📢 Highlights
Orthus, new RNA foundation model, released by University of Toronto
Recursion’s brain tumor drug, REC-2282, proceeds to phase 1 trials
European biotech VC, Forbion, raises over $2B for diverse investments
Not yet a member of our super awesome slack community of >8000? Join HERE 🤗
👀 In Case You Missed it ..
Orthrus: a new RNA foundation model for RNA property prediction
Researchers from the University of Toronto, home of recent Noble Prize winning scientist Geoffrey Hinton, and Ontario-based Vector Institute have released a preprint introducing Orthrus, a new RNA foundation model aimed at improving RNA property prediction. While protein and DNA models are becoming well-established, RNA models hold unique value. Indeed, predicting mRNA properties is key for therapies like mRNA vaccines, and RNA sequences provide highly informative signals despite making up a small portion of the genome. Orthrus uses a contrastive learning approach that aligns splicing isoforms and orthologous transcripts to capture functional and evolutionary patterns. Trained on data from 10 species and over 400 mammalian genomes, Orthrus performs well even in low-data settings, surpassing current models in several RNA prediction tasks, including RNA half-life prediction with just 45 labeled examples. This model provides a practical tool for RNA research and could contribute to advancements in therapeutic development. You can find Orthus on Github here.
FDA Clears Recursion's AI-Discovered Drug REC-2282 for Phase 1 Trial
Recursion Pharmaceuticals has received FDA clearance to initiate a Phase 1 clinical trial for REC-2282, targeting meningiomas with mutations in the neurofibromatosis type 2 (NF2) gene, which account for approximately 50% of all sporadic meningiomas affecting around 33,000 US patients annually. The trial will enroll up to 36 patients. Preclinical studies showed that REC-2282 reduced tumor growth by over 60% in NF2-mutated models. This milestone demonstrates the potential of AI to accelerate drug discovery and address rare, hard-to-treat cancers. The promising drug was found by the company's AI platform, which performs more than 2 million experiments weekly, Recursion identifies phenotypic relationships across 1.5 billion cellular images and 11 petabytes of data. This approach has led to the discovery of 37 novel drug candidates, with four currently in clinical trials for conditions like familial adenomatous polyposis and cerebral cavernous malformation. Claiming to have created a functional map of biology relevant to drug discovery, Recursion shows no sign of slowing down.
Over >$2B Raised by Forbion to Invest in 35-40 Innovative Biotech Companies
Netherlands and Germany-based biotech VC Forbion has raised more than €2 billion (about $2.17B USD) for its sixth venture capital fund and second growth opportunities fund. The Forbion Ventures Fund VI, totaling €1.35 billion, will invest in early-stage companies, while the €750 million Growth Opportunities Fund II targets late-stage enterprises. The funds plan to invest in 35-40 companies focusing on areas like gene therapy, oncology, and rare diseases. Historically, Forbion-backed companies have achieved a 3x return on investment, which highlights the firm's successful track record. Building on Arch Venture Partners and Flagship Pioneering’s multi billion dollar raises, the biotech VC industry has no shortage of cash.
GlycoShape: Open-Access Glycan structure database and toolbox
A team of researchers at the University of Southampton and Maynooth University has released GlycoShape, an open-access database of 3D structural data for glycans. This information “can be used to rebuild glycoproteins to their functional, native state through a bespoke tool, named Re-Glyco.” Re-Glyco is an algorithm designed to be compatible with open-access structure repositories such as the Protein Data Bank and the AlphaFold Protein Structure Database. This platform could be useful for furthering the understanding of the role of glycans and glycosylation, one of the most common post-translational modifications. GlycoShape and Re-Glyco are both accessible through API’s and both the code and data are available on Github.
