Find the evidence, fast.

82 results

1. Story

   Summit and Akeso report a Phase 3 biliary-cancer win for ivonescimab

   Summit and Akeso said ivonescimab plus chemotherapy improved overall survival versus durvalumab plus chemotherapy in a China-based Phase 3 trial, but numerical results remain pending.

   drug-discovery
2. Story

   FDA approves Revolution Medicines’ Rasonque for metastatic pancreatic cancer

   The FDA approved once-daily Rasonque, or daraxonrasib, for adults with metastatic pancreatic adenocarcinoma after prior systemic therapy or when multiagent therapy is not an option.

   drug-discovery · policy-regulation
3. Story

   Generate’s AI-engineered asthma antibody suppresses biomarkers for six months

   Generate:Biomedicines reported that a single 300-mg dose of GB-0895 suppressed four inflammatory biomarkers for at least six months in a Phase 1 asthma study.

   drug-discovery · protein-design
4. Story

   Massachusetts biotech funding rebounds while its workforce shrinks

   Capital and public listings improved in early 2026, but employment data still reflects the industry's recent contraction.

   policy-regulation
5. Story

   FDA extends its review of Capricor's Duchenne cell therapy

   The agency moved deramiocel's decision date to November 22 while it reviews new follow-up data and analyses.

   policy-regulation · drug-discovery
6. Story

   J&J's Imaavy wins FDA approval for warm autoimmune hemolytic anemia

   The FcRn blocker becomes the first FDA-approved treatment specifically for adults and adolescents with warm autoimmune hemolytic anemia.

   drug-discovery · policy-regulation
7. Story

   Outer Biosciences is pairing living human skin with an AI model

   The startup wants repeated experiments on viable human skin to improve predictions about how compounds will behave before clinical testing.

   biological-foundation-models · drug-discovery · lab-automation
8. Story

   Independent report says Cellares will resize after a customer exit

   Cellares plans to resize after an unnamed large pharmaceutical customer ended a partnership, according to independent reporting.

   lab-automation · drug-discovery
9. Story

   Network Bio launches with $50 million and an NVIDIA model collaboration

   Network Bio paired a $50 million launch financing with plans to build a cell-free RNA foundation model alongside NVIDIA.

   biological-foundation-models · datasets-benchmarks
10. Story

    Merck and Moderna report positive Phase 3 INTerpath-001 interim topline results

    The companies say intismeran plus Keytruda met recurrence-free and distant metastasis-free survival endpoints; effect sizes and overall-survival data are not yet available.

    drug-discovery · datasets-benchmarks
11. Story

    GenScript says its AI drug-discovery business doubled in the first half

    GenScript reported that its AI-enabled drug-discovery business doubled year over year, without disclosing standalone segment revenue.

    drug-discovery · biological-foundation-models
12. Story

    FDA opens debate on how generative-AI medical software should be tested

    The agency is asking how medical software that generates content or actions should be assessed for risk, tested before launch, and monitored afterward.

    policy-regulation
13. Story

    Amylyx reports positive Phase 3 LUCIDITY topline results for avexitide

    Amylyx reports fewer severe hypoglycemic events with avexitide, while complete arm-level and registry-posted results remain unavailable.

    drug-discovery · policy-regulation
14. Story

    EU research centre maps AI-for-biology capabilities and policy gaps

    A Joint Research Centre report calls for realistic capability claims, transparent reporting, and reproducible validation of biology AI systems.

    policy-regulation · biological-foundation-models · datasets-benchmarks
15. Paper

    Finetuning Foundation Models for Temporal Clinical Transcriptomics Data

    Mathur and colleagues fine-tuned foundation-model gene embeddings and used temporal graph neural networks to distinguish treatment-response patterns across four inflammatory diseases.

    biological-foundation-models · datasets-benchmarks
16. Paper

    Assessing the translation of AI-prioritized genome-derived peptide fragments into validated antimicrobial candidates

    Researchers closed the loop from genome mining and deep-learning peptide ranking to synthesis and antimicrobial testing against Staphylococcus aureus.

    protein-design · drug-discovery
17. Paper

    A Mammalian High-Throughput Screen for AI-Designed Peptide-Guided Protein Degraders

    Zhao and colleagues paired protein-language-model design with pooled mammalian-cell screening to identify peptide-guided degraders against four targets.

