Edit · 2026 03 31 155435 Linkspringercom S11030 026 11521 6

Saving needs a token. Log in or register to get one. Edits are public and licensed CC-BY-SA-4.0.

# Integrating modern computational techniques elevates binding mode identification for molecular fragments | Molecular Diversity | Springer Nature Link

**URL:** https://link.springer.com/article/10.1007/s11030-026-11521-6

**Saved:** 2026-03-31T22:54:35.472Z

---

Sergei Evteev, Fedor Sizov, Anna Pastukhova, Alexey Ereshchenko, Denis Adjugim & Yan Ivanenkov

113 Accesses

1 Altmetric

Explore all metrics

Abstract

Molecular docking is a routine and essential procedure in computational drug discovery. However, it is well known that current techniques are still far from perfect, especially when being applied to molecular fragments. In this work, we combined advantages of traditional energy-based docking, a diffusion model, intermolecular interaction filters, and ML-assisted scoring function to achieve higher accuracy. We compiled a comprehensive dataset of molecular fragments to evaluate our new protocol - HybriDock - in comparison with three other docking algorithms including DiffDock, Matcha and AutoDock Vina. HybriDock demonstrated remarkable improvements over these methods, highlighting the advantage of combining modern molecular modeling approaches. Additionally, we analyzed the influence of fragment chemical properties and protein family on the ability to predict accurate binding modes and highlighted up-to-date limitations and future directions.

Graphical abstract

This is a preview of subscription content, log in via an institution  to check access.

Explore related subjects
Discover the latest articles, books and news in related subjects, suggested using machine learning.
Chromosome conformation capture-based methods
Computational Chemistry
Molecular Modelling
Molecular Biophysics
Molecular Dynamics
Protein-Ligand Interactions
Computational Drug Discovery and Design Strategies
Data availability

All experiments were performed with use of open source databases and software. All additional details can be requested via email.

References

Abramson J, Adler J, Dunger J et al (2024) Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630(8016):493–500. https://doi.org/10.1038/s41586-024-07487-w

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Bender BJ, Gahbauer S, Luttens A et al (2021) A practical guide to large-scale docking. Nat Protoc 16(10):4799–4832. https://doi.org/10.1038/s41596-021-00597-z

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Buttenschoen M, Morris GM, Deane CM (2023) PoseBusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences. Chem Sci 15(9):3130–3139. https://doi.org/10.1039/d3sc04185a

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Corso G, Stärk H, Jing B, Barzilay R, Jaakkola T (2022) Diffdock: diffusion steps, twists, and turns for molecular docking. arXiv:2510.14586

Eberhardt J, Santos-Martins D, Tillack AF, Forli S (2021) AutoDock Vina 1.2.0: New docking methods, expanded force field, and python bindings. J Chem Inf Model 61(8):3891–3898. https://doi.org/10.1021/acs.jcim.1c00203

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Evteev SA, Ereshchenko AV, Ivanenkov YA (2023) SiteRadar: utilizing graph machine learning for precise mapping of protein-ligand-binding sites. J Chem Inf Model 63(4):1124–1132. https://doi.org/10.1021/acs.jcim.2c01413

Article
 
CAS
 
PubMed
 
Google Scholar

Evteev S, Ivanenkov Y, Semenov I et al (2024) Quantum-assisted fragment-based automated structure generator (QFASG) for small molecule design: an in vitro study. Front Chem 12:1382512. https://doi.org/10.3389/fchem.2024.1382512

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Evteev S, Ereshchenko A, Adjugim D et al (2025) Skittles: GNN-assisted pseudo-ligands generation and its application for binding sites classification and affinity prediction. Proteins. https://doi.org/10.1002/prot.70056

Article
 
PubMed
 
Google Scholar

Frolova D, Daulbaev T, Sevriugov E, et al. (2025) Matcha: multi-stage riemannian flow matching for accurate and physically valid molecular docking. arXiv:2510.14586

Herron L, Dakka J, Yao K, Shi D, Zhang Y, Jerome SV (2025) DiffDock-Glide: a hybrid physics-based and data-driven approach to molecular docking bioRxiv 2025.06.02.657461

Hu X, Shelver WH (2003) Docking studies of matrix metalloproteinase inhibitors: zinc parameter optimization to improve the binding free energy prediction. J Mol Graph Model 22(2):115–126. https://doi.org/10.1016/S1093-3263(03)00153-0

Article
 
CAS
 
PubMed
 
Google Scholar

Jiang D, Hsieh CY, Wu Z et al (2021) InteractionGraphNet: a novel and efficient deep graph representation learning framework for accurate protein-ligand interaction predictions. J Med Chem 64(24):18209–18232. https://doi.org/10.1021/acs.jmedchem.1c01830

