Synergy Between Expert and Machine‐Learning Approaches Allows for Improved Retrosynthetic Planning

Abstract

When computers plan multistep syntheses, they can rely either on expert knowledge or information machine‐extracted from large reaction repositories. Both approaches suffer from imperfect functions evaluating reaction choices: expert functions are heuristics based on chemical intuition, whereas machine learning (ML) relies on neural networks (NNs) that can make meaningful predictions only about popular reaction types. This paper shows that expert and ML approaches can be synergistic—specifically, when NNs are trained on literature data matched onto high‐quality, expert‐coded reaction rules, they achieve higher synthetic accuracy than either of the methods alone and, importantly, can also handle rare/specialized reaction types.

Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions

“…[21][22][23][24][25] Significant effort has also been invested in computer-aided synthesis planning (CASP) 26 and the development of retrosynthetic design algorithms. [27][28][29][30] To supplement these tools, initial attempts have been made to predict reaction conditions in the forward direction based on the substrates and products involved. 31 Thus far, studies have focused on global datasets with millions of data points of mixed reaction types.…”

Combinatorial Synthesis of Oxysulfides in the Lanthanum–Bismuth-Copper System

“…The composition-dependent kinetics and thermodynamics limit the design of thermal processing protocols to obtain the desired thin film composition and phase. Models for predicting synthesis protocols are being developed, for example via machine learning from the literature for solid state materials 13 and combining machine learning with human insights 14 and symbolic AI 15 for molecular synthesis. While these powerful approaches will undoubtedly be useful in specific settings, the proposed synthesis of thin film oxysulfide alloys is not amenable to synthesis design by such models at this time, due to the lack of relevant training data, both with respect to the La-Bi-Cu oxysulfide chemistry and with respect to the thin film format of complex oxysulfides.…”

Computer-Assisted Planning of Hydroxychloroquine’s Syntheses Commencing from Inexpensive Substrates and Bypassing Patented Routes.

“…In addition, the failure of the worldwide logistics and supply chains that accompanies COVID-19 pandemic might render some key substrates temporarily unavailable, in effect delaying execution of the proven synthetic routes and calling for alternative synthetic solutions. Anticipating such complications, we harnessed the power of Chematica [8][9][10][11][12][13][14][15][16] -an experimentally-tested 9,10 platform for computer-assisted retrosynthesis of both known and unknown target molecules -to design syntheses of HCQ that would (1) commence from various inexpensive and popular starting materials (so that the syntheses minimize the abovementioned supply problems); (2) circumvent patented methodologies whenever possible 16 ; and (3) minimize the use of expensive methodologies and/or reagents. In the following, we briefly outline the computational methods underlying Chematica's retrosynthetic searches, summarize the known syntheses of HCQ, and then describe novel ones identified by Chematica to meet conditions (1)- (3).…”

“…Chematica is a sophisticated platform for fully automated design of pathways leading to arbitrary (i.e., both known and new) targets. The software combines elements of network theory 16,17 with an expert knowledge-base of synthetic transformations as well as multiple reaction-evaluation routines (based on machine learning, 11,12 quantum mechanics, 8,9 and molecular dynamics 9,13 ) to search over vast trees of synthetic possibilities. The reaction transforms (currently, ~ 100,000) are expert-coded based on the underlying reaction mechanisms and are broader than any specific literature precedents (for comparison with machine extraction of rules from reaction repositories, see 13 ).…”

“…Each rule specifies the scope of admissible substituents, accounts for stereo-and regiochemistry requirements, recognizes groups that must be protected under given reaction conditions, and identifies functionalities that are outright incompatible. The searches are guided by combinations of functions (either heuristic 8,9 or best-in-class AI-based 12 ) that score both synthetic positions as well as costs of individual reactions. The pathways identified by the program terminate in either commercially available chemicals (here, more than 200,000 molecules from Sigma-Aldrich catalogs, each with price per unit quantity; also see below for price re-scaling) or those already known in the literature (ca.…”