Chemical reactivity predictions: Use of data mining techniques for analyzing regioselective azidolysis of epoxides

XGBoost-based intelligence yield prediction and reaction factors analysis of amination reaction

Buchwald-Hartwig amination reaction catalyzed by palladium plays an important role in drug synthesis. In the last few years, machine learning-assisted strategies emerged and quickly gained attention. In this article, an importance and relevance-based integrated feature screening method is proposed to effectively filter high-dimensional feature descriptor data. Then, a regularized machine learning boosting tree model, eXtreme Gradient Boosting, is introduced to intelligently predict reaction performance in multidimensional chemistry space. Furthermore, convergence, interpretability, generalization, and the internal association between reaction conditions and yields are excavated, which provides intelligent assistance for the optimal design of coupling reaction system and evaluating the reaction conditions. Compared with recently published results, the proposed method requires fewer feature descriptors, takes less time, and achieves more accurate prediction accuracy.

Exploring topics related to data mining on Wikipedia

Purpose

Data mining has been a popular research area in the past decades. Many researchers study data-mining theories, methods, applications and trends; however, there are very few studies on data-mining-related topics in social media. This paper aims to explore the topics related to data mining based on the data collected from Wikipedia.

Design/methodology/approach

In total, 402 data-mining-related articles were obtained from Wikipedia. These articles were manually classified into several categories by the coding method. Each category formed an article-term matrix. These matrices were analysed and visualized by the self-organizing map approach. Several clusters were observed in each category. Finally, the topics of these clusters were extracted by content analysis.

Findings

The articles obtained were classified into six categories: applications, foundation and concepts, methodologies, organizations, related fields and topics and technology support. Business, biology and security were the three prominent topics of the applications category. The technologies supporting data mining were software, systems, databases, programming languages and so forth. The general public was more interested in data-mining organizations than the researchers. They also focused on the applications of data mining in business more than in other fields.

Originality/value

This study will help researchers gain insight into the general public’s perceptions of data mining and discover the gap between the general public and themselves. It will assist researchers in finding new techniques and methods which will potentially provide them with new data-mining methods and research topics.

Data-driven computer aided synthesis design

Enabled by an increasing body of electronically available experimental data and by advances in computer hardware and software, new technologies are emerging that are designed to support the creativity of chemists during synthesis planning. Leading this development are innovative synthetic route prediction tools that are designed to suggest new reactions and paths to target molecules as an idea-generating engine. Other tools are using known reactions in a combinatorial fashion to suggest new routes that are cost-optimized or satisfy some other global criteria. We review the latest developments and the main tools in this domain.

ReactionPredictor: prediction of complex chemical reactions at the mechanistic level using machine learning

Proposing reasonable mechanisms and predicting the course of chemical reactions is important to the practice of organic chemistry. Approaches to reaction prediction have historically used obfuscating representations and manually encoded patterns or rules. Here we present ReactionPredictor, a machine learning approach to reaction prediction that models elementary, mechanistic reactions as interactions between approximate molecular orbitals (MOs). A training data set of productive reactions known to occur at reasonable rates and yields and verified by inclusion in the literature or textbooks is derived from an existing rule-based system and expanded upon with manual curation from graduate level textbooks. Using this training data set of complex polar, hypervalent, radical, and pericyclic reactions, a two-stage machine learning prediction framework is trained and validated. In the first stage, filtering models trained at the level of individual MOs are used to reduce the space of possible reactions to consider. In the second stage, ranking models over the filtered space of possible reactions are used to order the reactions such that the productive reactions are the top ranked. The resulting model, ReactionPredictor, perfectly ranks polar reactions 78.1% of the time and recovers all productive reactions 95.7% of the time when allowing for small numbers of errors. Pericyclic and radical reactions are perfectly ranked 85.8% and 77.0% of the time, respectively, rising to >93% recovery for both reaction types with a small number of allowed errors. Decisions about which of the polar, pericyclic, or radical reaction type ranking models to use can be made with >99% accuracy. Finally, for multistep reaction pathways, we implement the first mechanistic pathway predictor using constrained tree-search to discover a set of reasonable mechanistic steps from given reactants to given products. Webserver implementations of both the single step and pathway versions of ReactionPredictor are available via the chemoinformatics portal http://cdb.ics.uci.edu/.