Acquisition Companies (SPACs) route, rathen than via the traditional IPO path. On April 1, stockes started trading on NASDAQ.

The merger with Andretti Acquisition Corp., a blank-check company led by former IndyCar driver Michael Andretti, initially raised $230 million in its 2022 IPO. but Zapata shares saw their share price plummet by 70% from their pre-merger valuation, closing at less than $3.

This event underscores the broader challenges faced by companies opting to go public through Special Purpose Acquisition Companies (SPACs), a trend that has been marked by heightened market volatility and investor hesitancy.

As Matt Swayne explains in his article for The Quantum Insider, due to a high rate of cash redemption by investors, the actual funds received by Zapata were substantially lower.

The redemption feature of SPACs, which allows investors to sell their shares back to the SPAC at the initial offering price, has contributed to this trend, with a median redemption rate of 96% observed in completed deals over the past year.

Founded in 2017 by Harvard researchers, Zapata initially focused on quantum computing, contributing to the development of quantum algorithms such as the Variational Quantum Eigensolver (VQE).

Despite shifting its primary focus to generative AI and optimization software, the company continues to advance its quantum computing initiatives, evidenced by the recent acquisition of patents related to quantum research.

Zapata boasts a prestigious clientele, including Sumitomo Mitsui Trust Bank, Banco Bilbao Vizcaya Argentaria SA, and BP Plc, illustrating its impact across various sectors.

In response to the market challenges, Zapata has engaged in strategic financial agreements to stabilize its position.

Among these is a partnership with Lincoln Park Capital Fund LLC, aimed at bolstering Zapata's balance sheet and ensuring liquidity. Additionally, a forward purchase agreement with Sandia Investment Management LP promises future financial support by setting terms for Sandia to acquire shares at a later date.

Christopher Savoie, CEO of Zapata, emphasized the advantages of being a public entity vs. a private one, highlighting access to diverse capital-raising strategies not available to private companies.

Leave a comment

New $1.4 Billion Alliance Towards AI-Driven ADC Development

In a significant move to advance cancer treatment, Germany's Merck KGaA has established a strategic partnership with Caris Discovery, a technology-driven biotechnology company, focusing on the utilization of artificial intelligence (AI) in the development of antibody-drug conjugates (ADCs).

This collaboration, valued at $1.4 billion, is structured around an initial payment, alongside research funding, and encompasses a range of financial incentives including discovery, development, regulatory, and sales-based milestones, as well as royalties on sales for any marketable ADCs resulting from the alliance.

The collaborative effort is set to span several years, targeting the discovery and design of ADCs against up to 15 unique cancer targets.

Caris Discovery will lead the initial discovery and design phase of the ADCs, leveraging its extensive clinical and omics data repository, AI analytics capabilities, and the ADAPT Biotargeting platform.

This platform is instrumental in identifying variances in protein expression patterns between diseased and healthy individuals, potentially uncovering new biomarkers or drug targets. Upon reaching the preclinical development phase, Merck, through its U.S. subsidiary, EMD Serono, will assume responsibility for further development.

The partnership is a key component of Merck's strategy to enhance the productivity of its R&D operations, with an ambitious goal of launching a new product every 18 months. ADCs represent a critical aspect of Merck's future R&D endeavors.

Merck's current ADC pipeline features CEACAM5-targeted M9140, a leading candidate developed using Merck's proprietary platform, currently undergoing early-stage clinical trials for colorectal cancer and other solid tumors.

This collaboration with Caris Discovery follows Merck's termination of a previous agreement with Mersana Therapeutics, although Merck continues to engage with Mersana on a separate $830 million project focused on STING-agonist ADCs. Additionally, Merck recently opted into a collaboration with Jiangsu Hengrui Pharmaceuticals for a claudin18.2-targeted ADC.

The Unexpected Side-Effect of AI Progress in Drug Discovery: Prior Art Flood

Artificial intelligence (AI) is significantly impacting the pharmaceutical industry, serving as a catalyst for new drug discoveries, but it also presents some non-obvious problems for patenting experts: complication of the patent application process due to the creation of extensive AI-generated prior art.

The industry's engagement with AI spans drug design to molecule identification, with major pharmaceutical companies partnering with AI firms to enhance their drug discovery pipelines.

Prior art in the legal realm refers to any evidence that an invention is already known before a given date, potentially affecting its patentability due to lack of novelty.

Pharmaceutical companies are increasingly encountering AI-generated prior art during patent applications, a scenario where evidence suggests an invention is already known, thereby making it ineligible for patenting.

This phenomenon is raising concerns about the potential hindrance to innovation, as companies may be deterred from investing in R&D without the prospect of patent protection.

The novelty of an invention is a cornerstone of patent eligibility, and AI's capability to rapidly generate vast amounts of prior art is challenging this principle.

Legal professionals and academics highlight the paradox of AI in drug discovery. This issue is not just theoretical; litigation cases have already seen the use of AI-generated material to challenge patents.

The United States Patent and Trademark Office (USPTO) has recognized the need to address AI's role in the creation of prior art.

Although current guidelines permit the use of AI to assist inventors, they exclude purely AI-generated inventions from patent eligibility. However, the USPTO has yet to clarify how AI-generated prior art will be treated.

The pharmaceutical industry's reliance on patents to secure ROI on R&D investments is well-documented. With annual R&D expenditures exceeding $100 billion, the stakes are high. AI's potential to disrupt this investment by complicating the patenting process could have significant implications for drug development and public health.

This, of course, opens doors to various types of patent trolls, entities that acquire patents not to produce or further develop the underlying inventions but to profit from licensing fees or litigation against alleged infringers.

Legal experts suggest strategies to mitigate the impact of AI-generated prior art, including emphasizing human involvement in research and focusing on in-depth experimental data in patent applications.

Additionally, the concept of defensive publications—public disclosures intended to prevent others from patenting the same invention—is being explored as a countermeasure against AI-generated prior art.

Legal and regulatory frameworks will need to adapt to ensure that AI serves as a complement rather than a hindrance to innovation. The ongoing dialogue between the USPTO, legal professionals, and the pharmaceutical industry is critical to shaping the future of AI in drug development and patenting.

Share

A Case of AI-enabled Target Discovery

When I was researching Berg Health a while ago (they were acquired by BPG Bio in 2023), I came across a really neat infographic describing the process of AI-enabled ontology construction and target discovery, starting with some human samples to mine omics data.

The infographics depict the timeline approximation for such a process, which I guess is a good reference point to benchmark against other (legacy) R&D strategies:

BPGbio stands out in the biopharma sector by applying a Bayesian approach to artificial intelligence (AI), a method that's less common compared to the widely used machine learning techniques.

Bayesian methods leverage Bayes' Theorem to update the probability of a hypothesis as new evidence is introduced, effectively incorporating prior knowledge and observed data into a coherent framework of probabilistic inference.

These methods start with initial assumptions (priors) and refine these assumptions into updated probabilities (posteriors) based on new data, allowing for a dynamic and adaptable approach to modeling uncertainty.

Unlike fixed dataset-dependent machine learning techniques, Bayesian methods excel in situations where data is incomplete or uncertain, continuously evolving their predictions as more information becomes available.

This approach utilizes the enormous processing power of the world's first exascale supercomputer, Frontier, to analyze vast amounts of data from patients, reaching trillions of data points for each.

Through Bayesian networks, the company maps the intricate relationships between variables in large-scale multi-omics datasets, gaining deep insights into human biology and identifying new targets for drugs and diagnostics. This method allows for hypothesis generation directly from the data, avoiding the biases that can affect machine learning models trained on data with existing assumptions.

BPGbio's application of this method has already yielded promising therapeutic and diagnostic discoveries, including their lead program, BPM31510.

The company plans to conduct a Phase IIb study of BPM 31510 as a first-line therapy in combination with chemotherapy for pancreatic cancer.

The development of oncology drugs faces significant challenges, including a high failure rate (97%) in clinical trials, due to complex genetic interactions, emerging drug resistance, and limitations in preclinical models.

