Biostatistics - Data scientist & Bioinformatics enthusiast

Salut ! Je suis Fousseni SAMA

Explore my projects, read my blog, or get in touch.

👨‍💻

Overview

My journey in the field of data science began with a solid background in statistical engineering in Dakar, Senegal, where I acquired fundamental analytical skills at ENSAE. After gaining practical experience as a statistician and research assistant, I deepened my knowledge by applying statistics to biology and medicine through specialized training in biostatistics at Laval University. Since 2022, I have been putting these multidisciplinary skills into practice as a data analyst, working on projects at the intersection of biostatistics, bioinformatics, and machine learning. I use statistical modeling, genomic data analysis, and modern machine learning techniques to help solve complex problems in healthcare and life sciences research.

Skills

Python90%

R95%

Machine learning100%

Genomics60%

Tools & Technologies

PythonRTensorFlowPyTorchPandasBioconductorBLASTDockerSQLGit

Education

Master's in Biostatistics with thesis

Université Laval, Québec, Canada

January 2022 - January 2025

Advanced statistical methods, statistical modeling, high-dimensional data analysis, scientific programming (R, Python, Bash)

Bachelor's in Statistics: Statistical Engineering

ENSAE, Dakar, Senegal

September 2016 - August 2020

Probability, mathematical statistics, impact evaluation methods, propensity score and matching analysis, longitudinal and survival data analysis, machine learning predictive models for prognostic factor identification, big data, econometrics

Experiences

Data Manager and Data Analyst

ROSEPH | Québec, Québec, Canada

Feb 2022

Design and implementation of data collection and analysis pipelines for projects. Development of detailed statistical analysis plans (SAP) including missing data management. Statistical analysis of data and manipulation of large multi-source databases with R and Excel to ensure data integrity and quality. Creation of interactive dynamic dashboards (R Shiny) for communicating complex results to non-technical audiences. Development of automated reporting tools with R and Power Platform, reducing report generation time by nearly 40%. Close collaboration with multidisciplinary teams to define analytical needs and translate scientific questions into actionable statistical analyses.

Data Analyst

University | Québec, Québec, Canada

Fall 2023 - Winter 2024

Cleaning, validation and structuring of textual data from articles. Manipulation and harmonization of large multi-source databases with SQL, Python, Big Query and R to ensure data integrity and quality.

Data Analyst

University | Québec, Québec, Canada

Winter 2023

Processing and statistical analysis of education data for identifying determinants of school performance. Development of an interactive R Shiny interface for visualization and exploration of results.

Chief Statistician

CRES | Dakar, Senegal

February 2021 - January 2022

Design of stratified probabilistic sampling plans for multi-site observational studies ensuring representativeness of target populations. Development of standardized data collection protocols with electronic tools (CSPro) ensuring data quality and traceability. Supervision of collection, harmonization and structuring of multi-source databases from field surveys. Performance of bivariate and multivariate statistical analyses for identifying factors associated with outcomes of interest.

Statistician and Data Manager

ISRA | Dakar, Senegal

January 2021 - February 2021

Cleaning, harmonization and structuring of multi-source research data for subsequent statistical analyses. Application of anomaly detection and outlier detection techniques to ensure data integrity before analysis. Standardization of data formats according to predefined protocols to facilitate integration into centralized databases.

Data Manager and Data Analyst

StatInfo | Dakar, Senegal

September 2020 - December 2020

Design and implementation of field data collection systems with interviewer training. Development of sampling methods adapted to study objectives and operational constraints. Creation of data visualizations (graphs, tables) with R and Excel for communicating results to clients. Statistical processing of survey data with R and production of descriptive and inferential analyses.

Projects

Genome Analysis Tool

A comprehensive tool for analyzing genomic sequences with advanced ML algorithms.

PythonBioinformatics

View Project →

ML Genomics Pipeline

Machine learning pipeline for variant calling and disease prediction.

TensorFlowGenomics

View Project →

Data Visualization Dashboard

Interactive dashboard for exploring and visualizing genomic datasets.

JavaScriptReact

View Project →

View All Projects

Certifications

Ready to transform your data into knowledge? Let's discuss how I can help you achieve your goals.