Muhammad Usman

Processed and analyzed 1,000+ genomic and proteomic samples, reduced pipeline runtime by 35%, and benchmarked variant calling pipelines improving SNP detection sensitivity by 8%. Built ETL workflows handling 50 GB/week, engineered a Neo4j knowledge graph of 10,000+ entities, and delivered 30+ interactive dashboards to accelerate research decisions across clinical programs.

Applied AI-driven CADD methods for biosynthetic pathway optimization and automated ML pipelines using Python, PyTorch, and Scikit-learn on Linux to improve model testing and reproducibility for computational-synthetic biology projects.

Analyzed and integrated NGS and LC-MS/MS proteomics datasets contributing to discovery of 15 novel biosynthetic gene clusters and developed ML models increasing expression-efficiency prediction accuracy by 22%; built Snakemake pipelines saving 40+ hours/month.

Supported sequencing-driven synthetic biology projects validating 100+ molecular cloning experiments, led student training and workflow standardization reducing onboarding time by 30%, and performed sequencing-based validation for construct integrity.

Pursuing M.Sc. in Bioinformatics with focus on computational biology, genomics, NGS, and machine learning; thesis on ML-driven exploration of NRPS engineering in E. coli.

Grade: GPA: 3.721/4.0

Completed B.Sc. in Biomedical Engineering with honors; thesis on ECG analysis and monitoring of signs and symptoms.