iPADD: A Computational Tool for Predicting Potential Antidiabetic Drugs Using Machine Learning Algorithms
Authors:
- 27 July 2023
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 63 (15) , 4960-4969
Abstract
Diabetes mellitus is a chronic metabolic disease, which causes an imbalance in blood glucose homeostasis and further leads to severe complications. With the increasing population of diabetes, there is an urgent need to develop drugs to treat diabetes. The development of artificial intelligence provides a powerful tool for accelerating the discovery of antidiabetic drugs. This work aims to establish a predictor called iPADD for discovering potential antidiabetic drugs. In the predictor, we used four kinds of molecular fingerprints and their combinations to encode the drugs and then adopted minimum-redundancy-maximum-relevance (mRMR) combined with an incremental feature selection strategy to screen optimal features. Based on the optimal feature subset, eight machine learning algorithms were applied to train models by using 5-fold cross-validation. The best model could produce an accuracy (Acc) of 0.983 with the area under the receiver operating characteristic curve (auROC) value of 0.989 on an independent test set. To further validate the performance of iPADD, we selected 65 natural products for case analysis, including 13 natural products in clinical trials as positive samples and 52 natural products as negative samples. Except for abscisic acid, our model can give correct prediction results. Molecular docking illustrated that quercetin and resveratrol stably bound with the diabetes target NR1I2. These results are consistent with the model prediction results of iPADD, indicating that the machine learning model has a strong generalization ability. The source code of iPADD is available at https://github.com/llllxw/iPADD.Keywords
Funding Information
- Natural Science Foundation of Sichuan Province (2022NCFSC00647)
- National Natural Science Foundation of China (82130112)
- Beijing Hospital Authority (DFL20190702)
- Youth Beijing Scholar (2022-051)
This publication has 63 references indexed in Scilit:
- Abscisic Acid Regulates Inflammation via Ligand-binding Domain-independent Activation of Peroxisome Proliferator-activated Receptor γJournal of Biological Chemistry, 2011
- Extended-Connectivity FingerprintsJournal of Chemical Information and Modeling, 2010
- Sodium-Glucose Co-Transport InhibitorsDrugs, 2010
- The anti‐diabetic effect of anthocyanins in streptozotocin‐induced diabetic rats through glucose transporter 4 regulation and prevention of insulin resistance and pancreatic apoptosisMolecular Nutrition & Food Research, 2009
- LANCL2 Is Necessary for Abscisic Acid Binding and Signaling in Human Granulocytes and in Rat Insulinoma CellsJournal of Biological Chemistry, 2009
- Identification of the Dual Action Antihypertensive Drugs Using TFS-Based Support Vector MachinesChem-Bio Informatics Journal, 2009
- HbA1c as a screening tool for detection of Type 2 diabetes: a systematic reviewDiabetic Medicine, 2007
- LigScore: a novel scoring function for predicting binding affinitiesJournal of Molecular Graphics and Modelling, 2005
- SMILES. 2. Algorithm for generation of unique SMILES notationJournal of Chemical Information and Computer Sciences, 1989
- The Generation of a Unique Machine Description for Chemical Structures-A Technique Developed at Chemical Abstracts Service.Journal of Chemical Documentation, 1965