Clinical trial designs often lack specificity, failing to consider genetic factors unique to cancer types, resulting in trials without biomarker integration being 12 times more likely to fail.

To address these issues, Dallas-based Lantern Pharma (NASDAQ: LTRN) utilizes the RADR® AI platform, which applies machine learning to analyze genomic and transcriptomic data, enhancing the understanding of drug mechanisms, identifying patient-specific therapeutic responses, and optimizing clinical trial designs.

In this deep dive interview, Panna Sharma, the CEO of Lantern Pharma, offers an insightful look into the company's progression in the challenging fields of cancer research, drug discovery, and the use of artificial intelligence.

Sharma, with his diverse background that includes leading a cancer diagnostics company and a stint in investment banking, discusses Lantern Pharma's expansion from a small, budding team to a formidable force in the oncology sector, now managing 14 cancer indications and advancing several drugs into clinical trials.

He highlights pivotal moments in his career, such as taking Cancer Genetics public in 2013 and joining Lantern Pharma in 2018, leading up to a successful public fundraising effort in mid-2020 that raised about $96 million.

The conversation also ventures into the establishment of Starlight Therapeutics, focused on brain cancer research.

The history behind Starlight Therapeutics is truly inspiring for AI fans! It was born out of spontaneous patterns that AI identified while being applied to searching for a different thing. The team at Lantern did not even pay attention to that discovery, at first, thinking it was just an artefact. Later, they did a second run, and when the result persisted, the story began for the new R&D direction that would eventually be formed into a separate company.

If you've received it, then you either subscribed or someone forwarded it to you. If the latter is the case, subscribe by pressing this button:

Subscribe now

Now, let’s get to this week’s topics!

Disclaimer: This post is not medical advice of any kind, it is for informational and educational purposes only.

How AI Empowers Biomarker-Driven Clinical Trials

(This article is sponsored by Lantern Pharma (NASDAQ: LTRN))

Clinical trials are the lifeline of modern medicine, bridging the gap between lab-borne scientific discoveries and the availability of life-saving treatments for patients. Unfortunately, the success rate of clinical trials, particularly in the field of oncology, is not as robust as one might hope. In fact, a 2019 study of 7,455 interventional phase trials in oncology conducted from 2000 to 2015 suggests an estimate that only 3.4% of cancer drugs that enter Phase I clinical trials ultimately receive FDA approval. Many of these failures can be attributed to obstacles such as poor trial design and inefficient patient selection, often resulting from a lack of biomarker-driven insights. As a result, drug development can be a laborious and expensive process, with the cost of bringing a new drug to market estimated to be around $2.6 billion. As we grapple with these challenges, there is an urgent call for more efficient and targeted methods of drug development, and the answer may lie in the utilization of novel actionable biomarkers and the power of artificial intelligence (AI) to plan and execute clinical trials. For instance, IQVIA's artificial intelligence-based platform, using their Real World Data assets, have enabled precise patient and healthcare professional (HCP) targeting, doubling identified eligible patients, finding 30% more with uncontrolled symptoms, predicting 81% likely to quit treatment early, pinpointing events linked to early discontinuation, and boosting treatment transition success by 500% compared to prior methods.

What is a clinical trial?

Clinical trials form an integral part of the drug development process. They are carefully designed studies involving human participants, undertaken to determine the safety and efficacy of a new drug or medical device. This process is usually divided into four stages. Phase I trials primarily assess safety and dosage in a small group of healthy volunteers or patients. Phase II trials involve a larger group of patients and aim to assess the drug's efficacy and side effects. Phase III trials test the drug in an even larger group of patients over a longer period of time to confirm its effectiveness, monitor side effects, and compare it to commonly used treatments. 

Designing clinical trials for central nervous system (CNS) drug evaluation, for example, for brain tumors, represents an additional challenge due to unique properties of the blood-brain barrier (BBB). The BBB's unique and stringent selectivity often necessitates the implementation of specialized Phase 0 trials in CNS oncology programs. Because of BBB, these trials require higher systemic drug concentrations to achieve detectable levels within the CNS, as compared to other therapeutic areas, increasing the complexity and risk of the process. 

The arena of clinical studies encompasses various approaches, including double-blind studies and more transparent strategies like open-label trials. With high failure rates in drug development, biomarkers are emerging as pivotal components of clinical trial experiment design, refining patient selection for more accurate outcomes. The trend towards using master protocols indicates a push for efficiency, as this model allows simultaneous examination of various treatments. More specialized frameworks, like basket and umbrella trials, further incorporate factors such as genetic biomarkers, reflecting the industry's shift towards more nuanced methodologies.
 

The Evolution of Clinical Biomarkers

Advancements in Next-Generation Sequencing (NGS) and our understanding of the human genome have revolutionized the field of biomarker discovery, particularly in oncology. Traditional biomarkers often utilized circulating markers in blood, plasma, and serum, or those detectable through imaging techniques. However, with the advent of genomics, we have been able to delve deeper, identifying individual genetic variations that play pivotal roles in disease pathology, specifically in cancers where genetic mutations often take center stage.

One of the defining moments in this biomarker-led therapeutic revolution was the approval of Herceptin (trastuzumab), a monoclonal antibody, by the FDA in 1998. Designed to target the HER2 protein, it was used to treat HER2-positive metastatic breast cancer, either as a first-line therapy in combination with other drugs, or as a standalone second-line treatment. This represented a significant stride forward in targeted cancer therapy, and opened the floodgates for similar advances. Today, we have a plethora of HER2-targeting drugs, including Tyrosine Kinase Inhibitors (TKIs) such as neratinib, lapatinib, and tucatinib, which have broadened the therapeutic scope beyond breast cancer to other cancers that overexpress the HER2 protein or exhibit HER2 gene amplification.

HER2's sibling in the human epidermal growth factor receptor (ErbB) family, EGFR (also known as HER1), has been another game changer in the oncology biomarker landscape. EGFR mutations or overexpression are commonly found in many cancers, including glioblastoma, lung cancers, colorectal cancer, head and neck cancer, and breast cancer. The development of EGFR-inhibiting drugs such as TKIs (erlotinib, gefitinib, lapatinib) and monoclonal antibodies (cetuximab and panitumumab) have further emphasized the significant role of biomarkers in targeted cancer therapy.

Share

Biomarker-driven clinical trials

The story of biomarker evolution in oncology doesn't stop here. Apart from HER2 and EGFR, numerous other biomarkers like KRAS, BRCA1/2, and PD1/PD-L1 have shaped the therapeutic strategies for several cancers, including breast cancer, non-small cell lung cancer, and ovarian cancer. Additionally, an astounding number of 76 biomarkers have been identified as potential indicators of tumor invasiveness, including S100 proteins, annexins, galectins, CATD, TGM2, gelatinases, fibronectins, proteoglycans, TGFBI, FGG, APMAP, and more. The oncology biomarker discoveries underpin a remarkable shift towards personalized medicine, where treatment decisions are increasingly driven by the individual patient's unique genetic makeup.

In the intricate world of clinical trials, biomarkers serve as a guiding light, enabling more accurate prediction of therapeutic success and shaping the course of personalized medicine. Their contribution to medical progress has been highlighted by a comprehensive study that scrutinized over 10,000 clinical trials and focused on 745 drugs. The findings are powerful: introducing the factor of biomarker status significantly improved the prediction model for the trajectory of drugs throughout different clinical trial stages.

The 2021 study published in Cancer Medicine, employed two Markov models, which represent a statistical method that calculates the probability of transitioning from one state to another. When observing the effects of biomarker application across various types of cancers, the advantage was clear. The hazard ratios – the probability of a drug's approval – were significantly elevated when biomarkers were employed. For all indications combined, there was nearly a fivefold increase in the chances of drug approval. The most striking improvements were seen in specific cancers: a 12-fold increase for breast cancer, an 8-fold boost for melanoma, and a 7-fold growth for non-small cell lung cancer (NSCLC). Even for exploratory biomarkers that are not yet FDA approved, the model incorporating these biomarkers outperformed the model without biomarkers by 4-fold.

