974 papers
This paper introduces TOGGLE, a self-supervised graph diffusion framework that leverages deep learning and reinforcement-guided clustering to delineate fine-grained functional heterogeneity and predict cell fate within transcriptionally similar populations, successfully identifying distinct neuronal states in ischemic stroke and epigenetic memory in neural stem cells without prior labels.
This study reveals that in *Caenorhabditis elegans*, strain-specific structural variant architectures significantly influence mutation retention dynamics following mutagenesis, with higher outcrossing rates paradoxically leading to greater structural variant burdens and reduced purging of deleterious mutations.
This study introduces EscapeMap, a modular framework that integrates deep mutational scanning and generative modeling to predict SARS-CoV-2 escape variants, validate antibody resilience through designed RBD mutants, and identify optimal antibody combinations for therapeutic strategies.
This paper introduces the Tiling Algorithm, a reference-free method for characterizing the structural diversity and minor species of Adeno-associated virus (AAV) genomes using accurate long-read sequencing data, thereby overcoming the limitations of alignment-based approaches in handling AAV-specific challenges like inverted terminal repeats and replication artifacts.
The paper introduces siMILe, a weakly-supervised multiple instance learning method enhanced by adversarial erasing that enables the discriminative identification of condition-specific oligomeric protein structures from 3D single-molecule localization microscopy data without requiring structure-level supervision.
RNApdbee 3.0 is a unified web server that provides comprehensive RNA secondary structure annotation by integrating 2D and 3D data to classify diverse nucleotide interactions, handle structural inconsistencies, and generate standardized outputs and visualizations from 3D coordinates.
This paper presents a validated, standardized framework that bridges the platform gap between array-based and high-throughput sequencing data, enabling the robust adaptation of legacy epigenetic clocks for cell-free DNA analysis through optimized parameters and transfer learning.
This study reveals that organ-specific autoimmune diseases are driven by altered antigen processing that exposes previously "cryptic" self-proteins to the immune system, distinguishing them from systemic diseases caused by a breakdown of tolerance toward normally presented self-antigens.
This paper presents a novel genotype-only computational framework that achieves near-perfect classification of half-sibling versus niece/nephew pairs by leveraging across-chromosome phasing and haplotype-level sharing features, thereby resolving a critical ambiguity in large-scale genomic biobanks without requiring pedigree information.
This paper establishes a formal framework proving that under the Infinite Sites Model, the NP-hard problem of optimizing genome orderings for phylogenetic compression becomes polynomially solvable via Neighbor Joining, thereby mathematically explaining the high efficacy of tree-based heuristics in bacterial genomics.
GYDE is an open-source, web-based collaborative platform that empowers bench scientists to easily access and utilize AI-powered tools for protein and antibody design, analysis, and drug discovery through an intuitive visual interface.
This study introduces TattleTail, a novel bioinformatic tool that accurately distinguishes Pseudomonas aeruginosa pyocins from prophages by leveraging conserved gene markers and the absence of viral packaging genes, a capability experimentally validated through the successful identification, induction, and characterization of bactericidal pyocins in clinical isolates.
KyDab is a comprehensive, publicly accessible database that curates over 120,000 paired antibody sequences and full-funnel selection data from standardized Kymouse immunization studies to support the development and evaluation of artificial intelligence models for antibody discovery.
MEIsensor is a deep-learning framework that significantly improves the accuracy and computational efficiency of detecting and classifying mobile element insertions (Alu, LINE1, and SVA) from long-read sequencing data, particularly within complex and repetitive genomic regions where existing tools struggle.
This paper introduces a reinforcement learning framework to fine-tune diffusion-based molecular docking models, significantly enhancing their ability to generate physically valid and interaction-preserving poses without compromising structural accuracy or increasing inference-time computation.
SAPTICoN is a robust, no-code, Snakemake-based pipeline built on the Seurat framework that enables biologists with limited computational expertise to perform reproducible single-cell transcriptomic analyses on non-model species and poorly annotated tissues by automatically generating necessary annotation packages.
This paper introduces two maximum likelihood methods that incorporate lineage abundance priors—interpreting multifurcations as unresolved signals of common strains or modeling sequencing rates proportional to prevalence—to significantly improve the accuracy of phylogenetic inference for rapidly evolving pathogens like SARS-CoV-2 by prioritizing the placement of sequences onto common ("horse") rather than rare ("zebra") lineages.
This paper proposes a method to enhance single-cell RNA sequencing analysis by jointly training language models on both quantitative scRNA-seq data and targeted biomedical literature, thereby creating interpretable, knowledge-augmented embeddings that improve functionality, disease association, and temporal trajectory insights.
Seqwin is an open-source framework that automates the discovery of microbial signature sequences by leveraging weighted pan-genome minimizer graphs to efficiently identify highly specific and sensitive targets across tens of thousands of genomes, outperforming existing methods in both speed and accuracy for diagnostic assay design.
The paper introduces Amaranth, a novel single-cell transcript assembler that significantly improves full-length transcript reconstruction accuracy by employing discriminative modeling to address the distinct biological and statistical biases between UMI-linked and internal reads in Smart-seq protocols.