Quentin Fournier

A biological-response compound representation allows chemical perturbation prediction across cell lines

The paper introduces BioPert, a framework that uses gene expression responses to predict chemical perturbations across cell lines, achieving higher accuracy than chemical structure-based methods.

pLM representations unlock metagenomic space beyond homology

This paper shows that protein language models can better annotate metagenomic proteins when trained on curated data, enabling retrieval of diverse enzyme candidates from billions of sequences.

High-resolution dissection of concept acquisition in different families of protein language models

This study analyzes how biological concepts are encoded in protein language models across their layers and finds that complexity increases with depth, with pretraining data and compute having a greater impact than parameter scaling.

A systematic analysis of machine learning pipelines for robust antimicrobial resistance prediction

This study evaluates ML pipelines for AMR prediction using genomic data, identifying key factors affecting performance and supporting tree-based models.

Protein Language Models: Is Scaling Necessary?

This paper introduces AMPLIFY, a protein language model that achieves better performance with less training cost by improving data quality and architecture, challenging the need for scaling.