Weekly Tech+Bio Highlights #7
ALSO: Embracing AI Transformation: Let’s Start with Data; The First R&D Platform Using Human Neurons for Biocomputing; This AI-driven Antibody Design Company Shows Promise
Hi! I am Andrii Buvailo, and this is my weekly newsletter, ‘Where Tech Meets Bio,’ where I talk about technologies, breakthroughs, and great companies moving the biopharma industry forward.
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:
Now, let’s get to this week’s topics!
News Highlights
🔬 Insilico Medicine, in collaboration with Fosun Pharma, has delivered its second preclinical candidate for solid tumor treatment using synthetic lethal strategy, leveraging AI-driven platforms. The candidate, targeting DNA damage repair, will proceed to the IND-enabling stage with a pre-IND submission expected in Q4 2024.
📈 Recursion Pharmaceuticals announces a $200 million public offering of Class A common stock at $6.50 per share, with Goldman Sachs and J.P. Morgan as lead book-running managers. The offering includes an option for underwriters to purchase an additional 4.6 million shares.
🔬 Chinese researchers from Tianjin University and the Southern University of Science and Technology have developed a robot powered by a lab-grown human brain organoid, aiming to achive advances in brain-computer interfaces (BCIs) and potential applications in brain repair and therapeutic strategies.
🔬 Expanding on the above news, China proposes establishing a brain computer interface (BCI) standardization technical committee under the Ministry of Industry and Information Technology (MIIT) to enhance industrial standards and boost domestic innovation, with public opinions solicited until July 30, 2024.
The initiative aims to guide technological development and support BCI research, building on existing policies and significant financial investments.
Watch insightful episode about basics of BCI, challenges and opportunities, and the market dynamics:
Ex-NASA Expert Unveils Everything You Need to Know About Brain-Computer Interfaces
🤝 PostEra partners with Amgen to leverage AI for drug discovery, using PostEra's Proton platform and Amgen's expertise to advance up to five small molecule programs, enhancing the efficiency and cost-effectiveness of medicinal chemistry.
🔬 Signet Therapeutics Inc. received FDA approval for its IND application for sigx1094, enabling Phase I clinical trials for diffuse gastric cancer and other advanced solid tumors, leveraging AI and organoid disease models for accelerated drug discovery and development.
🤝 Aptamer Group collaborates with AstraZeneca to evaluate Optimer binders for targeted siRNA delivery to fibrotic liver cells, aiming to generate demonstrator data in animal models, to enhance non-viral delivery systems for gene therapies.
💰 Waypoint Bio raises $14.5 million in seed funding led by Hummingbird Ventures to advance drug discovery using its innovative in vivo spatial pooled screening technology for solid tumor treatments.
This technology combines spatial biology with pooled screening to analyze cell therapy interactions within the tumor microenvironment at the single-cell level, aiming to enhance the identification of effective treatments.
Spatial biology explores how individual cells interact within the context of a tissue. It examines the influence of their environment on behavior, their precise locations, and the reasons behind their positioning. This field encompasses spatial transcriptomics, spatial genomics, spatial proteomics, spatial profiling, and spatial omics.
🌍 Owkin, an AI-biotech unicorn, expands into Germany, Austria, and Switzerland, partnering with nine hospitals to accelerate research in prostate cancer, muscle invasive bladder cancer (MIBC), and cardiovascular disease (CVD) using multimodal patient data and AI tools to improve patient outcomes and develop personalized treatments.
💰 Granza Bio, a San Francisco-based biotech, raises $7.14M in seed funding to advance its therapeutic delivery platform for cancer treatment, led by Felicis and Refactor Capital with participation from Y Combinator and other investors.
🧠 Paradromics Inc., a developer of brain-computer interfaces, joins the FDA's Total Product Life Cycle Advisory Program, accelerating the development of its Connexus® Direct Data Interface. The company also announces a new patient registry to prepare for clinical trials in 2025, targeting ALS, spinal cord injury, and stroke patients.
The First R&D Platform Using Human Neurons for Biocomputing
World's first bioprocessor uses 16 human brain organoids and consumes "a million times less power" than a digital chip.
Recently, FinalSpark, a pioneering Swiss biocomputing startup, has unveiled its Neuroplatform, which delivers access to biological neurons in vitro, marking a significant step forward in biocomputing technology.
Neuroplatform provides remote access to 16 human brain organoids capable of learning and processing information.
It is claimed to consume a million times less power than traditional digital processors, significantly reducing environmental impact.
The platform utilizes four Multi-Electrode Arrays (MEAs) housing the living tissue – 3D cell masses of brain tissue (organoids). Each MEA holds four organoids, interfaced by eight electrodes for both stimulation and recording.
Data is transferred via digital analog converters (Intan RHS 32 controller) with a 30kHz sampling frequency and a 16-bit resolution.
Supported by a microfluidic life support system and monitoring cameras.
Features a software stack allowing researchers to input data variables and interpret processor output.
Currently, nine institutions have access to the Neuroplatform to spur bioprocessing R&D. Over three dozen universities have shown interest in accessing the platform.
Subscription cost for educational institutions is $500 per user per month.
Organoid lifespan was initially lasted a few hours, but now organoids have a lifespan of around 100 days, making them suitable for experiments running for several months.
