Deep Learning of Proteins with Local and Global Regions of Disorder

TL;DR

This paper introduces IDPForge, a novel machine learning method using transformer models to generate detailed conformational ensembles of intrinsically disordered proteins and regions, maintaining folded domains and aligning with experimental data.

Contribution

IDPForge is a new transformer-based approach that creates all-atom IDP and IDR ensembles without sequence-specific training or ensemble reweighting, improving structural predictions of disordered proteins.

Findings

IDPForge produces ensembles that agree well with experimental data.

The method maintains folded domains within disordered ensembles.

IDPForge does not require sequence-specific training or ensemble reweighting.

Abstract

Although machine learning has transformed protein structure prediction of folded protein ground states with remarkable accuracy, intrinsically disordered proteins and regions (IDPs/IDRs) are defined by diverse and dynamical structural ensembles that are predicted with low confidence by algorithms such as AlphaFold. We present a new machine learning method, IDPForge (Intrinsically Disordered Protein, FOlded and disordered Region GEnerator), that exploits a transformer protein language diffusion model to create all-atom IDP ensembles and IDR disordered ensembles that maintains the folded domains. IDPForge does not require sequence-specific training, back transformations from coarse-grained representations, nor ensemble reweighting, as in general the created IDP/IDR conformational ensembles show good agreement with solution experimental data, and options for biasing with experimental restraints are provided if desired. We envision that IDPForge with these diverse capabilities will facilitate integrative and structural studies for proteins that contain intrinsic disorder.