Nevertheless, biomarkers are not a foolproof guarantee of success. If they are not fully validated, they can potentially contribute to unsuccessful clinical trial outcomes. 

Artificial Intelligence: A game changer in clinical trials

In the modern era, Artificial Intelligence, or AI, has found utility across a diverse range of sectors, including healthcare. AI refers to the development of computer systems capable of performing tasks that typically require human intelligence. It encompasses a range of applications, from learning from experience and interpreting complex data to drawing conclusions and making decisions.

Now, the world of clinical research, particularly biomarker-led trials, is witnessing an AI revolution. The sheer complexity and volume of data in these trials call for a technological intervention. AI, with its capacity to process vast amounts of data, detect potential biomarkers, and even forecast patient responses, is transforming how clinical trials are designed and executed. Already now, AI-powered tools demonstrate tangible improvements in oncology clinical trials, such as a 50% increase in identifying potentially eligible patients and a 25% reduction in time for patient screening. Moreover, in automating trial matching and eligibility determinations, AI algorithms, applied to both structured and unstructured data, have achieved accuracies up to 87.6% with agreements between manual professionals and AI algorithms ranging from 81% to 94% in areas like breast cancer trials.

AI-based platforms are becoming transformative tools in the clinical trials landscape. Notable companies like Lantern Pharma, Owkin, and Biotx.ai, to name a few, are leveraging AI platforms for improving drug discovery and clinical trials, marking strides in the industry.

To illustrate this, Dallas-based clinical-stage precision oncology company Lantern Pharma, for instance, developed AI drug discovery platform RADR® which leverages transcriptomic, genomic, and drug sensitivity data from diverse sources, analyzing a vast volume of over 25 billion clinical data points, 154 drug-tumor interactions, and 130,000+ patient records across 17 databases. By integrating public resources, commercial studies, and Lantern's ex vivo 3D tumor models, the platform establishes correlations between genetic biomarkers and drug activity. Through this comprehensive approach, RADR® enables the transformation of multi-omics data into predictive models, facilitating the identification of candidate biomarkers and enhancing patient stratification for optimized clinical trial design. 

Utilizing their RADR® platform, Lantern Pharma tapped into AI to uncover the crucial role of the biomarker PTGR1 for their drug candidate LP-184. With this AI-led guidance, it became clear that LP-184 could be particularly effective against cancers with DNA Damage Repair (DDR) vulnerabilities. This insightful revelation, rooted in artificial intelligence, has paved the way for LP-184's upcoming clinical trials, aiming to target specific cancers such as pancreatic, prostate, ovarian, and breast that exhibit HR/NER pathway discrepancies.

In another example, Paris and New York-based precision oncology company Owkin developed AI-driven biomarker models to predict treatment response to immune checkpoint inhibitor (ICI) and prognosis in Non-Small Cell Lung Cancer (NSCLC) patients from clinical and histological data.

Owkin collaborates with leading academic centers to curate deep, multimodal data that is AI-ready, and they are developing a technology platform, Abstra, designed to expedite AI biomedical research by helping researchers discover collaborators and datasets. Through the application of AI to this rich data, they subtype patients, pinpoint novel biomarkers, and enhance drug discovery while reducing clinical trial risks.

Berlin-based Biotx.ai utilizes a combination of expert judgment, mechanistic validation, and artificial intelligence to identify drug candidates poised for success in phase IIb. Led by Jack Scannell, the expert drug selection committee assesses treatments using their synthetic clinical trial platform, which predicts drug efficacy and side effects based on independent mechanistic models. These potential treatments are unearthed using unique wide data algorithms that uncover intricate relationships between genes, revealing links between drug targets and diseases. Instead of the common big data approach, Biotx.ai focuses on wide data, deciphering complex patterns from limited examples by employing knowledge graphs to simplify hypothesis spaces, using predictive power algorithms. Their prowess was evident when they identified a link between variants on the CDK6 gene and severe COVID-19 outcomes, which was subsequently verified by the University of Bristol through in-vitro testing.

7th Annual Cell & Gene Therapy Innovation Leaders Summit 2024

Event Date: Feb. 7, 2024 - Feb. 8, 2024

Location: Spain, Barcelona, Atzavara Hotel & Spa

Website: 7th annual Cell & Gene Therapy Innovation Summit #CGTI 2024

Promo Code exclusive to our readers: BIOTREND20

With more regenerative medicine products approaching clinical testing and commercialisation, seize this opportunity to hear detailed insights and industry best practices from renowned presenters.

Achieve a deeper understanding of the many manufacturing and industrialisation burdens unique to carrying durable and curative therapies to needy patients.

The Shift to Decentralized Clinical Trials

As the FDA increasingly embraces decentralized clinical trials (DCTs), the industry is responding by exploring new ways to conduct clinical research. Decentralized clinical trials companies are leveraging technology such as telemedicine, mobile apps, and wearables to facilitate remote data collection and monitoring. This shift is driven by the need to improve trial efficiency, reduce costs, and enhance patient accessibility.

Pros of Decentralized Clinical Trials

1. Improved patient access and diversity: DCTs allow patients from various geographic locations and backgrounds to participate, leading to more representative and inclusive trials.

2. Reduced burden on patients: Patients can participate from the comfort of their own homes, eliminating the need for frequent travel to clinical trial sites.

3. Faster enrollment and retention: The convenience and flexibility of DCTs can lead to faster patient recruitment and reduced dropout rates.

4. Real-time data collection: Continuous monitoring through digital devices enables real-time data collection and analysis, improving the overall quality of data.

   Share

Cons of Decentralized Clinical Trials

1. Data security and privacy concerns: Protecting sensitive patient information and maintaining data integrity is critical, necessitating robust security measures.

2. Technological barriers: Limited access to technology or connectivity issues can exclude certain patient populations or introduce bias in the results.

3. Regulatory challenges: As DCTs are relatively new, regulatory bodies like the FDA are still developing guidelines to ensure compliance and safety.

Several companies have already adopted decentralized clinical trials with notable success. Science 37, a prominent DCT company, has collaborated with major pharmaceutical firms such as Novartis and Sanofi to conduct remote trials. In one particular case, their partnership with AOBiome led to the successful completion of a Phase 2b trial for a novel acne treatment, with 372 participants recruited in just three months.

Another example is Medable, which has developed a digital platform to streamline the DCT process. Their collaboration with PPD, a global contract research organization, has enabled more efficient and patient-centric trials across various therapeutic areas.

Several drug candidates have been tested or are being tested using DCTs. For instance, Pfizer's COVID-19 vaccine trials included a decentralized component, utilizing telemedicine and remote monitoring to manage a large participant pool.

RELATED: 9 Notable AI Companies in Clinical Research to Watch in 2023

Notable decentralized clinical trial companies:

Science 37 (https://www.science37.com/): 

Science 37 is a leader in decentralized clinical trials, offering an end-to-end solution through its NORA (Network Oriented Research Assistant) platform. The platform includes features such as telemedicine, eConsent, ePRO, and eCOA, enabling remote patient participation and data collection for various therapeutic areas.

Medable (https://www.medable.com/): 

Medable provides a flexible, modular platform for decentralized clinical trials, offering capabilities such as remote data collection, patient monitoring, and eConsent. Their platform aims to streamline the clinical trial process, increase patient engagement, and reduce study timelines.

THREAD Research (https://www.threadresearch.com/): 

THREAD specializes in decentralized clinical trials with a comprehensive platform that includes telehealth, eConsent, ePRO, and eCOA solutions. They focus on offering patient-centric experiences, which can improve recruitment and retention rates in clinical trials.

PRA Health Sciences (acquired by ICON) (https://www.prahs.com/): 

PRA Health Sciences (now ICON) offers a range of services for decentralized clinical trials, including remote patient monitoring, virtual site visits, and digital health tools. Their solutions are designed to provide flexibility and scalability, enabling sponsors to conduct trials efficiently and with improved patient outcomes.

