Skip to content
#protein folding Open access

Constraint-Guided Protein Structure Reconstruction Using ESM-2 Representations and Multi-Task Deep Learning

Nov 2026 · Computer and Decision Making: An International Journal · 0 citations

TL;DR

The proposed work presents an ESM-2-guided framework that combines multi-task prediction of inter-residue distances, contacts, and backbone torsion angles with training-only fragment retrieval, stochastic assembly, differentiable refinement, OpenMM cleanup, and frozen multi-criteria ranking.

Abstract

Native-free protein-structure reconstruction requires candidate generation, refinement, physical assessment, and ranking without access to native coordinates. The proposed work presents an ESM-2-guided framework that combines multi-task prediction of inter-residue distances, contacts, and backbone torsion angles with training-only fragment retrieval, stochastic assembly, differentiable refinement, OpenMM cleanup, and frozen multi-criteria ranking. A leakage-controlled CASP12 dataset was used for model development, with proteins restricted to 40–250 residues and exact sequence overlap removed across partitions. The frozen pipeline was externally applied to 15 eligible single-chain CASP15 targets after metadata and training-homology screening. Fifty candidates were generated and refined for each target, producing 750 candidates; 150 shortlisted structures underwent OpenMM minimization, and one physically valid model was selected per target without native-coordinate access. Post-hoc evaluation was performed for 10 targets with resolved native structures. The selected models achieved mean C-alpha RMSD of 14.5366 Å, backbone RMSD of 14.4318 Å, pairwise distance MAE of 6.8380 Å, and contact F1 of 0.1032. The results establish the operational feasibility and auditability of the pipeline but indicate limited structural accuracy. The framework is therefore presented as a reproducible proof of concept rather than a high-accuracy or state-of-the-art folding system.

Read PDF

Similar papers

#computer vision Review Open access May 2015

A survey study on major technical barriers affecting the decision to adopt cloud services

The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.

Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al. · 111 citations · ⚡8
#computer vision Open access Feb 2018

Lean Internal Startups for Software Product Innovation in Large Companies: Enablers and Inhibitors

This study investigates how Lean internal startup facilitates software product innovation in large companies and identifies its enablers and inhibitors, and shows the potential of the method-in-action framework to investigate the Lean startup approach in non-startup context.

Henry Edison, Nina M. Smørsgård, Xiaofeng Wang et al. · 78 citations · ⚡6
#computer vision Book Open access Jul 2015

Understanding the affect of developers: theoretical background and guidelines for psychoempirical software engineering

This paper highlights the challenges to conduct proper affect-related studies with psychology, provides a comprehensive literature review in affect theory, and proposes guidelines for conducting psychoempirical software engineering.

D. Graziotin, Xiaofeng Wang, P. Abrahamsson · 56 citations · ⚡4
#machine learning Open access May 2017

What Influences the Speed of Prototyping? An Empirical Investigation of Twenty Software Startups

This study conducts a multiple case study on twenty European software startups and proposes a prototype-centric learning model in early stage software startups, and identifies factors that occur as barriers but also facilitators for prototyping in earlystage software startups.

Anh Nguyen-Duc, Xiaofeng Wang, P. Abrahamsson · 44 citations · ⚡5
#protein folding Open access Sep 2026

Programmable design of functional proteins from natural language

Pinal, a 16-billion-parameter foundation model that produces protein candidates from natural-language functional descriptions, supports natural language as a high-level interface for candidate generation in protein design, enabling programmable exploration with reduced reliance on manually specified structural or seque...

Fengyuan Dai, Shiyang You, Yudian Zhu et al. · 31 citations · ⚡3

Related blog posts

Google DeepMind Blog Sep 30, 2026

Introducing SynthID Bio

Proof of concept for watermarking AI-generated proteins while preserving biological function.

MIT News · Artificial Intelligence Aug 27, 2026

Looking beyond natural sequences

A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.