    protein-design · drug-discovery
18. Paper

    Mapping Alzheimer's neuropathology signatures to the whole brain transcriptome using machine learning data fusion

    A data-fusion model projected cortical Alzheimer's signatures across a 108-region whole-brain single-cell atlas.

    single-cell-spatial · datasets-benchmarks
19. Paper

    Assay concordance sets exact ceilings on what one biological score can predict

    A model-free analysis argues that disagreement among biological assays places a measurable ceiling on predictor performance.

    datasets-benchmarks
20. Paper

    BfBio: a graph-based tool for the prediction of Angiogenic Stalk Cell genes using a Personalized PageRank algorithm

    A graph-ranking system used integrated omics and interaction networks to prioritize under-characterized genes linked to angiogenic stalk cells.

    drug-discovery · datasets-benchmarks
21. Paper

    Coala: a standard-based framework for converting CWL-described command-line tools into agentic toolsets

    Hu and colleagues built Coala to expose Common Workflow Language tools to language-model agents through the Model Context Protocol.

    scientific-agents · datasets-benchmarks
22. Paper

    DeepPathway: Predicting Pathway Expression from Histopathology Images

    Ahsan and colleagues trained a contrastive learning model on spatial transcriptomics and tissue images to predict pathway-level expression from routine histology.

    single-cell-spatial · datasets-benchmarks
23. Paper

    A multi-scale structural and biophysical atlas of TCR-peptide-HLA recognition dynamics

    DynaTPH adds standardized molecular-dynamics trajectories and biophysical features to 256 representative T-cell-receptor complexes.

    datasets-benchmarks
24. Paper

    Deciphering the comprehensive relationship between 5′ UTR and 3′ UTR sequences with deep learning

    Suga and colleagues combined pretrained RNA-language-model representations with contrastive learning to identify coordinated relationships between 5′ and 3′ untranslated regions.

    biological-foundation-models · drug-discovery
25. Paper

    Temporal dynamics improves machine learning-based prediction of cell state from quantitative phase imaging

    A spatiotemporal neural network classified six cell states from label-free imaging more accurately as additional frames were added.

    datasets-benchmarks
26. Paper

    scDisent: regulatory-aware disentangled representation learning for multi-omic single-cell analysis

    scDisent separates expression-linked and regulation-linked variables instead of compressing multi-omic measurements into one latent space.

    single-cell-spatial · biological-foundation-models
27. Paper

    A mechanism-annotated benchmark reveals limited fidelity to drug-response signatures in single-cell perturbation models

    A mechanism-aware benchmark found that high expression similarity often failed to preserve the drug-response signatures models were meant to predict.

    single-cell-spatial · datasets-benchmarks · drug-discovery
28. Paper

    Robustness to nuisance perturbations enables unsupervised evaluation of single-cell foundation models

    An unsupervised stress test separated single-cell foundation models that looked nearly equivalent on standard downstream benchmarks.

    single-cell-spatial · biological-foundation-models · datasets-benchmarks
29. Paper

    Unobserved Sequence Space Has Many Functional Proteins

    Wet-lab tests found many functional proteins far from known natural sequences while exposing inconsistent predictions from protein language models.

    protein-design · datasets-benchmarks
30. Paper

    Elevated contractility drives implantation failure in mouse embryos from aged females

    Older mouse embryos were more contractile and viscous, which impaired spreading during implantation; related imaging signatures also tracked human embryo potential.

    single-cell-spatial
31. Paper

    The proportional scaling of mRNA and ribosome concentrations controls eukaryotic cell growth

    Yeast cells grew faster by increasing mRNA and ribosome concentrations together, raising the number of active ribosomes without speeding elongation.

    single-cell-spatial
32. Paper

    Combinatorial group testing for efficient scaling across biological applications

    PoolPy cut the number of measurements needed by 60% to 93% across three kinds of biological experiments.

    lab-automation · datasets-benchmarks
33. Paper

    Predictive design of tissue-specific mammalian enhancers that function in the mouse embryo

    Chen and colleagues used deep learning to design 15 synthetic enhancers that activated the intended tissues in mouse embryos.

    protein-design · datasets-benchmarks
34. Paper

    DREAMS illuminates spatial DNA and RNA modification landscapes

    DREAMS maps multiple DNA and RNA modifications across tissue and linked TET1 loss to altered RNA m1A patterns in mouse brain.

