Revealing the Relationship Between Publication Bias and Chemical Reactivity with Contrastive Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912238685650944 |
|---|---|
| author | Gao, Wenhao Raghavan, Priyanka Shprints, Ron Coley, Connor W. |
| author_facet | Gao, Wenhao Raghavan, Priyanka Shprints, Ron Coley, Connor W. |
| contents | A synthetic method's substrate tolerance and generality are often showcased in a "substrate scope" table. However, substrate selection exhibits a frequently discussed publication bias: unsuccessful experiments or low-yielding results are rarely reported. In this work, we explore more deeply the relationship between such publication bias and chemical reactivity beyond the simple analysis of yield distributions using a novel neural network training strategy, substrate scope contrastive learning. By treating reported substrates as positive samples and non-reported substrates as negative samples, our contrastive learning strategy teaches a model to group molecules within a numerical embedding space, based on historical trends in published substrate scope tables. Training on 20,798 aryl halides in the CAS Content Collection$^{\text{TM}}$, spanning thousands of publications from 2010-2015, we demonstrate that the learned embeddings exhibit a correlation with physical organic reactivity descriptors through both intuitive visualizations and quantitative regression analyses. Additionally, these embeddings are applicable to various reaction modeling tasks like yield prediction and regioselectivity prediction, underscoring the potential to use historical reaction data as a pre-training task. This work not only presents a chemistry-specific machine learning training strategy to learn from literature data in a new way, but also represents a unique approach to uncover trends in chemical reactivity reflected by trends in substrate selection in publications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16882 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Revealing the Relationship Between Publication Bias and Chemical Reactivity with Contrastive Learning Gao, Wenhao Raghavan, Priyanka Shprints, Ron Coley, Connor W. Chemical Physics Artificial Intelligence Machine Learning Biomolecules A synthetic method's substrate tolerance and generality are often showcased in a "substrate scope" table. However, substrate selection exhibits a frequently discussed publication bias: unsuccessful experiments or low-yielding results are rarely reported. In this work, we explore more deeply the relationship between such publication bias and chemical reactivity beyond the simple analysis of yield distributions using a novel neural network training strategy, substrate scope contrastive learning. By treating reported substrates as positive samples and non-reported substrates as negative samples, our contrastive learning strategy teaches a model to group molecules within a numerical embedding space, based on historical trends in published substrate scope tables. Training on 20,798 aryl halides in the CAS Content Collection$^{\text{TM}}$, spanning thousands of publications from 2010-2015, we demonstrate that the learned embeddings exhibit a correlation with physical organic reactivity descriptors through both intuitive visualizations and quantitative regression analyses. Additionally, these embeddings are applicable to various reaction modeling tasks like yield prediction and regioselectivity prediction, underscoring the potential to use historical reaction data as a pre-training task. This work not only presents a chemistry-specific machine learning training strategy to learn from literature data in a new way, but also represents a unique approach to uncover trends in chemical reactivity reflected by trends in substrate selection in publications. |
| title | Revealing the Relationship Between Publication Bias and Chemical Reactivity with Contrastive Learning |
| topic | Chemical Physics Artificial Intelligence Machine Learning Biomolecules |
| url | https://arxiv.org/abs/2402.16882 |