Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias

Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias

Machine learning algorithms offer new possibilities for automating reaction procedures. The present paper investigates automated reaction’s prediction with Molecular Transformer, the state-of-the-art model for reaction prediction, proposing a new debiased dataset for a realistic assessment of the mo...

Full description

Bibliographic Details
Main Authors: Dávid Péter Kovács, William McCorkindale, Alpha A. Lee
Format: Article
Language:English
Published: Nature Publishing Group 2021-03-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-021-21895-w
id doaj-f5f5a1b384fd4609aa785325aa34d776
record_format Article
spelling doaj-f5f5a1b384fd4609aa785325aa34d7762021-03-21T12:14:40ZengNature Publishing GroupNature Communications2041-17232021-03-011211910.1038/s41467-021-21895-wQuantitative interpretation explains machine learning models for chemical reaction prediction and uncovers biasDávid Péter Kovács0William McCorkindale1Alpha A. Lee2Cavendish Laboratory, University of CambridgeCavendish Laboratory, University of CambridgeCavendish Laboratory, University of CambridgeMachine learning algorithms offer new possibilities for automating reaction procedures. The present paper investigates automated reaction’s prediction with Molecular Transformer, the state-of-the-art model for reaction prediction, proposing a new debiased dataset for a realistic assessment of the model’s performance.https://doi.org/10.1038/s41467-021-21895-w
collection DOAJ
language English
format Article
sources DOAJ
author Dávid Péter Kovács
William McCorkindale
Alpha A. Lee
spellingShingle Dávid Péter Kovács
William McCorkindale
Alpha A. Lee
Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias
Nature Communications
author_facet Dávid Péter Kovács
William McCorkindale
Alpha A. Lee
author_sort Dávid Péter Kovács
title Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias
title_short Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias
title_full Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias
title_fullStr Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias
title_full_unstemmed Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias
title_sort quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias
publisher Nature Publishing Group
series Nature Communications
issn 2041-1723
publishDate 2021-03-01
description Machine learning algorithms offer new possibilities for automating reaction procedures. The present paper investigates automated reaction’s prediction with Molecular Transformer, the state-of-the-art model for reaction prediction, proposing a new debiased dataset for a realistic assessment of the model’s performance.
url https://doi.org/10.1038/s41467-021-21895-w
work_keys_str_mv AT davidpeterkovacs quantitativeinterpretationexplainsmachinelearningmodelsforchemicalreactionpredictionanduncoversbias
AT williammccorkindale quantitativeinterpretationexplainsmachinelearningmodelsforchemicalreactionpredictionanduncoversbias
AT alphaalee quantitativeinterpretationexplainsmachinelearningmodelsforchemicalreactionpredictionanduncoversbias
_version_ 1724210812595208192

Similar Items