Thinking out loud
about R&D data

Réflexions sur
la data en R&D

Articles on statistics, data engineering, and AI applied to pharmaceutical, biotech, and cosmetic research. In French and English.

Coming soon

How to build a reproducible R&D data pipeline from scratch

Excel and ad-hoc scripts are not a pipeline. A practical guide to Dagster, dbt, and Docker for research teams.

Coming soon

Graph machine learning for molecular similarity in cosmetic formulation

How metapath2vec embeddings on heterogeneous molecular graphs enable smarter raw material substitution.

Coming soon

CDISC in practice: common mistakes and how to avoid them

A practitioner's guide to SDTM/ADaM implementation: naming conventions, controlled terminology, and automated validation.

Coming soon

Survival analysis for cosmetic panel studies: beyond Kaplan-Meier

When Kaplan-Meier is not enough: stratified Cox regression, time-varying covariates, and competing risks in wear longevity studies.

Coming soon

Building R Shiny tools that non-statisticians actually use

UX principles, sensible defaults, and automated reporting patterns that turn Shiny apps into real decision-support tools.

Coming soon

EU 655/2013 and cosmetic claims: what your statistician needs to know

A critical review of claim substantiation requirements, SAP design, and the methodological traps the regulation does not protect you from.

No articles match your search.

Aucun article ne correspond à votre recherche.