Search

With the rapid improvement of machine translation approaches, neural machine translation has started to play an important role in retrosynthesis planning, which finds reasonable synthetic pathways for a target molecule. Previous studies showed that utilizing the sequence-to-sequence frameworks of neural machine translation is a promising approach to tackle the retrosynthetic planning problem. In this work, we recast the retrosynthetic planning problem as a language translation problem using a template-free sequence-to-sequence model. The model is trained in an end-to-end and a fully data-driven fashion. Unlike previous models translating the SMILES strings of reactants and products, we introduced a new way of representing a chemical reaction based on molecular fragments. It is demonstrated that the new approach yields better prediction results than current state-of-the-art computational methods. The new approach resolves the major drawbacks of existing retrosynthetic methods such as generating invalid SMILES strings. Specifically, our approach predicts highly similar reactant molecules with an accuracy of 57.7%. In addition, our method yields more robust predictions than existing methods.

We present the open-source AiZynthFinder software that can be readily used in retrosynthetic planning. The algorithm is based on a Monte Carlo tree search that recursively breaks down a molecule to purchasable precursors. The tree search is guided by an artificial neural network policy that suggests possible precursors by utilizing a library of known reaction templates. The software is fast and can typically find a solution in less than 10 s and perform a complete search in less than 1 min. Moreover, the development of the code was guided by a range of software engineering principles such as automatic testing, system design and continuous integration leading to robust software with high maintainability. Finally, the software is well documented to make it suitable for beginners. The software is available at http://www.github.com/MolecularAI/aizynthfinder.

In computer-assisted synthesis planning (CASP) programs, providing as many chemical synthetic routes as possible is essential for considering optimal and alternative routes in a chemical reaction network. As the majority of CASP programs have been designed to provide one or a few optimal routes, it is likely that the desired one will not be included. To avoid this, an exact algorithm that lists possible synthetic routes within the chemical reaction network is required, alongside a recommendation of synthetic routes that meet specified criteria based on the chemist’s objectives. Herein, we propose a chemical-reaction-network-based synthetic route recommendation framework called “CompRet” with a mathematically guaranteed enumeration algorithm. In a preliminary experiment, CompRet was shown to successfully provide alternative routes for a known antihistaminic drug, cetirizine. CompRet is expected to promote desirable enumeration-based chemical synthesis searches and aid the development of an interactive CASP framework for chemists.

Scaffold analysis of compound data sets has reemerged as a chemically interpretable alternative to machine learning for chemical space and structure–activity relationships analysis. In this context, analog series-based scaffolds (ASBS) are synthetically relevant core structures that represent individual series of analogs. As an extension to ASBS, we herein introduce the development of a general conceptual framework that considers all putative cores of molecules in a compound data set, thus softening the often applied “single molecule–single scaffold” correspondence. A putative core is here defined as any substructure of a molecule complying with two basic rules: (a) the size of the core is a significant proportion of the whole molecule size and (b) the substructure can be reached from the original molecule through a succession of retrosynthesis rules. Thereafter, a bipartite network consisting of molecules and cores can be constructed for a database of chemical structures. Compounds linked to the same cores are considered analogs. We present case studies illustrating the potential of the general framework. The applications range from inter- and intra-core diversity analysis of compound data sets, structure–property relationships, and identification of analog series and ASBS. The molecule–core network herein presented is a general methodology with multiple applications in scaffold analysis. New statistical methods are envisioned that will be able to draw quantitative conclusions from these data. The code to use the method presented in this work is freely available as an additional file. Follow-up applications include analog searching and core structure–property relationships analyses.

Both the automated generation of reaction networks and the automated prediction of synthetic trees require, in one way or another, the definition of possible transformations a molecule can undergo. One way of doing this is by using reaction templates. In view of the expanding amount of known reactions, it has become more and more difficult to envision all possible transformations that could occur in a studied system. Nonetheless, most reaction network generation tools rely on user-defined reaction templates. Not only does this limit the amount of chemistry that can be accounted for in the reaction networks, it also confines the wide-spread use of the tools by a broad public. In retrosynthetic analysis, the quality of the analysis depends on what percentage of the known chemistry is accounted for. Using databases to identify templates is therefore crucial in this respect. For this purpose, an algorithm has been developed to extract reaction templates from various types of chemical databases. Some databases such as the Kyoto Encyclopedia for Genes and Genomes and RMG do not report an atom–atom mapping (AAM) for the reactions. This makes the extraction of a template non-straightforward. If no mapping is available, it is calculated by the Reaction Decoder Tool (RDT). With a correct AAM—either calculated by RDT or specified—the algorithm consistently extracts a correct template for a wide variety of reactions, both elementary and non-elementary. The developed algorithm is a first step towards data-driven generation of synthetic trees or reaction networks, and a greater accessibility for non-expert users. Electronic supplementary material The online version of this article (10.1186/s13321-018-0269-8) contains supplementary material, which is available to authorized users.