LAUSR

MoleMCL: a multi-level contrastive learning framework for molecular pre-training

Sign Up to like & get
recommendations!
0 Published in 2024 at "Bioinformatics"

DOI: 10.1093/bioinformatics/btae164

Abstract: Abstract Motivation Molecular representation learning plays an indispensable role in crucial tasks such as property prediction and drug design. Despite the notable achievements of molecular pre-training models, current methods often fail to capture both the… read more here.

Keywords: semantics; pre training; molecular pre; contrastive learning ... See more keywords

MolPrompt: improving multi-modal molecular pre-training with knowledge prompts

Sign Up to like & get
recommendations!
0 Published in 2025 at "Bioinformatics"

DOI: 10.1093/bioinformatics/btaf466

Abstract: Abstract Motivation Molecular pre-training has emerged as a foundational approach in computational drug discovery, enabling the extraction of expressive molecular representations from large-scale unlabeled datasets. However, existing methods largely focus on topological or structural features,… read more here.

Keywords: molecular pre; pre; pre training; knowledge prompts ... See more keywords

Prevalence of pathogenic mismatch repair mutations in an Irish cohort after clinical and molecular pre-selection.

Sign Up to like & get
recommendations!
0 Published in 2017 at "Journal of Clinical Oncology"

DOI: 10.1200/jco.2017.35.4_suppl.574

Abstract: 574Background: Lynch syndrome (LS) is a highly penetrant, autosomal dominant multi-system disorder characterised by an inherited predisposition to a range of cancers. LS is caused by germline mutations in one of the mismatch repair (MMR)… read more here.

Keywords: molecular pre; pre selection; prevalence pathogenic; irish cohort ... See more keywords

MolProphecy: Bridging Medicinal Chemists' Knowledge and Molecular Pre-Trained Models via a Multi-Modal Framework

Sign Up to like & get
recommendations!
0 Published in 2025 at "Journal of advanced research"

DOI: 10.48550/arxiv.2507.02932

Abstract: INTRODUCTION In drug discovery, the tacit domain knowledge of experts plays a critical role in guiding molecular design and decision-making.However, existing molecular pre-trained models rarely incorporate such expert knowledge, leading to suboptimal molecular design decisions.… read more here.

Keywords: pre trained; framework; molecular pre; multi modal ... See more keywords