Machine Learning Data Science

SHEETAL NIGHUT

**** ***** **, #***, *******, TX *7030

716-***-**** ad5evp@r.postjobfree.com LinkedIn GitHub Master of Science in Bioinformatics - Data Science, GPA 3.6 May 2023 Northeastern University Boston, MA

Bachelor of Bio-medical Engineering GPA 3.5 May 2016 Vidyalankar Institute of Technology Mumbai, India

TECHNICAL SKILLS:

Programming: Python, R, SQL Bash Shell Machine Learning: SVM, Random Forest, Regression, KNN, PCA Databases: MySQL, SQL, Oracle Statistical Software and package- SAS, STATA, Hypothesis Testing, ANOVA, Linear Regression, BioPython, Bioconductor, pandas, NumPy, Matplotlib, Seaborn, Heatmap, Volcano plot Cloud Services: AWS (including EC2, S3) Bioinformatics Visualization Tools: DESeq2, GATK, IGV, NCBI, Ensembl, BLAST Collaboration & Version Control: GitHub, Docker, Git Sequence File Formats & Analysis Tools: FASTA, Trimmomatic, BEAST2, BEAUTi, Samtools, FASTQC, MultiQC, Trim Galore, STAR, RSEM, Nextflow, Bowtie2, VCF, SAM/BAMs, Snakemake, WDL/Cromwell Data Processing & QC: Quality assessment, alignment, quantification, normalization WORK EXPERIENCE

Employer: Texas Children’s Hospital, Houston, TX Oct 2023 to Feb 2024 Title: Bioinformatics Programmer II

• Collaborated with the TCH IS Pathology Clinical Informatics and Cancer Genomics teams in the development and testing of Next Generation Sequencing pipelines using Python. This included the importation, configuration, and customization of third-party bioinformatics software.

• Provided comprehensive support to medical technologists in operating Illumina sequencers and troubleshooted FASTQ file processing issues, significantly enhancing the efficiency and accuracy of bioinformatics analysis.

• Analyzed sophisticated bioinformatics solutions, ensuring compliance with regulatory standards and alignment with the strategic objectives of the organization. Independently conducted programming to resolve intricate bioinformatics challenges for variant calling for missense mutation.

• Handled database operations, including data retrieval, and updating, using SQL queries for the Laboratory Information System (LIS) team to ensure accurate and efficient management of blood bank data.

Employer: ElevateBio – Cell & Gene Therapy, Waltham, MA July 2022 to Dec 2022 Title: Co-op Bioinformatics Analyst, Next Generation Sequencing core team

• Developed a next-generation sequencing (NGS) bioinformatics pipeline on AWS EC2 and Linux using NextFlow, which included standard operating procedures

(SOPs), customizable workflows, and scripts for efficient data processing.

• Led an RNA-seq Transcriptome analysis project to study the early-stage differentiation of iPSCs into iT cells, handling everything from data collection to statistical analysis using DESe2 and interpretation, providing key biological insights in PowerPoint presentation.

• Managed single-cell RNA sequencing (ScRNA-seq) sample processing and data analysis, employing techniques like MultiQC, CellNet analysis, PCA, hierarchical clustering, UMAP and differential gene expression analysis to derive and share important findings with a Cellular engineering team.

• Improved data visualization and analysis through innovative techniques, such as correcting batch effects in RNA samples, and enhanced project collaboration and reproducibility by creating a GitHub repository and implementing secure AWS protocols for amplicon sequencing. Breast Cancer Subtype Prediction Using Proteome Dataset - Academic Project at Northeastern University March 2023

• 12,553 proteins and implemented feature selection techniques, including repeated lasso regression, to identify and select 38 proteins that accurately predict breast cancer subtype. Developed multi-class classification models (Random Forests, SVM, Neural Network) and achieved 79% accuracy with the SVM model; further improved performance to 85% by designing a stacked ensemble model combining individual models. Employer: CitiusTech Healthcare IT, Mumbai, India Sept 2016 to Oct 2019 Title: Associate Clinical Informatics

• Performed data mining, analysis, and created visualizations using SQL, Excel, and Power BI to summarize complex information into appropriate charts, tables, and figures, thereby conveying the meaning of the data to customers and decision-makers.

• Developed an RMM software tool that provides healthcare organizations with the flexibility to build and manage complex quality measures, including clinical, operational, financial, and ad-hoc rules.

• Improved the quality of insights for the team by conducting end-to-end analysis, which included sourcing and normalizing requisite data gathered from large and complex datasets and employing advanced statistical and machine learning methods for processing and analysis.

Contact this candidate