Registry / all records
315 research AI agents · live GitHub metrics · community reviews
Retired projects →doi.org/10.1016/j.cell.2026.08.032
Cell perspective (Zitnik lab) — world models that simulate biomedicine.
doi.org/10.1016/j.cell.2026.07.003
Cell perspective — toward native biological language models.
doi.org/10.1016/j.cell.2026.08.040
Cell EIC editorial — Cell evolves its scope alongside AI-era life science.
doi.org/10.1016/j.drudis.2025.104593
Drug Discovery Today review — generative AI in pharma R&D, from LLMs to AI agents to regulation.
doi.org/10.1016/j.cell.2024.09.022
Cell review — how AI agents empower biomedical discovery: tool use, reasoning and orchestration across the discovery pipeline.
doi.org/10.1016/j.cell.2026.08.004
Cell paper — Arc Institute community benchmark of zero-shot perturbation-response generalization across cellular contexts.
doi.org/10.1093/bib/bbag110
Briefings survey of LLM agents across genomics, proteomics, spatial biology and biomedicine.
doi.org/10.1016/j.cell.2026.08.042
Cell perspective (Xing & Song) — a world-model vision for the virtual cell.
huggingface.co/tahoebio/Tahoe-100M
An atlas of ~100 million single-cell transcriptomes profiling 50 cancer cell lines across ~1,100 drug-dose treatments, pairing single-cell with molecular phenotypes to link drug mechanisms to cellular responses — an openly available substrate for training predictive models of cell behavior. Data lives on Hugging Face (CC0); no official GitHub repo.
doi.org/10.1016/j.xinn.2025.101091
The Innovation review — how LLMs advance battery research across materials discovery, device manufacturing and system-level control and optimization.
rxrx.ai/rxrx3-core
Curated release of the RxRx3 high-content microscopy corpus: cell-painting images across compound treatments for benchmarking drug-target and mechanism-of-action inference. Dataset hosted on rxrx.ai; no official GitHub repo.
doi.org/10.1016/j.cell.2026.07.025
Cell review (Ghassemi lab) — recurring failure modes of clinical AI and how to avoid them.
doi.org/10.1038/s44401-026-00143-7
npj Health Systems perspective — structural requirements for intelligent clinical digital twins in feedback-driven care.
doi.org/10.3390/mps9020033
Methods and Protocols review of multi-agent AI systems for biological and clinical data analysis.
figshare.plus/29190726
Genome-wide Perturb-seq datasets produced on a scalable fix-cryopreserve platform, released to train dose-dependent biological foundation models. Data on figshare (CC BY 4.0); no official GitHub repo.
doi.org/10.1016/j.cell.2026.07.004
Cell perspective — 15 open challenges for generative AI in cell biology.
anthropic.com/claude-science
Anthropic's closed-source AI workbench for scientists — a coordinating agent with 60+ curated skills and connectors across genomics, single-cell, proteomics, structural biology and cheminformatics, with local, SSH and HPC compute. Beta for Claude Pro, Max, Team and Enterprise.
huggingface.co/zifeng-ai/BioDSA-1K
Benchmark for data-driven biomedical hypothesis validation — 1,029 hypothesis-centric tasks with 1,177 analysis plans curated from 300+ published studies on cBioPortal patient data. Includes non-verifiable hypotheses the data can neither support nor refute. Dataset on Hugging Face (ODbL); ships with the BioDSA framework.