ProtFlap: Structure-based Deep Learning Prediction of Protein Flexibility from Atomic Energy Networks
Year: 2026
Type: preprint
Abstract: Protein flexibility is a key determinant of molecular recognition, catalysis, and regulation, yet remains difficult to characterise at scale. Molecular dynamics (MD) simulations provide detailed descriptions of time-dependent dynamics but are computationally expensive. Although recent AI-based structure prediction methods have substantially improved access to high-quality static protein structures, they inherently lack information regarding the dynamic fluctuations essential for functional understanding. There is therefore a need for scalable, structure-based computational approaches that can infer intrinsic protein flexibility without explicit dynamical sampling. We present ProtFlap, a graph neural network framework for predicting relative residue-level flexibility directly from static protein structures. ProtFlap represents proteins as residue interaction graphs and integrates empirical atomic energy features extracted from a single energy-minimised snapshot with structural and sequence-derived descriptors. Central to our approach is the hypothesis that the local atomic energy network encoded in a frozen protein structure contains sufficient information to estimate structural flexibility. Trained using atomic mobility labels, quantified via normalised root-mean-square fluctuation (RMSF) derived from short MD simulations, ProtFlap achieves robust and accurate flexibility prediction across diverse protein domains. Feature attribution analysis reveals that van der Waals–related energy terms are the dominant contributors to the prediction. Key Points ProtFlap is a graph neural network that predicts intrinsic residue-level protein flexibility. The framework evaluates single, static structures, bypassing computationally expensive molecular dynamics simulations. Predictions are physically grounded by integrating structural descriptors with empirical atomic energy terms. Feature analysis reveals that local thermodynamic constraints, primarily Van der Waals forces, dominate flexibility prediction.
Authors: Humaira Lubna, Yoonjoo Choi
Institution: Chonnam National University
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
Awards: G2224603685, G7397100741
OpenAlex ID: W7233792917