Covance (https://www.covance.com/): 

As a part of Labcorp, Covance provides services for decentralized clinical trials that include patient recruitment, remote monitoring, and digital endpoints. They leverage their extensive clinical research experience to offer tailored solutions for various therapeutic areas and study types.

IQVIA (https://www.iqvia.com/): 

IQVIA is a global provider of advanced analytics, technology solutions, and contract research services. They offer a suite of solutions for decentralized clinical trials, including data management, virtual site visits, and patient engagement tools, designed to optimize trial efficiency and improve patient experiences.

Parexel (https://www.parexel.com/): 

Parexel is a global clinical research organization that offers a variety of services for decentralized clinical trials. Their solutions include eClinical platforms, digital health tools, and remote patient monitoring, which aim to enhance patient engagement and streamline the clinical trial process.

Oracle Health Sciences (https://www.oracle.com/industries/life-sciences/): 

Oracle offers a cloud-based platform for decentralized clinical trials, featuring data management, patient engagement, and remote monitoring solutions. Their integrated platform is designed to support innovative trial designs and improve trial efficiency.

Evidation Health (https://evidation.com/): 

Evidation Health focuses on generating real-world evidence from decentralized clinical trials by leveraging digital technology for data collection and analysis. Their platform enables the measurement of patient behavior and outcomes outside of traditional clinical settings, providing valuable insights for healthcare decision-making.

ObvioHealth (https://www.obviohealth.com/): 

ObvioHealth offers an end-to-end solution for decentralized clinical trials, including patient recruitment, remote data collection, and virtual site management. Their platform, ClaimIt, combines mobile technology, telemedicine, and data analytics to facilitate efficient and patient-centric clinical trials.

AI Technologies and Decentralized Clinical Trials

AI technologies are transforming various aspects of decentralized clinical trials, from patient recruitment to data analysis. Here are some key areas where AI is making a significant impact:

1. Patient recruitment and retention: AI algorithms can analyze vast amounts of patient data from electronic health records (EHRs), social media, and other sources to identify potential trial participants. This targeted approach improves recruitment rates and ensures a diverse and representative study population. Additionally, AI-driven chatbots and virtual assistants can improve patient engagement, leading to better retention rates throughout the trial.

2. Trial design optimization: AI can help optimize trial design by analyzing historical data and simulating different scenarios to predict outcomes. This can lead to more efficient study designs, reducing the duration and cost of trials, and enhancing the overall success rate.

3. Real-time data analysis: AI-driven analytics platforms can process and analyze large volumes of data collected during decentralized clinical trials, including data from wearables, mobile apps, and telemedicine consultations. This enables real-time monitoring, early detection of potential safety issues, and quicker decision-making.

4. Personalized interventions: AI technologies can analyze individual patient data to recommend tailored interventions, enhancing the patient experience and improving outcomes. In decentralized clinical trials, personalized medicine can lead to better treatment adherence and more accurate evaluations of drug candidates.

5. Regulatory compliance: AI can help decentralized clinical trials companies ensure compliance with FDA and other regulatory guidelines by automating data validation, monitoring data integrity, and identifying potential discrepancies in real-time.

Below let’s review eight companies making waves in the DCT landscape, showcasing the remarkable progress they've made in recent years. From blockchain-powered data management to AI-driven patient recruitment, these cutting-edge organizations are breaking down traditional barriers and empowering patients to participate in trials with greater ease, flexibility, and convenience.

The space is dominated by large contract research players, like IQVIA, In this post, we will review eight relatively young companies enabling decentralized clinical trials. 

Deep 6 AI

Deep 6 AI is a health technology company founded in 2015, specializing in artificial intelligence (AI) solutions for decentralized clinical trials. Their platform focuses on patient recruitment, trial feasibility, and site selection by analyzing structured and unstructured real-world data from electronic health records (EHRs) and other sources.

Using natural language processing (NLP) and machine learning algorithms, Deep 6 AI's platform identifies eligible patients for clinical trials based on specific criteria such as demographics, medical history, and diagnoses. This helps researchers expedite the recruitment process, which is often a time-consuming and costly aspect of clinical trials.

The platform also assists in determining trial feasibility by providing insights into patient populations, ensuring trials are designed with realistic expectations. Additionally, Deep 6 AI's solution aids in selecting the most suitable trial sites, factoring in aspects like patient availability, site performance, and investigator experience.

ClinTex

ClinTex is a health technology company founded in 2017 that utilizes blockchain and machine learning to enhance the efficiency and cost-effectiveness of decentralized clinical trials. Their primary product, Clinical Trials Intelligence (CTi), is a suite of seven applications aimed at addressing various clinical trial pain points.

By leveraging blockchain technology, ClinTex ensures data integrity, security, and transparency, which are crucial in clinical trial processes. CTi's machine learning algorithms identify trends, predict outcomes, and optimize trial performance by analyzing data from various sources, enabling proactive issue resolution.

CTi offers a range of applications, including operational analytics, predictive recruitment, and risk-based monitoring, to streamline trial management, reduce patient attrition, and improve trial performance. Its real-time monitoring capabilities allow for better collaboration and informed decision-making among stakeholders.

In summary, ClinTex is revolutionizing decentralized clinical trials with its blockchain-based Clinical Trials Intelligence platform. By utilizing machine learning and blockchain technology, ClinTex aims to improve trial efficiency, reduce costs, and accelerate the development of new medical treatments.

Aural Analytics

Aural Analytics is a health technology company founded in 2015 that focuses on developing speech analytics as a digital biomarker for use in decentralized clinical trials. Their platform is designed to monitor and assess neurological, respiratory, and mental health conditions by analyzing patients' speech patterns.

The technology behind Aural Analytics is built on advanced algorithms and machine learning techniques that extract clinically relevant information from speech data. This includes aspects like pronunciation, fluency, and rhythm, which can provide insights into a patient's health status and disease progression.

One of the key advantages of Aural Analytics' platform is its ability to support multiple languages and work across various devices, making it adaptable and inclusive for clinical trials conducted in different countries and populations.

In decentralized clinical trials, the platform enables remote patient monitoring, reducing the need for in-person assessments. This not only improves patient convenience but also helps in increasing trial participation and retention rates. Additionally, it allows researchers to collect data continuously, providing real-time insights into treatment efficacy and safety.

Savvy Cooperative

Savvy Cooperative is a patient-owned platform founded in 2017, focusing on connecting patients and researchers to enable patient-centric decentralized clinical trials. By facilitating collaboration and data sharing between patients and researchers, Savvy Cooperative aims to improve the clinical trial process and accelerate medical advancements.

As a co-op, Savvy Cooperative empowers patients to become active partners in research, giving them a voice and an opportunity to share their experiences and insights. This approach ensures that trial designs are more patient-centered and reflective of the needs and preferences of the target population. Researchers can access a diverse pool of patient insights, leading to more effective trial outcomes and faster development of new treatments.

Savvy Cooperative offers various services, including patient recruitment, survey design, patient experience research, and user testing. By engaging patients directly, the platform helps address common challenges in clinical trials, such as recruitment and retention, while simultaneously promoting patient advocacy and involvement in the research process.

Teckro

Teckro is a clinical trial technology company founded in 2015 in Ireland. Their digital platform aims to simplify and modernize clinical trial conduct by streamlining trial management and providing mobile access to essential information. Teckro's solution enhances efficiency, communication, and collaboration among sponsors, CROs, trial sites, investigators, and patients.

Key features include mobile access to trial information, real-time updates and notifications, secure communication, machine learning and AI for optimized search and retrieval of trial data, and integration with existing systems. With Teckro's mobile app, investigators and clinical trial staff can quickly access study protocols, inclusion and exclusion criteria, and other critical trial details. The platform's real-time updates help maintain consistency across trial sites and improve overall trial conduct. By leveraging machine learning and artificial intelligence, Teckro ensures efficient decision-making and improved patient care.

myClin

myClin is a Philadelphia-based company that offers a secure, collaborative platform for clinical trial management. Founded in 2008, myClin focuses on streamlining communication, document management, and compliance tracking among clinical research stakeholders, including sponsors, contract research organizations (CROs), clinical trial sites, and investigators.

myClin's platform addresses some of the key challenges in clinical trial management, such as information silos, fragmented communication, and inefficient document handling. By providing a centralized, user-friendly system, myClin makes it easier for clinical trial teams to work together and ensure that essential trial information is easily accessible and up-to-date.