Embracing AI Transformation: Let’s Start with Data
The integration of AI into early-stage drug discovery promises to accelerate hit discovery, optimization, and overall drug development processes. A recent article published in Nature Communications by Kristina Edfeldt et al. highlights the pivotal role of data management, dissemination, and AI integration within the Structural Genomics Consortium (SGC). Drawing insights from this comprehensive roadmap, I highlithed the key points to consider when thinking about building/updating your organization’s data storage and processing principles:
Adhere to FAIR Principles
Ensure all data is Findable, Accessible, Interoperable, and Reusable. Implement standardized metadata schemas and persistent identifiers (e.g., DOIs) for all datasets to enhance findability and accessibility. Use interoperable data formats like XML or JSON to facilitate data exchange and integration.
Establish Precise Ontologies and Standardized Vocabulary
Define clear ontologies for data categorization, such as the BioAssay Ontology (BAO) for biological screening assays. Use standardized vocabularies like Medical Subject Headings (MeSH) to ensure consistency and improve machine readability.
Implement Centralized Database Architecture
Develop a unified data architecture using relational databases (e.g., PostgreSQL) or graph databases (e.g., Neo4j) to store and manage data. Ensure schema compatibility with established repositories like ChEMBL and PubChem to facilitate seamless data integration and dissemination.
Leverage Lab Automation and Integrated ELN/LIMS Systems
Utilize automation tools such as liquid handlers and robotic workstations to record detailed experimental metadata (e.g., reagent purity, ambient temperature). Integrate ELNs (e.g., LabArchives) with LIMS (e.g., LabWare) through APIs to streamline data capture and protocol linkage.
Promote Transparent and Reproducible Data Processing
Develop and publish open-source data processing pipelines using languages like Python and R. Document all preprocessing steps, including quality control measures, normalization techniques, and data transformation methods, in code repositories such as GitHub.
Create and Manage Multimodal Data Objects
Combine diverse data types (e.g., proteomics, genomics, chemical screening) into comprehensive data objects using data integration platforms like KNIME or Galaxy. Utilize BioCompute objects for tracking data processing pipelines and ensuring reproducibility.
Versioning and Archiving
Implement version control systems (e.g., Git) to track changes in datasets and maintain detailed change logs. Use data nutrition labels to summarize key characteristics, updates, and quality metrics for each dataset version.
Utilize Cloud-Based Data Hosting and Analysis
Leverage cloud platforms (e.g., AWS, Google Cloud, Microsoft Azure) for scalable data storage and computational resources. Employ the Model2Data approach by bringing analysis code to cloud-based data storage to minimize data transfer costs and enhance processing efficiency.
Engage in Active Learning and DMTA Cycles
Design data-driven feedback loops within the Design-Make-Test-Analyze (DMTA) cycles, using predictive models to guide experimental design. Implement active learning strategies to prioritize experiments that reduce prediction uncertainty and maximize data informativeness.
Foster Collaboration Between Experimentalists and Data Scientists
Promote a collaborative environment where experimentalists and data scientists work together from the onset of data generation. Incorporate data science into experimental design to enhance the impact and efficiency of research efforts, utilizing platforms like Jupyter Notebooks for shared analysis.
This AI-driven Antibody Design Company Shows Promise
AbSci started its journey in 2011 in the city of Vancouver, Washington, US, and a decade later went public having raised about $200 million in an IPO in 2021. AbSci aims to change the biopharmaceutical industry with their protein production platform, using advanced artificial intelligence (AI).
I wrote about the company earlier on multiple occaions. For instance here you can read about their Zero-shot moonshot, using generative AI to design antibodies with limited or no training data from known antibodies binding to particular targets of interest.
As Alex Philippidis reports for Genetic Engineering & Biotechnology News, Absci is gearing up for a breakthrough year in 2025, with its lead AI-designed drug candidate, ABS-101, poised to enter clinical trials.
Key Points:
ABS-101 Clinical Trials: Absci plans to launch its first-in-human Phase I trial for ABS-101 early next year, with interim data expected by mid-2025. This candidate targets TL1A to treat inflammatory bowel disease (IBD).
Preclinical Success: ABS-101 has shown superior or equal potency compared to leading TL1A-targeting drugs from Roche and Merck, positioning it for potential clinical differentiation.
Additional Candidates: Absci is also advancing ABS-201, aimed at a dermatological condition, and ABS-301, a novel oncology treatment discovered through its Reverse Immunology platform.
Strategic Partnerships: The company aims to establish at least four new drug creation partnerships in 2024, enhancing its collaborative efforts and expanding its impact.
Why This is Important:
The advancement of ABS-101 into clinical trials marks a critical step towards new treatments for IBD, offering hope for patients with limited options.
Moreover, the success of Absci’s additional candidates, ABS-201 and ABS-301, could lead to breakthroughs in dermatology and oncology, respectively. These developments not only enhance Absci's pipeline but also underscore the potential of AI in drug discovery, setting a precedent for future innovations in the industry.
Interestingly, as with many AI-driven biotech stocks, the Absci stock is underperforming so far relatively to what it once was. I am not a stock trading expert, I don’t hold ABSI 0.00%↑ and this is not an investment advice, but just to pay attention that science and stock market performance of companies is not always seemingly aligned these days.
Time to Reflect on the First Half of 2024
Last December, enjoying calm Christmas days off, I have compiled a list of growing trends in the biotech/pharma industries, mostly focused on technology and science drivers.
You can check it below, but next Thursday, July 11, I am releasing the new overview of trends with reflections on what happened in the first half of 2024, speculation about my last year’s predicitons (how the trends developed into 2024) and several other very impactful trends that we uncovered in 2024. Both articles highlight a number of companies that are pushing the trends forward.