# Construction of an Interpretable Regression Model for Yield Prediction and Mechanistic Insight Enabled by Automated Reaction Path Exploration

https://mdr.nims.go.jp/datasets/a46583c2-26c6-411e-a959-a1ff1cecaf24

## File

- [chemrxiv-2025-0qr26.pdf](https://mdr.nims.go.jp/filesets/3f62be6d-5d26-498a-a459-929a47b3ba35/download) ([Detail](https://mdr.nims.go.jp/filesets/3f62be6d-5d26-498a-a459-929a47b3ba35.md))

## Id

a46583c2-26c6-411e-a959-a1ff1cecaf24

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2026-11-02T05:05:29.055024Z

## Updated at

2026-11-02T06:10:20.792373Z

## Published at

2026-11-02T07:34:12.141491Z

## Doi



## First published url

https://doi.org/10.1021/jacs.6c05203

## Date published

2026-07-01

## Recorded date published

2026-7-1

## Resource type

journal_article

## Manuscript type

authors_original

## Collection



## Title

- title: Construction of an Interpretable Regression Model for Yield Prediction and
    Mechanistic Insight Enabled by Automated Reaction Path Exploration
  title_type: original
  lang: en

## Description

- description: In the past decade, machine learning has emerged as a powerful tool
    to predict reaction outcomes. However, mechanistic interpretability of the constructed
    machine learning models remains limited due to the use of domain-specific and
    often arbitrary descriptors. Herein we demonstrate that an energy descriptor comprising
    the energies of the possible intermediates in the reaction system serves as a
    physically motivated representation for constructing interpretable regression
    models that provide mechanistic insight. The energy descriptor was calculated
    using the single-component artificial force induced reaction (SC-AFIR) method,
    which autonomously and comprehensively searches for intermediates of a target
    reaction, and subsequently used to train regression models for reaction yield
    prediction. Linear models with regularization showed good predictions for the
    hold-out samples (RMSE < 7% yield) and the coefficients of the models provided
    information on how the energies of the intermediates relate to the reaction outcome.
    This work highlights the utility of energy descriptors in constructing mechanistically
    interpretable regression models for predictive tasks in chemistry.
  description_type: abstract
  lang: und

## Creator

- name: Takahiro Doba
  role: author
- name: Yu Harabuchi
  role: author
- name: Yuuya Nagata
  role: author
  orcid: https://orcid.org/0000-0001-5926-5845
  organization: National Institute for Materials Science
- name: Satoshi Maeda
  role: author

## Contact agent



## Publisher

organization: American Chemical Society (ACS)

## Managing organization



## Keyword

- subject: Automated Reaction Path Exploration
  schema: not_defined
- subject: Interpretable Machine Learning
  schema: not_defined
- subject: Reaction Yield Prediction
  schema: not_defined
- subject: Reaction Mechanism Elucidation
  schema: not_defined
- subject: Quantum Chemical Calculations
  schema: not_defined

## Rights

- description: This document is the unedited Author’s version of a Submitted Manuscript
    subsequently accepted for publication in Journal of the American Chemical Society,
    copyright © 2026 American Chemical Society. To access the final published article,
    see https://doi.org/10.1021/jacs.6c05203.
  identifier: https://creativecommons.org/licenses/by-nc/4.0/

## Other identifier(s)



## Data origin



## Embargo



## Journal

- title: Journal of the American Chemical Society
  issn: '15205126'
  volume: '148'
  issue: '25'
  start_page: 26150
  end_page: 26160

## Conference



## Related item



## Funding

- identifier: 22KJ0043
  funder_name: Japan Society for the Promotion of Science
- identifier: 23B203
  funder_name: Japan Society for the Promotion of Science
- identifier: JPMJER1903
  funder_name: Japan Science and Technology Agency
- identifier: JPMJFR2221
  funder_name: Japan Science and Technology Agency

## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: 3f62be6d-5d26-498a-a459-929a47b3ba35
  filename: chemrxiv-2025-0qr26.pdf
  content_type: application/pdf
  size: 3863147
  md5: 0d6ecd268d7aa3b870e1cec4c242f8ec

## Thumbnail

fileset_id: 3f62be6d-5d26-498a-a459-929a47b3ba35
filename: chemrxiv-2025-0qr26.pdf