EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MolPIF: a parameter interpolation flow model for molecule generation

Yaowei Jin, Junjie Wang, Yufan Tang, Wenkai Xiang iD, Duanhua Cao, Dan Teng iD, Zhehuan Fan, Jiacheng Xiong, Xia Sheng, Chuanlong Zeng, Duo An, Mingyue Zheng iD und 2 weitere

Bioinformatics · 01.06.2026 · 42 (6)

DOI: 10.1093/bioinformatics/btag323 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 23.05.2026. Verfasst von Yaowei Jin und 13 weiteren Autor:innen. Beteiligte Einrichtung: Lingang Laboratory, Shanghai 200031, China. Hauptthemen laut MEDLINE: Drug Design, Software, Proteins, Models, Molecular. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Rising-Star Program, National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Structure-based drug design (SBDD) has advanced with deep generative models, but bridging the gap between continuous atomic coordinates and discrete atom types remains a challenge. Current approaches, such as diffusion and flow matching models, often fail to unify these heterogeneous modalities, relying on separate strategies or ill-fitting Euclidean metrics for discrete variables. This lack of a consistent framework limits generative models’ ability to capture the geometric and chemical structure of protein–ligand complexes. Results We present MolPIF, a parameter interpolation flow mechanism designed to unify the generation of continuous and discrete molecular variables. Unlike traditional flow models that operate in sample space, MolPIF interpolates between distributions in the parameter space, theoretically recovering Wasserstein-2 optimal transport for continuous coordinates and establishing Fisher–Rao geodesics for discrete atom types. We further incorporate a geometry-enhanced learning strategy to improve the capture of atomic contexts. Extensive evaluations on the CrossDocked2020 dataset demonstrate that MolPIF outperforms baselines in binding affinity, chemical validity, geometric fidelity, and chemical space coverage. Additionally, MolPIF exhibits versatility in lead optimization and offers flexible prior distribution selection (such as Laplace), establishing a robust paradigm for SBDD. Availability and implementation Source code is freely available at https://github.com/BLEACH366/MolPIF.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DesignSoftwareProteinsModels, MolecularComputational BiologyLigandsAlgorithms

Substanzen

LigandsProteins

Autor:innen und Institutionen

  • Lingang Laboratory, Shanghai 200031, China.
  • School of Information Science and Technology, ShanghaiTech University, Shanghai 201210, China.
  • College of Computer Science and Artificial Intelligence, Fudan University, Shanghai 200433, China.
  • Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai 201203, China.
  • Global Institute of Future Technology, Shanghai Jiao Tong University, Shanghai 200240, China.

ORCID-Profile: Wenkai Xiang, Dan Teng, Mingyue Zheng, Qian Shi

Förderung

  • Shanghai Rising-Star Program
  • National Key Research and Development Program of China

Zitieren

APA

Jin, Y., Wang, J., Tang, Y., Xiang, W., Cao, D., Teng, D., Fan, Z., Xiong, J., Sheng, X., Zeng, C., An, D., Zheng, M., Zheng, S., & Shi, Q. (2026). MolPIF: a parameter interpolation flow model for molecule generation. Bioinformatics, 42(6). https://doi.org/10.1093/bioinformatics/btag323

Vancouver

Jin Y, Wang J, Tang Y, Xiang W, Cao D, Teng D, et al. MolPIF: a parameter interpolation flow model for molecule generation. Bioinformatics. 2026;42(6). doi:10.1093/bioinformatics/btag323

BibTeX
@article{Jin2026,
  author = {Jin, Yaowei and Wang, Junjie and Tang, Yufan and Xiang, Wenkai and Cao, Duanhua and Teng, Dan and Fan, Zhehuan and Xiong, Jiacheng and Sheng, Xia and Zeng, Chuanlong and An, Duo and Zheng, Mingyue and Zheng, Shuangjia and Shi, Qian},
  title = {MolPIF: a parameter interpolation flow model for molecule generation},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {6},
  doi = {10.1093/bioinformatics/btag323}
}
Kostenlos starten →