Company news
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.
Independent reporting4 sources
Topic
Data and benchmarks
Datasets, evaluations, splits, metrics, and reproducibility infrastructure for biological machine learning.
News
Recent clusters
Clinical
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.
Independent reporting4 sources
Policy & regulation
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.
Reported development1 source
Research
Related papers
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.
Mapping Alzheimer's neuropathology signatures to the whole brain transcriptome using machine learning data fusion
Bhattacharya, A. and colleagues report that a data-fusion model projected cortical Alzheimer's signatures across a 108-region whole-brain single-cell atlas.
Assay concordance sets exact ceilings on what one biological score can predict
Liu, Z. reports that a model-free analysis argues that disagreement among biological assays places a measurable ceiling on predictor performance.
BfBio: a graph-based tool for the prediction of Angiogenic Stalk Cell genes using a Personalized PageRank algorithm
Bettoni, L. and colleagues used integrated omics and interaction networks to prioritize under-characterized genes linked to angiogenic stalk cells using a graph-ranking system.
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.
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.
A multi-scale structural and biophysical atlas of TCR-peptide-HLA recognition dynamics
Zhang, S. and colleagues report that dynaTPH adds standardized molecular-dynamics trajectories and biophysical features to 256 representative T-cell-receptor complexes.
Temporal dynamics improves machine learning-based prediction of cell state from quantitative phase imaging
Alizada, S. and colleagues classified six cell states from label-free imaging more accurately as additional frames were added using a spatiotemporal neural network.
A mechanism-annotated benchmark reveals limited fidelity to drug-response signatures in single-cell perturbation models
Li, L. and colleagues found that high expression similarity often failed to preserve the drug-response signatures models were meant to predict using a mechanism-aware benchmark.
Robustness to nuisance perturbations enables unsupervised evaluation of single-cell foundation models
Sallam, A. and colleagues report that an unsupervised stress test separated single-cell foundation models that looked nearly equivalent on standard downstream benchmarks.
Unobserved Sequence Space Has Many Functional Proteins
Diplock, N. and colleagues report that wet-lab tests found many functional proteins far from known natural sequences while exposing inconsistent predictions from protein language models.
Combinatorial group testing for efficient scaling across biological applications
Lorenzo Talamanca and colleagues report that poolPy cut the number of measurements needed by 60% to 93% across three kinds of biological experiments.
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.
Adaptive model-guided protein evolution with sparse data optimizes compact eukaryotic genome editors
Shijie Wan and colleagues report that 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.
Beyond benchmarking: an expert-guided consensus approach to spatially aware clustering
Jieran Sun and colleagues report that sACCELERATOR combines agreement among algorithms with expert tissue knowledge to make spatial-clustering benchmarks more biologically useful.
A novel benchmark dataset for enzyme function prediction reveals the limitations of state-of-the-art models
Joao Sartori and colleagues report that enzymARC tests whether enzyme-function predictors reject structure-guided decoys whose catalytic machinery has been disrupted.
GRASSP: RNA Language Model–Enhanced Graph Attention with Adaptive Gating for RNA–Small Molecule Binding Site Prediction
Thi Lan Nguyen and colleagues report that gRASSP combines pretrained RNA representations with lightweight graph refinement for RNA-small molecule binding-site prediction.
Performance, Generalizability, and Fairness of a Peripheral Artery Disease Detection Model Across Patient Phenotypes and Health Systems
Karoline Kallis and colleagues report that an EHR model performed similarly across five health systems but much less sensitively in patients with sparse documentation.
Plant Spatio-Temporal Integration Network (PSTN): A framework for dynamic single-cell and spatial transcriptomics in fungal–plant interactions
Yuheng Zhu and colleagues report that pSTN links single-cell and spatial transcriptomics across infection time points instead of integrating each stage separately.
Delays between CE mark and FDA regulatory approval of AI-enabled software for radiology
Yijun Ren and colleagues report that a cross-jurisdiction analysis finds longer second-authorization delays when radiology AI reaches Europe before the United States.
bulk2scDiff: Generating Single-Cell Expression Profiles from Pseudobulk Data with Conditional Diffusion Models
Jiedan Xiao and colleagues report that a conditional diffusion model reconstructs plausible single-cell populations from bulk-like expression summaries.
A self-supervised DNA foundation model with collapse-resistant multimodal fusion
Yuyan Chen reports that a DNA foundation model combines sequence with local and global chromatin accessibility while trying to prevent one modality from overwhelming the representation.
A blinded, prospective benchmark of in silico antibody discovery anchored to experimental affinity and developability
M. Frank Erasmus and colleagues report that a prospective, blinded antibody challenge found real pockets of strong performance, but most methods did not generalize across its three tasks.
Prospective evaluation of a large language model clinical decision support system in the emergency department
Liron Leibovitch and colleagues report that a four-week emergency-department evaluation found mostly appropriate sampled outputs but falling clinician adoption and no reduction in length of stay.
Supervised Learning of Phosphopeptide Sequence Constraints Enables Global Prediction of SH2 Domain Binding
Alekhya Kandoor and colleagues report that spY-C learns shared sequence constraints for whether a human phosphotyrosine site can participate in SH2-domain binding.
Single-cell foundation models benefit from cross-modal training: adding proteomics data beats parameter scaling
Maximilien Burq and colleagues matched or beat much larger RNA-only models on most reported benchmarks using a small biological foundation model trained with proteomics.
AlphaConformers: Structure-guided sampling enables prediction of multiple protein conformations
Julie Liliane Daniel and colleagues report that alphaConformers uses structures from related proteins as template hypotheses to steer AlphaFold2 toward alternative conformations.
Perturb-ME: Scalable mechanism discovery from phenotype-enriched genome-wide screens
Hanchen Wang and colleagues report that perturb-ME combines phenotype enrichment, genome-scale CRISPR, and multimodal single-cell readouts to map mechanisms behind a selected phenotype.
Mechanistic machine learning for prediction of prime editing outcomes
Alvin Hsu and colleagues report that optiPrime uses a mechanism-based machine-learning model to predict prime-editing outcomes and nominate edits intended to evade mismatch repair.
Products & tools
Related releases
Radiological Society of North America
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.
- Access
- benchmark
- License
- Not specified
Capital & partnerships
Related deals
seed financing
Transfyr
Build the platform, expand the Cambridge team, and generate training data in an in-house wet lab.
- Deal value
- $25 million
- Lead investor
- General Catalyst
research collaboration
Network Bio
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.
- Deal value
- Undisclosed
- Lead investor
- Not stated
series financing
Craif
Expand U.S. research and reimbursement-driven launch preparation, support a Japanese regulatory filing for pancreatic-cancer diagnostic software, and advance a prospective pancreatic-cancer study.
- Deal value
- ~$33M
- Lead investor
- Granite-Integral