$60 Million Funding Boosts Basecamp's AI Model for Protein Function Prediction
London based Basecamp Research has raised $60 million to develop AI models that can predict protein structures and functions with up to 90% accuracy. The company's database includes genomic and environmental data from over 50,000 microorganisms collected globally. By training AI on this diverse dataset, they aim to design novel enzymes and bioactive compounds. Potential applications include biomanufacturing, where engineered enzymes could increase production efficiency by 35%, and drug discovery, targeting a development cost reduction of $200 million per drug.
$250M Deal Between AI-Lux Biologics and Janssen for AI-Driven Drug Discovery
Subsidiary of China-based XtalPi, AI-Lux Biologics, has entered a licensing agreement with Janssen Biotech to utilize AI in biologics discovery. The deal includes upfront payments and milestones totaling up to $250 million. AI-Lux's platform integrates quantum physics and machine learning to predict protein structures and optimize candidates. The collaboration aims to reduce discovery timelines by 50% and costs by 40%, focusing on therapeutic areas like oncology and autoimmune diseases.
Thomas J. Fuchs Joins Eli Lilly as Chief AI Officer to Drive Digital Transformation
Eli Lilly and Company has appointed Dr. Thomas J. Fuchs as its first Chief Artificial Intelligence Officer in the 148 year old pharma giant. Dr. Fuchs, formerly a dean at Mount Sinai Health System, brings over 15 years of experience in computational pathology and AI. He will lead Lilly's AI initiatives to enhance drug discovery, development, and commercialization processes. Under his leadership, Lilly aims to integrate AI to reduce clinical trial durations by up to 30% and improve success rates. The appointment reflects Lilly's strategic investment of over $250 million in digital and AI technologies.
>$2M in Funding for Shift Bioscience's AI-Driven Mitochondrial Rejuvenation
UK-based Shift Bioscience has secured £1.6 million (roughly $2M USD) in seed financing to develop therapies that reverse mitochondrial aging using their AI based platform. The system identifies compounds that restore mitochondrial function, which declines by up to 10% per decade after age 30. Their lead candidate improved mitochondrial efficiency by 35% and increased cellular energy production by 25% in aged cell models. The funding will support continued preclinical development and safety studies, aiming to address age-related diseases like sarcopenia and neurodegeneration.
Stem Cell Longevity Research Gets $5.3 Million Boost from Clock.bio Funding
University of Cambridge spin-out, Clock.bio, has secured $5.3 million in seed funding to advance its platform that uses AI to decode the genetics of aging and rejuvenation. The company analyzes genomic data from over 100,000 individuals to identify key genes involved in cellular aging and claims to have identified over 200 genetic targets of cellular aging. Their technology aims to reset epigenetic markers, effectively reducing cellular age by up to 80% in lab models. By reprogramming cells to a youthful state, Clock.bio aims to develop therapies that can extend healthspan by up to 20 years. Preclinical results showed a 45% improvement in biomarkers of cellular aging.
$15M Raised by Booster Therapeutics for Proteasome Activators
The Berlin-based biotech, Booster Therapeutics, has secured $15 million in Series A funding to develop small molecules that activate the proteasome system, enhancing the degradation of misfolded proteins linked to neurodegenerative diseases. Their lead compound, BT-001, increased proteasome activity by 70% and reduced toxic protein aggregates by 60% in preclinical Alzheimer's models. The funds will support IND-enabling studies and the initiation of Phase 1 clinical trials by 2025. This approach could address a market projected to reach $14 billion by 2026.
AI Copilots for non-invasive brain-machine interfaces
A researchers team based out of UCLA has published a pre-print presenting a non-invasive brain-machine interface (BMI). The paper highlights the tradeoffs between invasive and non-invasive interface with regards to performance and neurosurgical risk. To address these tradeoffs, the team implemented “a novel EEG decoding approach and artificial intelligence (AI) copilots that infer task goals and aid action completion.” They leveraged a key insight: in addition to neural signals, other information such as task structure, historical movements, and computer vision can be used to infer a user's goals. The ultimate aim is to enable paralyzed patients to control computer cursors and robotic arms.
