Bits In Bio Weekly - February 25th 2025
Updates From and Around the Bits in Bio Community
📢 Highlights
Evo 2 Sets a New Benchmark for AI in Biology—Predicting Mutations at Unprecedented Scale
DeepMind Releases AI ‘Co-Scientist’ to Accelerate Hypothesis Generation
Salt Lake City’s Altitude Lab Steps Up to Support Startups Amidst Federal Funding Uncertainty
Not yet a member of our super awesome slack community of >8500? Join HERE 🤗
👀 In Case You Missed it ..
Evo 2, the Largest AI Model in Biology to Date, Predicst Genetic Mutation Effects
A multidisciplinary collaboration between Arc Institute, University of California Berkeley, NVIDIA, and more have introduced Evo 2, an AI model designed to predict harmful genetic mutations and generate small eukaryotic genomes. Building on the capabilities of Evo 1, which focused on bacterial genomes, Evo 2 expands its scope to genetic sequences across various life forms, including microbes, plants, and humans. The model is trained on 9.3 trillion nucleotides from 128,000 species and has 40 billion parameters, enabling broader predictive capabilities than earlier biological AI models. It can efficiently detect pathogenic mutations and generate DNA sequences comparable in scale to yeast chromosomes or small bacterial genomes. Researchers can access Evo 2 through an API and further refine it. You can find the code, courtesy of the Arc Institute, at their Github repo.
Accelerating Scientific Breakthroughs with an AI ‘Co-Scientist’
Google DeepMind has unveiled an AI-powered “co-scientist” built on its Gemini 2.0 model to act as a virtual collaborator in biomedical research. This multi-agent system can autonomously generate hypotheses, analyze data, and propose experiments, digesting vast scientific literature far faster than a human could. Their approach allegedly goes beyond surface-level analysis, using advanced models to propose hypotheses and even design new experiments. Importantly, it’s designed to augment rather than replace human scientists: early trials (e.g. in liver fibrosis) showed the AI suggesting promising solutions and even rediscovering known mechanisms, all while remaining a collaborative tool that amplifies scientists’ productivityEarly trials demonstrated significant reductions in the time it takes to validate research findings, hinting that labs might accelerate hypothesis-generation stages of scientific discovery in select domains. At 70 pages, their research paper is not for the faint of heart.
Safety Net from Altitude in Salt Lake City Amid NIH Grant Concerns
Worried about shaky NIH funding, Altitude Lab (a Salt Lake City biotech incubator backed by Recursion CEO Chris Gibson) is stepping in to support early-stage biotechs with alternative funding and lab space outside the traditional grant system.This move comes as many young companies worry about reduced NIH budgets, which traditionally fuel early-stage research through grants. Altitude’s model reduces overhead for startups, letting them focus on validating new therapeutic modalities without the financial strain of maintaining standalone facilities. Meanwhile, founders and scientists can share best practices and resources, nurturing a mini-ecosystem of collaboration. The fund will offer: $100,000–$250,000 in pre-seed investment capital, 12 months of lab and office space at Altitude Lab, Access to Altitude Lab’s accelerator program, including mentorship from industry leaders and connections to national investors. The hope is that by pooling risks and resources, the sector remains resilient—even if government funding becomes less predictable. Interested parties can submit an applications here.
Agentic AI in Healthcare form NVIDIA and IQVIA Alliance
NVIDIA and IQVIA have struck a partnership to develop “agentic AI” models tailor-made for healthcare and life sciences, essentially turning AI systems into active research agents rather than passive tools. By leveraging NVIDIA’s GPU clusters, IQVIA hopes to run complex models in record time, speeding up clinical trial simulations and real-world evidence studies. They’re also exploring federated learning techniques, which allow algorithms to train on decentralized data without compromising patient privacy. This architecture could unlock new insights in oncology, rare diseases, and beyond by accelerating the search for treatment patterns hidden in huge datasets.
