Positional embeddings and zero-shot learning using BERT for molecular-property prediction

Positional embeddings and zero-shot learning using BERT for molecular-property prediction

Abstract Recently, advancements in cheminformatics such as representation learning for chemical structures, deep learning (DL) for property prediction, data-driven discovery, and optimization of chemical data handling, have led to increased demands for handling chemical simplified molecular input li...

وصف كامل

التفاصيل البيبلوغرافية
المؤلفون الرئيسيون: Medard Edmund Mswahili, JunHa Hwang, Jagath C. Rajapakse, Kyuri Jo, Young-Seob Jeong
التنسيق: مقال
اللغة:English
منشور في: BMC 2025-02-01
سلاسل:Journal of Cheminformatics
الموضوعات:
Transformers
BERT
Positional embedding/encoding
Zero-shot learning
Molecular-property prediction
SMILES
الوصول للمادة أونلاين:https://doi.org/10.1186/s13321-025-00959-9

الانترنت

https://doi.org/10.1186/s13321-025-00959-9

مواد مشابهة