Andaman7

Andaman7 is a Belgium-based health technology company founded in 2015. The company's primary focus is on creating a patient-centered platform for decentralized clinical trials, as well as for the management of personal health records. Their vision is to improve the overall healthcare ecosystem by facilitating collaboration between patients, researchers, and healthcare professionals while ensuring patient privacy and data security.

Andaman7's solution is a mobile application called A7 Health, which serves as a personal health record (PHR) for patients and a remote data collection tool for researchers. The app empowers patients by allowing them to collect, store, and manage their health data securely on their smartphones. Additionally, the platform enables patients to share their data with healthcare providers, researchers, and other authorized parties on a need-to-know basis, maintaining control over their information.

Reify Health

Reify Health is a healthcare technology company that focuses on accelerating clinical trials and improving the overall clinical research process. Founded in 2013 and headquartered in Boston, Massachusetts, Reify Health provides a cloud-based platform designed to streamline clinical trial management for sponsors, clinical research organizations (CROs), and clinical trial sites.

Reify Health's primary product is StudyTeam, a platform that offers an array of tools and features for clinical trial management, and it can be integrated with EHRs.

Examples of AI success in clinical trials: Case study based on IQVIA’s reports

1. Improved Precision in Identification of Asthma Patients With Unmet Needs Using Predictive Models:

IQVIA's machine learning capabilities allowed the client to improve precision in targeting uncontrolled asthma patients by 30%.

A 6-month analysis of real-world data post-launch showed a 17% reduction in uncontrolled disease status for asthma patients in the region compared to pre-launch figures.

Patients that were accurately predicted to have a high likelihood of having asthma were 86%, eliminating around 30% of non-target patients based on the machine learning prediction versus rules-based findings.

2. Leveraging Machine Learning to Optimize Care for Patients with Type 2 Diabetes and Obesity:

In a span of just 3 weeks, IQVIA customized two distinct machine learning applications to specifically identify patients with unmet needs in T2D and obesity.

3. Machine Learning Predicted and Improved Transition of More Patients to Better Treatments:

The machine learning solution expanded patient identification from ~1,000 patients per month to ~2,000 per month.

Patients predicted by IQVIA’s AIML solution to initiate a biologic for asthma had a rate of transition that was 5 times greater than those identified using the previous rules-based approach.

A 3-month analysis of control groups showed that healthcare providers prioritized by IQVIA's machine learning solution had a 20% increase in patients initiating the client’s therapy, thus facilitating quicker access to the right treatment.

4. Boosting Adherence in MS Patients

Situation: A biotechnology firm wanted to know why multiple sclerosis patients stopped their selective immunosuppressant treatment early.

Solution: Using IQVIA’s Real World Data and machine learning, a predictive model was built. This model used data from IQVIA PharMetrics® Plus and physician data from the American Medical Association.

Outcome: The model predicted patients at high risk of early discontinuation with 81% accuracy, and none with the lowest predicted risk discontinued.

5. Identifying At-Risk Lymphoma Patients

Situation: A newly FDA-approved drug for lymphoma needed to be promoted as a second line of treatment.

Solution: Using AI/ML, IQVIA identified patients unresponsive to the first line of treatment, allowing more focused promotional efforts.

Outcome: There was a 27% increase in therapy starts for the client’s drug in just 5 months.

6. Predicting Non-Adherence in Lupus Treatment

Situation: A treatment for lupus showed patients on average received one month less therapy compared to other brands.

Solution: IQVIA employed AI/ML to detect potentially non-adherent patients.

Outcome: About 900 patients at risk of early discontinuation were accurately identified, allowing timely interventions.

7. Diagnosing Exocrine Pancreatic Insufficiency (EPI)

Situation: A pharma company's product treated EPI, which often goes undiagnosed.

Solution: Machine learning identified potential EPI patients who remained undiagnosed.

Outcome: Over a 20-month period, the model predicted patients were up to 39 times more likely to get an accurate diagnosis and treatment for EPI.

8. Enhancing Early Treatment Adoption in Oncology

Situation: A client wanted to promote early adoption of their oncology treatment.

Solution: Three machine learning algorithms were developed by IQVIA to identify patients likely to initiate early treatment.

Outcome: The AI algorithm increased the precision of patient identification by 15 times and achieved a treatment transition rate of 28% over three months.

9. Predicting Treatment Transition in Autoimmune Therapy

Situation: A pharma client had a second-line treatment for an autoimmune disease and faced market competition.

Solution: IQVIA’s machine learning algorithm identified patients likely to seek an alternative treatment, linking them to their healthcare providers.

Outcome: The client was able to prioritize outreach to high-risk patients and physicians, ensuring better treatment transitions.

If you've received it, then you either subscribed or someone forwarded it to you. If the latter is the case, subscribe by pressing this button:

Subscribe now

Now, let’s get to this week’s topics…

Unveiling Lantern Pharma's Success Story in AI-powered Precision Oncology

(Sponsored by Lantern Pharma)

Dallas-based clinical stage biotech Lantern Pharma (NASDAQ: LTRN) has developed AI-driven RADR® platform which is now reimagining oncology drug development by identifying novel mechanism of action (MoA), expanding the space of therapeutic indications and drug combinations, and creating patient response signatures to design focused clinical trials with better success rates. 

This is actual precision oncology, enabled by artificial intelligence, so let’s delve into this a bit deeper today. 

The current challenges in oncology drug discovery include the high failure rate of potential drugs, mischaracterization of drug targets and their inhibitors, and ineffective clinical trial designs. RADR® analyzes over 25 billion data points from genomic and transcriptomic data, thereby helping identify the most suitable patient groups for specific therapies. This increases the likelihood of successful clinical trials and FDA approval, thereby mitigating risks and optimizing success in drug development.

One recent success story is Lantern's IND clearance for LP-184, a synthetically lethal small molecule developed entirely using RADR® insights. The company also dosed its first patient in the Phase 2 multi-center Harmonic™ clinical trial earlier in 2023, while LP-300 increased survival rates for never-smokers with advanced non-small cell lung cancer. Furthermore, Lantern garnered an Orphan Drug Designation (ODD) for LP-284 for treating mantle cell lymphoma, one of the four ODD stage drug candidates in its pipeline.

The operation of Lantern Pharma's RADR® platform involves a complex, yet finely tuned process of data analysis and interpretation. 

It begins by ingesting a vast array of data, including transcriptomic, genomic, and drug sensitivity information, sourced from public resources, commercial clinical studies, and Lantern's ex vivo 3D tumor models. Utilizing machine learning algorithms, the platform analyzes over 25 billion data points, 154 drug-tumor interactions, and more than 130,000 patient records across 17 databases. It then correlates this wealth of data with genetic biomarkers and drug activity to create an optimal model predicting drug responses. This unique process assists in generating candidate biomarkers, leading to more precise patient stratification for clinical trial design. Additionally, RADR® can adapt its operational workflow to cater to different stages of drug candidates, aiding in defining indications, combinations, and doses. The platform's capabilities extend to augmenting success rates and de-risking clinical trials, thereby fast-tracking the delivery of vital therapies and potentially improving patient outcomes.

Lantern Pharma welcomes collaborations to help its partners increase the value of their oncology assets. 

Lantern Pharma's AI-driven platform holds value for the broader scientific community. The company has a history of successful partnerships with leading organizations, including Actuate Therapeutics (drug candidate Elraglusib, in Phase 2), and TTC Oncology (drug candidate TTC-352, in Phase 1), as well as collaborations with John Hopkins, Fox Chase, UT Health San Antonio, Danish Cancer Society Research Center, Mayo Clinic, and others. For instance, in a recent collaboration with the National Cancer Institute (US), Lantern Pharma utilized its artificial intelligence platform, RADR®, to aid in the discovery of a DNA damaging agent for the ultra-rare cancer known as Atypical Teratoid Rhabdoid Tumors (ATRT), an advancement discussed in a newly published paper. 

