Julio Sáez-Rodríguez

The Human Gut Cell Atlas v1.0: A Unified, Community-Built Reference of Cellular Diversity Across the Gut

The paper presents the Human Gut Cell Atlas v1.0, a unified reference of gut cell diversity, revealing how tissue structure influences cellular composition and enabling disease and organoid analysis.

mc-ASTRA maps population-level variation to interpretable multicellular tissue organization processes

mc-ASTRA integrates molecular, spatial, and sample-level data to create interpretable maps of tissue-state variability and multicellular processes.

Turning Domain Expertise into Multi-Dimensional Evaluation of Biomedical AI with Karenina

This paper introduces Karenina, a framework that evaluates biomedical AI using expert knowledge across multiple dimensions beyond traditional scoring.

Function-driven geometry directs human pilosebaceous unit development

The paper builds a spatiotemporal map of human pilosebaceous unit development using single-cell multiomics and machine learning, showing how epithelial-mesenchymal interactions drive organogenesis and how sebaceous gland programs are disrupted in tumors.

Integrated metabolomics data analysis to generate mechanistic hypotheses with MetaProViz

The paper introduces MetaProViz, an R package for metabolomics data analysis that integrates prior knowledge to generate mechanistic hypotheses, using kidney cancer data to demonstrate its capabilities.

The SEA-AD DREAM Challenge: Community benchmarking human and AI agent solutions for Alzheimer's disease neuropathology prediction from single-nucleus transcriptomics

The paper presents a benchmarking challenge to predict Alzheimer's disease neuropathology from single-nucleus transcriptomics using human and AI models, finding that top methods achieve near-perfect categorical staging predictions.

Towards Principled Evaluation of Single-Cell Perturbation Prediction Models

The paper evaluates single-cell perturbation prediction models by developing a taxonomy and tool to standardize benchmarking protocols across datasets.

Time-resolved inference of gene regulatory networks underlying human cranial neural crest development suggests novel risk genes for orofacial clefting.

ParTIpy: A Scalable Framework for Archetypal Analysis and Pareto Task Inference

ParTIpy scales archetypal analysis for biological trade-offs and integrates with single-cell workflows, enabling task inference in large datasets.

Combining prior knowledge and transcriptomics data for logic models of patient subgroups

The paper introduces FICUS, a framework that integrates omics data with logic models to identify shared signaling mechanisms across patient subgroups.

OmniPath Metabo: chemical structures, interactions and mechanisms to study the metabolome

OmniPath Metabo integrates metabolomics data with prior knowledge to enable mechanistic analysis of the metabolome through harmonized databases and network construction.

A transcriptional patient map of systemic lupus erythematosus reveals disease-related multicellular immune programs conserved between blood and kidney

This paper constructs a transcriptional patient map of SLE using single-cell and bulk RNA-seq data, identifying conserved immune programs in blood and kidney tissue.

CROssBARv2: A Unified Computational Framework for Heterogeneous Biomedical Data Representation and LLM-Driven Exploration

CROssBARv2 integrates heterogeneous biomedical data into a knowledge graph with embeddings and LLM-driven tools for predictive modeling and question-answering.

Topography Aware Optimal Transport for Alignment of Spatial Omics Data

TOAST improves spatial omics data alignment by integrating spatial constraints into optimal transport, enhancing accuracy and biological interpretability.

Shared and organ-specific gene expression programs of fibrotic diseases

This paper performs a cross-organ meta-analysis of single-cell transcriptomic data to identify shared and organ-specific gene expression programs in fibrotic diseases.

Towards Useful and Private Synthetic Omics: Community Benchmarking of Generative Models for Transcriptomics Data

The paper benchmarks generative models for synthetic bulk RNA-seq data, finding trade-offs between utility, biological preservation, and privacy risks across different methods.

CIRCE: a scalable Python package to predict cis-regulatory DNA interactions from single-cell chromatin accessibility data

CIRCE predicts cis-regulatory DNA interactions from single-cell chromatin accessibility data, improving speed and memory use compared to Cicero.

Multi-omics and biophysical phosphoproteomics upon BRAF inhibition uncover functional networks of BRAFV600E-driven signaling

This study uses multi-omics and biophysical phosphoproteomics to analyze BRAFV600E signaling, identifying ETV3 as a new downstream regulator and revealing mechanisms of drug resistance.

SpaCEy: Discovery of Functional Spatial Tissue Patterns by Association with Clinical Features Using Explainable Graph Neural Networks

SpaCEy identifies spatial tissue patterns linked to clinical outcomes using explainable graph neural networks in proteomic cancer data.

Modelling multicellular coordination by bridging cell-cell communication and intracellular regulation through multilayer networks

ReCoN models multicellular coordination by integrating cell-cell communication and intracellular regulation to predict cellular responses to perturbations.

Multicellular signaling and partial recovery define reverse cardiac remodeling

This study shows that reverse cardiac remodeling is a constrained multicellular state with partial recovery of metabolic programs but persistent inflammatory-mitochondrial dysfunction, mediated by lymphatic-derived Reelin.

MetAlyzer to Perform Streamlined, Interactive, and Pathway-Mapping Analysis of Targeted Metabolomics Data from the biocrates Platform

MetAlyzer streamlines and visualizes targeted metabolomics data from biocrates, enabling interactive analysis without coding.

OmniPath: integrated knowledgebase for multi-omics analysis

OmniPath integrates molecular knowledge from 168 resources to support multi-omics analysis, offering curated data, predictions, and tools for causal modeling across bulk, single-cell, and spatial data.

A cross-study transcriptional patient map of heart failure defines conserved multicellular coordination in cardiac remodeling

This paper integrates bulk and single-cell transcriptomic data from 25 heart failure studies to identify conserved multicellular coordination patterns in cardiac remodeling.

Bioinformatic inference of the exercise-responsive control of p70 S6 kinase through RPS6KB1 expression

This study uses a bioinformatic network inference algorithm to identify causal signaling networks regulating RPS6KB1 expression in response to aerobic and resistance exercise in human skeletal muscle.

Cellular and Spatial Drivers of Unresolved Injury and Functional Decline in the Human Kidney

The paper presents a multi-modal atlas of human kidney disease, identifying cellular and spatial mechanisms of injury resolution or failure and linking them to clinical outcomes.

NeKo: a tool for automatic network construction from prior knowledge

NeKo automates biological network construction by integrating molecular interactions from databases, enabling efficient network building for research applications.

ScAPE: A lightweight multitask learning baseline method to predict transcriptomic responses to perturbations

ScAPE predicts drug-induced gene expression changes using a lightweight multitask learning approach, achieving strong performance in a benchmark challenge.

Community-based biomedical context to unlock agentic systems

This paper introduces BioContextAI, an open-source initiative that provides standardized access to validated biomedical knowledge to improve the reliability of AI systems in biomedical research.

RIDDEN: Data-driven inference of receptor activity from transcriptomic data

RIDDEN predicts receptor activity from receptor-regulated gene expression, outperforming methods that use ligand-receptor co-expression, and identifies mechanistic biomarkers in cancer patients.