paper-with-me

Papers

ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction

2020-10-19 · Seyone Chithrananda, Gabriel Grand, Bharath Ramsundar

GNNs and chemical fingerprints are the predominant approaches to representing molecules for property prediction. However, in NLP, transformers have become the de-facto standard for representation learning thanks to their strong downstream task transfer. In parallel, the software ecosystem around transformers is maturing rapidly, with libraries like HuggingFace and BertViz enabling streamlined training and introspection. In this work, we make one of the first attempts to systematically evaluate transformers on molecular property prediction tasks via our ChemBERTa model. ChemBERTa scales well with pretraining dataset size, offering competitive downstream performance on MoleculeNet and useful attention-based visualization modalities. Our results suggest that transformers offer a promising avenue of future work for molecular representation learning and property prediction. To facilitate these efforts, we release a curated dataset of 77M SMILES from PubChem suitable for large-scale self-supervised pretraining.

📄 PDF Abstract BibTeX arXiv:2010.09885

Code (3)

seyonechithrananda/bert-loves-chemistry 공식 구현 pytorch
SylwiaNowakowska/LLM_Fine_Tuning_Molecular_Properties
XuHangkun/Compound-Protein-Interaction pytorch

Tasks

Molecular Property Predictionmolecular representationPredictionProperty PredictionRepresentation Learning

Similar Papers 제목 키워드 기반

ChemBERTa-2: Towards Chemical Foundation Models

2022-09-05 · Walid Ahmad, Elana Simon, Seyone Chithrananda, Gabriel Grand 외

Large pretrained models such as GPT-3 have had tremendous impact on modern natural language processing by leveraging self-supervised learning to learn salient representations that can be used to readily finetune on a wid…

Molecular Property PredictionSelf-Supervised Learning

Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction

2026-05-13 · Deepak Warrier, Raja Sekhar Pappala arxiv

Modern SMILES-based chemical language models obtain strong MoleculeNet performance by treating SMILES as generic text and compensating with multi-million-molecule self-supervised pretraining. We ask: when a domain carrie…

Molecular Property Prediction

Generative Pre-Training from Molecules

2021-09-16 · ChemRxiv 2021 9 · Sanjar Adilov

SMILES is a line notation for entering and representing molecules. Being inherently a language construct, it allows estimating molecular data in a self-supervised fashion by employing machine learning methods for natural…

Feature EngineeringGeneral KnowledgeLanguage ModellingMolecular Property Prediction+1

Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges

2023-12-29 · Xiaoqian Liu, Jianbin Jiao, Junge Zhang

Decision-making is a dynamic process requiring perception, memory, and reasoning to make choices and find optimal policies. Traditional approaches to decision-making suffer from sample efficiency and generalization, whil…

Decision MakingFew-Shot Learning

A Large-scale Evaluation of Pretraining Paradigms for the Detection of Defects in Electroluminescence Solar Cell Images

2024-02-27 · David Torpey, Lawrence Pratt, Richard Klein

Pretraining has been shown to improve performance in many domains, including semantic segmentation, especially in domains with limited labelled data. In this work, we perform a large-scale evaluation and benchmarking of …

BenchmarkingDefect DetectionSegmentationSemantic Segmentation