As a member of the Bioinformatics team:
• Optimized deep CNN machine learning models for improved DNA sequencing.
• Generated, validated, and enhanced code for Phred quality models.
• Researched the impact of filtering on homopolymer distribution, Q-score, and throughput.
• NGS pipeline software development and configuration management for all steps.
• Studied accuracy as a function of coverage for karect based correction module.
• Implemented positive results of ad-hoc studies in Python software and algorithms.
• Improved alignment tools and demultiplexing code.
• Performed Verification and Validation testing and configuration management for software releases.
• Supported new team members, reviewed pull requests, and documented processes.
for the continuous improvement of the base-calling pipeline.
Worked with BWA, BLAST, SAMtools, FASTQ, Karect, Cutadapt, Trimmomatic.