Archive
October 2026backfilled
Tap a day for its top 5
Joint latent spaces link histology, omics and single-cell data across modalities PARTIAL Machine learning models encode biological structure across single-cell and spatial omics Tools for macromolecular structure preparation, comparison, search and model selection Tools for macromolecular structure preparation, comparison, search and model selection Structural tools span complex selection, RNA prediction and ligand binding-site mapping Probabilistic and graph models infer cell identity from spatial transcriptomic data Software and statistical tests for single-cell, spatial, and omics inference Mechanistic and causal models for dynamic, zero-inflated, and spatial omics data Single-cell analysis tools adapt validated methods to new data types and noise regimes Mechanistic models link enzyme allocation, growth limits and electron flux in cells New frameworks resolve gene programs and clustering instability in spatial omics Spatial and single-cell omics methods separate modeling choices from inferred structure Transcriptomics software is validated for stability, reproducibility and cross-species use Structure-based methods predict ligand binding sites, poses and cryptic pockets Benchmarks expose limits of co-folding and docking for ligand pose and pocket prediction Benchmarks reveal how somatic and structural variant callers perform across platforms Cross-platform benchmarks reshape somatic and structural variant detection standards Models infer cell fate and spatial organization from single-cell and spatial omics data Models infer cell fate, spatial organization and drug response from single-cell profiles Computational methods infer cell states and niches from single-cell and spatial omics Evaluation design, not model choice, shapes reported agreement in biomedical ML Geometry-aware models infer cell dynamics and spatial organization from single-cell data Pipelines resolve ambient RNA, allele-specific reads and transcript-level assignment Integrated multi-omics resources make heterogeneous public datasets jointly analysable Local geometry coupled to single-cell dynamical and spatial inference Computational methods resolve cell states, niches and interactions from single-cell data Structure prediction coupled to learning drives biomolecular design and scoring Structure prediction coupled to sampling and optimization for de novo biomolecular design Coupled structure prediction and physics sampling drive new biomolecular binder design Single-cell and spatial transcriptomics tools resolve niche-dependent gene co-expression LLM agents orchestrate domain bioinformatics tools with auditable, checkable execution
September 2026backfilled
Tap a day for its top 5
Geometry-aware models refine antibody and peptide binding and stability prediction Computational methods resolve cell and spatial structure in transcriptomic data Learned models target binding, toxicity, and design with geometry-aware representations Truth-anchored variant calling extends to long reads, pangenomes and nonmodel genomes Statistical models address compositional, batch, and covariate structure in omics data Formal models for compositionality, batch effects, and uncertainty in omics inference Computational frameworks model single-cell perturbations, fate, and regulatory networks Somatic mutation and copy number methods map tissue-scale genomic variation Multimodal deep learning integrates omics, histology, and spatial data for prediction Copy number, indel, and mutational-process calling across tissue and cancer genomes Benchmarks and pipelines reshape single-cell and spatial transcriptomics analysis Supervised and self-supervised models for protein prediction and evaluation design Probing data and learned models resolve RNA structure and ligand-binding sites Methods extracting cell-level information from spatial and single-cell transcriptomes Structured predictive models of cells, drugs and molecules aim for interrogable outputs Biological priors as scaffolds for interpretable prediction in cancer and genomics PARTIAL Deep learning on learned molecular and protein representations for interaction prediction Biological structure scaffolds interpretable ML across drug, genomic and perturbation data Biological priors and attribution shape predictive models for drug and gene discovery Biological structure and perturbation atlases are shaping predictive single-cell models Single-cell resources and models map regulators, cell types and differentiation Paired snRNA and snATAC profiling with benchmarked gene regulatory network inference Benchmarking single-cell annotation, doublet calling and differential testing Structure-derived readouts benchmarked across binding, pocket, and interface prediction Computational tools refine segmentation and annotation in spatial transcriptomics Computational control of cell-level inference errors in spatial transcriptomics Benchmarks reveal limits of deep learning for protein and ligand prediction Generative and graph models predict single-cell perturbation and regulatory states Latent generative models predict single-cell perturbation responses across modalities Graph and structure-aware models encode biological priors for omics-based prediction
