TrendBio

Top 40

View all ›

BACKFILLED Code and industry signals are partial for backfilled days.

Rank 1

ML / AI methods

Interpretable models link omics and histology data to cancer biomarkers and prognosis

Interpretable architectures now target multi-omics, histology and legacy microarray data for cancer biomarker discovery and prognosis.

8 preprints · 1 published · ↑ 3.0× vs 4-wk avg
Rank 2

Structural bio & protein design

Machine learning links protein topology and ensembles to binding prediction

Recent work adds dynamics, ensembles, and topology to structure-based learning for binding affinity, docking, and interface prediction.

8 preprints · 3 published · ↑ 2.4× vs 4-wk avg
Rank 3

ML / AI methods

Controlled evaluation of representation and context in biological foundation models

Independent benchmarks now test RNA, splicing, and enzyme predictors on novel folds, decoys, and synthetic variants, exposing generalization limits.

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

Epigenomics

Cell-type chromatin accessibility links brain aging, longevity, and disease risk

Single-cell chromatin accessibility now resolves aging clocks, longevity signatures, and disease regulatory networks at cell-type resolution.

5 preprints · 2 published · ↑ 1.7× vs 4-wk avg
Rank 5

Structural bio & protein design

Model-guided design of aptamers, glues and degraders tested in wet-lab screens

Design pipelines now close the loop between structure-model feedback and wet-lab measurement across aptamers, glues, degraders, and genome editors.

5 preprints · 1 published · ↑ 1.7× vs 4-wk avg