Integrative in Silico modeling for mTOR inhibition: From ridge classifiers to descriptor-free deep neural networks
Inhibiting the mammalian Target of Rapamycin (mTOR) represents a promising strategy in cancer therapy due to its crucial role in cell growth, survival, and metabolism. Using a variety of quantitative structure-activity relationship (QSAR) models, we present a comprehensive comparison of deep learnin...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Computer Methods and Programs in Biomedicine Update |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666990025000333 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849316944717545472 |
|---|---|
| author | Seyed Alireza Khanghahi Hadi Kamkar Seyedehsamaneh Shojaeilangari Abdollah Allahverdi Parviz Abdolmaleki |
| author_facet | Seyed Alireza Khanghahi Hadi Kamkar Seyedehsamaneh Shojaeilangari Abdollah Allahverdi Parviz Abdolmaleki |
| author_sort | Seyed Alireza Khanghahi |
| collection | DOAJ |
| description | Inhibiting the mammalian Target of Rapamycin (mTOR) represents a promising strategy in cancer therapy due to its crucial role in cell growth, survival, and metabolism. Using a variety of quantitative structure-activity relationship (QSAR) models, we present a comprehensive comparison of deep learning (DL) and classical machine learning (ML) techniques for modeling mTOR inhibitor activity. Unlike prior studies that focused on specific algorithms or limited descriptors, we benchmark a wide range of models, from traditional models like Random Forest, logistic regression, and SVM to modern algorithms like CNNs, GRUs, and LSTMs, on both descriptor-based features obtained by Dragon and descriptor-free inputs, including raw SMILES string, and Morgan fingerprints. This comprehensive analysis provides a robust foundation for using the best QSAR models specific to mTOR inhibition. Our findings revealed that while the Random Forest classifier achieved the highest accuracy among all models (0.9290 accuracy, 0.8940 F1-score, 0.9737 AUC), DL methods also demonstrated strong predictive capabilities, with nearly all models attaining an accuracy above 0.90. Among the DL models, CNN-QSAR using Morgan fingerprints achieved the highest accuracy (0.9271), F1-score (0.8950), and AUC (0.9696), demonstrating its effectiveness in capturing structural characteristics. The GRU-QSAR and LSTM-QSAR models, which utilized tokenized SMILES, achieved accuracies of 0.9002 and 0.9021, F1-scores of 0.8595 and 0.8603, and AUCs of 0.9270 and 0.9529, respectively, leveraging their ability to process sequential data. |
| format | Article |
| id | doaj-art-5cfbdbbd757f4299af721d189c4d9968 |
| institution | Kabale University |
| issn | 2666-9900 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computer Methods and Programs in Biomedicine Update |
| spelling | doaj-art-5cfbdbbd757f4299af721d189c4d99682025-08-20T03:51:25ZengElsevierComputer Methods and Programs in Biomedicine Update2666-99002025-01-01810020810.1016/j.cmpbup.2025.100208Integrative in Silico modeling for mTOR inhibition: From ridge classifiers to descriptor-free deep neural networksSeyed Alireza Khanghahi0Hadi Kamkar1Seyedehsamaneh Shojaeilangari2Abdollah Allahverdi3Parviz Abdolmaleki4Department of Biophysics, Faculty of Biological Science, Tarbiat Modares University, Jalal Ale Ahmad Highway, Tehran P.O. Box 14115-111, IranDepartment of Biophysics, Faculty of Biological Science, Tarbiat Modares University, Jalal Ale Ahmad Highway, Tehran P.O. Box 14115-111, IranBiomedical Engineering group, Department of Electrical and Information Technology, Iranian Research Organization for Science and Technology (IROST), 33535111 Tehran, Iran; Corresponding authors.Department of Biophysics, Faculty of Biological Science, Tarbiat Modares University, Jalal Ale Ahmad Highway, Tehran P.O. Box 14115-111, IranDepartment of Biophysics, Faculty of Biological Science, Tarbiat Modares University, Jalal Ale Ahmad Highway, Tehran