Article
 
CAS
 
PubMed
 
Google Scholar

Khan O, Jones G, Kozakov D, Beglov D, Joseph-McCarthy D, Vajda S (2025) E-FTMap: a protein structure based pharmacophore identification server for guiding fragment expansion. J Mol Biol 437(15):168956. https://doi.org/10.1016/j.jmb.2025.168956

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Krishna R, Wang J, Ahern W et al (2024) Generalized biomolecular modeling and design with RoseTTAFold All-Atom. Science 384(6693):eadl2528. https://doi.org/10.1126/science.adl2528

Article
 
CAS
 
PubMed
 
Google Scholar

Leidner F, Kurt Yilmaz N, Paulsen J, Muller YA, Schiffer CA (2018) Hydration structure and dynamics of inhibitor-bound HIV-1 protease. J Chem Theory Comput 14(5):2784–2796. https://doi.org/10.1021/acs.jctc.8b00097

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Lexa KW, Carlson HA (2012) Protein flexibility in docking and surface mapping. Q Rev Biophys 45(3):301–343. https://doi.org/10.1017/S0033583512000066

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Manglik A, Kim TH, Masureel M et al (2015) Structural insights into the dynamic process of β2-Adrenergic Receptor signaling. Cell 161(5):1101–1111. https://doi.org/10.1016/j.cell.2015.04.043

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Mqawass G, Popov P (2024) graphLambda: fusion graph neural networks for binding affinity prediction. J Chem Inf Model 64(7):2323–2330. https://doi.org/10.1021/acs.jcim.3c00771

Article
 
CAS
 
PubMed
 
Google Scholar

Neves MA, Totrov M, Abagyan R (2012) Docking and scoring with ICM: the benchmarking results and strategies for improvement. J Comput Aided Mol Des 26(6):675–686. https://doi.org/10.1007/s10822-012-9547-0

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Pettersen EF, Goddard TD, Huang CC et al (2021) UCSF ChimeraX: structure visualization for researchers, educators, and developers. Protein Sci 30(1):70–82. https://doi.org/10.1002/pro.3943

Article
 
CAS
 
PubMed
 
Google Scholar

Stroganov OV, Novikov FN, Stroylov VS, Kulkov V, Chilov GG (2008) Lead finder: an approach to improve accuracy of protein-ligand docking, binding energy estimation, and virtual screening. J Chem Inf Model 48(12):2371–2385. https://doi.org/10.1021/ci800166p

Article
 
CAS
 
PubMed
 
Google Scholar

Verdonk ML, Cole JC, Hartshorn MJ, Murray CW, Taylor RD (2003) Improved protein-ligand docking using GOLD. Proteins 52(4):609–623. https://doi.org/10.1002/prot.10465

Article
 
CAS
 
PubMed
 
Google Scholar

wwPDB consortium (2019) Protein Data Bank: the single global archie for 3D macromolecular structure data. Nucleic Acids Res 47(D1):D520–D528. https://doi.org/10.1093/nar/gky949

Article
 
CAS
 
Google Scholar

Zdrazil B, Felix E, Hunter F et al (2024) The ChEMBL Database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods. Nucl Acids Res 52(D1):D1180–D1192. https://doi.org/10.1093/nar/gkad1004

Article
 
CAS
 
PubMed
 
PubMed Central
 
Google Scholar

Download references

Author information
Authors and Affiliations

Dukhov Automatics Research Institute (VNIIA), Moscow, Russian Federation

Sergei Evteev, Fedor Sizov, Anna Pastukhova, Alexey Ereshchenko, Denis Adjugim & Yan Ivanenkov

Contributions

S.E.—investigation, writing original manuscript; F.S.—code writing, investigation, manuscript editing; A.P.—code writing, investigation, manuscript editing; A.E.—code writing, manuscript editing; D.A.—code writing, manuscript editing; Ya.I.—supervision, manuscript editing.

Corresponding author

Correspondence to Sergei Evteev.

Ethics declarations
Conflict of interest

The authors declare that they have no conflict of interest.

Additional information
Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 264 kb) (download DOCX )
Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article
Cite this article

Evteev, S., Sizov, F., Pastukhova, A. et al. Integrating modern computational techniques elevates binding mode identification for molecular fragments. Mol Divers (2026). https://doi.org/10.1007/s11030-026-11521-6

Download citation

Received
05 December 2025

Accepted
13 March 2026

Published
25 March 2026

Version of record
25 March 2026

DOI
https://doi.org/10.1007/s11030-026-11521-6

Keywords
Molecular docking
Molecular fragments
Diffusion model
Intermolecular interactions
Machine learning

Cancel

Preview · live