Predicting AXL Tyrosine Kinase Inhibitor Potency Using Machine Learning with Interpretable Insights for Cancer Drug Discovery - Article

Aug 4, 2026

AXL tyrosine kinase is central to cancer progression, metastasis, and therapy resistance, yet conventional drug discovery for AXL inhibitors is slow, costly, and provides limited mechanistic understanding of potency determinants. A machine learning workflow was applied to a dataset of 972 compounds using 550 molecular descriptors, comparing Random Forest, Gradient Boosting, SVR, and Decision Tree models. Random Forest achieved the best predictive performance (R² 0.703) and interpretable SHAP analysis highlighted molecular features such as RNCG and TopoPSA(NO) as key contributors to inhibitor potency, supporting structure-activity interpretation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Introduction

AXL as a Cancer Therapeutic Target

Limitations of Traditional AXL Drug Discovery

Role of AI and Interpretable Machine Learning

Study Aim

Vol 3 No 1 2025 . , . , | Predicting AXL Tyrosine Kinase Inhibitor Potency Using Machine Learning with Interpretable Insights for Cancer Drug Discovery
Teuku Rizky Noviandy 1, Ghifari Maulana Idroes 2, Essy Harnelly 3, Irma Sari 4, Fazlin Mohd Fauzi 5 and Rinaldi Idroes 4,6,*
1 Department of Information Systems, Faculty of Engineering, Universitas Abulyatama, Aceh Besar 23372, Indonesia; [rizky_si@abulyatama.ac.id](rizky_si@abulyatama.ac.id) (T.R.N.)
2 Department of Nuclear Engineering and Engineering Physics, Universitas Gadjah Mada, Yogyakarta 55281, Indonesia; [ghifarimaulana145@gmail.com](ghifarimaulana145@gmail.com) (G.M.I.)
3 Department of Biology, Faculty of Mathematics and Natural Sciences, Universitas Syiah Kuala, Banda Aceh 23111, Indonesia; [essy.harnelly@usk.ac.id](essy.harnelly@usk.ac.id) (E.H.)
4 Department of Pharmacy, Faculty of Mathematics and Natural Sciences, Universitas Syiah Kuala, Banda Aceh 23111, Indonesia; [irmasari@usk.ac.id](irmasari@usk.ac.id) (I.S.); [rinaldi.idroes@usk.ac.id](rinaldi.idroes@usk.ac.id) (R. I.)
5 Faculty of Pharmacy, Universiti Teknologi MARA Selangor, Puncak Alam Campus, 42 300 Bandar Puncak Alam, Selangor, Malaysia; [fazlin5465@uitm.edu. my](fazlin5465@uitm.edu. my) (F.M.F.)
6 School of Mathematics and Applied Sciences, Universitas Syiah Kuala, Banda Aceh 23111, Indonesia
* Correspondence: [rinaldi.idroes@usk.ac.id](rinaldi.idroes@usk.ac.id) | | | --- | --- | | Article History | Abstract | | Received 7 January 2025
Revised 25 February 2025 Accepted 8 March 2025
Available Online 15 March 2025
Keywords: | AXL tyrosine kinase plays a critical role in cancer progression, metastasis, and therapy resistance, making it a promising target for therapeutic intervention. However, traditional drug discovery methods for developing AXL inhibitors are resource-intensive, timeconsuming, and often fail to provide detailed insights into molecular determinants of potency. To address this gap, we applied machine learning techniques, including Random Forest, Gradient Boosting, Support Vector Regression, and Decision Tree models, to | | AXL tyrosine kinase
Machine learning | predict the potency (pIC50) of AXL inhibitors using a dataset of 972 compounds with 550 molecular descriptors. Our results demonstrate that the Random Forest model | | Drug discovery
SHAP analysis | outperformed others with an R² of 0 .703, MAE of 0 . 553, RMSE of 0 .720, and PCC of 0 .841, showcasing strong predictive accuracy. SHAP analysis identified critical molecular | | Cancer therapeutics | features, such as RNCG and TopoPSA(NO), as key contributors to inhibitor potency, providing interpretable insights into structure-activity relationships. These findings highlight the potential of machine learning to accelerate the identification and optimization of AXL inhibitors, bridging the gap between computational predictions and rational drug design and paving the way for effective cancer therapeutics. | | | Copyright: © 2025 by the authors. This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License.([https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)) | 1. Introduction AXL, a receptor tyrosine kinase, is critical in various physiological and pathological processes, including cell survival, proliferation, migration, and immune response [1] . Overexpression or dysregulation of AXL has been implicated in the progression of several cancers, including hepatocellular carcinoma [2], non-small cell lung cancer [3], and breast cancer [4] . It is critical in promoting metastasis, therapy resistance, and poor patient prognoses. As a result, AXL has emerged as a promising therapeutic target in cancer drug discovery, with inhibitors of AXL tyrosine kinase showing potential Figure 1. Representative chemical structures of AXL inhibitors from the ChEMBL database. for mitig

FAQs

为什么AXL酪氨酸激酶被认为是癌症药物发现的重要靶点？

AXL参与细胞生存、增殖、迁移和免疫反应，且其过表达或失调与多种癌症进展、转移、治疗耐药和较差预后相关，因此被认为适合作为治疗靶点。

本研究使用了哪些机器学习模型预测AXL抑制剂的效力？

研究比较了Random Forest、Gradient Boosting、Support Vector Regression（SVR）和Decision Tree模型，用于预测AXL抑制剂的pIC50。

如何利用可解释性方法理解哪些分子特征影响抑制剂效力？

通过SHAP（Shapley Additive Explanations）分析，识别对模型预测贡献关键的分子特征，例如RNCG和TopoPSA(NO)，从而支持结构-活性关系的解释与理性药物设计。

Aug 4, 2026

Upload by River Wang