Search for: All records

Computer-aided synthesis planning (CASP) algorithms have demonstrated expertlevel abilities in planning retrosynthetic routes to molecules of low to moderate complexity. However, current search methods assume the sufficiency of reaching arbitrary building blocks, failing to address the common real-world constraint where using specific molecules is desired. To this end, we present a formulation of synthesis planning with starting material constraints. Under this formulation, we propose Double-Ended Synthesis Planning (DESP), a novel CASP algorithm under a bidirectional graph search scheme that interleaves expansions from the target and from the goal starting materials to ensure constraint satisfiability. The search algorithm is guided by a goal-conditioned cost network learned offline from a partially observed hypergraph of valid chemical reactions. We demonstrate the utility of DESP in improving solve rates and reducing the number of search expansions by biasing synthesis planning towards expert goals on multiple new benchmarks. DESP can make use of existing one-step retrosynthesis models, and we anticipate its performance to scale as these one-step model capabilities improve. 

DFT-level descriptor libraries were constructed to train 2D and 3D graph neural networks for on the-fly the prediction of carboxylic acid and alkyl amine descriptors suitable for statistical modeling of medicinally relevant molecules. 

An open-source fine-tuned large language model can extract reaction information from organic synthesis procedure text into structured data that follows the Open Reaction Database (ORD) schema. 

This Figshare repository contains the datasets and models for our paper titled: Rapid Prediction of Conformationally-Dependent DFT-Level Descriptors using Graph Neural Networks for Carboxylic Acids and Alkyl Amines. It is organized into 2D and 3D, which represent the modeling architectures used in building graph neural networks for molecular descriptors corresponding to acids and amines. Carboxylic acid, primary alkyl amine, and secondary alkyl amine (as well as a combined alkyl amine) libraries are provided in their entirety, including conformer properties. Additional test and external validation statistics for each library are also provided within this repository. 

The field of predictive chemistry relates to the development of models able to describe how molecules interact and react. It encompasses the long-standing task of computer-aided retrosynthesis, but is far more reaching and ambitious in its goals. In this review, we summarize several areas where predictive chemistry models hold the potential to accelerate the deployment, development, and discovery of organic reactions and advance synthetic chemistry.