Sreevatsa Nukala Email & Phone Number

Cambridge, Massachusetts, United States

Cambridge, Massachusetts, United States

• Scaled-up analysis platform by migrating targeted amplicon NGS analysis pipeline of standalone Bash scripts to Nextflow/Docker workflow, hosted on AWS compute environment with Seqera Platform (Nextflow Tower). Boosted performance through Nextflow parallelization, resulting in 1.25x speed-up and overcoming major bottleneck of analysis for NGS editing assay.• Performed quality control on reads from NextSeq sequencer to validate results for NextSeq sequencing in-house.

Cambridge, Massachusetts, United States

• Built website to streamline primary data analysis platform using Plotly Dash to plot and analyze experiment data via Benchling PostgreSQL Warehouse queries and deploy on AWS Fargate ECS.• Spearheaded analysis of barcoded high throughput screening to understand biodistribution of engineered virus-like particles. Perform statistical validation/modeling of barcoded screening for novel editing/therapy delivery mechanism in-vivo.• Established containerized pipeline for quality control of Oxford Nanopore sequencing reads, including alignment to reference genome and generation of improved consensus sequence. Aided in cutting costs of Nanopore sequencing by migrating to in-house sequencing and comparing quality control results to CRO data.

Boston, Massachusetts, United States

• Taught students advanced data science concepts, such as natural language processing, evolutionary computing, dashboards, simulations, etc.• Held office hours with ~50 students each week, graded labs and homework, and guided students during projects• Directed weekly labs for students, taught review lessons, answered questions on support portal, and aided students in lab assignments

Boston, Massachusetts, United States

• Processed NHANES accelerometer health data on HPC• Helped develop tools to visualize data, apply activity recognition algorithms to dataset, and characterize algorithm performance

San Francisco, California, United States

• Deployed Bash scripts and utilized extensive Pytest testing to test Python code written by code-generation machine learning model• Wrote detailed analyses and reports on training and revising code-generation AI models through iterative debugging methods

Tucson, Arizona, United States

Project Title: Overcoming the Limitations of TCR-Beta Repertoire Modeling through an In-Silico DNA Recombination Algorithm• Accelerate algorithm’s execution time with 1.3x speed up by optimizing performance and throughput via CUDA profiling, streaming, and restructuring kernels• Contributed novel “anomaly detection” functionality to algorithm to target and explore significant or desired gene sequences• Presented winning poster at UA’s summer research conference and produced research paper (available on request)Project Description: Genetic recombination in developing lymphocytes during the early stages of T and B cell maturation is the primary mechanism for generating a diverse repertoire of T-cell receptors (TCRs) and immunoglobulins essential to the adaptive immune system. We design experiments to study TCR synthesis and quantify TCR performance benefits on a High-Performance Computing (HPC) system. We conduct statistical analyses to differentiate unique recombination paths.

Bachelor Of Science - Bs, Data Science And Biology

3.94 Unweighted, 4.86 Weighted

Activities and Societies: - Varsity Basketball (2020-2021) - Junior Varsity Basketball (2018-2019) - Varsity Volleyball (2018-2019) - Red.