August 2026backfilled
Tap a day for its top 5
Deep learning models predict gene expression, drug interactions, and protein properties Learned models extract more biology from sequence and read data across genomics Biological priors constrain deep learning for expression, lethality and drug response Inferring time-resolved regulatory dynamics from single-cell and spatial transcriptomics Biological priors constrain deep models of gene expression prediction and deconvolution Biological priors constrain deep models of spatial gene expression and histology External biological knowledge encoded as structural priors in deep prediction models Learned embeddings and linear models predict perturbation and binding outcomes Histology-conditioned models infer spatial gene expression and tissue niches Histology and omics foundation models predict spatial gene expression and tissue niches Generalization of learned models to unseen transcriptional perturbation responses H&E histology models predict spatial gene expression at single-cell resolution Pretrained biomolecular language model embeddings reused for task-specific prediction Generative flow and diffusion models predict single-cell perturbation responses Histology-conditioned models predict spatial gene expression from H&E morphology Generative and causal models infer unobserved single-cell and spatial omics profiles Validated omics methods: ground-truth benchmarks, simulators and uncertainty estimates Network models of neural activity and oscillations explain disease-linked brain dynamics Histology-to-spatial-transcriptomics prediction moves to diffusion over gene programs Histology-to-transcriptomics models now target programs, priors, and shared latent spaces Pangenome graphs and variant-effect models sharpen variant interpretation across genomes Benchmarks expose limits of learned models in protein, drug, and enzyme prediction AI models design and rank binders, antibodies, and molecular glues Biological foundation models are benchmarked for efficiency, fidelity and transfer AI molecular design is increasingly judged by validation, dataset quality and ADMET Learned models couple histology, transcriptomics, and regulatory networks in omics Interpretable models link omics and histology data to cancer biomarkers and prognosis Benchmarks test whether perturbation models capture mechanism and intervention geometry Learned models fuse histology, transcriptomic, and chromatin data to infer biology Biomedical ML models lose accuracy under acquisition and corruption shifts Frameworks integrate spatial, histology, and single-cell transcriptomic data
July 2026backfilled
Tap a day for its top 5
Foundation and deep learning models predict transcriptomic, drug and sequence phenotypes Neural and graph models reconstruct and integrate spatially resolved transcriptomic data Computational methods refine spatial gene expression to cell-level resolution Interpretable deep learning and graph methods integrate multiomics and spatial molecular… Graph and generative models infer spatial gene programs and cell states from omics data Graph and generative learning models decode spatial and single-cell transcriptomes Graph and generative models resolve spatial transcriptomes and multi-omics to cell level Graph and probabilistic learners decode spatial and single-cell omics architectures Graph and deep generative models resolve cell identity and spatial gene programs Computational models infer cell fate, perturbation response and spatial gene programs Higher-order and topological views recover disease structure from multi-omic data Deep learning infers cell states and regulatory logic from single-cell and cfDNA data Computational tools reshape bulk and single-cell transcriptome analysis workflows Deep models predict regulatory, mutational, and drug-response outcomes from omics data Structure-based web servers address docking, glycosylation, and metal-binding sites Web servers package structure-based methods for modeling, docking, and protein engineering Web servers and platforms extend reproducible annotation, search, and peptide analysis Network inference links molecular measurements to regulatory and causal gene programs Structural priors fused with multimodal inputs predict clinical and regulatory outcomes Open-source tools standardize omics, peptide sequencing, and benchmarking workflows Graph and foundation models fuse spatial, omic and imaging inputs into shared embeddings Graph and pathway priors guide multimodal representations of single-cell and patient data Single-cell and transcriptomic tools for cell-cell, signaling and perturbation analysis Deep models couple histology, transcriptomes and biological priors to predict expression Pangenome and haplotype-resolved methods reshape human genome variant analysis and phasing Extending GWAS and colocalization to admixed and multi-ancestry populations Single-cell multiomics links 3D genome and isoform structure to cell-type regulation Reference database contamination and new pipelines reshape microbial genomic analysis Modular pipelines and toolkits standardize reproducible analysis across omics data types Updated tools for microbial pangenomics, plasmid recovery and phylogenetic inference Deep models fuse heterogeneous data to predict resistance, drug response, and outcomes