    single-cell-spatial
35. Paper

    Adaptive model-guided protein evolution with sparse data optimizes compact eukaryotic genome editors

    A sparse-data machine-learning loop helped researchers engineer a compact Fanzor genome editor that worked across mammalian-cell targets and in a mouse experiment.

    protein-design · datasets-benchmarks
36. Paper

    Beyond benchmarking: an expert-guided consensus approach to spatially aware clustering

    SACCELERATOR combines agreement among algorithms with expert tissue knowledge to make spatial-clustering benchmarks more biologically useful.

    single-cell-spatial · datasets-benchmarks
37. Paper

    Obligate cross-feeding of metabolites is common in soil microbial communities

    Many bacteria isolated from German soils could not grow alone without metabolites supplied from outside the cell.

    drug-discovery
38. Paper

    Searching the Druggable Genome using Large Language Models

    A Model Context Protocol server lets language models query current, structured drug-gene interaction data from DGIdb.

    scientific-agents · drug-discovery
39. Paper

    A novel benchmark dataset for enzyme function prediction reveals the limitations of state-of-the-art models

    EnzymARC tests whether enzyme-function predictors reject structure-guided decoys whose catalytic machinery has been disrupted.

    datasets-benchmarks · biological-foundation-models · protein-design
40. Paper

    GRASSP: RNA Language Model–Enhanced Graph Attention with Adaptive Gating for RNA–Small Molecule Binding Site Prediction

    GRASSP combines pretrained RNA representations with lightweight graph refinement for RNA-small molecule binding-site prediction.

    biological-foundation-models · drug-discovery · datasets-benchmarks
41. Paper

    Performance, Generalizability, and Fairness of a Peripheral Artery Disease Detection Model Across Patient Phenotypes and Health Systems

    An EHR model performed similarly across five health systems but much less sensitively in patients with sparse documentation.

    datasets-benchmarks · policy-regulation
42. Paper

    Plant Spatio-Temporal Integration Network (PSTN): A framework for dynamic single-cell and spatial transcriptomics in fungal–plant interactions

    PSTN links single-cell and spatial transcriptomics across infection time points instead of integrating each stage separately.

    single-cell-spatial · datasets-benchmarks
43. Paper

    Delays between CE mark and FDA regulatory approval of AI-enabled software for radiology

    A cross-jurisdiction analysis finds longer second-authorization delays when radiology AI reaches Europe before the United States.

    policy-regulation · datasets-benchmarks
44. Paper

    bulk2scDiff: Generating Single-Cell Expression Profiles from Pseudobulk Data with Conditional Diffusion Models

    A conditional diffusion model reconstructs plausible single-cell populations from bulk-like expression summaries.

    single-cell-spatial · biological-foundation-models · datasets-benchmarks
45. Paper

    A self-supervised DNA foundation model with collapse-resistant multimodal fusion

    A DNA foundation model combines sequence with local and global chromatin accessibility while trying to prevent one modality from overwhelming the representation.

    biological-foundation-models · single-cell-spatial · datasets-benchmarks
46. Paper

    A blinded, prospective benchmark of in silico antibody discovery anchored to experimental affinity and developability

    A prospective, blinded antibody challenge found real pockets of strong performance, but most methods did not generalize across its three tasks.

    protein-design · datasets-benchmarks · drug-discovery
47. Paper

    Prospective evaluation of a large language model clinical decision support system in the emergency department

    A four-week emergency-department evaluation found mostly appropriate sampled outputs but falling clinician adoption and no reduction in length of stay.

    scientific-agents · policy-regulation · datasets-benchmarks
48. Paper

    Supervised Learning of Phosphopeptide Sequence Constraints Enables Global Prediction of SH2 Domain Binding

    SpY-C learns shared sequence constraints for whether a human phosphotyrosine site can participate in SH2-domain binding.

    datasets-benchmarks · drug-discovery
49. Paper

    Single-cell foundation models benefit from cross-modal training: adding proteomics data beats parameter scaling

    A small biological foundation model trained with proteomics matched or beat much larger RNA-only models on most reported benchmarks.

    biological-foundation-models · single-cell-spatial · datasets-benchmarks
50. Paper

    AlphaConformers: Structure-guided sampling enables prediction of multiple protein conformations

    AlphaConformers uses structures from related proteins as template hypotheses to steer AlphaFold2 toward alternative conformations.

