AdaMR: Adaptable Molecular Representation for Unified Pre-training Strategy

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ding, Yan, Cheng, Hao, Ye, Ziliang, Feng, Ruyi, Tian, Wei, Xie, Peng, Zhang, Juan, Gu, Zhongze
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911856431464448
author Ding, Yan
Cheng, Hao
Ye, Ziliang
Feng, Ruyi
Tian, Wei
Xie, Peng
Zhang, Juan
Gu, Zhongze
author_facet Ding, Yan
Cheng, Hao
Ye, Ziliang
Feng, Ruyi
Tian, Wei
Xie, Peng
Zhang, Juan
Gu, Zhongze
contents We propose Adjustable Molecular Representation (AdaMR), a new large-scale uniform pre-training strategy for small-molecule drugs, as a novel unified pre-training strategy. AdaMR utilizes a granularity-adjustable molecular encoding strategy, which is accomplished through a pre-training job termed molecular canonicalization, setting it apart from recent large-scale molecular models. This adaptability in granularity enriches the model's learning capability at multiple levels and improves its performance in multi-task scenarios. Specifically, the substructure-level molecular representation preserves information about specific atom groups or arrangements, influencing chemical properties and functionalities. This proves advantageous for tasks such as property prediction. Simultaneously, the atomic-level representation, combined with generative molecular canonicalization pre-training tasks, enhances validity, novelty, and uniqueness in generative tasks. All of these features work together to give AdaMR outstanding performance on a range of downstream tasks. We fine-tuned our proposed pre-trained model on six molecular property prediction tasks (MoleculeNet datasets) and two generative tasks (ZINC250K datasets), achieving state-of-the-art (SOTA) results on five out of eight tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2401_06166
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle AdaMR: Adaptable Molecular Representation for Unified Pre-training Strategy
Ding, Yan
Cheng, Hao
Ye, Ziliang
Feng, Ruyi
Tian, Wei
Xie, Peng
Zhang, Juan
Gu, Zhongze
Biomolecules
Artificial Intelligence
Machine Learning
We propose Adjustable Molecular Representation (AdaMR), a new large-scale uniform pre-training strategy for small-molecule drugs, as a novel unified pre-training strategy. AdaMR utilizes a granularity-adjustable molecular encoding strategy, which is accomplished through a pre-training job termed molecular canonicalization, setting it apart from recent large-scale molecular models. This adaptability in granularity enriches the model's learning capability at multiple levels and improves its performance in multi-task scenarios. Specifically, the substructure-level molecular representation preserves information about specific atom groups or arrangements, influencing chemical properties and functionalities. This proves advantageous for tasks such as property prediction. Simultaneously, the atomic-level representation, combined with generative molecular canonicalization pre-training tasks, enhances validity, novelty, and uniqueness in generative tasks. All of these features work together to give AdaMR outstanding performance on a range of downstream tasks. We fine-tuned our proposed pre-trained model on six molecular property prediction tasks (MoleculeNet datasets) and two generative tasks (ZINC250K datasets), achieving state-of-the-art (SOTA) results on five out of eight tasks.
title AdaMR: Adaptable Molecular Representation for Unified Pre-training Strategy
topic Biomolecules
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2401.06166