June 2026backfilled
Tap a day for its top 5
New computational tools decode gene regulation and cell identity from single-cell omics Deep learning couples histology and spatial transcriptomics to map tissue organization Reproducible software tools for integrating omics and regulatory genomics data analysis Error-aware low-frequency variant calling and reproducible pipelines for sequencing data Graph neural networks resolve spatial niches and domains in tissue transcriptomics Learned models infer regulation, dynamics and cell identity from single-cell omics data Graph-based learning extends spatial transcriptomics to imputation, denoising and 3D Software and benchmarks for reproducible multi-omics analysis and interpretation Learned models impute, translate and infer dynamics in single-cell and spatial data Learned models reconstruct spatial and temporal single-cell transcriptomic profiles Learned structure models are being applied to binder design, co-folding, and stability Biological priors are being built into single-cell and spatial transcriptomics models Learned models predict perturbation responses and design molecules and binders Learned models integrate spatial and single-cell omics across modalities and tissues Structure-aware models retain spatial and lineage dependence in single-cell analyses PARTIAL Deep learning links single-cell morphology, imaging and spatial transcriptomic profiles Genome-wide data curation and evolutionary inference across viral and bacterial pathogens PARTIAL Generative models span peptide, TCR, binder, antibody and PROTAC design Allele, copy-number and recombination resolution reshape pathogen genome analysis Inferring spatial cell states from histology, imaging and weakly anchored sections Accessible tools wrap enrichment, survival and multi-omic network analyses in GUIs Sequence and network models advance prediction of TF binding and chromatin insulation ML models predict antibody-antigen binding, developability, and epitope-targeted design ML models predict antibody-antigen binding, developability and epitope-targeted design Computational inference bridges sparse spatial and single-cell measurements Reference-anchored methods for spatial cell-type annotation and deconvolution Standardized tools and benchmarks for reproducible multi-omics and single-cell analysis Reusable tools target reproducible inference across multi-omics and single-cell data Computational methods infer spatial and developmental dynamics from single-cell data PARTIAL Leakage-free validation and benchmarking reshape omics ML biomarker discovery
May 2026backfilled
Tap a day for its top 5
Single-cell and spatial maps resolve immune programs in lupus and breast cancer Single-cell models and causal methods test transferable gene regulatory knowledge Software tools correct technical artifacts and reuse public omics data at scale Graph and contrastive models recover spatial and single-cell transcriptomic structure Graph and autoencoder models recover structure from sparse spatial transcriptomes Graph and contrastive learning recover spatial structure lost in sparse transcriptomes Learned models recover structure from sparse spatial and single-cell transcriptomes Learned models recover structure from sparse spatial and single-cell transcriptomes Learned representations fuse single-cell, spatial and histology data into shared models Graph and prior-informed models infer hidden regulatory structure from omics data Computational inference of niche-level cell communication from spatial transcriptomics Graph-based models of cell-cell interactions and gene regulation in single-cell data Biomolecular generators encode multiple objectives, diversity, and physics-based checks Graph neural networks model molecular interactions, drug synergy and disease drivers Learned models resolve cell states and spatial niches from transcriptomic data Learned models infer cell structure in single-cell and spatial transcriptomics Learned models recover cellular and spatial structure from transcriptomic data across… Learned embeddings recover spatial structure and cell states from transcriptomic data Learned latent models recover spatial and single-cell transcriptomic structure Open computational frameworks infer molecular states from sequencing data Long-read pangenomes resolve mobile and repetitive variation in human genomes Benchmarks expose leakage and inconsistent evaluation in biological prediction tools Computational methods target batch effects and missing values in single-cell omics data Single-cell multi-omics resolves regulatory and transcript changes in aging and disease Improved variant calling across short-read, long-read, and low-pass sequencing data Multiomic single-cell profiling resolves regulatory and transcript architecture Single-cell tools resolve transcript and regulatory architecture across tissues Computational frameworks resolve cell states, spatial niches and perturbation effects Pooled CRISPR screens and spatial transcriptomics resolve perturbation effects in tissue Deep learning biomolecular models coupled to experimental and geometric constraints Deep models gain experimental restraints and geometric priors for biomolecular design