Top 40
View all ›BACKFILLED Code and industry signals are partial for backfilled days.
Transcriptomics
Graph and generative models infer spatial gene programs and cell states from omics data
Recent methods pair graph learning and probabilistic models with spatial and single-cell multi-omics to address integration and interpretability.
ML / AI methods
Multimodal deep learning couples drug structure with biological context for prediction
Recent preprints and journal papers apply structure-, graph-, and language-model encoders to drug response, combination, ADMET, and generation tasks.
ML / AI methods
Testing whether biological priors and deep architectures improve omics prediction
Deep learning and probabilistic models are now applied to small-sample, multi-omics and single-cell data where uncertainty and interpretability matter.
Structural bio & protein design
Learned models predict protein binding sites, stability and mutational effects
Recent work pairs protein language model embeddings with graph and equivariant architectures, alongside new representation and evaluation strategies.
Epigenomics
Deep sequence models and DMR tools sharpen interpretation of regulatory methylation
Early-July 2026 preprints and publications extend sequence-to-function models and methylation tools to finer-scale regulatory questions.