Top 40
View all ›BACKFILLED Code and industry signals are partial for backfilled days.
Single-cell
Learned representations fuse single-cell, spatial and histology data into shared models
Co-assayed and cross-modal omics data now feed foundation models and graph methods that are tested against defined biological tasks.
Transcriptomics
Learned models recover structure lost to sparsity and modality gaps in transcriptomics
Recent spatial and single-cell papers apply graph, contrastive, and transformer learning to sparse, incomplete, or multi-omic transcriptomic measurements.
Single-cell
Graph and network models infer regulatory links and subtypes from multi-omics data
Learned and network models now target regulatory interactions, driver mutations and subtypes that standard omics analyses do not capture directly.
ML / AI methods
Graph neural networks predict drug response, molecular interactions, and biological age
Recent 2026 papers apply hierarchical, multi-relational, and equivariant graph architectures across drug, protein, RNA, and epigenetic prediction tasks.
Transcriptomics
Context-resolved cell communication inferred from single-cell and spatial transcriptomics
Recent preprints and publications add niche-, condition-, and state-resolved inference to spatial and single-cell transcriptomics analyses.