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

لیست مقالات

لیست مقالات بایگانی شده

A Computational Approach to Identify Potent Inhibitors of Janus Kinase 1 from Natural Products: Structure-Based High-Throughput Virtual Screening and LightGBM Classifier.

Parisa Valipour

Curcumin’s Journey Through Cellulose: Binding Dynamics Across Cellulose-derived Bio-Nanofibers

Ayla Esmaeilzadeh - Maryam Azimzadeh Irani - Mehdi Jahanfar - Naser Farrokhi

ATIC as a Theranostic Biomarker in Gastrointestinal Cancers: Insights from Autophagy Pathway Analysis

Pooya Jalali - Maryam Eghbali - Zahra Eghabli - Yasaman Gholinezhad - Zahra Salehi

Identification of circRNA-miRNA-mRNA Interaction in Myocardial Infarction

Amir Hesam Pahlevani - Ashkan Nazari - Kiarash Zare - Mohammad Ghorbani - Abdolhakim Aalkamel - Mohammad Mehdi Naghizadeh

Towards Efficient Recombinant Protein Production: In-silico screening of signal peptides for secretory production of recombinant factor C in mammalian cells

Maryam Latifi - Kosar Asadi - Mansoureh Shahbazi Dastjerdeh

Diagnosis of Diabetic Retinopathy with Fuzzy Technique and Deep Learning

Samaneh Noroozi - Sajad Haghzad Klidbary

Drug reproposing for brain cancer

Zahra Shahini - Farinaz Roshani

BIRC5: The Silent Architect of Tumor Persistence and Senescence in Hepatocellular Carcinoma

Amirhosein Farrokhzad - Maryam Kaboli - Elahe Hoseinnia - Elham Rismani - Massoud Vosough

Innovative Biomarkers for Lung Cancer Classification and Prediction Using High-Dimensional Machine Learning: A Novel Approach to Targeted Therapies

Marzie Shadpirouz - Morteza Hadizadeh - Zahra Salehi - Maziyar Veisi - Reza Maddah - Mohammad Shirinpour - Kazem Abbaszadeh-Goudarzi - Kaveh Kavousi

Exploring the Anticancer Potential of Flavonoids from Morus alba Against Breast Cancer: An In Silico Approach

Kimia Asadi - Negar Ghaleh Navi - Ehsan Karimi

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.7.0