-Research projects were considered among the top 50 and top 20 to be presented, respectively, in 2020 and 2021 on Scientific Computing Days at the FDA.2020 Scientific Computing Days: https://www.fda.gov/media/142043/download2021 Scientific Computing Days: https://www.fda.gov/media/151892/download-Created ML models capable of predicting drug response for AML patients with IDH1 and IDH2 mutations, using clinical and genomics data. https://doi.org/10.1182/blood-2021-147099-Worked with high-performance computer clusters to create machine learning models for a wide range of projects. -Maintained and updated Covid19 sequence databases obtained from GISAID and NIH weekly, employed Dask package to handle the significant data updates -Evaluated machine learning algorithms that can identify clusters of cell types and time series trajectories on single-cell RNA-seq data. Worked collaboratively with single-cell sequencing labs to create visualizations to describe scientific findings and write methods portions of manuscripts.-Integrated clinical and genomics data and apply machine learning algorithms, such as Random Forest and other ensemble-based methods to understand the effect of genetic mutations on the health parameters and clinical outcomes.-Placed 10th in PrecisionFDA Brain Cancer Predictive Modeling and Biomarker Discovery Challenge by utilizing p-values imputed permutation importance feature selection method. Used 17 features to achieve this result. Winning solution used ~50 features.-Created a machine learning model from germline mutation data to predict the immune-related adverse events outcome in cancer patients treated with immune-checkpoint inhibitors. I used an ensemble approach to select features and LightGBM to create predictive models that achieve ~96% accuracy.- Improved an existing rule-based Anaphylaxis case definition algorithm using ML techniques. The data for the model was curated by screening 66 million records from the CMS database.

I have been working with Elsevier as a student collaborator and intern.Since then, I was part of the Pathway Studio team, developing workflows and analyzing biological data in order to understand human pathology and rare disease networks.As a result of this collaboration, we have also created a workbook for Pathway Studio software which is called Elsevier in Classroom, that aims to help students to effectively search relationships between molecules and biological entities. If you are interested, you can access the workbook online following this link: http://downloads.pathwaystudio.com/documentation/EICWorkbook_Interactive_12-12-17.pdf-Designed creative workflows for Pathway Studio Platform. These workflows were published as a workbook called “Elsevier in Classroom” as a result.-Worked extensively with graph algorithms and Neo4j to search, connect and discover biological relationships mined using NLP and studied the feasibility of converting big relational data to different graph databases.-Using NBSVM (NLP), successfully predicted sample source name and disease name using GEO metadata that could help researchers find data easily and more efficiently.

I am currently teaching 2 Genetics 311 Lab Rotations.

-Performed statistical analysis on global health data available from public sources using R.-Led a team of student researchers on their statistical analysis regarding Global Health data, including HBV prevalence, NAFLD and NASH using correlation tests, ANOVA and Exploratory Data Analysis.-Conducted research to understand molecular models of aging and its effects on human fibroblast cells using publicly available datasets with GeneXplain platform.-Identified promoter regions, transcription factor binding sites and master molecules in charge of aging effects and progeria using TRANSFAC and TRANSPATH databases.

-Experienced with coating, production and biosensor design in class 100 and 1000 rooms-Synthesized Monodispersed Silica Nanospheres.-Conducted research on nanoplating of certain surfaces for fabrication of biosensors.-Coated surfaces with gold and platinum for fabrication of cellular specific biosensors.

-Controlled quality and optimization of manufactured chemicals.-Prepared industrial and home base cleaning products like soap, shampoos, chlorinated industrial cleaners, etc. -Observed manufacturing, packaging and shipping process.