Week 16, 2026 · Apr 13 – Apr 19

Top 40

Structural bio & protein design

Generative models steered by RL, fragments, and SMARTS for molecule and linker design

Single-cell

Spatial and single-cell models infer multicellular motifs, regulators and disease links

Systems biology

Correcting RNA degradation and hashtag demultiplexing in single-cell transcriptomics

ML / AI methods

Machine learning maps tissue and molecular profiles to cancer outcomes and subtypes

Genomics

Internal ground truths benchmark RNA-seq transcript and expression inference tools

6 Learned multimodal and graph representations for protein and RNA predictionML / AI methods

7 Learned predictors score protein interactions, variant effects, and peptide activityML / AI methods

8 Explicit latent structure for single-cell perturbation response and multi-omic modelingML / AI methods

9 Benchmarks probe AlphaFold model accuracy across peptides, RNA, and antibody complexesStructural bio & protein design

10 Fitted mechanistic models link single-cell and patient omics to regulatory dynamicsML / AI methods

11 Graph and language-model encoders advance drug-target and synergy predictionStructural bio & protein design

12 Free energy and coarse-grained physics methods for biomolecular binding and interfacesStructural bio & protein design

13 Biological foundation models face scrutiny over pretraining, benchmarks, and baselinesML / AI methods

14 Pretrained generative models extend to fMRI forecasting, diagnosis, and imagerySystems biology

15 Sequence- and structure-based models predict protein function and dynamicsML / AI methods

16 Machine-learning-guided de novo design of protein and peptide bindersML / AI methods

17 Chromatin structure and nucleosome states inferred from sequencing and contact mapsStructural bio & protein design

18 Multi-omic and structural data are converted into drug and target prioritization outputsGenomics

19 Simulation methods extend to cyclic peptides, non-canonical residues and polypeptoidsStructural bio & protein design

20 Design-aware statistical models for differential analysis of omics and imaging dataSystems biology

Show 20 more

21 Isoform-resolved single-cell and single-molecule methods quantify transcript variantsEpigenomics

22 Reproducible environments, DNA library design and standard formats for biology toolsStructural bio & protein design

23 Benchmarks and packaged pipelines standardize omics analysis toolsTools & infrastructure

24 Mechanistic models link cell-scale rules to invasion, containment and therapy outcomesSystems biology

25 Graph storage and streaming parsers reshape population-scale variant computationTools & infrastructure

26 New tools for recombination, metagenomic decontamination, and microbial community designTools & infrastructure

27 Biophysical models link ion channel, noise and modulation to network firing dynamicsSystems biology

28 Noise-driven dynamics shape neuronal firing, calcium states, and gait fluctuationsSystems biology

29 Constraints and cross-feeding shape inferred metabolic fluxes and microbial nichesSystems biology

30 Refined inference of tumor methylation, structural variants and clonal structureSingle-cell

31 Bifurcation structure and heterogeneity determine persistence beyond threshold indicesSystems biology

32 MD and cofolding models probe conformational states in kinases, Aβ, and HIV-1 EnvStructural bio & protein design

33 Encoding spatial and relational structure in high-dimensional omics analysisSingle-cell

34 Reproducible tools for assessing and streamlining omics data analysis workflowsTools & infrastructure

35 Context-aware models refine variant calling, eQTL mapping and polygenic predictionGenomics

36 New tools speed variant annotation, GWAS, and epigenomic and cytometry analysisTools & infrastructure

37 Computational models link genetic variants to RNA binding and cell-type expressionTools & infrastructure

38 Comparative genomics partitions duplication, transfer and synteny across lineagesGenomics

39 Transformer and deep learning tools benchmarked against established genomics methodsGenomics

40 LLM agents and multimodal models convert literature and spectra into molecular knowledgeTools & infrastructure