In the MMLI, advanced AI and machine learning (ML) methods will be developed and deployed in the context of four key thrusts:
Thrust 1: AI-Enabled Synthesis Planning
In this thrust we will develop an AI-enabled synthesis planning tool for molecule discovery and manufacturing called AlphaSynthesis. AlphaSynthesis uses AI to identify the most effective and automatable synthetic routes to explore both chemical and biological catalysts for the manufacture and discovery of new molecules. The unique features of AlphaSynthesis include the following firsts:
- synthesis framework, preferentially utilizing highly versatile building blocks and coupling reactions to maximize the efficiency, practicality and ease of small molecule making;
- AI-driven synthesis design operable in both forward and reverse modes, to enable discovery and manufacturing goals, respectively;
- integrating both chemical and biological catalysts;
- driven by a dynamic database of chemical and biological catalytic reactions, the content of which will be continuously optimized via AI-guided automated experimentation;
- building a chemical information knowledge base and database with efficient querying and search inferences for chemical and biological catalytic reactions.
Thrust 2: AI-Enabled Catalyst Discovery
The AlphaSynthesis can be used for both manufacturing of target molecules with known functions (reverse synthesis) and discovery of molecules with new functions (forward synthesis). In both cases, identifying catalysts is critical to the success of implementing the synthetic routes. Therefore, the main goal of Thrust 2 is to develop new AI algorithms or approaches to discover catalysts that are required to implement the synthetic routes designed by AlphaSynthesis.
Thrust 3: Al-Enabled Manufacturing of Target Molecules and Materials
Inspired by exciting recent advances in molecule synthesis, the main goals of Thrust 3 are (1) to validate and test the AI-driven synthesis planning tool AlphaSynthesis (Thrust 1) and the related AI tools for catalyst design and optimization (Thrust 2), and (2) to develop AI-driven tools for end-to-end optimization of entire synthesis plans. We will explore the retrosynthesis platform of AlphaSynthesis (reverse synthesis) to design synthetic routes for manufacturing of the following three target molecules with known functions: C2’epi amphotericin B (a novel potent and non-toxic antifungal drug candidate), artemisinin (a critical antimalaria drug), and Millad NX 8000 (an environmentally advantageous colorless, odorless thermoplastic clarifier for polypropylene). These routes will explore both chemical catalysis and biological catalysis.
Thrust 4: AlphaSynthesis Enabled Discovery of Novel Molecules and Materials
Organic photovoltaics (OPV) are next-generation devices for harvesting renewable energy that are becomingly increasingly desired over traditional silicon solar cells. The two primary challenges preventing the widespread adoption of OPV relative to silicon-based solar cells are inferior power conversion efficiency and apparent instability to sunlight. Therefore, the main goal of Thrust 4 is to develop new machine learning tools to guide the discovery of highly efficient and indefinitely stable organic photovoltaics via automated synthesis, manufacture, and testing at the device level.