    protein-design · biological-foundation-models · datasets-benchmarks
51. Paper

    Perturb-ME: Scalable mechanism discovery from phenotype-enriched genome-wide screens

    Perturb-ME combines phenotype enrichment, genome-scale CRISPR, and multimodal single-cell readouts to map mechanisms behind a selected phenotype.

    single-cell-spatial · scientific-agents · datasets-benchmarks
52. Paper

    Automated synthetic cell-based screening for designed proteins with emergent functions

    PUREdrop automates time-resolved screening of designed proteins inside picoliter synthetic cells, demonstrated with FtsZ variants and modulators.

    lab-automation · protein-design
53. Paper

    Mechanistic machine learning for prediction of prime editing outcomes

    OptiPrime uses a mechanism-based machine-learning model to predict prime-editing outcomes and nominate edits intended to evade mismatch repair.

    datasets-benchmarks · drug-discovery · biological-foundation-models
54. Paper

    Virtual-cell verification enables self-auditing AI discovery for immune rejuvenation

    A preprint combines an immune-aging score, a tokenized virtual-cell model, and an agent that revises its own compound-scoring objective.

    biological-foundation-models · single-cell-spatial · scientific-agents
55. Release

    Insilico Virtual Aging Cell preview

    Insilico Medicine launched an informational webpage and previewed a multi-agent virtual-cell concept that treats biological age as a conditioning variable across several biological scales.

    multi-omics · cell state · biological aging
56. Release

    Genedata Profiler Biomarker Discovery Agent

    Genedata announced an AI-guided biomarker workflow inside its commercial Profiler platform, with structured study design, quality control, modeling, and reporting steps.

    patient data · proteomics · multi-omics
57. Release

    2026 RSNA Knee Abnormality Detection AI Challenge

    RSNA opened a multimodal knee-MRI challenge using images and radiology-report text from sites across five continents, with an expert-annotated evaluation set.

    knee MRI · radiology reports
58. Deal

    Gates Foundation commits up to $35 million to ProFound’s AI search for preeclampsia targets

    The Gates Foundation committed an initial $20 million—and up to $15 million more—to ProFound Therapeutics for a maternal-health discovery program built around the company’s expanded-proteome platform.

    drug-discovery · protein-design
59. Deal

    Biohaven licenses opakalim to SK Biopharmaceuticals in a deal worth up to $795 million

    SK Biopharmaceuticals agreed to take global rights to Biohaven’s Kv7 platform and opakalim, the Phase 2/3 epilepsy candidate also known as BHV-7000. Biohaven receives $350 million at closing and $50 million in 2027; development, regulatory, and prior-owner obligations account for the rest of the announced value.

    drug-discovery
60. Deal

    Faro raises $37.3 million to scale agentic AI across clinical development

    Faro announced a $37.3 million Series B co-led by Merck Global Health Innovation Fund and S32, with existing and new investors participating. The company says it will use the financing to expand AI agents for clinical-development workflows.

    scientific-agents · drug-discovery
61. Deal

    Onos Health raises $17 million for behavioral-health AI

    Onos Health raised a $17 million Series A led by Costanoa Ventures, with Flare Capital Partners and CVS Health Ventures participating. The company plans to expand its behavioral-health clinical-intelligence platform and health-plan deployments.

    scientific-agents
62. Deal

    Transfyr launches with $25 million to capture the tacit knowledge of lab work

    General Catalyst led Transfyr's $25 million seed round. The startup uses sensors and multimodal models to record the unwritten details that can determine whether experiments reproduce or transfer between labs.

    lab-automation · datasets-benchmarks
63. Deal

    Lundbeck takes EVERSANA's AI platform across its U.S. commercial operation

    Lundbeck is expanding EVERSANA's AI-enabled platform across marketing, medical communications, market access, and media in its U.S. organization. The companies did not disclose financial terms or product-level performance.

    biological-foundation-models
64. Deal

    Sentivera licenses a Haisco inflammation drug in a deal worth up to $1.5 billion

    Haisco granted Sentivera rights outside Greater China to a preclinical small molecule for Type 2 inflammatory diseases. Haisco says the package includes $75.89 million in upfront cash and equity consideration, up to $1.46 billion in milestones, and tiered royalties; Fierce Biotech separately reported the transaction.