Up to $500,000 Investment for Southeast Asian Biotech Startups in Pfizer and Ignition
Pfizer has collaborated with Ignition's AI Accelerator to support for biotech startups in Southeast Asia focusing on AI-driven drug discovery. The program alleges it offers up to $500,000 in resources per startup as well as mentorship from Pfizer's global R&D team. Ignition AI Accelerator is a collaborative initiative formed between NVIDIA, Tribe, and Digital Industry Singapore (DISG), with a focus on AI-driven innovation. Targeting markets like Singapore and Malaysia, which have seen a 25% annual growth in biotech sectors, the initiative aims to accelerate the development of novel therapeutics addressing diseases prevalent in the region, such as dengue fever and hepatitis.
Nuclera’s Desktop Protein Printer Receives $42.5M
In the ‘first close’ of its Series B funding, Nuclera has raised $42.5 million to commercialize its desktop protein printing platform, eProtein™. The technology enables researchers to synthesize proteins in under 24 hours, compared to traditional methods taking up to two weeks—a reduction of approximately 85%. The platform can produce up to 50 different proteins simultaneously with high fidelity. The funding will support scaling manufacturing, global distribution, and customer support ahead of the product launch planned for mid-2025.
Diverse Genomes for Equitable Medicine Development
New private-public efforts are underway to address the imbalance in genomic research, where 78% of data derives from European populations. Initiatives like the All of Us Research Program aim to sequence 1 million genomes with at least 50% representation from minority groups. This diversification could improve the accuracy of polygenic risk scores for diseases like diabetes and hypertension in underrepresented populations by up to 60%. Additionally, global projects are investing over $1 billion to collect diverse genomic data, which is expected to enhance drug efficacy and reduce adverse drug reactions across different ethnic groups.
Longboard Pharmaceuticals Bought by Lundbeck for $75M
Danish pharmaceutical company, Lundbeck, has acquired Longboard Pharmaceuticals in a deal worth $75 million upfront, with potential milestone payments up to $430 million. Longboard's lead compound, LP352, is a next-generation 5-HT2C receptor agonist in Phase 1b/2a trials for developmental and epileptic encephalopathies. Early data indicates a 55% reduction in seizure frequency among participants. The acquisition strengthens Lundbeck's neuroscience portfolio, aiming to capture a share of the epilepsy therapeutics market projected to reach $9.5 billion by 2027.
🗓️ Upcoming BiB Events
See our handy dandy Lu.ma event calendar HERE, please RSVP so folks can plan accordingly!
San Francisco Builder Showcase – Thursday, October 17th at FutureHouse
Thank you Beko Jang, Eti Sinha, Shantenu Agarwal, and Nicholas Larus-Stone for organizing!
Bits in Bio Global Learning Mixer – Thursday, October 22nd
Thank you to Sahil Patel and Shantenu Agarwal for organizing!
San Francisco Data Driven Pharma Networking Event – Thursday, October 24th at Merck Event Space
Thank you Ilya Captain for organizing!
📰 Top Community Conversations
@Mirasbek is getting guidance for catching up on the GLP1 crazy!
🏢 New Job Openings
Notable postings below - over 100 more on our community job board!
Founding Engineer at Pauling
Program Coordinator & Recruiter at STEM Muse
🙋 🙏 Community Asks
Feedback: How is the Newsletter doing? We’re trying different formats/content. In case the hyperlink above didn’t get your attention, maybe a bright orange button will!
Volunteer: Want to get involved with Bits in Bio, meet new members across the community, and learn about the ecosystem? We are looking for volunteers to help us create great content and manage the community.
🙏 Thank you for being a BiB Weekly reader!
We want to deliver what matters most in Bio AI and would love your feedback on how we can do better. Please weigh in as anon here or DM me directly!
— Vince Alessi, BiB Editor in Chief