TrendBio

Top 40

View all ›

BACKFILLED Code and industry signals are partial for backfilled days.

Rank 1

Structural bio & protein design

Learned structure models are being applied to binder design, co-folding, and stability

Recent preprints and two peer-reviewed benchmarks test structure-aware models for co-folding, inverse folding, and binding prediction.

12 preprints · 2 published · ↑ 2.4× vs 4-wk avg
Rank 2

Transcriptomics

Histology-to-spatial omics models infer gene expression from routine H&E sections

Spatial omics is now distilled into models operating on routine H&E, enabling transcriptomic inference from widely available histology.

10 preprints · 1 published · ↑ 2.0× vs 4-wk avg
Rank 3

Single-cell

Generative models infer single-cell dynamics, transitions and perturbation responses

Growing multimodal, spatial and time-resolved single-cell datasets demand models that jointly infer cell states, dynamics and perturbation responses.

9 preprints · 2 published · ↑ 2.0× vs 4-wk avg
Rank 4

Epigenomics

Deep models and epigenome annotation infer regulatory elements from chromatin data

Foundation and segmentation models now couple DNA sequence, methylation, histone marks and accessibility to predict regulatory elements and states.

7 preprints · 4 published · ↑ 2.0× vs 4-wk avg
Rank 5

Tools & infrastructure

Scalable tools benchmark genome alignment, assembly, and phylogenetic inference methods

Recent preprints and a published OrthoFinder extension target runtime, memory, and accuracy limits in large-scale genome comparison.

7 preprints · 1 published · ↑ 1.6× vs 4-wk avg