Week 40, 2026 · Sep 28 – Oct 4

Top 40

Tools & infrastructure

Computational models link genetic variants to RNA binding and cell-type expression

ML / AI methods

Spatial models couple influenza dispersal, defective particles and interferon signalling

Tools & infrastructure

Learned models link histology and spatial transcriptomics to predict expression and niches

Systems biology

Bifurcation structure and heterogeneity determine persistence beyond threshold indices

Genomics

Chromosome-level assemblies link genome gigantism and gene loss to lineage evolution

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

7 Learned latents steer protein conformations and encode evolutionary structureML / AI methods

8 Comparative genomics partitions duplication, transfer and synteny across lineagesGenomics

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

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

11 LLM agents automate bioinformatics workflows with verifiable, grounded outputsML / AI methods

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

13 Deep learning automates microscopy and histology image analysis with less labelled dataML / AI methods

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

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

16 MD ensembles and replica-exchange sampling map folding and binding pathwaysStructural bio & protein design

17 Benchmarks and tools expose technical biases in sequencing-based genomic assaysEpigenomics

18 Correcting RNA degradation and hashtag demultiplexing in single-cell transcriptomicsSystems biology

19 Network models nominate interventions from omics and screening dataSystems biology

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

Show 20 more

21 Generative models steered by RL, fragments, and SMARTS for molecule and linker designStructural bio & protein design

22 MD simulations link conformational states to membrane binding and organizationStructural bio & protein design

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

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

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

26 Integrating diverse variant and annotation data to improve genetic risk predictionGenomics

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

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

29 Graph neural networks model molecular interactions, drug synergy and disease driversSystems biology

30 Ensemble and free-energy methods now resolve RNA, protein and ligand binding physicsStructural bio & protein design

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

32 Internal ground truths benchmark RNA-seq transcript and expression inference toolsGenomics

33 Computational models link germinal center B cell states to antibody affinity maturationGenomics

34 Adhesion, noise, and discretization shape collective and single-cell migration modelsSystems biology

35 Models link non-genetic B cell state dynamics to antibody affinity maturationSystems biology

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

37 Simulations Link RNA Modifications to Conformation and Electronic StructureStructural bio & protein design

38 Updated tools for microbial pangenomics, plasmid recovery and phylogenetic inferenceSystems biology

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

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