Providing strategic and technical consulting services in Data Science, CompBio, and R&D to Healthtech/Biotech companies. Recent clients include:• LinusBio (Data Science; Biomarker development and diagnostics; Pharma collaborations).• Vitality.ai (Data Science; B2B wellness/longevity)• Decode Age (Data Science & Bioinformatics; Microbiome/metagenomics, D2C Wellness/longevity)• InsideTracker (Data Science; R&D; DTC wellness/longevity/biomarkers)• DropBio Health (Data Science; R&D; DTC wellness/longevity/biomarkers)

• Built a data science team - interviewed, hired, and led junior and senior scientists.• Developed strategy for computational biology and data science - to ensure genetic stability and product safety while supporting development of multiple cell therapy products across different oncology indications. • Led team in building bioinformatic pipelines using AWS and open-source tools with custom scripts to analyze high throughput NGS data to support pre-IND data package’s submission to FDA while advancing product development and iPSC platforms.

• Lead design and implementation of data science infrastructure - AWS system to store, manage, and analyze data within centralized cloud to gain insights for product improvement and innovation.• Worked with vendors to define scope of NGS services and initial bioinformatic analyses, secure proprietary databases, and design custom bioinformatic pipelines that analyze results and verify genetic profile of interest for IND submission.• Provided data insights to research teams to evaluate and rank potential tumor targets and drive product improvement decisions.• Tech environment: AWS, RStudio, Jupyter Notebooks, Unix/Linux, R, and Python.

• Owned successful release of bioinformatic pipeline software update, coordinating a ten-member cross-functional team to drive project completion using Python and GitHub.• Analyzed NGS data from bioinformatic pipeline and ran custom scripts to quantify mutation types and load to support biotech and pharma partners’ in identifying biomarkers of response in their clinical trials.

• Built a data science team - interviewed, hired, and led three researchers across several projects for pharmaceutical companies. • Implemented additional initiatives to develop bioinformatic pipelines to identify biomarkers using clustering, logistic regression, random forest, and generalized lineal models.• Worked with team to identify potential biomarkers of early inflammation in microbiome for early cancer detection and intervention.• Performed cross-sectional and longitudinal analysis of gut microbiome in IBD patients and controls to monitor changes in microbiome associated with clinical improvements and serving as biomarkers as part of IBD drug program.• Directed analysis of clinical labs, genetics, and lifestyle in obese individuals to identify biomarkers of response to weight loss coaching, as part of pharma’s diabetes and obesity programs.

• Oversaw projects for pharmaceutical and food corporations to analyze association between lifestyle, microbiome, and clinical labs. • Directed cross-functional team in synthesizing microbiome actionable insights from internal database and existing scientific literature and developing a machine learning model based on list of taxa and metabolomics data to predict risk of high TMAO.

• Developed a machine learning solution via Python, Jupyter notebooks, and Random Forest to improve Arivale product by enhancing clinician’s ability to make recommendations to members based on their clinical labs and lifestyle choices.• Designed and implemented a bioinformatic pipeline analyzing composition of microbial community from stool samples by leveraging open source metagenomic tools such as PICRUSt, enabling Arivale to reduce costs per sample analyzed by 30%.

• Developed a machine learning and statistical framework using non-negative linear regression, Shapley value analysis, multi-taxa permutation analysis, and Wilcoxon test to identify bacterial species driving disease-associated functional shifts.• Implemented a computational pipeline to identify microbial shifts in cystic fibrosis patients and nominate potential biomarkers.