TrendBio

Top 40

View all ›

BACKFILLED Code and industry signals are partial for backfilled days.

Rank 1

ML / AI methods

Biology-informed deep learning links multimodal omics with interpretable predictions

Transformer foundation models and graph learning with biological priors now integrate spatial, single-cell, and proteomic omics data.

5 preprints · 5 published · ↑ 3.5× vs 4-wk avg
Rank 2

Single-cell

Deep learning links single-cell and spatial data to phenotype and cell-cell structure

Recent single-cell and spatial deep learning work pairs graph or attention architectures with interpretability and explicit baseline benchmarking.

6 preprints · 1 published · ↑ 3.3× vs 4-wk avg
Rank 3

Single-cell

Computational integration of multimodal single-cell and spatial molecular measurements

Reference-free and parameter-light methods now span CITE-seq, spatial transcriptomics, single-cell proteomics and long-read isoform data.

3 preprints · 6 published · ↑ 3.0× vs 4-wk avg
Rank 4

Systems biology

Spatial omics tools resolve ligand signaling and multicellular gene programs

Spatial omics datasets are now paired with reaction-diffusion, motif-discovery and foundation-model frameworks for mechanistic inference.

8 preprints · 2 published · ↑ 2.6× vs 4-wk avg
Rank 5

Structural bio & protein design

Sampling and energy methods are benchmarked against structural and kinetic readouts

Recent preprints and publications test sampling, scoring and energy-function methods against stability data and RNA structure accuracy.

3 preprints · 4 published · ↑ 2.5× vs 4-wk avg
Rank 6 Structure-based scoring ranks predicted and experimental models by interface relevance↑ 2.2×Structural bio & protein designRank 7 Learned models design sequences under structural and translational constraints↑ 2.3×Structural bio & protein designRank 8 Benchmarks and synthetic ground truth for segmentation in 3D tissue and spatial omics↑ 2.0×Tools & infrastructureRank 9 Simulations resolve selectivity and binding in membrane proteins, peptides, and fibrils↑ 2.0×Structural bio & protein designRank 10 Computational inference of microbial traits from sequence, expression and plasmid data↑ 2.1×Systems biologyRank 11 Lineage-explicit simulation and germinal center models probe antibody affinity maturation↑ 2.0×ML / AI methodsRank 12 Benchmarks challenged for perturbation and drug-response prediction in biology↑ 1.9×ML / AI methodsRank 13 Protein and RNA language models predict interactions, expression, and enzyme function↑ 2.0×ML / AI methodsRank 14 Learned models convert heterogeneous scientific data into structured molecular knowledge↑ 2.0×MetabolomicsRank 15 Benchmarking sequence, structure and chemical-biology models across splits and time↑ 2.0×Tools & infrastructureRank 16 Spatial and single-cell methods infer cell interactions and trajectories↑ 1.7×Single-cellRank 17 Graph and pangenome references improve structural variant detection accuracy↑ 1.9×GenomicsRank 18 Verifying proteomics software outputs via FDR diagnostics and cross-tool benchmarks↑ 1.9×ProteomicsRank 19 Benchmarking transcriptome reconstruction and assembly quality with new RNA-seq toolsTranscriptomicsRank 20 Recovering single-cell kinetics and trajectories from static and noisy measurementsEpigenomics