There is an interesting data from a recent poster (#3079) presented at ASCO 2023, where Lantern Pharma’s RADR® AI platform managed to predict Elraglusib’s clinical response to metastatic melanoma, resistant to checkpoint inhibitors, with 88% accuracy --  for a group of 26 patients, a pretty impressive result as to me.  

Read the full article exploring the years-long path of RADR® platform here. 

Share

Digital Pathology: The New Frontier in Drug R&D and AI Integration

According to a survey commissioned by Proscia, approximately 75% of life sciences organizations have invested in digital pathology to advance drug R&D, although over half (53%) continue to rely predominantly on legacy software systems. The survey involved 40 senior executives from leading pharmaceutical companies and CROs, revealing a rising necessity for integrating teams, applications, AI, and pathology data through modern software platforms to streamline all R&D stages. It highlighted that digital pathology is perceived as a solution to R&D's major challenges, with 83% of respondents citing improved collaboration and streamlined operations as primary motivations for digitization. Interestingly, the technology is considered by 80% of respondents as a way to bypass lengthy timelines and by 68% as a cost reduction method. Notably, AI implementation in digital pathology is becoming commonplace, with 82% of users having begun to incorporate AI and 87% using image analysis applications. Finally, the survey highlighted that creating data assets through digital pathology, seen as a significant driver by 55% of respondents, offers a new opportunity for valuable real-world data acquisition.

Open-Source Collaboration Pivotal in Life Sciences Research, According to Survey

Seqera Labs' study reveals 72% of 500 surveyed researchers globally regard open-source collaboration as fundamental to their work, having boosted sequencing and avoided duplication. Open-source platforms are used globally, with 41% emphasizing their cross-organizational collaborative potential. International collaboration benefits are recognized by a third of researchers. Community adoption of workflow systems is seen as essential to future research by 41% of respondents, with 34% acknowledging substantial financial savings. Public cloud adoption is increasing, now utilized by 42% of researchers, and up to 80% in the private sector. Amazon Web Services is the preferred provider among potential migrators. These insights underline the transformative potential of open-source tools and cloud services in life sciences research.

Dr. James Field on Breaking the 'Cognition Barrier' in Antibody Discovery with AI and Robotics

Here I am sharing select insights from my latest interview with Dr James Field, CEO @ LabGenius, a London-based biotech which discovers next-generation protein therapeutics using machine learning, robotic automation and synthetic biology. 

Andrii: Could you expound on the "cognition barrier" you mention, and elaborate how LabGenius is utilizing mathematical models to understand molecular responses to diseases? What differentiates your approach from conventional methods? 

James: Humanity’s incredible success (at least reproductively) can largely be attributed to our capacity to hypothesise and invent. But even this superpower has limits. Concretely, hypothesis-driven innovation requires the inventor to understand the system that they’re working with at an appropriate level of abstraction. Now, here's the rub. There are many arenas in which hypothesis-driven innovation performs poorly because the human brain simply isn't wired to grapple with the complexity of the underlying system. 

For example, consider biological systems. Earth’s flora and fauna provide living proof of what can be built with biology, and at the same time highlight the sheer inadequacy of human-led hypothesis-driven innovation within this domain. This shouldn’t come as a surprise. After all, at no point in our evolutionary history has an intuition for manipulating organic matter at the nanoscale conferred a selective advantage!

To address some of humanity’s greatest challenges, it’s clear that we need to break through the ‘cognition barrier’ presented by hypothesis-driven innovation. In the absence of a suitable nootropic, this means that we must develop new forms of innovation that do not require a human to understand the underlying system. 

This concept is not new. For decades, scientists, engineers and technologists have dreamt of building ‘robot scientists’ capable of autonomously discovering new knowledge, technologies, and sophisticated real-world products. For protein engineers, that dream is now a real possibility. 

The rapid pace of technological development across the fields of synthetic biology, robotic automation, and ML has given us access to the tools required to create a smart, robotic platform capable of intelligently discovering novel therapeutic proteins. 

At LabGenius, we’ve spent several years building a platform capable of generating hypotheses, testing them in the lab and then using the resulting data to iteratively refine its understanding of how a molecule’s design determines its performance. 

With this approach, we have been able to overcome some major antibody engineering challenges. For example, traditional antibody engineering involves the sequential optimization of different molecular properties through rational design. With this approach, improving one property can inadvertently worsen others. These trade-offs inevitably lead to costly failures or sub-optimal outcomes for patients. In contrast, with our approach, we can now efficiently co-optimise antibodies across multiple features (e.g. potency, efficacy, selectivity, and developability). 

Share

Andrii: The results of LabGenius' research indicate a remarkable improvement over clinical benchmarks. Could you discuss the specific methodology employed in accelerating the discovery of these targeted molecules, and how they might alleviate the toxic side effects associated with existing immunotherapies?

James: T-cell engagers (TCEs) are a type of engineered antibody that redirect the immune system's T-cells to recognize and kill cancer cells. 

Despite showing real promise, the progression of solid tumour-targeting TCEs through clinical trials has been plagued by issues with dose-limiting ‘on-target, off-tumour’ toxicity. This occurs when healthy cells expressing a tumour-associated antigen (TAA) get unintentionally targeted, which can cause toxic side effects for patients. 

In a recent platform demonstration project, we used our ML-driven discovery platform to systematically identify novel TCEs that had strong killing selectivity, were highly potent and also had good developability profiles. The top-performing molecules demonstrated ≥10,000-fold killing selectivity, corresponding to a >400-fold improvement over a relevant clinical benchmark, Runimotamab (a TCE currently in phase I clinical trials) [ref].

The specific form of ML that we used to efficiently navigate design space and find high-performing TCEs is a form of active learning, called Multi-Objective Bayesian Optimization (MOBO).

We're using this capability to develop our own pipeline of highly selective TCEs for the treatment of solid tumours.  

Read full interview at BiopharmaTrend.com s week’s topics…

Syntekabio's STB CLOUD is a fully automated, cloud-based AI platform aimed at accelerating early-stage drug development. Traditionally, this process takes five years or more, but with STB CLOUD, developers can reach the pre-clinical stage in just about two years.

The platform overcomes five technical difficulties in the AI drug development process: virtual screening, AI-deep learning, MD simulation, pocket diversity, and ADME/Tox.

STB CLOUD integrates heterogeneous hardware and hundreds of bio software, utilizing Kubernetes and Docker containerization for seamless operation. Its core product, DeepMatcher™-Hit, drives the platform by screening billions of compounds for target proteins and deriving active substances. STB CLOUD minimizes the need for specialized personnel, as it automates the entire process, allowing users to find small molecular drug candidates with high binding affinity within several weeks.

The platform's commercialization will include the addition of NEO-ARS™, a neo-antigen discovery platform, as well as other drug development platforms in the future. By simplifying and automating drug development, STB CLOUD enables innovations and expands access to global researchers.

Read "The Power of STB CLOUD in Remote AI Drug Development".

Ok, now, let’s get to the topic of today’s newsletter.

If you are a biologist or a drug hunter and you haven’t read a blog by Dr. Vijay Pande, a general partner at Andreessen Horowitz (a16z) and founding investor of a16z’s Bio Fund -- you should probably do it. 

Apart from being an influential venture capitalist in the biotech space, having companies like Insitro and BioAge in the fund’s portfolio, Dr. Pande is regularly sharing his vision of how technologies are changing drug discovery and biotech research. According to him, we are in the middle of an industrial revolution happening in drug discovery and biotech, the driving force of this change being artificial intelligence (AI), machine learning, and automation. 

Hard to disagree with such a vision. 

