Molecular contrastive learning with graph attention network (MoCL-GAT) for enhanced molecular representation
Learning the representation of molecules is crucial for drug discovery but is often hindered by the scarcity of labeled experimental data, which limits the performance of supervised machine learning models. While self-supervised learning (SSL) offers a solution by leveraging vast unlabeled chemical...
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Article (Journal) |
| Lingua: | inglese |
| Pubblicazione: |
09 April 2026
|
| In: |
BMC bioinformatics
Year: 2026, Volume: 27, Pages: 1-18 |
| ISSN: | 1471-2105 |
| DOI: | 10.1186/s12859-026-06409-z |
| Accesso online: | Verlag, kostenfrei, Volltext: https://doi.org/10.1186/s12859-026-06409-z
|
| Note sull'autore: | Alperen Dalkıran, Ahmet Sureyya Rifaioglu, Rengul Cetin-Atalay, Aybar C. Acar, Tunca Doğan and M. Volkan Atalay |
| Riassunto: | Learning the representation of molecules is crucial for drug discovery but is often hindered by the scarcity of labeled experimental data, which limits the performance of supervised machine learning models. While self-supervised learning (SSL) offers a solution by leveraging vast unlabeled chemical databases, many existing methods focus on learning from either local structural information or global molecular properties, but not both simultaneously. We introduce MoCL-GAT, a novel contrastive and transfer learning-based SSL framework that addresses this gap by simultaneously learning from two complementary objectives. It combines a local contrastive task on molecular subgraphs to capture fine-grained chemical environments with a global predictive task to learn holistic molecular descriptors. This dual-objective approach, powered by a Graph Attention Network, is designed to create more robust, versatile, and transferable molecular representations. |
|---|---|
| Descrizione del documento: | Gesehen am 21.09.2026 |
| Descrizione fisica: | Online Resource |
| ISSN: | 1471-2105 |
| DOI: | 10.1186/s12859-026-06409-z |