Computational biology and data science employing R, Python, and MATLAB — to implement big data analysis in the biological sciences, to monitor students' learning and performance in the classroom, and to apply machine learning methods.
Each project links to its code and a written report so the analysis can be reproduced end to end.
SELDI-TOF mass spectrometry from blood samples of two groups — ovarian cancer vs. control — analyzed in MATLAB. Scripts pre-process the data, plot the groups' spectrograms, and rank features with a two-way t-statistic. Data from the FDA-NCI Clinical Proteomics Program.
Transcriptome sequencing (RNA-seq) data from human post-mortem brains, sequenced on an Illumina platform and retrieved from a public database. Reads were aligned, quality-controlled, and quantified; exploratory analysis and fitted statistical models identified genes differentially expressed between fetal and adult brains — an example of reproducible research in genomic sciences.
Evidence-based decisions in the classroom are essential for implementing adjustments in students' learning. This project shares data science approaches, projects, and peer-reviewed publications that support pedagogical interventions in biological sciences courses.
Pitch for a Shiny app designed to predict the next words following the user's input.
Consulting on data science, machine learning, and scientific workflow implementation is offered through FERMLLC Ventures, independently of my academic appointment.
