基于人工智能的药物人体肠道吸收性质预测

濮澄韬; 顾灵茜; 陈兴晔; 张艳敏

doi:10.11665/j.issn.1000-5048.2023032102

基于人工智能的药物人体肠道吸收性质预测

中国药科大学理学院，医药大数据与人工智能研究院，南京 211198

计量
- 文章访问数: 510
- HTML全文浏览量: 23
- PDF下载量: 436
出版历程
- 收稿日期: 2023-03-20
- 修回日期: 2023-06-12
- 刊出日期: 2023-06-24

Prediction of human intestinal absorption properties based on artificial intelligence

Institute of Medical Big Data and Artificial Intelligence, School of Science, China Pharmaceutical University, Nanjing 211198, China

摘要

摘要: 人体肠道吸收性（human intestinal absorption，HIA）是衡量药物口服生物利用度的重要标志之一。利用人工智能方法在药物发现早期对药物的HIA进行预测评估，能够加速药物发现过程并且降低成本。本研究分别使用分子模拟软件MOE（molecular operating environment）的2D、3D描述符和ECFP4（extended connectivity fingerprints）对分子进行表征，针对2 061条HIA数据建立支持向量机（SVM）、随机森林（RF）、深度神经网络（DNN）等8种模型。结果表明，基于2D、3D描述符和ECFP4指纹的组合描述符构建的SVM模型在各项评价指标上进行综合评价后是最优的，最优模型的受试者工作特征曲线下面积（AUC）、马修斯系数和Kappa系数分别为0.94，0.75及0.74。综上，本研究建立一个鲁棒性高、泛化能力强的预测HIA性质的机器学习模型，该模型可以用于为药物药代动力学性质研究提供指导及早期的分子筛选。
- 人体肠道吸收 /
- 药代动力学性质 /
- 机器学习 /
- 深度神经网络 /
- 分类模型 /
- 人工智能
Abstract: Human intestinal absorption (HIA) is a crucial indicator for measuring the oral bioavailability of drugs.This study aims to use artificial intelligence methods to predict and evaluate the HIA of drugs in the early stages of drug discovery, thus accelerating the drug discovery process and reducing costs.This study used MOE''s 2D, 3D descriptors, and ECFP4 (extended connectivity fingerprints) to characterize the molecules and established eight models, including support vector machine (SVM), random forest (RF), and deep neural network (DNN).The results showed that the SVM model constructed using a combination of 2D, 3D descriptors and ECFP4 fingerprints was the optimal model according to comprehensive evaluation of various evaluation indicators.The area under the receiver operating characteristic curve (AUC), Matthews correlation coefficient, and Kappa coefficient of the optimal model were 0.94, 0.75, and 0.74, respectively.In conclusion, this study established a robust and generalizable machine learning model for predicting HIA properties, which can provide guidance for early molecular screening and the study of pharmacokinetic properties of drugs.
- human intestinal absorption /
- pharmacokinetic properties /
- machine learning /
- deep neural networks /
- classification model /
- artificial intelligence

HTML全文

参考文献(21)

[1]	Pillai N, Dasgupta A, Sudsakorn S, et al. Machine Learning guided early drug discovery of small molecules[J]. Drug Discov Today, 2022, 27(8): 2209-2215.
[2]	Basant N, Gupta S, Singh KP. Predicting human intestinal absorption of diverse chemicals using ensemble learning based QSAR modeling approaches[J]. Comput Biol Chem, 2016, 61: 178-196.
[3]	Hou TJ, Wang JM, Li YY. ADME evaluation in drug discovery. 8. The prediction of human intestinal absorption by a support vector machine[J]. J Chem Inf Model, 2007, 47(6): 2408-2415.
[4]	Kumar R, Sharma A, Siddiqui MH, et al. Prediction of human intestinal absorption of compounds using artificial intelligence techniques[J]. Curr Drug Discov Technol, 2017, 14(4): 244-254.
[5]	Fu MY, Zhu YY, Wu CY, et al. Prediction of plasma protein binding rate based on machine learning[J]. J China Pharm Univ (中国药科大学学报), 2021, 52(6): 699-706.
[6]	Wang YC, Liu HC, Fan YR, et al. In silico prediction of human intravenous pharmacokinetic parameters with improved accuracy[J]. J Chem Inf Model, 2019, 59(9): 3968-3980.
[7]	Yang M, Chen JL, Xu LW, et al. A novel adaptive ensemble classification framework for ADME prediction[J]. RSC Adv, 2018, 8(21): 11661-11683.
[8]	Xing GM, Liang L, Deng CL, et al. Activity prediction of small molecule inhibitors for antirheumatoid arthritis targets based on artificial intelligence[J]. ACS Comb Sci, 2020, 22(12): 873-886.
[9]	Jadhav SD, Channe HP.. Comparative study of K-NN, naive Bayes and decision tree classification techniques[J]. Int J Sci Res, 2016, 5(1): 1842-1845.
[10]	Wang MWH, Goodman JM, Allen TEH. Machine learning in predictive toxicology: recent applications and future directions for classification models[J]. Chem Res Toxicol, 2021, 34(2): 217-239.
[11]	Geurts P, Ernst D, Wehenkel L. Extremely randomized trees[J]. Mach Learn, 2006, 63(1): 3-42.
[12]	Ke GL, Meng Q, Finley T, et al. LightGBM: a highly efficient gradient boosting decision tree[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: ACM, 2017: 3149-3157.
[13]	Chen TQ, Guestrin C. XGBoost: a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 785-794.
[14]	Dou LJ, Li XL, Zhang LC, et al. iGlu_AdaBoost: identification of lysine glutarylation using the AdaBoost classifier[J]. J Proteome Res, 2021, 20(1): 191-201.
[15]	Ciregan D, Meier U, Schmidhuber J. Multi-column deep neural networks for image classification[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence. IEEE, 2012: 3642-3649.
[16]	Tharwat A. Classification assessment methods[J].Appl Comput Inform, 2018, 12(1): 1-13.
[17]	Warr WA. Scientific workflow systems: pipeline pilot and KNIME[J]. J Comput Aided Mol Des, 2012, 26(7): 801-804.
[18]	Tipping ME, Bishop CM. Probabilistic principal component analysis[J]. J R Stat Soc, 1999, 61(3): 611-622.
[19]	Maaten L, Hinton GE. Visualizing data using t-SNE[J]. J Mach Learn Res, 2008, 9: 2579-2605.
[20]	Rogers D, Hahn M. Extended-connectivity fingerprints[J].J Chem Inf Model, 2010, 50(5): 742-754.
[21]	Carracedo-Reboredo P, Li?ares-Blanco J, Rodríguez-Fernández N, et al. A review on machine learning approaches and trends in drug discovery[J].Comput Struct Biotechnol J, 2021, 19: 4538-4558.