Machine Learning-based Algorithm for Screening Drug Candidates in Breast Cancer Treatment
Authors: 
Yuxuan Zhou, Yuhan Ye, Caiyun FanAuthors Info & Claims
Yuxuan Zhou, Yuhan Ye, Caiyun FanAuthors Info & ClaimsPages 868 - 874
Abstract
Breast cancer is one of the most prevalent malignant tumors globally. This study aims to develop and optimize a model for predicting biological activity and estimating pharmacokinetic (ADMET) properties using machine learning algorithms. The goal is to screen potential drug candidates for breast cancer. Based on this model, we propose a molecular screening model for breast cancer drug molecules utilizing a greedy-genetic-LGB algorithm to enhance the efficiency of drug molecule screening.
First, two rounds of screening of potential drug molecules using LightGBM and the Permutation importance algorithm were performed to identify the 20 most relevant molecular descriptors for biological activity.
Secondly, the PSO-LGB algorithm was proposed. Based on this model, regression prediction models for compound bioactivity and classification prediction models for pharmacokinetic properties were established and compared with popular industry machine models, demonstrating the superiority of the proposed models.
Finally, the greedy-genetic-LGB algorithm was proposed to transform the drug molecule screening problem into a multi-objective optimization problem. The objective function is the prediction result of the two models, and the optimization objective is the descriptor value of the drug molecule, based on the PSO-LGB compound bioactivity and PSO-LGB pharmacokinetic property prediction models. To verify the superiority of the proposed algorithm, experiments were conducted on the public dataset of breast cancer drug molecule screening provided by DrugBank. A set of optimal molecule values was obtained, resulting in an excellent active pIC50 value (8.7792) with this molecule combination along with good ADMET performance.
In summary, the machine learning approach proposed in this study can effectively predict the biological activity and ADMET properties of compounds and improve the speed and effectiveness of screening potential breast cancer drug molecules, as well as potentially facilitate their clinical studies.
References
[1]
Yang F, Chen S, He S, Huo Q and Xie N. 2020. Yb-1 interplays with erα to regulate the stemness and differentiation of er-positive breast cancer stem cells. Theranostics 10, 8 (February 2020), 3816-3832
[2]
Ferreira, Leonardo L. G. and Adriano Defini Andricopulo. 2019. ADMET modeling approaches in drug discovery. Drug discovery today 24, 5 (March 2019), 157-1165
[3]
Kunal Roy, Supratik Kar, Rudra and Narayan Das. 2015. Chapter 3 - Classical QSAR. Understanding the Basics of QSAR for Applications in Pharmaceutical Sciences and Risk Assessment, 81-102.
[4]
Zhou, S, Y. Li, and X. Y. Zhang. 2023. Optimization Modeling of Anti - breast Cancer Candidate Drugs. Biotechnology & genetic engineering reviews (March, 2023), 1-19.
[5]
Hua Rui and Zhu JM. 2023. Prediction of biological activity of anti-breast cancer drug candidate ERα based on deep neural network. Journal of Shaanxi University of Science and Technology (Natural Science Edition), 39, 2 (April, 2023), 47-53
[6]
JiaoLing Lu and QinQin Xie. 2021. Optimization of ERα activity of anti-breast cancer drug candidates based on K-MEANS algorithm[J]. Information Technology and Informatization, 12 (2021), 45-48.
[7]
Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: a highly efficient gradient boosting decision tree. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 3149–3157.
[8]
Altmann André, Toloşi Laura, Oliver S and Thomas L. 2010. Permutation importance: a corrected feature importance measure. Bioinformatics 26, 10 (May 2010), 1340–1347
[9]
Moriguchi L, Hirono S, Liu Q, Nakagome I and Matsushita Y. 1992. Simple method of calculating octanol/water partition coefficient. J-STAGE 40,1 (March 1992), 127-130
[10]
Mannhold R., Poda G.I., Ostermann C. and Tetko, I.V. 2009. State-of-the-Art and Comparison of Log P Methods on more than 96,000 compounds. J. Pharm. Sci. 98,3 (March 2009), 861-893.
[11]
Huang, Wenxiu. 2014. A study on the development of particle swarm optimization algorithms. Software 4 (January 2014), 73-77
[12]
Jingyi Zhang, Xin Chen, Bosheng Li and Fangrong Yan. 2023. A comparative study of adaptive trial designs for dose optimization. Pharmaceutical Statistics. 22, 5 (May 2023), 797-814
[13]
Yang, Lijuan, Jin, Chao, Yang, Guanghui, Bing, Zhitong, Huang, Liang, Niu, Yuzhen and Yang, Lei. 2023. Transformer-based deep learning method for optimizing ADMET properties of lead compounds. Physical Chemistry Chemical Physics [J] 25, 3 (January 2023), 2377-2385
[14]
Jigenlin. 2004. A review of genetic algorithm research. Computer Applications and Software. 21,2 (February 2004)5
Index Terms
- Machine Learning-based Algorithm for Screening Drug Candidates in Breast Cancer Treatment
Recommendations
Discovering breast cancer drug candidates from biomedical literature
We developed a new paradigm with the ultimate goal of enabling disease-specific drug candidate discovery with molecular-level evidences generated from literature and prior knowledge. We showed how to implement the paradigm by building a prototype ...
In Silico Design and Evaluation of Novel Triazole-Based Compounds as Promising Drug Candidates Against Breast Cancer
Bioinformatics Research and ApplicationsAbstractComputational development of novel triazole-based aromatase inhibitors (AIs) was carried out followed by investigation of the possible interaction modes of these compounds with the enzyme and prediction of the binding affinity by tools of ...
Breast cancer drug toxicity prediction Based on AdaBoost Extremely Random Tree
BIC '22: Proceedings of the 2022 2nd International Conference on Bioinformatics and Intelligent ComputingEstrogen Receptor α (ERα) is considered as an important target for treating breast cancer, so compounds that can antagonize ERα may be candidate drugs for breast cancer. We predict the toxicities of candidate compounds by machine learning to achieve the ...
Comments
Information & Contributors
Information
Published In
August 2024
967 pages
ISBN:9798400717826
DOI:10.1145/3706890
Copyright © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 13 January 2025
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
ISAIMS 2024
ISAIMS 2024: 2024 5th International Symposium on Artificial Intelligence for Medicine Science
August 13 - 17, 2024
Amsterdam, Netherlands
Acceptance Rates
Overall Acceptance Rate 53 of 112 submissions, 47%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 24Total Downloads
- Downloads (Last 12 months)24
- Downloads (Last 6 weeks)20
Reflects downloads up to 28 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in