Alboukadel Kassambara
Computational Biologist & Data Science Expert
Discover the journey of Alboukadel Kassambara, a leading expert in computational biology who bridges advanced data science, machine learning, bioinformatics and biostatistics to drive innovation research, biomarker discovery, precision medicine, and open-access learning resources.
Professional Profile
Alboukadel Kassambara, PhD, is a leading computational biologist and data scientist with over a decade of experience in bioinformatics pipeline development, machine learning, biostatistics, and multi-omics data integration.
His work focuses on translating large-scale biological and clinical data into actionable insights, driving biomarker discovery, prognostic modeling, and digital pathology applications in precision medicine.
Founder of datanovia.com and STHDA.com, Alboukadel is passionate about democratizing data science through open-source tools and comprehensive learning resources.
Core Expertise
Technical Capabilities
- Bioinformatics workflow automation and reproducible pipelines
- AI and Machine Learning applied to genomics, transcriptomics and digital pathology
- Spatial analytics and AI-powered digital pathology for immune profiling and biomarker discovery
- Immuno-oncology biomarker discovery and multi-omics data integration
- Prognostic and predictive signature modeling
- Biostatistical analysis and visualization
- Leadership and mentoring of cross-functional scientific teams, including AI engineers and bioinformaticians
Professional Journey
Current Role
Associate Director, Computational Biology at Veracyte (2023 - Present)
- Leading AI/machine learning-driven discovery research
- Developing predictive biomarker signatures for patient stratification
- Implementing deep learning models for immune infiltration prediction
- Supervising cross-disciplinary computational biology projects
Significant Achievements
- Creating multi-omics data integration framework for patient stratification and prognostic modeling
- Developing robust cfRNA prognostic signatures for clinical decision-making
- Co-developing Immunoscore-IC patented method (US20250035635A1)
- Predicting immune infiltration (Immunoscore-AI) in breast cancer using deep learning
- Oral presenter at European Congress of Digital Pathology (ECDP) 2024 on interpretable AI and Immunoscore-AI
Academic Background
- PhD in Cancer Biology & Bioinformatics (2007-2011)
- INSERM, Montpellier, France
- Specialized in identifying biomarkers and potential therapeutic targets in multiple myeloma
- MSc in Health & Biology (2005–2007)
- University Joseph Fourier, Grenoble, France
Open-Source Contributions
Alboukadel is a prolific contributor to the R programming ecosystem and the founder of many widely-used open-source tools:
ggpubr
Create publication-ready plots with minimal code
factoextra
Streamline multivariate data analysis and visualization
survminer
Enhance survival analysis with elegant visualizations
rstatix
Perform statistical tests with a consistent, pipe-friendly syntax
Research Impact
- 40+ peer-reviewed publications (ResearchGate)
- 4 patents in biomarker discovery and immunotherapy (Google Patents)
- Key speaker at international conferences, including the European Congress of Digital Pathology (ECDP2024)
Selected Publications
Alboukadel’s scientific contributions include impactful publications at the intersection of immuno-oncology, multi-omics data integration, transcriptomics and cancer biology.
- Immunoscore immune checkpoint and prediction of immunotherapy efficacy in NSCLC. EBioMedicine, 2023. Display the article
- Tumor lymphocyte infiltration and immune-checkpoint inhibitors in metastatic colorectal cancer (AtezoTRIBE study). Journal for Immunotherapy of Cancer, 2023. Display the article
- Upfront FOLFOXIRI plus bevacizumab with or without atezolizumab in metastatic colorectal cancer (AtezoTRIBE phase 2 trial). The Lancet Oncology, 2023. Display the article
- Veracyte Biopharma Atlas: machine learning to capture tumor immune contexture. Cancer Research, AACR Poster, 2023. Display the article
- RNA-Seq-based prognostic score in multiple myeloma. Journal of Personalized Medicine, 2021. Display the article
- Mutational landscape in multiple myeloma cell lines. Theranostics, 2019. Display the article
- RNA-sequencing data-driven dissection of human plasma cell differentiation reveals new potential transcription regulators. Frontiers in Immunology, 2018. Display the article
- miRNA and transcriptional regulation in plasma cell differentiation. Nucleic Acids Research, 2017. Display the article
- DNA repair score predicts survival in multiple myeloma. Oncotarget, 2014. Display the article
Training & Collaborations
Alboukadel has actively collaborated with leading academic and research institutions across Europe and the United States, contributing to multiple projects in oncology, immunology, and bioinformatics.
- Weill Cornell Medical College, New York, USA — Research collaborations and training on NGS data analysis (2015 & 2016)
- European Molecular Biology Laboratory (EMBL), Heidelberg, Germany — Training on NGS (2014)
- German Multiple Myeloma Group, Heidelberg — Long-term research collaboration (2007–2014)
- Multiple Myeloma European OVER-MYR project — Collaborative research project for overcoming clinical relapse in multiple myeloma (2012–2015)
- SIRIC Montpellier Cancer, Montpellier — Cancer research network collaboration (2013–2014)
Publications and Resources
Books & Tutorials:
- Machine Learning Essentials
- Practical Guide to Cluster Analysis in R
- R Graphics Essentials for Great Data Visualization
- View all books
Founding Platforms:
- datanovia.com — Tutorials in R, Python, Machine Learning, Bioinformatics and bioinformatics
- sthda.com — R-based statistical guides
Connect and Collaborate
Alboukadel Kassambara continues to contribute to the evolving field of computational biology and data science, with his work aiming to translate complex biological data into meaningful insights that support medical innovation, precision medicine, and AI-powered digital pathology.