EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Foundation and Multimodal Models for Drug Discovery in Molecular Informatics: Principles, Evaluation, and Practical Guidance

Emmanuel Pio Pastore iD, Francesco De Rango iD

Molecular Informatics · 2026-03 · 45 (3)

DOI: 10.1002/minf.70027 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Molecular Informatics, online erschienen am 25.03.2026. Verfasst von Emmanuel Pio Pastore und 1 weiteren Autor:innen. Beteiligte Einrichtung: University of Calabria, Department of Biology, Ecology and Earth Science, Rende, Italy. Hauptthemen laut MEDLINE: Drug Discovery. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Foundation and multimodal models are rapidly becoming a core methodology in molecular informatics, particularly for drug discovery, by leveraging large‐scale pretraining across sequences, graphs, 3D structures, and text. This mini‐review provides practical guidance on when these models help, how to choose representations and data, and how to design pretraining and adaptation pipelines for real‐world use. We clarify what qualifies as a foundation model in chemistry; compare chemical language models, graph‐based architectures, and 3D equivariant networks; review multimodal strategies that connect molecules with proteins, pockets, and natural language; and summarize diffusion‐based generative modeling. We also emphasize rigorous evaluation, discussing realistic splitting protocols, distribution shift, activity cliffs, uncertainty calibration, and conformal prediction in the context of widely used benchmarks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DiscoveryModels, MolecularProteinsCheminformaticsHumans

Stichwörter der Autor:innen

benchmarkingchemical language modelsdiffusion modelsdrug discoveryfoundation modelsmultimodal learning

Substanzen

Proteins

Autor:innen und Institutionen

  • University of Calabria, Department of Biology, Ecology and Earth Science, Rende, Italy.

ORCID-Profile: Emmanuel Pio Pastore, Francesco De Rango

Zitieren

APA

Pastore, E. P., & De Rango, F. (2026). Foundation and Multimodal Models for Drug Discovery in Molecular Informatics: Principles, Evaluation, and Practical Guidance. Molecular Informatics, 45(3). https://doi.org/10.1002/minf.70027

Vancouver

Pastore EP, De Rango F. Foundation and Multimodal Models for Drug Discovery in Molecular Informatics: Principles, Evaluation, and Practical Guidance. Molecular Informatics. 2026;45(3). doi:10.1002/minf.70027

BibTeX
@article{Pastore2026,
  author = {Pastore, Emmanuel Pio and De Rango, Francesco},
  title = {Foundation and Multimodal Models for Drug Discovery in Molecular Informatics: Principles, Evaluation, and Practical Guidance},
  journal = {Molecular Informatics},
  year = {2026},
  volume = {45},
  number = {3},
  doi = {10.1002/minf.70027}
}
Kostenlos starten →