Research focus
Statistical and machine-learning methods for health and biological data
I work across computational genomics, statistical modelling and clinical AI. The projects below are where I've applied those methods so far.
Academic CVI come from statistics and machine learning, and I use it on health and biological data across a range of areas. What ties it together is the method. I care about high-dimensional modelling, validation that doesn't cut corners, and building analyses that hold up on the populations and cohorts they get used on. That skill set moves well between bioinformatics and clinical data science, whether the data is genomic variants or longitudinal patient records. My main project, vartriage, is a Python library that classifies clinical variants from whole-genome VCF files. It can stream files with over four million variants in under 2 GB of memory, and I've benchmarked it against GIAB and ClinVar.
My research so far spans ACMG/AMP variant classification, estimating pharmacogenomic allele frequencies for populations that aren't in reference databases like gnomAD, and, more recently, safety mechanisms for multi-agent clinical LLM systems when the knowledge base shifts out from under them. I trained as a statistician before moving into production ML engineering, so I usually start from the methods and then build something that runs on real data.
I want to take this further with a PhD in computational biology, bioinformatics, or clinical and health data science. The specific projects below sit in genomics, but the methods are what matter to me, and they carry over to most problems where the data is high-dimensional and validation is hard: longitudinal patient trajectories, risk scoring, patient stratification, and ML that's meant to run in a clinical setting. My training is in statistics and ML rather than the wet lab, so I'm most useful on the computational and modelling side of a group's work, and I pick up new biological domains quickly.
Research projects
These are in genomics, where I have worked most, and they show the methods I would bring to a new problem.
vartriage: clinical variant interpretation
A Python pipeline that turns whole-genome and gene-panel VCF files into ranked candidate variants with ACMG/AMP-classified reports. It streams files with more than four million variants in under 2 GB of memory, and supports cohort analysis, trio inheritance analysis, structural-variant triage, mitochondrial-variant analysis, and remote tabix scoring. Benchmarked against GIAB and ClinVar. Published on PyPI.
AfriPharmaGen: pharmacogenomic interpretation for African populations
An agentic AI system for patient-level pharmacogenomic interpretation in African populations, where CPIC and DPWG guidelines are often absent or miscalibrated. It calls star alleles with African-aware haplotypes, reasons through polypharmacy interaction chains for TB, HIV, and malaria, and generates research reports with evidence chains and stated uncertainty for novel variants.
AfriPharmaGen Catalog
A curated pharmacogenomic dataset and reproducible analyses for sub-Saharan African populations, a group underrepresented in reference genomics databases. Published as a dataset on Zenodo.
Bayesian PGx allele-frequency estimation
Bayesian hierarchical allele-frequency estimation for ACMG BA1 and BS1 variant classification in populations underrepresented in gnomAD. It produces calibrated frequencies with stated uncertainty where sample sizes are small.
Ovarian cancer prediction (M.Sc. research)
Trained and benchmarked baseline classifiers against ensemble methods on a clinical registry of 349 patients, using mRMR feature selection to reduce 49 predictors to 20 biomarkers. Model families were compared with cross-validation across three train/test split ratios, tracked in MLflow.
Publications
Peer-reviewed articles
- Dere, I. G., Ahmad, G. B. M., Oduleye, O. O., Ojekunle, J. A., & Sulaiman, M. A. (2023). Assessment of Operational Performance of Inland Water Transport in Borgu Local Government Area of Niger State. Journal of Environmental Studies, 5(1), 213–230.link
- Usman, A., Sulaiman, M. A., & Abubakar, I. (2019). Trend of neonatal mortality in Nigeria from 1990 to 2017 using time series analysis. Journal of Applied Sciences & Environmental Management, 23(5), 865.link
Preprints
- Sulaiman, M. A., & Oyeyemi, B. F. (2026). A Curated Pharmacogenomic Allele Catalog for Sub-Saharan African Populations. medRxiv. DOI: 10.64898/2026.08.25.26361354.link
- Sulaiman, M. A., & Oyeyemi, B. F. (2026). Concordance of Automated ACMG Variant Classification with Expert-Curated Assertions: A Systematic Evaluation Using the ClinGen Evidence Repository. Research Square. DOI: 10.21203/rs.3.rs-10615801/v1.linkcode
- Sulaiman, M. A., Oyeyemi, B. F., & Sarafadeen, H. (2026). Architectural Safety Mechanisms for Multi-Agent Clinical LLM Systems Under Knowledge Base Distribution Shift. medRxiv. DOI: 10.64898/2026.07.31.26359439.link
Book chapters
- Oyeyemi, B. F., Sulaiman, M. A., Dauda, S. O., Oyewusi, H. A., Oladipo, O. O., & Adekilekun, H. A. (2026). From Gene Discovery to Clinical Applications: The Journey of Genomic Research. In Genomics and Precision Healthcare: Innovations, Applications and Challenges, pp. 39–66.link
- Oyeyemi, B. F., Sulaiman, M. A., Dauda, S. O., Oyewusi, H. A., Oladipo, O. O., & Adekilekun, H. A. (2026). From Targeted Quantification to Untargeted Metabolomics: Applications and Prospects in Clinical Diagnosis. In Computational Systems Biology for New Chemical Entities Bioprospection, 1st ed., pp. 22–41. CRC Press.link
Dataset
- Sulaiman, M. A., & Oyeyemi, B. F. (2026). AfriPharmaGen Catalog: A Curated Pharmacogenomic Dataset for Sub-Saharan African Populations. Zenodo. DOI: 10.5281/zenodo.21910084.link
Conference presentations
- Adekanmbi, O., Sulaiman, M. A., Olomu, G., Ezule, P., & Ahmed, O. (2025). Scenario Planning for Next Best Action in Edo State. DHIS2 Annual Conference, University of Oslo, Norway.
- Oyeyemi, B. F., & Sulaiman, M. A. (2025). Elucidating the Epigenetic Landscape of Breast Cancer: Insights from Gene Expression Profiling of GDS662 Dataset. Biotechnology Society of Nigeria 37th Annual International Conference.
Full record on ORCID .
Contact
If any of this overlaps with your group's work, reach me at abiodun.msulaiman@gmail.com.
Back to portfolio