Multi‐View Biomedical Foundation Models for Molecule‐Target and Property Prediction
Advanced Science · 2026-03 · 13 (14)
DOI: 10.1002/advs.202517840 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, online erschienen am 28.01.2026. Verfasst von Parthasarathy Suryanarayanan und 17 weiteren Autor:innen. Beteiligte Einrichtung: IBM TJ Watson Research Center, 1101 Kitchawan Rd., Yorktown Heights, NY, USA. Hauptthemen laut MEDLINE: Models, Molecular, Alzheimer Disease, Receptors, G-Protein-Coupled, Drug Discovery. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Molecular foundation models hold promise to provide accurate predictions for a large and diverse set of downstream tasks in bio‐medical research. Quality molecular representations are key and foundation model development has typically focused on a single representation or molecular view, which may have strengths or weaknesses on a given task. We develop Multi‐view Molecular Embedding with Late Fusion (MMELON), an approach that integrates pre‐trained graph, image and text foundation models and may be readily extended to additional views and models. The multi‐view model performs robustly and is validated on over 120 tasks, including molecular solubility, ADME properties, and activity against G Protein‐Coupled receptors (GPCRs). The GPCR model array is leveraged to perform a virtual screen in search of ligands binding to Alzheimer's disease related GPCRs. We identify a number of such targets and employ the multi‐view model to select strong binders from a compound screen. Predictions are validated through structure‐based modeling and identification of key binding motifs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- IBM TJ Watson Research Center, 1101 Kitchawan Rd., Yorktown Heights, NY, USA.
- Cleveland Clinic Genome Center, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA.
- Genomic Medicine Institute, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA.
- IBM Research - Almaden, 650 Harry Rd, San Jose, CA, USA.
- IBM Research, 314 Main St, Cambridge, MA, USA.
- Department of Molecular Medicine, Cleveland Clinic Lerner College of Medicine, Case Western Reserve University, Cleveland, OH, USA.
ORCID-Profile: Parthasarathy Suryanarayanan, Yunguang Qiu, Shreyans Sethi, Diwakar Mahajan, Hongyang Li, Yuxin Yang, Elif Eyigoz, Aldo Guzmán-Sáenz, Daniel E Platt, Timothy H Rumbell, Kenney Ng, Sanjoy Dey, Myson Burch, Bum Chul Kwon, Pablo Meyer, Feixiong Cheng, Jianying Hu, Joseph A Morrone
Zitieren
APA
Suryanarayanan, P., Qiu, Y., Sethi, S., Mahajan, D., Li, H., Yang, Y., Eyigoz, E., Guzmán-Sáenz, A., Platt, D. E., Rumbell, T. H., Ng, K., Dey, S., Burch, M., Kwon, B. C., Meyer, P., Cheng, F., Hu, J., & Morrone, J. A. (2026). Multi‐View Biomedical Foundation Models for Molecule‐Target and Property Prediction. Advanced Science, 13(14). https://doi.org/10.1002/advs.202517840
Vancouver
Suryanarayanan P, Qiu Y, Sethi S, Mahajan D, Li H, Yang Y, et al. Multi‐View Biomedical Foundation Models for Molecule‐Target and Property Prediction. Advanced Science. 2026;13(14). doi:10.1002/advs.202517840
BibTeX
@article{Suryanarayanan2026,
author = {Suryanarayanan, Parthasarathy and Qiu, Yunguang and Sethi, Shreyans and Mahajan, Diwakar and Li, Hongyang and Yang, Yuxin and Eyigoz, Elif and Guzmán-Sáenz, Aldo and Platt, Daniel E and Rumbell, Timothy H and Ng, Kenney and Dey, Sanjoy and Burch, Myson and Kwon, Bum Chul and Meyer, Pablo and Cheng, Feixiong and Hu, Jianying and Morrone, Joseph A},
title = {Multi‐View Biomedical Foundation Models for Molecule‐Target and Property Prediction},
journal = {Advanced Science},
year = {2026},
volume = {13},
number = {14},
doi = {10.1002/advs.202517840}
}
EUVIMED