Top 40
View all ›BACKFILLED Code and industry signals are partial for backfilled days.
ML / AI methods
Graph neural networks model molecular interactions, drug synergy and disease drivers
Explicit relational structure is now combined with biological priors and benchmarked evaluation across PPI, drug-target, and cancer driver prediction tasks.
Single-cell
New computational methods for single-cell, spatial, and imaging data analysis
Recent preprints and publications introduce benchmarks, integration tools, and automated pipelines for single-cell, spatial, and microscopy data.
ML / AI methods
Standardized benchmarks expose limits of ML models in biomolecular prediction
Recent preprints apply standardized, leakage-aware benchmarks to ML predictors spanning drug screening, perturbation biology, peptide design, and siRNA…
Transcriptomics
Benchmarking transcriptomic methods against controlled failure modes and ground truth
Recent work tests transcriptomic methods against ground truth, perturbation prediction, and realistic benchmarks in single-cell and bulk data.
Transcriptomics
Long-read phasing and allele-specific RNA methods get benchmarks and joint models
Long-read data now enable haplotype-resolved allele analysis, prompting benchmarks of phasing determinants and joint inference models.