P.O. Box 14115-111, Iran; Corresponding authors.Inhibiting the mammalian Target of Rapamycin (mTOR) represents a promising strategy in cancer therapy due to its crucial role in cell growth, survival, and metabolism. Using a variety of quantitative structure-activity relationship (QSAR) models, we present a comprehensive comparison of deep learning (DL) and classical machine learning (ML) techniques for modeling mTOR inhibitor activity. Unlike prior studies that focused on specific algorithms or limited descriptors, we benchmark a wide range of models, from traditional models like Random Forest, logistic regression, and SVM to modern algorithms like CNNs, GRUs, and LSTMs, on both descriptor-based features obtained by Dragon and descriptor-free inputs, including raw SMILES string, and Morgan fingerprints. This comprehensive analysis provides a robust foundation for using the best QSAR models specific to mTOR inhibition. Our findings revealed that while the Random Forest classifier achieved the highest accuracy among all models (0.9290 accuracy, 0.8940 F1-score, 0.9737 AUC), DL methods also demonstrated strong predictive capabilities, with nearly all models attaining an accuracy above 0.90. Among the DL models, CNN-QSAR using Morgan fingerprints achieved the highest accuracy (0.9271), F1-score (0.8950), and AUC (0.9696), demonstrating its effectiveness in capturing structural characteristics. The GRU-QSAR and LSTM-QSAR models, which utilized tokenized SMILES, achieved accuracies of 0.9002 and 0.9021, F1-scores of 0.8595 and 0.8603, and AUCs of 0.9270 and 0.9529, respectively, leveraging their ability to process sequential data.http://www.sciencedirect.com/science/article/pii/S2666990025000333Mammalian target of rapamycin (mTOR)Quantitative structure-activity relationship (QSAR)Machine learningDeep learningMorgan fingerprintsSMILES |
| spellingShingle | Seyed Alireza Khanghahi Hadi Kamkar Seyedehsamaneh Shojaeilangari Abdollah Allahverdi Parviz Abdolmaleki Integrative in Silico modeling for mTOR inhibition: From ridge classifiers to descriptor-free deep neural networks Computer Methods and Programs in Biomedicine Update Mammalian target of rapamycin (mTOR) Quantitative structure-activity relationship (QSAR) Machine learning Deep learning Morgan fingerprints SMILES |
| title | Integrative in Silico modeling for mTOR inhibition: From ridge classifiers to descriptor-free deep neural networks |
| title_full | Integrative in Silico modeling for mTOR inhibition: From ridge classifiers to descriptor-free deep neural networks |
| title_fullStr | Integrative in Silico modeling for mTOR inhibition: From ridge classifiers to descriptor-free deep neural networks |
| title_full_unstemmed | Integrative in Silico modeling for mTOR inhibition: From ridge classifiers to descriptor-free deep neural networks |
| title_short | Integrative in Silico modeling for mTOR inhibition: From ridge classifiers to descriptor-free deep neural networks |
| title_sort | integrative in silico modeling for mtor inhibition from ridge classifiers to descriptor free deep neural networks |
| topic | Mammalian target of rapamycin (mTOR) Quantitative structure-activity relationship (QSAR) Machine learning Deep learning Morgan fingerprints SMILES |
| url | http://www.sciencedirect.com/science/article/pii/S2666990025000333 |
| work_keys_str_mv | AT seyedalirezakhanghahi integrativeinsilicomodelingformtorinhibitionfromridgeclassifierstodescriptorfreedeepneuralnetworks AT hadikamkar integrativeinsilicomodelingformtorinhibitionfromridgeclassifierstodescriptorfreedeepneuralnetworks AT seyedehsamanehshojaeilangari integrativeinsilicomodelingformtorinhibitionfromridgeclassifierstodescriptorfreedeepneuralnetworks AT abdollahallahverdi integrativeinsilicomodelingformtorinhibitionfromridgeclassifierstodescriptorfreedeepneuralnetworks AT parvizabdolmaleki integrativeinsilicomodelingformtorinhibitionfromridgeclassifierstodescriptorfreedeepneuralnetworks |