Indeed, there is a growing wave of companies building drug design platforms of new generation -- Recursion Pharmaceuticals (NASDAQ: RXRX), Insitro, Exscientia (NASDAQ: EXAI), Insilico Medicine, Deep Genomics, Valo Health, Relay Therapeutics (NASDAQ: RLAY), you name it -- companies that create highly integrated and automated AI-driven and data-centric drug design processes from biology modeling and target discovery, all the way to lead generation and optimization (sometimes referred to as “end-to-end” platforms) . I wrote about this trend in one of the articles in a series about AI in Drug Discovery: A New Breed of Biotechs Takes the Lead in AI Drug Discovery. These “digital biotechs” are trying to transform traditional drug discovery, a notoriously bespoke, artisan process, into a more streamlined, repeatable, data-driven process -- more resembling an industrial conveyor line for drug candidates.

Announcements over the last couple of years by Exscientia (NASDAQ: EXAI) (here), Deep Genomics (here), Insilico Medicine (here), and other companies point to a situation where the average time for an entire preclinical program -- from building disease hypothesis to official nomination of a preclinical drug candidate -- have shrunk down to timelines as short as 11-18 months, and at fraction of costs of a typical project of similar nature conducted “traditionally”. Rapid timelines are achieved in drug repurposing programs with previously known drugs or drug candidates, for example, using AI-generated knowledge graphs, e.g. BenevolentAI (AMS: BAI) in their Baricitinib program, or advanced multiomics analysis and network biology to derive precision biomarkers for better patient stratification and matching novel indications -- as Lantern Pharm (NASDAQ: LTRN) does to rapidly expand their clinical pipeline.

Share

However, a lot of those AI-driven “digital biotechs” are still relying on community-generated data to train machine learning models, and this may come as a limiting factor. While some of the leading players in the new wave, such as Recursion Pharmaceuticals and Insitro, are investing heavily into their own high-throughput lab facilities to get unique biology data at scale, other companies appear to be more focused on algorithms and building AI systems using data from elsewhere, and only having limited in-house capabilities to run experiments. 

A common practice is to use community-generated, publicly available data. But it comes with a caveat: an overwhelming majority of published data may be biased or even poorly reproducible. It also lacks standardization -- conditions of the experimentation may differ, leading to a substantial variation in data obtained by different research labs or companies.

A lot has been written about it, and a decent summary of the topic was published in Nature: “The reproducibility crisis in the age of digital medicine”. For instance, one company reported that their in-house target validation effort stumbled at their inability to reproduce published data in several research fields. The obtained in-house results were consistent with published results for only 20-25% of 67 target validation projects that were analyzed, according to the company’s report. There are numerous other reports citing poor reproducibility of experimental biomedical data. 

This brings us to a known bottleneck of “industrializing drug discovery”: the necessity for large amounts of high quality data, highly contextualized, properly annotated biological data that would be representative of the underlying biological processes and properties of cells and tissues. 

In order for a wide-scale industrialization of drug discovery to occur, the crucial thing is the emergence of widely adopted global industrial standards for data generation and validation -- and the emergence of the ecosystem of organizations which would be “producing” vast amounts of novel data following such standards. Then, large drug makers and smaller companies would be able to adopt AI technologies to a much deeper extent. If we take the automotive industry as an example, a component of, say, an engine, developed in one part of the world would often fit into a technological process line in the other part of the world. So, highly integrated processes can be built across geographies and companies, as a “plug-and-play” paradigm.

The same approach is required in the preclinical research in drug discovery: every lab experiment, every data generation process, every dataset generated, all must be “compatible” with all other research processes, machine learning pipelines, etc. -- across the pharmaceutical and biotech communities globally. When this tectonic shift occurs, we will witness a truly exponential change in the performance of the pharmaceutical industry, something I would call “commoditization” of preclinical research. 

There is, luckily, a growing number of companies that are starting to bring about the required change in how preclinical research is done. Companies that build standardized, highly automated, scalable, and increasingly compatible laboratory facilities, guided by AI-based experiment control systems, and supplemented by AI-driven data mining and analytics capabilities. Such “next gen” lab facilities are often available remotely, making preclinical experimentation more accessible to various players in a wider scope of geographies.  

One of the presentations during the November 2021 conference by Deep Pharma Intelligence was delivered by Dr. Martin-Immanuel Bittner, Co-founder and CEO of Arctoris -- the Oxford-based biotech platform company powered by robotics and data science. One slide (below) caught my particular attention as a quite illustrative way to summarize where the drug discovery industry is heading in terms of overcoming the data quality and availability bottleneck (I have moved Insilico Medicine to the upper-right quadrant as they have opened their own robotized facility recently).

So, the industry is shifting from the “traditional” scientific paradigm at the heart of the largest and most established corporations (the left-bottom quadrant) towards AI-first R&D models. A good old “design-make-test” cycle involves numerous iterations and is mostly controlled by humans, with a lot of manual work, disconnected processes -- all creating inefficiencies and additional cost.

There are a number of companies at the cutting-edge of AI research (upper-left quadrant), Atomwise, BenevolentAI, and others -- which are developing cutting edge algorithms, model architectures, and highly connected modular systems for mining and modeling data to rapidly discover novel targets, leads, biomarkers, etc. Although such companies may have internal data generation workflows of their own and even wet lab facilities, raw data generation is usually not a central focus, and such companies mostly rely on external public and private data sources to train models.  

Another cohort of companies (bottom-right quadrant), such as Strateous, and Emerald Cloud Labs, represent remote-controlled autonomous laboratories with cloud data infrastructures, where experiments can be run from around the globe. In contrast to "algorithms-focused" companies, they offer a standardized and scalable way to generate massive amounts of experimental biomedical data and represent a new way to outsource lab experiments. The same quadrant is shared also by synthetic biology companies such as Ginkgo Bioworks and Zymergen, mainly due to their abilities to generate massive amounts of biology data, among other things. Both types of companies in this quadrant have data generation via experiment automation and lab robotization as a cornerstone of their business model. I would call this category "Data-as-a-service" companies.

Finally, there is the upper-right quadrant which encompasses a small number of companies, such as Arctoris, Recursion Pharmaceuticals, Insilico Medicine, and Insitro, uniting the two worlds -- biology experiment automation/robotization, and cutting edge data science and AI systems.

For example, according to Dr. Martin-Immanuel Bittner, Arctoris is capable of generating vast amounts of robust, reach, and better-contextualized data for own research and for select R&D partners -- in a highly automated and standardized way (watch the full presentation here). This allows minimizing human intervention in the “design-make-test” cycle, hence, dramatically streamlining and accelerating the whole research work, as compared to “traditional” drug discovery. The highly annotated quality data generated by companies like Arctoris or Recursion Pharmaceuticals can be a game-changer for the progress in the development and adoption of pharmaceutical AI by many organizations. 

Democratizing biomedical science in academia

According to recent news, Carnegie Mellon University is preparing to launch the world’s first university cloud lab in early July, aiming to revolutionize the way science is conducted in academic environment. The Cloud Lab will provide students and faculty with remote access to over 200 different lab instruments, enabling them to code and submit their AI-assisted experiment parameters from anywhere in the world. Trained technicians and robots at the facility will execute the experiments, eliminating the need for on-site presence.

Emerald Cloud Lab, a private research facility founded by two CMU alumni, will assist in running the university's Cloud Lab until faculty members become proficient in using the technology. The Cloud Lab concept democratizes science by providing researchers from under-resourced institutions with the opportunity to conduct experiments that would otherwise be unattainable. It also offers a more accessible research platform for individuals with disabilities.

The Cloud Lab significantly streamlines the scientific method, as scientists can review and modify experiment codes from a centralized lab, accelerating progress and reducing errors associated with replication. Additionally, the shared use of instruments maximizes the potential of expensive equipment while ensuring cost-effective maintenance. Carnegie Mellon University's Cloud Lab represents a significant step towards more inclusive, efficient, and cost-effective scientific research.

