Bioinformatics & Aspiring Healthcare Data Science professional skilled in applying machine learning, statistics, and explainable AI to real-world problems in pharma, precision medicine, genomics, and clinical research. W…
Bioinformatics & Aspiring Healthcare Data Science professional skilled in applying machine learning, statistics, and explainable AI to real-world problems in pharma, precision medicine, genomics, and clinical research. With hands-on experience in Python, R, SQL, statistical modelling, QC workflows, metagenomics, and clinical datasets, I build data pipelines and evidence-based insights that support scientific and medical decision-making.
My project portfolio covers:
• Clinical ML & XAI: Built end-to-end ML and SHAP/LIME workflows for differential diagnosis using CBC data; deployed models using Flask.
• Genomics & Metagenomics: NGS/ONT data QC, host removal, and microbial profiling pipelines using Linux, Bash, Kraken2.
• Computational Biology: Conducted RNA-seq differential expression analysis (DESeq2) for cancer transcriptomics.
• Data Engineering Foundations: Data preprocessing, EDA, feature engineering, statistical validation, reproducible scripts.
I blend computational skills with strong biological understanding to create scalable, interpretable, and clinically relevant data solutions. I’m passionate about contributing to:
🔹 Pharmaceutical analytics
🔹 Clinical and real-world data science
🔹 AI/ML for diagnostics & drug development
🔹 Genomics and precision medicine
🔹 Healthcare innovation
Actively seeking opportunities in Data Science, Bioinformatics & Healthcare Analytics within pharma, biotech, and digital health, where I can contribute to impactful, patient-centric outcomes for improvised healthcare and precision medicine.
<ul><li>Built an automated Oxford Nanopore metagenomics pipeline: basecalling → adapter trimming (Porechop) → QC → host DNA removal → taxonomic classification using Kraken2 → summarized reports. </li><li>Conducted sample QC, filtering, metadata merging, contamination detection, and downstream analysis for necrotic tissue samples.</li><li>Collaborated with wet-lab teams to interpret microbial profiles for clinical relevance.</li><li>Produced reproducible scripts, documentation, and standardized analysis reports.</li></ul><p></p>
<p>Built ML models (RandomForest, AdaBoost, LightGBM) for clinical data classification (Vitamin B12 vs Folate Deficiency Anemia) using patient CBC data.<br>
Applied statistical testing, EDA, feature selection.<br>
Implemented feature engineering, model evaluation (accuracy, precision, recall, F1, MCC, AUC).<br>
Performed hyperparameter tuning.<br>
Designed experiments using cross-validation and GridSearchCV.<br>
Used pandas, numpy, sklearn, matplotlib, and seaborn.<br>
Achieved 99% accuracy.<br>
Built REST API using Flask and deployed the best performing model locally.<br>
Applied explainable AI (SHAP, LIME) for interpretability and transparency of the results.<br>
Investigated RBC segmentation with U-Net (Python, OpenCV, TensorFlow).<br>
Used data augmentation.<br>
Used patch-wise training on 3D phase images for morphological analysis.</p>
<p>Conducted RNA-seq analysis of TCGA datasets to study MALAT1 expression across multiple cancers.<br>
Applied statistical modeling and pathway analysis to identify biomarker and therapeutic potential.</p>
<p>Designed a responsive website using HTML and CSS.<br>
Supported calculation of users BMI to determine their ideal calorie intake.<br>
Used BeautifulSoup for webscraping/API-extraction in a separate project.</p>
<p>Built automated pipeline for Nanopore sequencing using Bash, Kraken2, Porechop, and Dorado.<br>
Wrote reproducible workflows.<br>
Generated QC dashboards.<br>
Worked with Linux, HPC, and version-controlled workflows.</p>
<ul><li>Worked as a project intern as a part of Masters thesis final dissertation to develop and deploy the machine learning model all the way from data collection and preprocessing till the deployment stage and model interpretability.</li><li>Built ML models (RandomForest, AdaBoost, LightGBM) for clinical data classification (Vitamin B12 vs Folate Deficiency Anaemia) using patient CBC data. Applied statistical testing, EDA, and feature selection. </li><li>Implemented feature engineering, model evaluation (accuracy, precision, recall, F1, MCC, AUC), hyperparameter tuning, experiment design (cross-validation, GridSearchCV), and used pandas, numpy, sklearn, matplotlib, and seaborn. The model performed very well with 99% accuracy.</li><li>Built a REST API using Flask & deployed the best-performing model locally.</li><li>Applied explainable AI (SHAP, LIME) for interpretability and transparency of the results. </li><li>Tried to integrate RBC image-based morphological features for better classification.</li><li>Deep learning: Investigated RBC segmentation with U-Net (Python, OpenCV, TensorFlow), data augmentation, and patch-wise training on 3D phase images for morphological analysis.</li><li>Extracted shape descriptors, height–length curves, and statistical features for classification.</li><li>Generated per-cell plots, CSV exports, and morphology profile visualizations.</li></ul><p></p>
The AI-first Recruitment Operating System that unifies and automates the entire hiring lifecycle for modern enterprises worldwide.
Dr Job FZ LLC. 2026 © All Rights Reserved
