Grégory GINOT

The paper trains a domain-specific plant peptide language model and compares its performance to generalist models, finding domain pretraining provides significant efficiency gains.

The paper uses multimodal analysis to uncover how fungal symbionts reprogram plant sensory systems through coordinated transcriptional, metabolic, and phenotypic responses, revealing novel integration hubs and mechanisms.

S2-PepAnalyst predicts plant small signalling peptides with high accuracy using machine learning and integrates plant-specific datasets.