Reaction mechanism search tools have demonstrated the ability to provide insights into likely products and rate-limiting steps of reacting systems. However, reactions involving several concerted bond changes - as can be found in many key steps of natural product synthesis - can complicate the search process. To mitigate these complications, we present a mechanism search strategy particularly suited to help expedite exploration of an exemplary family of such complex reactions, cyclizations. We provide a cost-effective strategy for identifying relevant elementary reaction steps by combining graph-based enumeration schemes and machine learning techniques for intermediate filtering. Key to this approach is our use of a neural network potential (NNP), AIMNet2-rxn, for computational evaluation of each candidate reaction pathway. In this article, we evaluate the NNP's ability to estimate activation energies, demonstrate the correct anticipation of stereoselectivity, and recapitulate complex enabling steps in natural product synthesis.

Identifying minimum-energy paths (MEPs) is crucial for understanding chemical reaction mechanisms but remains computationally demanding. We introduce MEPIN, a scalable machine-learning method for efficiently predicting MEPs from reactant and product configurations, without relying on transition-state geometries or pre-optimized reaction paths during training. The task is defined as predicting deviations from geometric interpolations along reaction coordinates. We address this task with a continuous reaction path model based on a symmetry-broken equivariant neural network that generates a flexible number of intermediate structures. The model is trained using an energy-based objective, with efficiency enhanced by incorporating geometric priors from geodesic interpolation as initial interpolations or pre-training objectives. Our approach generalizes across diverse chemical reactions and achieves accurate alignment with reference intrinsic reaction coordinates, as demonstrated on various small molecule reactions and [3+2] cycloadditions. Our method enables the exploration of large chemical reaction spaces with efficient, data-driven predictions of reaction pathways.

Identifying reliable synthesis pathways in materials chemistry is a complex task, particularly in polymer science, due to the intricate and often non-unique nomenclature of macromolecules. To address this challenge, we propose an agent system that integrates large language models (LLMs) and knowledge graphs (KGs). By leveraging LLMs' powerful capabilities for extracting and recognizing chemical substance names, and storing the extracted data in a structured knowledge graph, our system fully automates the retrieval of relevant literatures, extraction of reaction data, database querying, construction of retrosynthetic pathway trees, further expansion through the retrieval of additional literature and recommendation of optimal reaction pathways. A novel Multi-branched Reaction Pathway Search (MBRPS) algorithm enables the exploration of all pathways, with a particular focus on multi-branched ones, helping LLMs overcome weak reasoning in multi-branched paths. This work represents the first attempt to develop a fully automated retrosynthesis planning agent tailored specially for macromolecules powered by LLMs. Applied to polyimide synthesis, our new approach constructs a retrosynthetic pathway tree with hundreds of pathways and recommends optimized routes, including both known and novel pathways, demonstrating its effectiveness and potential for broader applications.

Mapping out reaction pathways and their corresponding activation barriers is a significant aspect of molecular simulation. Given their inherent complexity and nonlinearity, even generating a initial guess of these paths remains a challenging problem. Presented in this paper is an innovative approach that utilizes neural networks to generate initial guess for these reaction pathways. The proposed method is initiated by inputting the coordinates of the initial state, followed by progressive alterations to its structure. This iterative process culminates in the generation of the approximate representation of the reaction path and the coordinates of the final state. The application of this method extends to complex reaction pathways illustrated by organic reactions. Training was executed on the Transition1x dataset, an organic reaction pathway dataset. The results revealed generation of reactions that bore substantial similarities with the corresponding test data. The method's flexibility allows for reactions to be generated either to conform to predetermined conditions or in a randomized manner.

The exploration of transition state (TS) geometries is crucial for elucidating chemical reaction mechanisms and modeling their kinetics. Recently, machine learning (ML) models have shown remarkable performance for prediction of TS geometries. However, they require 3D conformations of reactants and products often with their appropriate orientations as input, which demands substantial efforts and computational cost. Here, we propose a generative approach based on the stochastic diffusion method, namely TSDiff, for prediction of TS geometries just from 2D molecular graphs. TSDiff outperformed the existing ML models with 3D geometries in terms of both accuracy and efficiency. Moreover, it enables to sample various TS conformations, because it learned the distribution of TS geometries for diverse reactions in training. Thus, TSDiff was able to find more favorable reaction pathways with lower barrier heights than those in the reference database. These results demonstrate that TSDiff shows promising potential for an efficient and reliable TS exploration.

The inference of chemical reaction networks is an important task in understanding the chemical processes in life sciences and environment. Yet, only a few reaction systems are well-understood due to a large number of important reaction pathways involved but still unknown. Revealing unknown reaction pathways is an important task for scientific discovery that takes decades and requires lots of expert knowledge. This work presents a neural network approach for discovering unknown reaction pathways from concentration time series data. The neural network denoted as Chemical Reaction Neural Network (CRNN), is designed to be equivalent to chemical reaction networks by following the fundamental physics laws of the Law of Mass Action and Arrhenius Law. The CRNN is physically interpretable, and its weights correspond to the reaction pathways and rate constants of the chemical reaction network. Then, inferencing the reaction pathways and the rate constants are accomplished by training the equivalent CRNN via stochastic gradient descent. The approach precludes the need for expert knowledge in proposing candidate reactions, such that the inference is autonomous and applicable to new systems for which there is no existing empirical knowledge to propose reaction pathways. The physical interpretability also makes the CRNN not only capable of fitting the data for a given system but also developing knowledge of unknown pathways that could be generalized to similar chemical systems. Finally, the approach is applied to several chemical systems in chemical engineering and biochemistry to demonstrate its robustness and generality.

Akihiro Kishimoto is a research staff member at IBM Research – Ireland working on a range of projects in artificial intelligence, parallel and distributed computing and search. His interest in these technical fields grew from his passion for board games. And while a student at the University of Tokyo, he and three of his fellow classmates designed ISshogi, a program to play the incredibly complex (and ancient) Japanese board game, Shogi. ISshogi won the World Computer Shogi Championships four times from 1997-2005. While studying AI at the University of Alberta, Akihiro was a member of the GAMES group (Game-playing, Analytical methods, Minimax search and Empirical Studies) in the Department of Computing Science, and worked with Jonathan Schaeffer and others to solve Checkers.

A fundamental question in AI is what mechanisms suffice for computer programs to make scientific discoveries. My Ph.D. thesis addresses this question by automating the following scientific task to a significant extent: Given observed data about a particular chemical reaction, discover the underlying set of reaction steps from starting materials to products, that is, elucidate the reaction pathway.