Isfahan University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
A Deep Learning Model Based on the Bert Pre-Trained Model to Predict the Antiproliferative Activity of Anti-Cancer Chemical Compounds Publisher Pubmed



Torabi M1 ; Haririan I2, 3 ; Foroumadi A4, 5 ; Ghanbari H6 ; Ghasemi F7, 8
Authors
Show Affiliations
Authors Affiliations
  1. 1. Biosensor Research Centre, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
  2. 2. Department of Pharmaceutics, Faculty of Pharmacy, Tehran University of Medical Sciences, Tehran, Iran
  3. 3. Department of Pharmaceutical Biomaterials and Medical Biomaterials Research Center (MBRC), Faculty of Pharmacy, Tehran University of Medical Sciences, Tehran, Iran
  4. 4. Department of Medicinal Chemistry, Faculty of Pharmacy, Tehran University of Medical Sciences, Tehran, Iran
  5. 5. Drug Design and Development Research Center, The Institute of Pharmaceutical Sciences (TIPS), Tehran University of Medical Sciences, Tehran, Iran
  6. 6. Department of Medical Nanotechnology, School of Advanced Technologies in Medicine, Tehran University of Medical Sciences, Tehran, Iran
  7. 7. Department of Bioinformatics and Systems Biology, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
  8. 8. Bioinformatics Research Center, School of Pharmacy and Pharmaceutical Sciences, Isfahan University of Medical Sciences, Isfahan, Iran

Source: SAR and QSAR in Environmental Research Published:2024


Abstract

Identifying new compounds with minimal side effects to enhance patients’ quality of life is the ultimate goal of drug discovery. Due to the expensive and time-consuming nature of experimental investigations and the scarcity of data in traditional QSAR studies, deep transfer learning models, such as the BERT model, have recently been suggested. This study evaluated the model’s performance in predicting the anti-proliferative activity of five cancer cell lines (HeLa, MCF7, MDA-MB231, PC3, and MDA-MB) using over 3,000 synthesized molecules from PubChem. The results indicated that the model could predict the class of designed small molecules with acceptable accuracy for most cell lines, except for PC3 and MDA-MB. The model’s performance was further tested on an in-house dataset of approximately 25 small molecules per cell line, based on IC50 values. The model accurately predicted the biological activity class for HeLa with an accuracy of (Formula presented.) and demonstrated acceptable performance for MCF7 and MDA-MB231, with accuracy between 0.56 and 0.66. However, the results were less reliable for PC3 and HepG2. In conclusion, the ChemBERTa fine-tuned model shows potential for predicting outcomes on in-house datasets. © 2024 Informa UK Limited, trading as Taylor & Francis Group.
Related Docs
View other Related Docs
1. Identification of New Potential Candidates to Inhibit Egf Via Machine Learning Algorithm, European Journal of Pharmacology (2024)
2. Identification of Potential Vascular Endothelial Growth Factor Receptor Inhibitors Via Tree-Based Learning Modeling and Molecular Docking Simulation, Journal of Chemometrics (2024)
3. Accelerating Big Data Analysis Through Lasso-Random Forest Algorithm in Qsar Studies, Bioinformatics (2022)
4. Stepwise Mlr and Pcr Qsar Study of the Pharmaceutical Activities of Antimalarial 3-Hydroxypyridinone Agents Using B3lyp/6-311++G* *Descriptors, Medicinal Chemistry Research (2013)
5. Linear and Nonlinear Qsar Modeling of 1,3,8-Substituted-9-Deazaxanthines As Potential Selective A2bar Antagonists, Medicinal Chemistry Research (2013)
6. Comparative Quantitative Structure-Activity Relationship Study of Some 1-Aminocyclopentyl-3-Carboxyamides As Ccr2 Inhibitors Using Stepwise Mlr, Fa-Mlr, and Ga-Pls, Medicinal Chemistry Research (2012)
7. Computer-Driven Development of an in Silico Tool for Finding Selective Histone Deacetylase 1 Inhibitors, Molecules (2020)
8. A Quantitative Structure-Activity Relationship (Qsar) Study of Some Diaryl Urea Derivatives of B-Raf Inhibitors, Research in Pharmaceutical Sciences (2016)
Experts (# of related papers)
View all Related Experts
Afshin Fassihi (16)
Lotfollah Saghaie Dehkordi (9)
Other Related Docs
9. Identification of Essential 2D and 3D Chemical Features for Discovery of the Novel Tubulin Polymerization Inhibitors, Current Topics in Medicinal Chemistry (2019)
10. Monastrol Derivatives: In Silico and in Vitro Cytotoxicity Assessments, Research in Pharmaceutical Sciences (2020)
11. A Qsar Study of Some Cyclobutenediones As Ccr1 Antagonists by Artificial Neural Networks Based on Principal Component Analysis, DARU, Journal of Pharmaceutical Sciences (2011)
12. Qsar Study of Anthranilic Acid Sulfonamides As Inhibitors of Methionine Aminopeptidase-2 Using Ls-Svm and Grnn Based on Principal Components, European Journal of Medicinal Chemistry (2010)
13. Protein Kinase Inhibitors’ Classification Using K-Nearest Neighbor Algorithm, Computational Biology and Chemistry (2020)
14. Qsar Study of Isatin Analogues As in Vitro Anti-Cancer Agents, European Journal of Medicinal Chemistry (2010)
15. Quantitative Structure Activities Relationships of Some 2-Mercaptoimidazoles As Ccr2 Inhibitors Using Genetic Algorithm-Artificial Neural Networks, Research in Pharmaceutical Sciences (2013)
16. Deep Neural Network in Qsar Studies Using Deep Belief Network, Applied Soft Computing Journal (2018)
17. Qsar Study of Anthranilic Acid Sulfonamides As Methionine Aminopeptidase-2 Inhibitors, Monatshefte fur Chemie (2012)
18. A Gu‑Net‑Based Architecture Predicting Ligand–Protein‑Binding Atoms, Journal of Medical Signals and Sensors (2023)
19. Qsar and Docking Analysis of A2b Adenosine Receptor Antagonists Based on Non-Xanthine Scaffold, Medicinal Chemistry Research (2015)
20. Qsar Study of Some Ccr5 Antagonists As Anti-Hiv Agents Using Radial Basis Function Neural Network and General Regression Neural Network on the Basis of Principal Components, Medicinal Chemistry Research (2012)
21. The Role of Different Sampling Methods in Improving Biological Activity Prediction Using Deep Belief Network, Journal of Computational Chemistry (2017)
22. Application of Partial Least Squares and Radial Basis Function Neural Networks in Multivariate Imaging Analysis-Quantitative Structure Activity Relationship: Study of Cyclin Dependent Kinase 4 Inhibitors, Journal of Molecular Graphics and Modelling (2010)