1005 papers
The paper introduces SIR, a nonparametric framework combining 2D isotonic regression with a wild bootstrap procedure to provide statistically rigorous, reproducible drug synergy testing that outperforms existing methods in concordance, robustness, and missing data prediction.
This paper introduces CosMxScope, an open-source Python framework that bridges the gap between CosMx Spatial Molecular Imager data and digital pathology tools by stitching image tiles, converting spatial coordinates into GeoJSON for QuPath compatibility, and enabling interactive visualization of gene expression alongside cell morphology.
The Track Hub Quickload Translator is a freely available Python-based web application that converts data between UCSC Genome Browser track hubs and Integrated Genome Browser Quickload formats, enabling researchers to visualize tens of thousands of published genome assemblies in either browser.
This paper presents BrainYears, a portable and cost-effective EEG-based machine learning model that accurately predicts brain age and demonstrates its utility as an intervention-ready biomarker by showing a significant reduction in predicted brain age following a neuromodulation program.
This study utilizes AI protein structure predictions to demonstrate that the hydrophobic ligand-binding cavity in vertebrate TLR2 is an evolutionarily conserved feature essential for pathogen recognition, while revealing that similar cavities in invertebrate TLRs and other LRR domains arose through independent convergent evolution rather than shared ancestry.
This paper presents an evolutionary AI framework that integrates generative models, reaction-based substructure searching, and iterative fine-tuning to efficiently navigate ultra-large chemical spaces, successfully identifying and validating novel, synthetically accessible ligands for the -opioid receptor within the Enamine REAL Space.
ClumPyCells is a statistical framework that accurately quantifies cell and marker aggregation in complex tissues by correcting for cell size biases and filtering out interfering cell types, thereby enabling more reliable spatial pattern analysis across various tumor types and omics technologies.
By constructing a transcriptomic atlas of 3,713 samples to identify four distinct molecular subtypes of sepsis, this study elucidates subtype-specific pathophysiological mechanisms and proposes targeted drug repurposing strategies, such as corticosteroids for C1 and methylene blue for the high-mortality C4 subtype, to advance precision medicine and explain the failure of previous broad-spectrum clinical trials.
The paper introduces methbiome, a reference-based Snakemake pipeline designed to profile DNA methylation signals in long-read metagenomic data from both Oxford Nanopore and PacBio platforms, enabling comparative epigenomic analysis across microbial communities and isolates.
The paper introduces the mod-minimizer, a simple and efficient two-step sampling algorithm that achieves provably lower and asymptotically optimal density compared to existing methods like random minimizers, resulting in significant space savings for k-mer indexing applications such as whole-genome storage.