Top 40
View all ›BACKFILLED Code and industry signals are partial for backfilled days.
Single-cell
Graph and contrastive learning recover spatial structure lost in sparse transcriptomes
Spatial and single-cell transcriptomes are often sparse or incompletely measured, motivating learned models that complete and integrate them with prior…
Single-cell
Benchmarking and new algorithms for spatial and single-cell omics analysis
Matched-platform benchmarks and model comparisons now test spatial and single-cell omics tools on shared reference datasets.
ML / AI methods
Protein language models augmented with structure, dynamics, and generative components
Recent work pairs pretrained protein language model embeddings with structural, dynamical, or generative modules for function prediction.
ML / AI methods
Graph learning models advance molecular property and interaction prediction
Graph neural networks and LLM embeddings are now applied to metabolism, reactions, PPIs and drug repurposing with benchmarked evaluation.
Tools & infrastructure
Computational tools link single-cell and bulk tumor omics to immune and drug response
Recent preprints and publications pair single-cell and bulk tumor transcriptomes with immune and drug-response inference across multiple cancer types.