Digital CMC Regulatory Lifecycle Framework

Helping innovators, manufacturers and regulators build confidence that digital tools are reliable, transparent, proportionate to risk, and suitable for regulatory or manufacturing use.

Overview

Our Digital CMC Regulatory Lifecycle (DCRL) Framework helps innovators, manufacturers and regulators build confidence that digital tools are reliable, transparent, proportionate to risk, and suitable for regulatory or manufacturing use.

The framework supports the responsible adoption of digital and AI-enabled tools across pharmaceutical Chemistry, Manufacturing and Controls (CMC), helping accelerate safe, sustainable and efficient medicines development while protecting product quality, patient safety and regulatory trust.

By providing a common language and practical workflow for industry, academia and regulators, the framework helps reduce uncertainty around evidence expectations, model credibility, documentation and lifecycle oversight.

What it supports

The DCRL Framework provides guidance across:

  • Context of use definition

  • Risk-proportionate credibility assessment

  • Validation and uncertainty evaluation

  • Lifecycle management

  • Regulatory documentation readiness

  • Inspection and submission preparedness

Framework structure

The framework is built around three connected layers that support the development, assessment and regulatory implementation of digital predictive tools in CMC.

Together, these layers create a regulator-ready bridge between digital innovation and pharmaceutical quality assurance, supporting consistent development, assessment and implementation of digital tools in CMC.

  • The DCRL framework is supported by four enablers that facilitate practical adoption and shared understanding across stakeholders. These include 4 regulatory use cases to demonstrate real-world application, Virtual Expert for Regulatory Assistance (VERA), a collaborative Digital CMC Sandbox  for static credibility assessment with an interactive element and evidence generation, and targeted, modular and interactive training platforms (e.g. SkillsFactory) to build capability.

    Together, these enablers provide the consistent language, approach, templates, knowledge for regulators, industry and academia to translate principles into consistent, regulator-ready practice.

  • The workflow guides digital tools through the 4 phases of computational model lifecycles from early concept and risk analysis through development, validation, verification, uncertainty quantification, regulatory use and lifecycle management.

    10 detailed workflow stages help users define the question of interest, context of use, model type, model risk, data requirements, credibility evidence, regulatory documentation and post-deployment control.

  • The bottom layer anchors the framework in five core principles adapted for Digital CMC which are applicable to knowledge driven, data-driven (including AI and empirical models) and hybrid models:

    • Safety, security and robustness

    • Transparency and explainability

    • ‍Fairness and avoidance of bias

    • Accountability and governance

    • Contestability, human oversight and redress

    ‍While not all the principles are applicable to all model types, by collating them and adapting them for a CMC context, the principles provide a valuable aide-memoir resource to help users consider all aspects and ensure credibility assessments are regulatory-aligned.  These principles are aligned to collated global regulatory guidance, standards and scientific literature, including ICH guidance, FDA, EMA and MHRA expectations, ASME standards, and peer-reviewed best practice.‍ ‍

Interactive DCRL Framework

CMAC Digital Tool Assessment Framework — Interactive Diagram

An interactive version of the DCRL Framework has been developed to help users explore the principles, considerations and evidence expectations relevant to computational models across different stages of the workflow. The framework also provides links to key guidance, standards and supporting resources to support practical implementation.

This interactive tool enables the user to understand some of the detail and key references behind the main elements of the framework for computational model lifecycles in CMC. This tool supports users understand computational model implementation in a regulatory setting by looking through 3 lenses:  

  1. 5 principles for computational model development

  2. Workflow stages

  3. 4 lifecycle phases of computational model

Click on each workflow stage, each lifecycle phase and each principle for a short description of that element and key references. For each of the 5 principles of computational model development, users can click on the 4 lifecycle phases to learn how and when each principle applies in the lifecycle of a computational model. References support the user in regulatory-aligned model development, implementation and onward management.

Explore the interactive DCRL Framework to identify the principles, evidence expectations and considerations relevant to different computational models and stages of development.

Key concepts

The DCRL Framework is underpinned by the following core regulatory and scientific concepts that support the responsible development, assessment and implementation of digital tools in pharmaceutical CMC:

  • Risk-based implementation

  • Human accountability and oversight

  • Transparency and explainability

  • Robust data governance

  • Lifecycle management and control

  • Regulatory readiness and traceability

These concepts align with international guidance and emerging best practice, including expectations from ICH, EMA, FDA and MHRA.

Explore more outputs from the Digital CMC CERSI.

Digital CMC CERSI Home Page