    drug-discovery
65. Deal

    Genentech licenses Hanmi's muscle-sparing obesity candidate

    Hanmi granted Genentech exclusive rights outside South Korea to HM17321, a clinical-stage UCN2 analogue. Hanmi says it will receive $190 million up front, may receive development, regulatory, and commercial milestones that bring the total value to as much as $2.3 billion, and is eligible for tiered sales royalties.

    drug-discovery
66. Deal

    Gossamer Bio announces a structured private placement of up to $250 million

    Gossamer expects $25 million at the initial close. A $125 million second tranche depends partly on FDA acceptance of a seralutinib NDA, while up to $100 million more would require later warrant exercises after approval; some issuance also needs stockholder approval.

    drug-discovery · policy-regulation
67. Deal

    Werewolf and Ambros announce a reverse merger with a concurrent $150 million PIPE

    The companies announced an all-stock reverse merger and concurrent $150 million private placement. Closing is expected in the first quarter of 2027 and remains subject to approvals and customary conditions; neridronate remains investigational.

    drug-discovery
68. Deal

    Chai Discovery and Bristol Myers Squibb announce an AI antibody-discovery collaboration

    The companies announced a research collaboration using Chai's models for antibody discovery. Targets, disease areas, economics, timelines, and candidate-level results were not disclosed.

    biological-foundation-models · protein-design · drug-discovery
69. Deal

    Network Bio and NVIDIA collaborate on a cell-free RNA foundation model

    Network Bio announced a collaboration combining its longitudinal cell-free RNA datasets with NVIDIA accelerated computing, Parabricks, and BioNeMo Recipes to build a foundation model called Nexus. Financial terms, development milestones, and external validation plans were not disclosed.

    biological-foundation-models · datasets-benchmarks
70. Deal

    Causaly and Syneos Health partner on evidence-grounded clinical research workflows

    Causaly and Syneos Health announced a strategic partnership to apply Causaly's platform across therapeutic-area expertise, medical advisory, real-world evidence, patient advocacy, and proposal development. The companies did not disclose financial terms or implementation milestones.

    scientific-agents · drug-discovery
71. Deal

    Craif raises approximately $33 million for urine-based cancer testing

    Craif announced an approximately $33 million Series D co-led by Granite Integral and Tauns Laboratories. The headline total combines approximately $30.7 million of equity, including a secondary component, with approximately $3.3 million of debt, so it should not be read as entirely new primary equity capital.

    drug-discovery · datasets-benchmarks
72. Deal

    Infinimmune closes $75 million Series A for human-derived antibodies

    Infinimmune said it closed a $75 million Series A co-led by Regeneron Ventures and Playground Global. The financing is intended to move its two atopic-dermatitis antibody programs toward first-in-human testing and support additional programs and platform development.

    protein-design · drug-discovery
73. Deal

    Aureka closes $100 million Series B for biological foundation models

    Aureka said it closed a $100 million Series B: Granite Asia exclusively funded the first tranche, while an unnamed strategic investor led a subsequent tranche. The company also named HighLight Capital and existing investors MPCi and NRL as participants; valuation and tranche sizes were not disclosed.

    biological-foundation-models · drug-discovery
74. Deal

    Novo Nordisk selects AWS as strategic AI and cloud partner for drug discovery

    Novo Nordisk selected AWS as its preferred cloud provider and strategic AI partner and said the companies will open a co-innovation hub in London. The stated work includes Amazon Bio Discovery, Bedrock, and Bedrock AgentCore; financial terms and delivery milestones were not disclosed.

    drug-discovery · scientific-agents
75. Topic

    Biological foundation models

    General-purpose learned representations for molecules, cells, tissues, and other biological systems.

76. Topic

    Data and benchmarks

    Datasets, evaluations, splits, metrics, and reproducibility infrastructure for biological machine learning.

77. Topic

    Drug discovery

    AI-assisted target selection, molecular design, experimental prioritization, and preclinical research workflows.

78. Topic

    Laboratory automation

    Robotics, orchestration software, and closed-loop experimentation for reproducible biological research.

79. Topic

    Policy and regulation

    Standards, governance, validation expectations, and public policy affecting AI-enabled life-science work.

80. Topic

    Protein design

    Computational generation and evaluation of proteins, antibodies, peptides, and their interactions.

81. Topic

    Scientific agents

    AI systems that plan, execute, verify, or escalate scientific and laboratory work under human oversight.

82. Topic

    Single-cell and spatial biology

    Machine learning for cellular measurements, perturbations, tissue context, and multimodal biological maps.