Skip to content
Datanovia

Computational Biologist · Creator of ggpubr & rstatix · ~50M CRAN downloads

Alboukadel Kassambara, PhD

Alboukadel Kassambara, PhD, is a computational biologist and R developer whose packages — ggpubr, rstatix, factoextra, survminer — have been downloaded some 50 million times from CRAN. Founder of Datanovia and STHDA, he has since 2025 worked as an independent computational-biology consultant and is the founder of Helomnix, a computational-oncology venture in hematologic oncology.

Portrait of Alboukadel Kassambara, PhD
A ggpubr boxplot comparing tooth length across three vitamin-C doses (0.5, 1 and 2 mg per day), with jittered raw points, a large dot marking each group mean, and significance brackets. Tooth length rises with dose and the differences are highly significant (Kruskal–Wallis p = 1.5e-9).
Made with ggpubr — the package he wrote, run 20 million times.

The proof

times the R community has run his code

50,000,000

times the R community has run his code · ≈ 640K downloads / month

as of July 2026, verified via cranlogs

From cancer genomics to your R console

For more than a decade, Alboukadel Kassambara has worked where biology meets computation — a through-line of multiple-myeloma research that runs from his PhD on prognostic biomarkers to RNA-seq risk signatures, spatial immune profiling, and AI-driven digital pathology. The problem was always the same: turning large, messy, multi-omics datasets into decisions researchers and clinicians can trust.

Along the way he open-sourced the tooling he needed himself. ggpubr, rstatix, factoextra and survminer began as the code that made his own analyses publication-ready and reproducible; today they are everyday tools in labs worldwide. He taught the same recipes — first freely on STHDA — Statistical Tools for High-throughput Data Analysis — then on Datanovia — in the practical, output-first voice that made his guides a fixture for R users.

Today he works as an independent computational-biology consultant and is the founder of Helomnix, a computational-oncology venture — while Datanovia carries the teaching mission forward: the tools, and the lessons that teach them, in one reproducible place.

I build the tools I wish I'd had at the bench — then I teach them, for free, to everyone who is now where I once was.
Alboukadel Kassambara

The R packages

Six open-source R packages, authored and maintained by Alboukadel — the same tools the lessons on this platform teach. Each one turns a fiddly analysis into a few readable lines.

  • ggpubr

    20.0Mdownloads

    Publication-ready ggplot2 plots, with the stats drawn on.

    Learn it
  • rstatix

    16.6Mdownloads

    Pipe-friendly statistical tests with tidy results.

    Learn it
  • factoextra

    7.6Mdownloads

    Multivariate analysis and visualization — PCA, clustering.

    Learn it
  • survminer

    3.2Mdownloads

    Survival-analysis curves that read like a clinical figure.

    Learn it
  • ggcorrplot

    2.3Mdownloads

    Correlation matrices, visualized clearly.

    Learn it
  • datarium

    0.41Mdownloads

    Clean teaching datasets for statistics and ML.

    Learn it

Alboukadel is the lead author and maintainer of these packages on CRAN. Download counts are all-time totals from cranlogs (July 2026).

Browse all package docs

The practical guides

Alboukadel's hands-on books distilled real analysis workflows into recipes you can run. On Datanovia they are single-sourced into free, runnable lessons — the book is the offline render, the lessons are always live.

Every guide is single-sourced into free, runnable lessons on this platform — the book is the offline render, the lessons are always live.

Research & academia

Today

Independent computational-biology consultant and founder of Helomnix, a computational-oncology venture in hematologic oncology; founder of Datanovia and STHDA.

Career highlight

Nearly seven years in clinical genomics in Marseille, France — R&D Scientist at HalioDx (2018–2021), then Senior Manager (2021–2022) and Associate Director, Computational Biology (2023–2025) at Veracyte after it acquired HalioDx — working on AI/ML biomarker discovery, immune-infiltration deep learning, and AI-driven digital pathology. Earlier, at INSERM, then CHRU Montpellier (2012–2018), he built GenomicScape.

Education

  1. 2007–2011

    PhD, Cancer Biology & Bioinformatics — With Honors

    University of Montpellier (research in an INSERM laboratory), France — biomarkers and therapeutic targets in multiple myeloma.

  2. 2005–2007

    MSc, Health & Biology

    University Joseph Fourier, Grenoble, France.

Selected publications

A decade of peer-reviewed work at the intersection of immuno-oncology, multi-omics integration, and cancer biology. Alboukadel is a named author on each — and first author on several.

See the full list on ResearchGate · ORCID

Patents & talks

Named inventor on four patent applications in biomarker discovery and immunotherapy-response prediction, including the published application US20250035635A1 (Immunoscore-IC). Presented at the European Congress of Digital Pathology (ECDP) 2024 on interpretable AI and Immunoscore-AI.

View patents on Google Patents

GenomicScape

A web tool for gene-expression analysis of the plasma-cell lineage, built during his years at CHRU Montpellier and published in PLOS Computational Biology (2015, Kassambara et al.).

Read the paper (PLOS Comp. Biol.)
A survminer Kaplan–Meier survival curve comparing male and female patients in the NCCTG lung-cancer cohort, with 95% confidence bands, median-survival reference lines, a log-rank p = 0.0013, and a number-at-risk table below the plot.
A survminer Kaplan–Meier curve — the survival-analysis toolkit he wrote, of the kind used in the oncology work he publishes.

Teaching & platforms

Alboukadel founded two open-access learning resources. STHDA — Statistical Tools for High-throughput Data Analysis — is where much of the R community first met him: free, practical statistics and R guides. Datanovia carries that mission forward as this platform — reproducible, interactive lessons, home of the AI tutor Prova.

Collaborations: Weill Cornell Medical College (NGS training, 2015–2016) · EMBL Heidelberg (2014) · German Multiple Myeloma Group (2007–2014) · OVER-MYR (2012–2015) · SIRIC Montpellier Cancer (2013–2014).

Why this matters for you

Every lesson on Datanovia is written by the person who built the tools it teaches and who uses them daily on real clinical and genomic data. The code isn't just correct — it's the code a practitioner actually ships, and Prova keeps every answer honest, because the runtime is the judge.

Learn data science the way the work actually happens

Free, runnable lessons for the global R & Python community — start today.