Gabriel Krouk

The paper presents PeTriPPI2, a hybrid model for protein-protein interaction prediction that combines sequence and structural features, achieving high accuracy on the Pinder dataset.

This study identifies S-acylation and oligomerization as key factors controlling HIR2 plasma membrane targeting and nanodomain organization in Arabidopsis.

The paper enhances protein-protein interaction detection using a fine-tuned transformer on AlphaFold 2 Multimer outputs and benchmarks it against machine learning algorithms.

The paper uses Classification and Regression Trees to predict transcription factor combinatorial interactions in scRNA-seq data from Arabidopsis thaliana roots.

This paper introduces NGG, a method that efficiently identifies epistatic interactions to explain missing heritability and improve phenotype prediction.

The paper introduces PeTriBERT, a Transformer model augmented with 3D structural data to predict amino-acid sequences from protein structures, demonstrating its ability to generate novel proteins with GFP-like structures.