The Life Sciences AI Handbook
Evidence and Decision Frameworks for AI in Biology and Drug Discovery
Welcome to The Life Sciences AI Handbook
Foundation models now predict protein structures before they are solved, represent cells in latent space, and generate molecules faster than chemistry can synthesize them. The model is no longer the bottleneck. Functional biology is.
The hard part is translation: separating what a model suggests from what biology has shown, and deciding what still has to be tested.
Each chapter answers two kinds of questions. First: what the field is trying to solve, the core idea, where the field stands, what is known and still open, and why it matters. Then: what is demonstrated, what remains theoretical, what is beyond current capability, what would make the area more promising, and what researchers, biotech teams, funders, and program leaders should do next.
This handbook is continuously updated as new papers, benchmarks, and model releases change what the evidence supports.
Important Disclaimers
This handbook is for research and educational purposes only. It does not constitute clinical advice, regulatory guidance, or a recommendation to use any specific tool or platform. Model outputs discussed here are hypotheses that require experimental validation; they are not endpoints.
Validation and safety remain context-specific. Researchers and program leaders should design appropriate validation experiments, assess reproducibility and safety, meet applicable biosafety and biosecurity requirements, and follow publication and data-sharing norms in their field.
Information may become outdated given the pace of model releases, benchmark updates, and laboratory automation tooling. Verify model versions, training data scope, and benchmark results against primary sources before relying on them.
For dual-use considerations, see Information Hazards in Capability Research and the companion Biosecurity Handbook.
Recent Updates
- Sep 22, 2026 Verified-access life-sciences model programs from Anthropic and OpenAI News & developments
- Sep 18, 2026 Zhang et al. (Science): a multi-agent Virtual Biotech curates outcomes from 55,984 trials New evidence
- Sep 9, 2026 DeepMind’s AlphaGenome Atlas and GPN-Star (Nature) for variant-effect prediction News & developments
Start Here
Start with the evidence framework, then read the best-established molecular example. This path shows how the handbook evaluates capability, evidence, and translation.
- Executive Summary: Evidence framework and core conclusions across the handbook
- AI for the Life Sciences: Scope, audience, and the chapter reference framework
- Protein Structure Prediction: The best-established capability, and what it does and does not solve
Then continue to Evaluation Principles before adopting any model in a research program.
For search, role-specific reading paths, and direct links to each research domain, see Start Here.
An AI assistant helping you should follow the Guidance for AI Agents.
Book Structure
Seven parts run from foundations to governance: Foundations; Molecular Discovery and Design; Cells, Tissues, and Systems Biology; Organismal and Environmental Biology; Therapeutic Discovery and Translation; Research Systems and Automation; and Evaluation, Practice, and Governance. A closing perspective, Emerging Frontiers, separates demonstrated progress from theoretical claims. Start Here describes each part.
Companion Handbooks
The Physician AI Handbook
Clinical AI across every ACGME-recognized medical specialty: FDA-cleared diagnostic tools, clinical decision support, AI-assisted documentation, LLMs in clinical practice, medical liability, privacy and HIPAA, workflow integration, and evaluation frameworks. Peer-reviewed evidence from JAMA, NEJM, Lancet, and specialty journals. For physicians, health system leaders, and anyone building or deploying clinical AI.
The Public Health AI Handbook
AI applications across population health: disease surveillance, epidemic forecasting, genomic pathogen analysis, outbreak detection, health department implementation, deployment failures, AI-assisted coding for epidemiological analysis, behavioral interventions, and health misinformation. For epidemiologists, public health practitioners, and health department leaders.
The Biosecurity Handbook
Where AI capability meets biological risk: laboratory biosafety, the Biological Weapons Convention, dual-use research oversight, DNA synthesis screening, AI-enabled pathogen design risks, LLM information hazards, red-teaming, autonomous lab agents, and governance frameworks for AI-bio convergence. For biosecurity professionals, AI safety researchers, policymakers, and laboratory personnel.
Free to read and reuse under CC BY 4.0 · DOI 10.5281/zenodo.22073136 · How to cite
This handbook is open and continuously maintained. Support the Life Sciences AI Handbook →