Mutahwa Liberty

I’m a skilled and highly motivated bioinformatician with a strong foundation in machine learning, genomic data analysis, and computational biology. I help researchers and organizations make sense of complex biological data by building predictive models, analyzing sequencing data, and creating reproducible bioinformatics workflows that drive real-world impact.

My core focus areas include RNA-seq analysis, antimicrobial resistance (AMR) prediction, and tumor classification using supervised learning. I recently developed a machine learning pipeline to predict AMR patterns and implemented a complete RNA-seq analysis workflow for identifying differentially expressed genes in triple-negative breast cancer. I also built a random forest model that classified breast cancer tumors with 97% accuracy, showcasing my ability to apply artificial intelligence in biomedical research.

Technically, I’m proficient in Python, R, Bash scripting, and SQL, and I use tools such as DESeq2, BLAST, SAMtools, Bowtie, and STRINGdb. I work comfortably in Linux environments, leveraging Jupyter Notebooks and RMarkdown to create well-documented, reproducible research pipelines. I also easily navigate biological databases like NCBI, UniProt, and KEGG.

I am passionate about using data science to improve health outcomes in Africa and beyond. My goal is to support global health innovation by combining bioinformatics, machine learning, and public health insight to power research, surveillance, and evidence-based interventions.

Whether you need support with genomic data processing, machine learning for classification tasks, or visualizing biological insights in a clear and structured way, I bring both the technical expertise and research mindset to deliver high-impact results. I’m detail-oriented, responsive, and committed to delivering work that is accurate, meaningful, and aligned with your goals.

Let’s collaborate to transform your data into actionable knowledge.