𧬠Bioinformatics Graduate Student | Machine Learning Enthusiast | Drug Discovery Researcher | NGS
Welcome to my GitHub profile! I'm a passionate Bioinformatics graduate student with a strong foundation in computational biology, machine learning, and data analysis. Currently pursuing my Masters in Bioinformatics while actively working on cutting-edge research in drug discovery and predictive modeling.
π Master of Science in Bioinformatics (2023-2025)
Rajiv Gandhi Institute of IT and Biotechnology, Pune
π Bachelor of Science in Biotechnology (2019-2022)
MES Abasaheb Garware College of Science and Arts, Pune
Currently developing Machine Learning-based QSAR models and molecular docking techniques to discover novel dual-inhibitors against Sodium-Glucose Co-Transporters (SGLT1 and SGLT2) for Type 2 Diabetes Mellitus. This work involves:
- Advanced descriptor analysis and activity prediction
- Virtual screening using Python and ML technologies
- Integration of computational chemistry with machine learning
Programming & Databases:
- π Python | R | SQL
Specializations:
- π€ Machine Learning | Data Analysis | Linux
Domain Expertise:
- π Computer-Aided Drug Design (CADD)
- 𧬠Bioinformatics Pipeline Development
Bioinformatics Techniques:
- 𧬠RNA-sequencing Analysis
- π Genome-Wide Variation Analysis
- π Genomic Data Processing
Data Visualization:
- π PowerBI | Tableau | Matplotlib | Seaborn
Built an end-to-end ML pipeline for breast cancer biomarker classification (569 samples, 30 features, 90:10 imbalance)
- Models: Logistic Regression, Random Forest, XGBoost with augmentation (SMOTE, ADASYN, Random Oversampling)
- Best Performance: Logistic Regression + Random Oversampling (98.89% ROC-AUC, 100% Recall)
- Impact: Achieved perfect sensitivity for medical diagnosis with comprehensive cross-validation
Developed and benchmarked 5 oversampling techniques for highly imbalanced datasets (500 samples, 20 features, 8.4:1 ratio)
- Methods: SMOTE, Borderline-SMOTE, ADASYN, Statistical Gaussian, Noise Injection with quality validation
- Best Performance: All methods achieved perfect metrics (100% ROC-AUC, 100% Recall, 100% F1-Score)
- Impact: Improved baseline recall from 27% to 100% with K-S test validation (p-value > 0.48) and excellent correlation preservation
Built an end-to-end ML pipeline using Ames Housing Dataset (2,932 records, 82 features)
- Models: Linear Regression, Random Forest, XGBoost
- Best Performance: XGBoost with cross-validation
- Impact: Delivered actionable insights for real estate price prediction
Developed Python script using BeautifulSoup for web scraping
- Sources: BBC and NDTV websites
- Output: Daily HTML email digest
- Automation: Scheduled news compilation and delivery
Executed comprehensive bioinformatics pipelines on Linux
- Analysis Types: Genome-Wide Variation and RNA-Seq
- Data: SRA datasets
- Environment: Linux command-line tools
Built predictive models during LearnToUpgrade AI Internship
- Applications: Cancer and BMI prediction
- Algorithms: KNN and NaΓ―ve Bayes
- Data: DNA K-mers count analysis
- Interface: Interactive Streamlit dashboards
- π Career Edge - Young Professional | TCS iON | Jun 2025
- 𧬠Genomics and Bioinformatics | IISER Kolkata | Aug 2025
- π Data Science & Analytics | hp LIFE | Aug 2025
Technical Excellence:
- Problem-Solving & Critical Thinking
- Statistical Analysis & Data Modeling
- Computational Biology Applications
Leadership & Communication:
- Team Collaboration & Leadership
- Scientific Communication
- Active Learning & Adaptability
- π Drug Discovery & Development
- 𧬠Computational Biology
- π€ Machine Learning in Healthcare
- π Genomics Data Analysis
- π¬ QSAR Modeling
- π» Bioinformatics Tool Development
- π§ Email: akankshawaghamode2001@gmail.com
- π± Phone: +91-8080640427
- πΌ LinkedIn: Connect with me
- π GitHub: You're already here!
- Advanced Deep Learning techniques for molecular modeling
- Cloud computing platforms for bioinformatics (AWS, Google Cloud)
- Advanced statistical methods for genomic data analysis
- MLOps for deploying ML models in production
- 𧬠Passionate about bridging the gap between biology and technology
- π Love turning complex biological data into actionable insights
- π― Always excited to collaborate on interdisciplinary projects
- π Believe in the power of open-source science
"Combining the power of computation with the complexity of biology to solve real-world problems."
β Feel free to explore my repositories and don't forget to star the ones you find interesting!