cff-version: 1.2.0
abstract: "<p>Sample simulation files for "Machine Learning-Based Predictions of Henry Coefficients for Long-Chain Alkanes in One-Dimensional Zeolites: Application to Hydroisomerization". Please read the README file for more information, and refer to the main manuscript for more details.</p><p><br></p><p>Shape-selective adsorption in zeolites plays a pivotal role in catalytic hydroisomerization of long-chain alkanes, a key process in producing sustainable aviation fuels from Fischer–Tropsch products. Accurately predicting adsorption behavior for the large number of alkane isomers in different zeolite frameworks is computationally intensive. To address this, we have developed a machine learning framework that rapidly and accurately predicts Henry coefficients of linear (C<sub>1</sub>–C<sub>30</sub>) and branched (C<sub>4</sub>–C<sub>20</sub>) alkanes in one-dimensional zeolites. Using descriptors based on chain length, branching patterns, and molecular graphs, we evaluate multiple ML models, including Random Forest, XGBoost, CatBoost, TabPFN, and D-MPNN in MTT-, MTW-, MRE-, and AFI-type zeolites. TabPFN and D-MPNN offer the highest predictive accuracy. Active learning further boosts model performance by efficiently selecting diverse and structurally informative isomers. We also uncover activity cliffs, where small changes in molecular structure lead to sharp variations in adsorption, and demonstrate that targeted oversampling of these cases improves model robustness. Finally, we combine the ML-predicted Henry coefficients with gas-phase thermodynamics to compute reaction equilibrium distributions for C<sub>16</sub>hydroisomerization. This integrated, data-driven approach enables efficient screening and design of shape-selective zeolite catalysts, thereby reducing the need for costly simulations.</p>"
authors:
  - family-names: Sharma
    given-names: Shrinjay
    orcid: "https://orcid.org/0000-0001-8345-7433"
  - family-names: Yang
    given-names: Ping
    orcid: "https://orcid.org/0000-0003-0105-6172"
  - family-names: Liu
    given-names: Yachan
    orcid: "https://orcid.org/0009-0001-2110-3303"
  - family-names: Rossi
    given-names: Kevin
    orcid: "https://orcid.org/0009-0001-5915-6275"
  - family-names: Bai
    given-names: Peng
    orcid: "https://orcid.org/0000-0002-6881-4663"
  - family-names: Rigutto
    given-names: Marcello S.
    orcid: "https://orcid.org/0000-0002-3671-3446"
  - family-names: Zuidema
    given-names: Erik
  - family-names: Agarwal
    given-names: Umang
    orcid: "https://orcid.org/0000-0002-5182-3141"
  - family-names: Baur
    given-names: Richard
  - family-names: Calero
    given-names: Sofia
    orcid: "https://orcid.org/0000-0001-9535-057X"
title: "Sample simulation files for &#34;Machine Learning-Based Predictions of Henry Coefficients for Long-Chain Alkanes in One-Dimensional Zeolites: Application to Hydroisomerization&#34;"
keywords:
version: 1
identifiers:
  - type: doi
    value: 10.4121/7fdc96f0-69ff-4c1a-be2b-8aa6a0a812cb.v1
license: CC BY 4.0
date-released: 2025-10-02