Protein binding affinity prediction under multiple substitutions applying eGNNs on Residue and Atomic graphs combined with Language model information: eGRAL

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Fiorellini-Bernardis, Arturo, Boyer, Sebastien, Brunken, Christoph, Diallo, Bakary, Beguir, Karim, Lopez-Carranza, Nicolas, Bent, Oliver
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929335388078080
author Fiorellini-Bernardis, Arturo
Boyer, Sebastien
Brunken, Christoph
Diallo, Bakary
Beguir, Karim
Lopez-Carranza, Nicolas
Bent, Oliver
author_facet Fiorellini-Bernardis, Arturo
Boyer, Sebastien
Brunken, Christoph
Diallo, Bakary
Beguir, Karim
Lopez-Carranza, Nicolas
Bent, Oliver
contents Protein-protein interactions (PPIs) play a crucial role in numerous biological processes. Developing methods that predict binding affinity changes under substitution mutations is fundamental for modelling and re-engineering biological systems. Deep learning is increasingly recognized as a powerful tool capable of bridging the gap between in-silico predictions and in-vitro observations. With this contribution, we propose eGRAL, a novel SE(3) equivariant graph neural network (eGNN) architecture designed for predicting binding affinity changes from multiple amino acid substitutions in protein complexes. eGRAL leverages residue, atomic and evolutionary scales, thanks to features extracted from protein large language models. To address the limited availability of large-scale affinity assays with structural information, we generate a simulated dataset comprising approximately 500,000 data points. Our model is pre-trained on this dataset, then fine-tuned and tested on experimental data.
format Preprint
id arxiv_https___arxiv_org_abs_2405_02374
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Protein binding affinity prediction under multiple substitutions applying eGNNs on Residue and Atomic graphs combined with Language model information: eGRAL
Fiorellini-Bernardis, Arturo
Boyer, Sebastien
Brunken, Christoph
Diallo, Bakary
Beguir, Karim
Lopez-Carranza, Nicolas
Bent, Oliver
Quantitative Methods
Artificial Intelligence
Machine Learning
Protein-protein interactions (PPIs) play a crucial role in numerous biological processes. Developing methods that predict binding affinity changes under substitution mutations is fundamental for modelling and re-engineering biological systems. Deep learning is increasingly recognized as a powerful tool capable of bridging the gap between in-silico predictions and in-vitro observations. With this contribution, we propose eGRAL, a novel SE(3) equivariant graph neural network (eGNN) architecture designed for predicting binding affinity changes from multiple amino acid substitutions in protein complexes. eGRAL leverages residue, atomic and evolutionary scales, thanks to features extracted from protein large language models. To address the limited availability of large-scale affinity assays with structural information, we generate a simulated dataset comprising approximately 500,000 data points. Our model is pre-trained on this dataset, then fine-tuned and tested on experimental data.
title Protein binding affinity prediction under multiple substitutions applying eGNNs on Residue and Atomic graphs combined with Language model information: eGRAL
topic Quantitative Methods
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.02374