282 – 282- Tools to Enable the Use of R by the Biopharmaceutical Industry in a Regulatory Setting
Developing a Risk-Based Approach for Assessing R Package Accuracy
Paulo Bargo
Janssen R&D
This contribution has the aim to discuss possible risk-based approaches to assess R package accuracy within a validated infrastructure. Ideas and suggestions reflect current thinking of the R Validation Hub working group, which is a cross-industry initiative funded by the R Consortium. R Validation Hub is a collaboration to support the adoption of R within a biopharmaceutical regulatory setting. In this setting, R is required to be part of a validated system, which encompasses software accuracy, reproducibility and traceability. We differentiate two types of R packages: Core and recommended packages are shipped with the basic installation. A rigorous software development lifecycle assures minimal risk. However, contributed packages may vary in their accuracy and development rigor, which could be assessed by various metrics. This cross-industry WG suggested several relevant quality metrics, and is developing an R package that provides a workflow to evaluate the quality of a set of R packages. This work may also be relevant in other regulated areas such as financial service industries and agriculture.