Skip to main content

Projects

Data science and bioinformatics projects by Devon Allies: RNA-seq, TB biomarkers, public health analyses and Databricks pipelines in R and Python.

Analyses, pipelines and models across genomics, clinical research, public health and finance. Use the tags on the right to filter by topic or tool, or search above the cards.

Credit Risk Pipeline on Databricks
Finance
Machine learning
Data engineering
Databricks
Python

A bronze/silver/gold lakehouse pipeline on Databricks that cleans messy lending data, builds a leakage-free loan table and trains MLflow-tracked default models, with a…

2026

Databricks Data Pipeline: Simulated BAL Study
Clinical research
Machine learning
Data engineering
Databricks
Python

Bronze, silver and gold Delta tables, tested cleaning functions, MLflow model tracking and a Streamlit demo, built on simulated clinical data.

2026

Compartmental TB Diagnostics: A Simulated BAL Cytokine Cohort
Clinical research
Statistics
R

Compartmental TB diagnostics on a simulated BAL cytokine cohort: cleaning and statistics in R, building towards a 3-class classifier for active TB, LTBI and uninfected.

2026

Differential Expression Analysis of Chromosome X RNA-seq Data
Bioinformatics
Statistics
R

Sex-based differential expression on chromosome X from 12 paired-end RNA-seq samples, using a Nextflow pipeline with HISAT2 and StringTie, and Ballgown in R.

2026

Global Tuberculosis Trends, 2000–2024
Public health
Exploratory analysis
Machine learning
Python

Exploratory analysis of global tuberculosis indicators from 2000 to 2024: South Africa’s trends, drivers of TB burden, and a forecast against the End TB 2030 targets.

2026

Using R and Python Together in Data Science
Bioinformatics
Machine learning
R
Python

A cross-language workflow on high-dimensional gene expression data: PCA with Python’s scikit-learn and statistical tables with R’s gtsummary, linked by reticulate.

2026

COVID-19 Blood Counts and Patient Outcomes
Public health
Exploratory analysis
Statistics
Python
R

Exploratory data analysis of complete blood count data from COVID-19 patients in Bangladesh, comparing patient outcomes by age, sex and blood markers in Python and R.

2026

A Nextflow Pipeline for Whole-Genome Variant Calling
Bioinformatics
Data engineering
Nextflow

A modular Nextflow DSL2 pipeline that takes paired-end whole-genome sequencing reads to joint-called, filtered variants with BWA-MEM, SAMtools and GATK, built to run on a…

2024
No matching items