👋 Hello and Welcome! 😊

Personal Portfolio

This is my personal portfolio. Below you can explore my background, research and self-guided projects, and experience.

About Me 🔎

Thank you for visiting my portfolio. My name is Lois Randolph, and I am a bioinformatician with a background in biology and a strong focus on computational and data-driven approaches to biomedical research. I was born and raised in San Antonio, Texas, and earned my B.S. in Biology with a minor in Mathematics from the University of Texas at San Antonio.

Following my undergraduate training, I completed a Postbacclaureate Research Education Program (PREP) at the University of Texas Health Science Center at San Antonio, where I gained intensive research experience and preparation for graduate school. I than earned my M.S. in Cancer Biology from the UT Health San Antonio Graduate School of Biomedical Sciences.

Although I am a biologist by training, I am a programmer at heart, with a strong passion for precision medicine, computational biology, data science, machine learning, AI, and data engineering. I am largely self-taugh in Python, SQL, Linux, and web development tools. I enjoy building predictive models for biomarker discovery, developing automated and reproducible data pipelines, and managing tools and databases that support data storage, processing, and quality control at scale.

Education 🎓

Skills

Programming Languages

Machine Learning

Deep Learning

Data Engineering & Databases

Worflow & Reproducibility

Experience

Bioinformatics Researcher

UT Health Science Center | Pediatrics · Dec. 2023–Present

• Lead the development of early diagnostic and prognostic models for neonatal and pediatric care to identify risk of disease onset and clinical outcomes.
• Integrated heterogeneous datasets including EMR, bulk RNA-seq, single-cell RNA-seq, spatial transcriptomics, methylation, microbiome, proteomics, and other omics or clinical data.
• Developed and applied statistical models ranging from simple linear regressions to mixed-effects frameworks on both static and longitudinal datasets, rigorously controlling for covariates and batch effects.
• Reproducible, containerized workflows that leverage parallel processing optimizing data handling, harmonization, multicohort meta-analyses, and regression and classification tasks.
• Unsupervised machine learning (exploratory analyses) and supervised machine learning.
• Refined single-cell type annotations and integrated single-cell with spatial transcriptomics mapping predicted cell types to lung spatial landscape.
• Version control using Git.
• Supported clinical decision-making by translating complex molecular and clinical data into actionable insights for risk assessment and patient stratification.
• Review research grants for methodological rigor and data integrity; conducted exploratory analyses to identify errors and gaps prior to submission.

Graduate Research Assistant

UT Health Science Center | Integrated Biomedical Sciences · Aug. 2021– Dec. 2023

• Processed raw bulk RNA-seq FASTQ files; quality assessment, trimming, alignment to mouse (mm9) and human reference genomes, and generation of gene-level expression count matrices.
• Processed raw single-cell RNA-seq FASTQ files to gene-by-cell expression matrices; demultiplexing, barcode and UMI processing, quality control, read alignment to reference genomes or transcriptomes, and feature count matrix generation.
• Computational analysis of EC359 treatment response across TNBC, inflammatory breast cancer (IBC), and Type II endometrial cancer (ECa) models (e.g., in vitro, xenograft, and PD-xenograft models).
• Performed transcriptomic profiling and differential expression modeling to characterize the effects of LIFR inhibition in biological pathways.
• Analyzed and quantified drug efficacy (t-test, one- and two-way ANOVA), treatment-response stratification, and immunohistochemistry images.

Intern

Baylor College of Medicine | Human Genome Sequencing Center · June 2021 - Aug. 2021

• Linked and organized data from over 10 entity types, including Allele Molecular Consequence, Variant, and Population Allele Frequency enhancing the curation process for ClinGen.
• Maintained and updated the LDH, ensuring availability of 1+ million data points in a highly accessible format for researchers and curators.
• Translated 1000+ lines of Ruby code into JavaScript, enabling smooth data parsing and interaction with APIs across multiple domains.
• Developed and optimized data pipelines to transform and aggregate gene and variant information, improving the efficiency of data retrieval and supporting 500+ ClinGen curation projects.

PREP Scholar

UT Health Science Center | Biochemical Mechanisms in Medicine · June 2020 - June 2021

• Designed custom code from ImageJ-processed microscopy images to identify regions of interest capturing colocalized proteins for 100+ images, analyzing multi color channels to pinpoint and quantify protein interactions.
• Image processing with Python tools to enhance microscopy images, improving quality and contrast, identifying samples, annotating labels, and tailoring visuals for professional reporting.

Fun Facts 💫

• Your friendly neighborhood bioinformatician 🖥️
• Avid Rollerblader 🛼
• Rubik’s Cube Enthusiast 🤓
• Unapologetically an anime fanatic 🥷
• Probably dancing while you’re reading this 💃🏾

Connect with me

Email LinkedIn GitHub