Komlan Atitey

Computational Biologist | Bioinformatics, Machine Learning & AI for Precision Medicine

Boston, City of Boston, SuffolkMember since November 16, 2025

Bayesian InferenceMachine LearningDeep LearningAgent-Based ModelingCancer Driver-Gene DiscoveryData VisualizationPython

About

Computational biologist with 7+ years of experience building Bayesian statistical models, machine learning pipelines, and large language model (LLM)-based tools to decode single-cell and spatial multi-omics data. Author of 14 peer-reviewed publications and developer of 7 open-source computational tools with 13,000+ combined downloads, applied to cancer driver-gene discovery, immune-response modeling, and drug/immunotherapy development. Proven track record leading multi-omics research programs at NIH and academic medical centers, mentoring graduate researchers, and securing competitive fellowships and scholarships.

Seeking a senior computational biology, bioinformatics, or AI/data science role in biotechnology, pharma, or research institutions.

Experience

Senior Research Associate - Case Western Reserve University School of Medicine, Department of Neurosciences - Cleveland, OH

(2026-03)

Lead the design, analysis, and interpretation of multi-omics, single-cell, and spatial datasets, delivering statistical expertise and building AI, machine learning, and LLM-based models to accelerate biomedical discovery.
Direct bioinformatics and AI workflow development and deliver hands-on training in computational biology, machine learning, and LLM applications to students, postdoctoral fellows, and research staff.

Research Fellow - Biostatistics and Computational Biology Branch (BCBB), National Institute of Environmental Health Sciences (NIEHS), NIH - Research Triangle Park, NC

(2020-11 - 2026-02)

Developed and applied hybrid statistical and Bayesian models including ODEs, agent-based modeling, and network inference to characterize immune dynamics, gene-gene interactions, and cancer driver identification within heterogeneous tumor microenvironments.
Designed and implemented computational frameworks integrating spatial, temporal, and multimodal single-cell data using Bayesian inference, Markov modeling, and high-dimensional visualization techniques.
Directed statistical integration and optimization strategies that improved interpretation and discovery from large-scale single-cell and spatial biomedical datasets.
Built and released 7 open-source computational tools (MIBCOVIS, DEGBOE, MMQE, GIBOOST, magicSubclonal, CancerTrace, PICDGI), collectively downloaded 13,000+ times by the research community.

Postdoctoral Research Associate - Department of Biochemistry, University of Nebraska-Lincoln - Lincoln, NE

(2019-10 - 2020-10)

Developed a mechanism-based, multiscale, multicellular model of the immune system incorporating ordinary differential equation (ODE) modeling to capture dynamic biological processes.
Integrated experimental data with computational models, combining ODE and agent-based modeling to simulate immune responses and disease progression.

Doctoral Researcher - College of Engineering, Swansea University - Swansea, United Kingdom

(2016-10 - 2019-10)

Conducted statistical analysis of gene expression dynamics in biological systems using Bayesian inference methods.
Modeled mRNA and protein distributions using stochastic processes combined with Bayesian modeling and posterior sampling techniques.
Quantified uncertainty in biochemical reaction rates and gene regulation via histogram fitting, Bayesian inference, stochastic modeling, and goodness-of-fit tests to infer gamma-distributed molecule counts.