{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/151666"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/151666","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Predicting Chemical Reactions at the MechanisticLevel through Deep Reinforcement Learning","abstract":"Reaction prediction is a fundamental problem in chemistry. Previous work has mostly targeted chemical product prediction only, but did not elucidate any mechanisms or elementary steps from which the reaction proceeds. Here, we attempt to predict chemical mechanisms via deep reinforcement learning. We first define a new type of graph molecular representation that can better keep track of electron flow and can be generalized to non-traditional bonding, such as 3- center-4-electron bonds. We then define a molecular environment Markov Decision Process (MDP) that codifies the allowed mechanistic steps and evaluates them by utilizing a thermodynamic energy oracle as the reward function. To solve this environment, we build a graph neural network-based policy and value network, where the policy network is first pre-trained on an open database of elementary radical reactions (RMechDB). Then, we use proximal policy optimization (PPO) to fine-tune the model and predict reasonable reaction mechanisms for two case studies: a radical oxidation of the terpene limonene, and a radical cyclization cascade in the synthesis of hirsutene.","abstract_html":"Reaction prediction is a fundamental problem in chemistry. Previous work has mostly targeted chemical product prediction only, but did not elucidate any mechanisms or elementary steps from which the reaction proceeds. Here, we attempt to predict chemical mechanisms via deep reinforcement learning. We first define a new type of graph molecular representation that can better keep track of electron flow and can be generalized to non-traditional bonding, such as 3- center-4-electron bonds. We then define a molecular environment Markov Decision Process (MDP) that codifies the allowed mechanistic steps and evaluates them by utilizing a thermodynamic energy oracle as the reward function. To solve this environment, we build a graph neural network-based policy and value network, where the policy network is first pre-trained on an open database of elementary radical reactions (RMechDB). Then, we use proximal policy optimization (PPO) to fine-tune the model and predict reasonable reaction mechanisms for two case studies: a radical oxidation of the terpene limonene, and a radical cyclization cascade in the synthesis of hirsutene.","abstract_has_math":false,"creators":["Jin, Edward H."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Coley, Connor W."],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-06","date_published":"2023-06","updated_at":"2026-07-22T22:21:29Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/151666","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Coley, Connor W."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Jin, Edward H."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-07-31T19:57:30Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-07-31T19:57:30Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-06"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/151666"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Reaction prediction is a fundamental problem in chemistry. Previous work has mostly targeted chemical product prediction only, but did not elucidate any mechanisms or elementary steps from which the reaction proceeds. Here, we attempt to predict chemical mechanisms via deep reinforcement learning. We first define a new type of graph molecular representation that can better keep track of electron flow and can be generalized to non-traditional bonding, such as 3- center-4-electron bonds. We then define a molecular environment Markov Decision Process (MDP) that codifies the allowed mechanistic steps and evaluates them by utilizing a thermodynamic energy oracle as the reward function. To solve this environment, we build a graph neural network-based policy and value network, where the policy network is first pre-trained on an open database of elementary radical reactions (RMechDB). Then, we use proximal policy optimization (PPO) to fine-tune the model and predict reasonable reaction mechanisms for two case studies: a radical oxidation of the terpene limonene, and a radical cyclization cascade in the synthesis of hirsutene."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Predicting Chemical Reactions at the MechanisticLevel through Deep Reinforcement Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Coley, Connor W."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Jin, Edward H."],"dc:date.accessioned":["2023-07-31T19:57:30Z"],"dc:date.available":["2023-07-31T19:57:30Z"],"dc:date.issued":["2023-06"],"dc:description.abstract":["Reaction prediction is a fundamental problem in chemistry. Previous work has mostly targeted chemical product prediction only, but did not elucidate any mechanisms or elementary steps from which the reaction proceeds. Here, we attempt to predict chemical mechanisms via deep reinforcement learning. We first define a new type of graph molecular representation that can better keep track of electron flow and can be generalized to non-traditional bonding, such as 3- center-4-electron bonds. We then define a molecular environment Markov Decision Process (MDP) that codifies the allowed mechanistic steps and evaluates them by utilizing a thermodynamic energy oracle as the reward function. To solve this environment, we build a graph neural network-based policy and value network, where the policy network is first pre-trained on an open database of elementary radical reactions (RMechDB). Then, we use proximal policy optimization (PPO) to fine-tune the model and predict reasonable reaction mechanisms for two case studies: a radical oxidation of the terpene limonene, and a radical cyclization cascade in the synthesis of hirsutene."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/151666"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Predicting Chemical Reactions at the MechanisticLevel through Deep Reinforcement Learning"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:29Z"}