Top 40
View all ›BACKFILLED Code and industry signals are partial for backfilled days.
ML / AI methods
ML models predict antibody-antigen binding, developability and epitope-targeted design
Learned models are now coupled to antibody generation, library design and developability profiling, not only affinity prediction.
Transcriptomics
Predicting spatial gene expression from H&E histology via transcriptomic foundation priors
Routine H&E histology is now paired with transcriptomic foundation-model priors and formal inference for imputed spatial transcriptomes.
Tools & infrastructure
Statistics-aware software for omics, spatial and network inference across modalities
Growing multi-omic and single-cell datasets require inference tools that validate statistical assumptions and integrate heterogeneous modalities.
Tools & infrastructure
Tools refine variant benchmarking, structural variant calling, and reference selection
Recent preprints and papers add open-source tools for variant benchmarking, read resampling, and reference choice, targeting comparison fidelity and throughput…
Genomics
Deep learning tools for genome annotation are being systematically benchmarked
Recent preprints systematically evaluate DNA language models and deep learning predictors across scaffolding, coding sequence, and gene annotation tasks.