Skip to main content
Search

# Biological foundation models

5 related articles

Subscribe to updates
  1. arXiv

    BioXArena-Pro turns biomedical modeling into 64 research-grade tasks: the best agent scores 55.1 and no task saturates

    BioXArena-Pro replaces biomedical modeling evaluation with 64 research-level tasks rebuilt from published studies, most holding out an entire biological unit such as a species, cohort or cell line, and audited in several rounds to close label leaks. Across 22 agent configurations the best scores 55.1 of 100 and no task saturates; on the nine tasks close to the original studies the strongest agent ties the reproduced published methods (54.9 versus 54.7), while on the 48 rebuilt tasks the methods trail by 8.2 points.

    Loka Li（First author）
    BioXArena-ProCoding AgentsBiomedical machine learningBiological foundation models
  2. bioRxiv

    Scientific foundation models can now be audited automatically: AutoSPECTRA exposes failure conditions that aggregate scores hide across four biological models

    Scientific foundation models usually ship with aggregate benchmark scores, while the performance limits that matter in use surface only after deployment through scattered reports. AutoSPECTRA constrains a general-purpose coding agent into a reproducible protocol: define a measurable generalization axis, run controlled comparisons against fixed reference methods, and confirm on data not used to select the axis. Across four biological foundation models, ESMFold2, STATE, CONCH and AlphaMissense, the audits tied performance shifts to protein sequence composition and relatedness to pretraining data, representation of perturbations in training, effective spatial resolution, and residue-level genomic, evolutionary and structural context, and rejected several initially plausible hypotheses.

    Broad Institute
    Yasha Ektefaie（First author, Corresponding author）
    AutoSPECTRACoding agentBiological foundation modelsModel generalizability auditing
  3. Intology

    Intology's Locus turns autonomous AI R&D on molecular discovery: matched compute, 1.5–2.8× fewer antibody candidates

    Intology extended its autonomous discovery system Locus from language-model post-training to molecular discovery, comparing it at matched compute against prior state-of-the-art methods from BioHub and Boltz and against frontier LLM agents Codex and Claude Code on molecular property prediction, small-molecule potency prediction and antibody design. On Boltz-2 adaptation across six targets, Locus reached a mean Spearman correlation of 0.622, against 0.225 for the Boltz-2.1 API, 0.450 for Claude Code and 0.569 for Codex. In antibody design, Locus reached comparable binding scores with 1.5–2.8× fewer generated candidates, but those scores are OpenDDE ipSAE proxies and still need wet-lab validation.

    Intology
    LocusAutonomous AI R&DAntibody DesignMolecular Property PredictionBiological foundation models
  4. Deep Genomics

    Deep Genomics adds a million-basepair context to siRNA activity prediction: removing the foundation models nearly halves performance

    Deep Genomics' DeepRNAi combines the local siRNA hybridization site with long-range context from the genomic region around the transcript, supplied by biological foundation models BigRNA, Enigma and REPRESS over up to one million base pairs of sequence. On seed-mediated knockdown prediction, DeepRNAi without the foundation models performs in aggregate about as well as a random forest with hand-built transcript features; with the foundation models, performance nearly doubles. In two drug-discovery cases the model predicted near-zero activity for siRNAs targeting the distal 3' UTR, matching Alnylam's published PLG experimental data.

    Deep Genomics
    DeepRNAiBiological foundation modelssiRNA activity prediction
  5. Helical

    Biological foundation models move into Codex: natural-language prompts run perturbation experiments, with free compute for academics

    Helical released a Model Context Protocol (MCP) integration for OpenAI's Codex that lets researchers call biological foundation models from the agentic tools they already use, and use or post-train those models on their own data through natural-language instructions. Using such models previously required researchers to configure infrastructure and build the workflows for an experiment. One model available at launch is PerturbGen, developed at the Wellcome Sanger Institute to predict how perturbations reshape cellular trajectories, and Helical with Nebius is offering free compute credits that academic researchers can request.

    HelicalWellcome Sanger Institute
    Model Context ProtocolCodexBiological foundation modelsPerturbGen

You’re all caught up