Bioinformatics Scientist
-Using Python text-processing tools (NLTK, whoosh, spaCy), generated an evidence base linking hundreds of infectious microorganisms to specific human diseases by extracting and parsing the language in 29M Pubmed abstracts.-Curated repositories of nucleic acid sequences from public databases (SRA, ARGOS, Silva) by phylogenetic clustering and identifying patterns of submission discrepancies.-Developed and scored detection thresholds for a metagenomics diagnostic platform using simulated sequencing data (Jellyfish, Bamtools, BWA) and binary classification models (scikit-learn).