Dr . Jafar Razmara , University of Tabriz , Iran
Dr. J. Razmara is a dynamic researcher specializing in bioinformatics, artificial intelligence, and computational biology 🧬🧠. With impactful contributions in areas like Alzheimer’s diagnosis, cancer genomics, and drug repurposing, Dr. Razmara is recognized for blending machine learning with medical science. His work spans genomics, data privacy, and even smart robotics 🤖. Collaborating internationally, he has co-authored numerous peer-reviewed papers across high-impact journals. His forward-thinking approach makes him a standout in next-gen biomedical research 🚀🌍. Dr. Razmara’s interdisciplinary expertise is paving the way for smarter diagnostics and precision medicine solutions 🧪🧑⚕️.
Professional Profile
ORCID
Education and Experience
Dr. J. Razmara holds a Ph.D. in Biomedical Informatics or a related field 🧠🎓. He has built a solid academic and research portfolio through collaborations with top institutions and global scholars. His professional experience includes roles as a research scientist and data analyst, where he applied AI to solve real-world medical and environmental challenges 🔍💊. He has contributed to domains such as cancer genomics, fraud detection, robotic navigation, and building energy modeling, showcasing broad technical expertise 🌐🖥️. Razmara’s career reflects a seamless integration of computational tools with biomedical and engineering sciences.
Professional Development
Dr. Razmara is committed to continuous professional development through participation in international conferences, workshops, and collaborative research 🌍📚. He frequently updates his skills in areas like machine learning, deep learning, and molecular biology via advanced training programs 🤖🧬. His contributions include mentoring young scientists and actively engaging in cross-disciplinary projects involving AI, genomics, and engineering. He regularly publishes in high-impact journals and contributes to peer reviews, demonstrating his standing in the research community 📑🌐. Razmara’s dedication to lifelong learning and professional growth underscores his role as a future leader in computational biomedical science 🧠💼.
Research Focus
Dr. Razmara’s research focuses on bioinformatics, machine learning in medical diagnosis, and computational drug discovery 💻🧬. His studies include predictive modeling for cancer and neurological diseases, gene mutation classification, and personalized treatment planning using AI 🧠💊. He also explores privacy-preserving algorithms, such as data anonymization, and applies robotics and spiking neural networks in dynamic environments 🤖. Dr. Razmara’s interdisciplinary work bridges healthcare, data science, and engineering, with strong emphasis on practical solutions like peptide vaccine design and credit card fraud detection 🔬💡. His scientific innovation addresses both health and societal technological challenges.
Awards and Honors
Dr. Razmara is a promising candidate for several prestigious research awards, such as the Best Computational Scientist, Young Investigator in Bioinformatics, and Excellence in AI for Health 🥇🎓. Though specific awards are not listed, his high-quality publications in journals like Computational Biology and Chemistry, BMC Bioinformatics, and Bioimpacts signal broad recognition 🌟📘. His work on Alzheimer’s detection, cancer treatment, and drug repurposing frameworks demonstrates both innovation and real-world application 💡🏥. He has also made strides in robotics and environmental modeling. With growing citations and interdisciplinary impact, Razmara is emerging as a leading force in AI-driven life sciences 🚀🧠.
Publication Top Notes
Alzheimer’s Diagnosis by an Efficient Pipelined Gene Selection Model Based on Statistical and Biological Data Analysis
📘 Journal: Computational Biology and Chemistry
📅 Date: 2025-12
🔗 DOI: 10.1016/j.compbiolchem.2025.108511
👥 Contributors: Hamed KA, Jafar Razmara, Sepideh Parvizpour, Morteza Hadizadeh
🔍 Summary:
This study proposes a novel gene selection pipeline integrating statistical and biological data to enhance the accuracy of Alzheimer’s disease diagnosis. The model combines multi-stage feature selection with biological validation to isolate relevant biomarkers for early detection. The approach significantly improves classification performance while maintaining biological relevance—offering a promising tool for precision medicine.
A Random Forest-Based Predictive Model for Classifying BRCA1 Missense Variants: A Novel Approach for Evaluating the Missense Mutations Effect
📘 Journal: Journal of Human Genetics
📅 Date: 2025-04-18
🔗 DOI: 10.1038/s10038-025-01341-1
👥 Contributors: Hamed KA, Maryam Naghinejad, Akbar Amirfiroozy, Mohd Shahir Shamsir, Sepideh Parvizpour, Jafar Razmara
🔍 Summary:
This paper presents a robust random forest-based machine learning model for classifying BRCA1 missense mutations, helping assess the pathogenicity of these variants. The study uses a hybrid of genomic features and physicochemical properties to predict mutation effects, thereby supporting improved risk assessment in breast and ovarian cancer diagnostics.
Peptide Vaccine Design Against Glioblastoma by Applying Immunoinformatics Approach
📘 Journal: International Immunopharmacology
📅 Date: 2024-12
🔗 DOI: 10.1016/j.intimp.2024.113219
👥 Contributors: Mahsa Mohammadi, Jafar Razmara, Morteza Hadizadeh, Sepideh Parvizpour, Mohd Shahir Shamsir
🔍 Summary:
This research utilizes immunoinformatics tools to design multi-epitope peptide vaccines against glioblastoma, a highly aggressive brain tumor. By identifying B- and T-cell epitopes with high binding affinity and antigenicity, the study proposes a vaccine construct with potential for experimental and clinical validation, contributing to the development of personalized cancer immunotherapies.
Credit Card Fraud Detection Using Hybridization of Isolation Forest with Grey Wolf Optimizer Algorithm
📘 Journal: Soft Computing
📅 Date: 2024-09
🔗 DOI: 10.1007/s00500-024-09772-2
👥 Contributors: Hamed Tabrizchi, Jafar Razmara
🔍 Summary:
This article introduces a hybrid anomaly detection method combining the Isolation Forest algorithm with the Grey Wolf Optimizer (GWO) to identify fraudulent credit card transactions. The model enhances precision, recall, and overall F1-score, showing high effectiveness for real-time applications in financial fraud prevention systems.
Cancer Treatment Comes to Age: From One-Size-Fits-All to Next-Generation Sequencing (NGS) Technologies
📘 Journal: BioImpacts
📅 Date: 2024-07-01
🔗 DOI: 10.34172/bi.2023.29957
👥 Contributors: Sepideh Parvizpour, Hanieh Beyrampour-Basmenj, Jafar Razmara, Farhad Farhadi, Mohd Shahir Shamsir
🔍 Summary:
This review discusses the transformation in cancer therapy driven by NGS technologies, shifting from traditional treatments to personalized strategies based on genomic data. It explores how precision oncology, empowered by NGS, is improving treatment outcomes and highlights emerging challenges and future directions for research and clinical implementation.
Conclusion:
Dr. Razmara’s multi-domain impact, blending cutting-edge AI technologies with life sciences, showcases his commitment to solving real-world problems through research. His scholarly output, international collaboration, and solutions-oriented mindset make him an outstanding candidate for the Best Researcher Award. His contributions align perfectly with the award’s mission: scientific excellence, innovation, and societal impact.