Co-Folding Models Localize Enzyme Active Sites but Fail to Accurately Predict Enzyme–Substrate Complex Structures

Abstract The accurate prediction of enzyme–substrate complex structures is challenging due to the transient and dynamic nature of these interactions. We evaluated the performance of eight machine–learning (ML) docking tools and the physics–based method AutoDock Vina as a reference in the prediction of enzyme–substrate complex structures using a curated data set of 210 diverse, non–redundant enzyme–substrate complexes, equally divided into three classes: metal–free enzymes (A), and enzymes with metal ions outside (B) or inside (C) the active site. All ML–based docking tools had low geometric accuracy and physical plausibility, with fewer than 10% hit rates at the stricter 2 Å threshold for substrate root-mean-square deviation. While no ML-based tools were able to outperform Vina in modeling physically plausible complexes, co–folding tools such as AlphaFold3 and Boltz–2 excelled at active–site localization, and many algorithms performed better for class C enzymes, and worse for class B enzymes. Surprisingly, DynamicBind, which was trained on less data with fewer parameters compared to other models, matched co-folding methods in active-site elucidation. Our results show that enzyme–substrate docking can be affected by the presence of a metal ion, and suggest that better performances for complex structure prediction may be achieved with data-centric strategies including molecular dynamics simulations rather than parameter-heavy ML architectures.

Authors

Institutions

Publication Details

Journal
Journal of Chemical Information and Modeling
Published
2026-11-17
DOI
https://doi.org/10.1021/acs.jcim.6c03068
Primary Topic
Protein Structure and Dynamics
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Co-Folding Models Localize Enzyme Active Sites but Fail to Accurately Predict Enzyme–Substrate Complex Structures

Ariane Nunes‐Alves, Daniil Lepikhov
2 links
Journal of Chemical Information and Modeling
Protein Structure and Dynamics
article

Co-Folding Models Localize Enzyme Active Sites but Fail to Accurately Predict Enzyme–Substrate Complex Structures

Ariane Nunes‐Alves, Daniil Lepikhov
article en

Abstract

Abstract The accurate prediction of enzyme–substrate complex structures is challenging due to the transient and dynamic nature of these interactions. We evaluated the performance of eight machine–learning (ML) docking tools and the physics–based method AutoDock Vina as a reference in the prediction of enzyme–substrate complex structures using a curated data set of 210 diverse, non–redundant enzyme–substrate complexes, equally divided into three classes: metal–free enzymes (A), and enzymes with metal ions outside (B) or inside (C) the active site. All ML–based docking tools had low geometric accuracy and physical plausibility, with fewer than 10% hit rates at the stricter 2 Å threshold for substrate root-mean-square deviation. While no ML-based tools were able to outperform Vina in modeling physically plausible complexes, co–folding tools such as AlphaFold3 and Boltz–2 excelled at active–site localization, and many algorithms performed better for class C enzymes, and worse for class B enzymes. Surprisingly, DynamicBind, which was trained on less data with fewer parameters compared to other models, matched co-folding methods in active-site elucidation. Our results show that enzyme–substrate docking can be affected by the presence of a metal ion, and suggest that better performances for complex structure prediction may be achieved with data-centric strategies including molecular dynamics simulations rather than parameter-heavy ML architectures.

Journal of Chemical Information and Modeling
Technische Universität Berlin (DE)
Deutsche Forschungsgemeinschaft, Ministério da Ciência, Tecnologia e Inovação, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Einstein Stiftung Berlin
Protein Structure and Dynamics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon