APPA : Agentic Preformulation Pathway Assistant

Julius Lange, Leonid Komissarov, Nicole Wyttenbach, Andrea Anelli

Keywords: LLM, Preformulation Sciences, Drug Development, Pharmaceutical Research, Agentic Workflows, Machine Learning

TL;DR: An AI formulation agent that accelerates drug development. It combines expert knowledge, data, and ML to predict drug properties and suggest optimal formulations, streamlining the path to new medicines.

Abstract:

The design and development of effective drug formulations is a critical process in pharmaceutical research, particularly for small molecule active pharmaceutical ingredients.
This paper introduces a novel agentic preformulation pathway assistant (APPA),
leveraging large language models coupled to experimental databases and a suite of machine learning models to streamline the preformulation process of drug candidates.
APPA successfully integrates domain expertise from scientific publications, databases holding experimental results, and machine learning predictors to reason and propose optimal preformulation strategies based on the current evidence.
This results in case-specific user guidance for the developability assessment of a new drug and directs towards the most promising experimental route,
significantly reducing the time and resources required for the manual collection and analysis of existing evidence.
The approach aims to accelerate the transition of promising compounds from discovery to preclinical and clinical testing.

Submission Number: 22