Top 40
View all ›BACKFILLED Code and industry signals are partial for backfilled days.
Transcriptomics
Graph and generative models resolve spatial transcriptomes and multi-omics to cell level
Spatial and single-cell transcriptomics methods increasingly combine graph learning, foundation models and explicit latent structure across modalities.
ML / AI methods
Biological priors and uncertainty are being built into omics prediction models
Small, incomplete, and heterogeneous omics cohorts are driving models that encode pathway structure, missingness, and calibrated uncertainty.
ML / AI methods
Learned encoders fused with biological context predict drug and perturbation outcomes
Tabular foundation models prove competitive with specialized perturbation predictors, while adapters target unseen genetic perturbations.
Single-cell
Trajectory-aware, multi-omic inference of cell-type-specific gene regulatory networks
Recent single-cell methods add trajectories, regulatory priors, and latent TF activity to network inference from scRNA and ATAC data.
Tools & infrastructure
Omics software, databases and atlases standardize analysis across datasets
Recent releases pair reusable pipelines and harmonized atlases with benchmarking across large, heterogeneous omics resources.