Molecular Contrastive Pretraining with Collaborative Featurizations.
J Chem Inf Model
; 64(4): 1112-1122, 2024 02 26.
Article
em En
| MEDLINE
| ID: mdl-38315002
ABSTRACT
Molecular pretraining, which learns molecular representations over massive unlabeled data, has become a prominent paradigm to solve a variety of tasks in computational chemistry and drug discovery. Recently, prosperous progress has been made in molecular pretraining with different molecular featurizations, including 1D SMILES strings, 2D graphs, and 3D geometries. However, the role of molecular featurizations with their corresponding neural architectures in molecular pretraining remains largely unexamined. In this paper, through two case studiesâchirality classification and aromatic ring countingâwe first demonstrate that different featurization techniques convey chemical information differently. In light of this observation, we propose a simple and effective MOlecular pretraining framework with COllaborative featurizations (MOCO). MOCO comprehensively leverages multiple featurizations that complement each other and outperforms existing state-of-the-art models that solely rely on one or two featurizations on a wide range of molecular property prediction tasks.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Descoberta de Drogas
/
Química Computacional
Tipo de estudo:
Prognostic_studies
Idioma:
En
Revista:
J Chem Inf Model
Assunto da revista:
INFORMATICA MEDICA
/
QUIMICA
Ano de publicação:
2024
Tipo de documento:
Article
País de afiliação:
Estados Unidos