همایش ملی بیوانفورماتیک ایران

صفحه اصلی / 4th international edition and 13th Iranian Conference on Bioinformatics

Predicting Adverse Drug Reactions with Advanced Machine Learning Techniques

نویسندگان :

AlI Mohammadian¹ Sara Haghighi Bardine² Fatemezahra Alizade³

1- Amol University of Special Modern Technologies 2- Amol University of Special Modern Technologies 3- Amol University of Special Modern Technologies

کلمات کلیدی :

Adverse drug reactions،Support Vector Machine،Gradient Boosted Trees،Ensemble leaning

چکیده :

Drug design is a complex and resource-intensive process, partly due to the challenge of predicting adverse drug reactions (ADRs), which can impact drug safety and efficacy and only becomes evident after clinical trials on a drug has already began. In this study, we developed machine learning (ML) methodologies aimed at predicting ADRs by leveraging data from the SIDER databases, which contain ADR information for approved drugs and clinical trials, respectively. ADR data was collected from 1,430 approved drugs. Molecular descriptors, such as polar surface area and molecular weight, were extracted from drug SMILES strings, and Extended Connectivity Fingerprints (ECFP) were used for molecular fingerprinting. We employed several machine learning algorithms, including Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosted Trees (GBT), for ADR classification tasks. To ensure robust evaluation and optimization of these ML methods, we utilized metrics such as accuracy, precision, recall, and F1-score, while addressing class imbalance using SMOTE-NC. Our results demonstrated that no single algorithm outperformed others in all cases; for example, the best balance between precision and recall for predicting common ADRs might be different from those algorithms for rare ADRs, or some algorithms perform better for some tissues and worse for the others. We suggest the use of ensemble learning to combine the strengths of different algorithms for improved ADR prediction in drug discovery. Future work should focus on optimizing ensemble models and extending the approach to other drug classes