Incyte’s $885M AI Pact with Genesis For Drug Discovery
Biopharma giant Incyte is entering a strategic collaboration worth up to $900 million with Genesis Gems, a startup using AI to pinpoint promising drug targets and molecules. Under the deal, Genesis Gems’ proprietary “GEMS” platform will analyze vast compound libraries to predict which structures have the highest therapeutic potential. Incyte aims to accelerate its pipeline, reducing early-stage guesswork by leveraging machine-driven insights. By coupling Genesis’s AI firepower with Incyte’s medicinal chemistry know-how, the partners aim to discover new drug candidates faster than traditional chemistry methods, potentially tackling diseases that have stumped conventional approaches. Ultimately, both parties hope this synergy will yield new treatments faster and more cost-effectively than traditional approaches.
Achira.ai’s AI-Powered Diagnostics Courtesy of Chan Zuckerberg Initiative
A new startup spun out of a Chan Zuckerberg Initiative – Achira.ai - has launched with a $33 million seed round (backed by NVIDIA’s venture arm) to build a hybrid AI + physics platform for biotechAchira.ai specializes in microfluidic platforms that run diagnostics at the point of care—think rapid tests for infectious diseases, hormone levels, and more—enhanced by machine learning insights. By integrating AI algorithms directly on-chip, they can analyze samples in real time without needing full lab infrastructure. The company also focuses on making these tests more affordable and user-friendly, which is a big plus for remote clinics or developing regions. Their solutions aim to minimize manual handling errors and expedite treatment decisions, boosting patient outcomes.
AI-Driven Robotics Lab Allegedly Uncovers TNIK Inhibition Effect on Aging
In a glimpse of how autonomous labs can speed up science, an AI-driven robotics laboratory (led by Insilico Medicine researchers) has allegedly discovered that inhibiting TNIK (Traf2- and Nck-interacting kinase) may combat the inflammatory effects of aging. Rather than killing senescent cells outright, these so-called “senomorphic” treatments aim to restore their function—potentially improving tissue health and longevity. By automating the search through large compound libraries, researchers discovered how blocking TNIK might reduce inflammation and bolster cellular repair pathways. The technique underscores the promise of integrated AI and robotics to identify new targets far more rapidly than manual methods. If validated clinically, it could expand the portfolio of anti-aging therapies beyond traditional senolytics.
Epitopea to Target Hidden Tumor Antigens in Merck Alliance
Biopharma giatn Merck & Co. is teaming up with cancer biotech Epitopea to hunt down previously unknown tumor antigens hidden in the genome’s “junk DNA” – aiming to expand the target list for next-gen cancer immunotherapies
Merck has teamed up with Epitopea to mine so-called “cryptic” tumor antigens—unique molecular markers often hidden from standard detection methods. By focusing on these overlooked targets, the collaboration seeks to develop next-generation immunotherapies that can bypass resistance mechanisms in difficult-to-treat cancers. The companies plan to integrate Epitopea’s novel antigen discovery platform with Merck’s immuno-oncology research pipeline, aiming for highly personalized approaches. This partnership also underscores the industry’s growing interest in deeper tumor profiling, where advanced analytics help reveal stealthier cancer signatures.
🗓️ Upcoming BiB Events
See our handy dandy Lu.ma event calendar HERE, please RSVP so folks can plan accordingly!
Zurich Bits in Bio Drinks, Tuesday, February 25 at 6:00 PM, at Kraftwerk
Thank you to Nives Rombini for organizing!
Bits in Bio Philadelphia March Happy Hour, Thursday, March 6 at 5:00 PM, at Copacabana University City
Thank you AJ Adejare for organizing!
RTP Bits in Bio, Thursday, March 6 at 6:00 PM, at Beer Study-Durham
Thank you to organizers Matt, Sean Sullivan, and Sahil Patel!
📰 Top Community Conversations
It's been quiet as our community keeps up with the rapidly changing NIH/NSF funding situation
Check out the BitsInBio Q&A channel to get your fix!
🏢 New Job Openings
Notable postings below - over 100 more on our community job board!
(Senior) Computational Biologist at Pioneer Labs
Account Manager at QBench
Research Assistant at Orakl Oncology
Senior Bioinformatician at Orakl Oncology
Senior Software Engineer at Orakl Oncology
🙋 🙏 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!