(This post is sponsored by Syntekabio)

Artificial intelligence (A.I.) and big data in a synergistic integration have led to promising results in new drug development by drastically reducing cost and time. This trend in the biopharmaceutical market has emerged as a new industry standard as startups—each with distinctive core A.I. algorithm—fiercely compete to capture their global market share. Syntekabio, the first KOSDAQ-listed A.I.-driven biotech company in South Korea, shares its view on the current and future trajectory of A.I. drug discovery and development in a series of exclusive articles for BiopharmaTrend.

Exploring A.I. Platform for New Drug Development

Companies that openly disclosed their A.I. drug development technologies so far include Schrödinger, Insilico Medicine and Atomwise. 

Schrödinger has a 'free energy perturbation (FEP+)' platform that shows strength in precise binding energy calculation based on molecular dynamics, which is best used for Me-Too drug design in new drug development. 

Insilico Medicine has Chemistry42, known as a generative A.I. drug design platform. This platform creates new compounds by using more than 30 generative models in parallel, and finally selects candidates in consideration of synthesis potential, novelty and diversity. An introduction of a robotic experiment also added to their strength.

An active A.I. driven drug development company since the beginning, Atomwise recently introduced A.I. based 'AtomNet PoseRanker (ANPR)' with improved performance. 

Schrödinger, Insilico Medicine and Atomwise all offer innovative services for discovering new drug candidates that are superior to traditional methods. They can at once discover active and optimized lead substances because a large amount of lead substance derivatives is made when verification analysis is performed immediately after selecting an active substance on the A.I. ​​new drug platform. This is also the reason why global pharmaceutical companies use their services despite the high cost. However, these services aren’t easily accessible for small and medium-sized pharmaceutical companies as well as new drug development research institutes and universities due to the cost.

Being amply aware of this service gap, Syntekabio launched STB CLOUD in late 2022, a suite of cloud-based proprietary platforms, to meet the unmet needs of these cost-conscious innovators seeking reliable yet affordable new drug candidate discovery services. Imagine screening 1 billion compounds that can be purchased with a single click anywhere, any time. STB CLOUD searches for the best pose in most targets through rapid recognition and deep learning. For 1,000 candidate substances at the final stage, it performs molecular dynamics simulations, and then finally selects 100 to 200 A.I.-hit candidates by free energy-based filtering out of 1,000 best poses.

What’s more is that STB CLOUD safely secures customer information, while the platform is completely automated and can be operated by anyone without professional training to quickly create a new drug development pipeline. Since the screening is performed based on commercially available compounds, it is also possible to discover new active substances with minimal synthesis, enabling the discovery of first-in-class compounds at an approximately four to five times lower than the average cost. This is a huge saving for most companies without compromising the quality of and timeline for new drug development.

[Figure 1. The flow diagram of DeepMatcher@Hit shows that compounds are first screened through three steps before being docked in a pocket of the target. Once the optimal pose is selected, the MD simulation is finally performed in a total of five steps.]

Factors on Hit-discovery Success Rate of A.I. Drugs

The following three steps are essential for computer-based Hit-discovery: candidate compound search, optimal pose generation, and molecular dynamics verification. A.I. and advanced algorithms contribute greatly to the stage of searching for candidates and generating optimal poses. After searching for a candidate compound, an optimal pose can be generated so that the correct binding energy can be applied. Then the experimental verification is performed according to the ranking order of the calculated candidate compound.

Share Where Tech Meets Bio

It is fundamental to reduce errors in the experimental verifications to minimize the experiment cost, because the cost increases exponentially depending on the level of the verification amount, depending on 100, 1000, or 5000. When the third step—molecular dynamics—is applied to the best pose selected in the second step of discovering hit compounds, the optimal pose is created with structure closest to the experimental value. Several papers have cited greatly reduced errors even when ranking is calculated only by binding energy.

An internally conducted research also confirmed that adding a molecular dynamics verification step to top-notch A.I. and advanced algorithms more than doubled the ability to discover viable drug candidates. It is possible to derive active substances with excellent efficacy by excluding error substances, rather than simply finding active substances. Currently, among A.I. drug development companies such as Schrödinger, Insilico Medicine, Atomwise, and Syntekabio, only Syntekabio operates all three stages automatically.

Drug Efficacy Optimization (Auto-Lead-Effi-Opt)

Among the general drug optimization software available today, Syntekabio’s own software command line interpreter (CLI) called Gap2 stands out. A graphical user interface (GUI) in the traditional method makes it impossible to attach a large R-group (substituent) when making a derivative. Gap2, on the other hand, can do this efficiently in a supercomputer environment, directly attaching an R-group to a specific atom of the drug scaffold within the protein-drug binding pocket.
Syntekabio currently has about 20,000 of its own R-group libraries. According to the paper published by Schrödinger, the attempt to attach the R-group to the drug scaffold is carried out outside the protein and then brought into the protein’s pocket. Contrary to this, Syntekabio has developed structures with high activity among 20,000 R-groups directly from within the pocket. Hence, quantitative structure-activity relationship (QSAR) is no longer necessary as it automatically compares and selects in terms of binding energy. Therefore, Syntekabio's drug optimization is called Auto-Lead-Efficacy-Optimization. It is operated semi-automatically for now in the local environment, with an aim to be installed on STB CLOUD within the second quarter of 2023.

[Figure2. Lead Optimization by DeepMatcher@Lead shows 20,000 R-groups are substituted and perturbed at the position of the mother compound, as the top 1,000 candidates are selected through grid cylinder filtering. Then 1,000 MD simulation is performed to complete the process.]

DeepMatcher:  an Innovative Platform for Discovering New Vaccines and Antibodies

Vaccines are a critical component of public health policy in eliminating serious infectious diseases, as seen in the recent Covid-19 pandemic. Making lifesaving drugs involves multiple forms and several processes in the manufacturing. Recent advances in vaccine technologies and platforms focusing on their mechanisms of action have opened a new pathway for the development of safe and efficacious formulations. In this context, Syntekabio's DeepMatcher, an A.I.-small molecule drug platform, has reached the stage of full commercialization. 

DeepMatcher provides registry information for all residues in the pocket as output, thus acquiring analysis information of key residues involved in binding within the pocket possible when calculating the final binding energy. Thanks to this feature, it is easy to calculate registry information on interactions between new small molecule drugs (protein-ligand), new vaccine drugs (MHC-peptide), and new antibody drugs (antigen-antibody CDR).

A.I. based small molecule new drug discovery process using DeepMatcher involves three steps: candidate substance search, optimal pose generation, and molecular dynamics verification. The second and third steps here can be used together for calculating new vaccines and antibodies, shortening the development period on A.I. vaccine and antibody new drug platforms. 

Complimentary to this technology, an A.I. vaccine drug platform NEO-ARS™ is in the verification stage, while Syntekabio develops AB-scan, an A.I. antibody drug platform. Neo-antigens discovered by NEO-ARS™ play a significant role in activating the immune system of cell therapy products from the market point of view. Cell therapy products have been growing gradually in the marketplace. It is greatly anticipated for the AB-scan platform to contribute to the new drug development once commercialized, especially in line with the growth of the markets for new antibody drugs and cell therapy.

At this time, DeepMatcher proceeds without interruption on a large number of CPU/GPU servers for three weeks, as STB CLOUD searches in three stages of operation for candidate compounds, optimal pose generation and molecular dynamics verification. In the first step, 1 million substances are selected from 1 billion compounds based on their physico-chemical properties and topology, and through physical docking with a fast docking algorithm, they enter deep learning docking and proceed to the final molecular dynamics verification.

The introduction of GPT, a hot topic these days, is being considered for implementation in the first screening stage to help improve the performance of DeepMatcher. Syntekabio is attempting proof of concept (POC) using GPT since its A.I. platform operates based on the registry information of all residues in the protein pocket, and these registries can be expressed as language models. 

All stages of the drug discovery process are working in concert seamlessly to bring batter speed and performance, propelling DeepMatcher to rise above others at the epicenter of innovative IT technology. With continuous innovation, Syntekabio is poised to take the lead as a global hit-discovery and optimization CRO unmatched in the industry.