Gaia Andreoletti

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.

The paper presents an ensemble model that improves predictions of perceptual similarity between odor mixtures using a curated dataset and collaborative challenge results.

The paper evaluates missense variant effect predictors using CAGI6 data, finding strong performance across settings and highlighting biases in some predictors.

The paper identifies optimized protein-based enhancers of HDR in human HSPCs through functional screening, improving HDR efficiency without increasing off-target effects.

This study benchmarks large language models in bioinformatics tasks, finding GPT-4 leads in most areas while Gemini excels in math and LLaMA struggles with code generation.

The paper identifies a reversible transcriptional switch in cardiac fibroblasts that governs fibroblast plasticity and contributes to chronic heart disease, with MEOX1 as a key regulator.

A computational drug repositioning pipeline identifies potential therapeutics for COVID-19 by matching SARS-CoV-2 gene expression signatures to drug profiles.

The paper develops predictive models for preterm birth using maternal blood multi-omics data, finding transcriptomic and proteomic markers can predict gestational age and spontaneous preterm birth with high accuracy.

This study identifies ethnicity-specific transcriptomic subgroups in SLE patients using RNA-seq data and correlates them with disease activity.

This study identifies a BRD4-GATA4 interaction that regulates mitochondrial homeostasis in adult cardiomyocytes by modulating gene expression related to energy production.