Automatized Assessment of Protective Group Reactivity: A Step Toward Big Reaction Data Analysis

Lin, Arkadii; Madzhidov, Timur; Klimchuk, Olga; Nugmanov, Ramil; Антипин, И. С.; Varnek, Alexandre

doi:10.1021/acs.jcim.6b00319

Cited by 49 publications

(48 citation statements)

References 26 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In order to characterize chemical transformations CGR uses “dynamic bonds” corresponding to broken formed or transformed bonds, and “dynamic atoms”, characterizing changes of atomic charges upon the transformation (see Scheme ). Previously this approach was used in the modeling of rate constants of various reactions (S N 2,,, bimolecular elimination, Diels‐Alder), optimal condition prediction as well as for detection of erroneous atom‐to‐atom mapping . Technically, a CGR can be obtained from the reaction equation by superposing related atoms in the molecular graphs of reactants and products.…”

Section: Computational Proceduresmentioning

confidence: 99%

“…Fragment descriptors generated for CGR can be successfully applied in any chemoinformatics application used a descriptors vector as an input. This approach has successfully been used for similarity searching in reaction space, for data analysis using Generative Topographic Mapping and for QSPR modeling of various kinetic and thermodynamic properties of reactions or optimal reaction conditions . On the other hand, some methods of data analysis considering chemical species as molecular graphs were never used for reactions analysis so far.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bimolecular Nucleophilic Substitution Reactions: Predictive Models for Rate Constants and Molecular Reaction Pairs Analysis

Gimadiev

Madzhidov

Tetko

et al. 2018

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

Here, we report the data visualization, analysis and modeling for a large set of 4830 S N 2 reactions the rate constant of which (logk) was measured at different experimental conditions (solvent, temperature). The reactions were encoded by one single molecular graph -Condensed Graph of Reactions, which allowed us to use conventional chemoinformatics techniques developed for individual molecules. Thus, Matched Reaction Pairs approach was suggested and used for the analyses of substituents effects on the substrates and nucleophiles reactivity. The data were visualized with the help of the Generative Topographic Mapping approach. Consensus Support Vector Regression (SVR) model for the rate constant was prepared. Unbiased estimation of the model's performance was made in cross-validation on reactions measured on unique structural transformations. The model's performance in cross-validation (RMSE = 0.61 logk units) and on the external test set (RMSE = 0.80) is close to the noise in data. Performances of the local models obtained for selected subsets of reactions proceeding in particular solvents or with particular type of nucleophiles were similar to that of the model built on the entire set. Finally, four different definitions of model's applicability domains for reactions were examined.

show abstract

Section: Computational Proceduresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Bimolecular Nucleophilic Substitution Reactions: Predictive Models for Rate Constants and Molecular Reaction Pairs Analysis

Gimadiev

Madzhidov

Tetko

et al. 2018

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Lin et al used a similarity-based approach to recommend catalysts for desired deprotection reactions, and demonstrated the approach in catalytic hydrogenation reactions. 31 …”

Section: Introductionmentioning

confidence: 99%

Using Machine Learning To Predict Suitable Conditions for Organic Reactions

et al. 2018

View full text Add to dashboard Cite

Reaction condition recommendation is an essential element for the realization of computer-assisted synthetic planning. Accurate suggestions of reaction conditions are required for experimental validation and can have a significant effect on the success or failure of an attempted transformation. However, de novo condition recommendation remains a challenging and under-explored problem and relies heavily on chemists’ knowledge and experience. In this work, we develop a neural-network model to predict the chemical context (catalyst(s), solvent(s), reagent(s)), as well as the temperature most suitable for any particular organic reaction. Trained on ∼10 million examples from Reaxys, the model is able to propose conditions where a close match to the recorded catalyst, solvent, and reagent is found within the top-10 predictions 69.6% of the time, with top-10 accuracies for individual species reaching 80–90%. Temperature is accurately predicted within ±20 °C from the recorded temperature in 60–70% of test cases, with higher accuracy for cases with correct chemical context predictions. The utility of the model is illustrated through several examples spanning a range of common reaction classes. We also demonstrate that the model implicitly learns a continuous numerical embedding of solvent and reagent species that captures their functional similarity.

show abstract

“…While their filters were all hand-encoded, data mining techniques can also be used to estimate functional group reactivity. [139,140] Selecting pathways within as earch space defined by combinations of known single-step reactions has taken on other forms as well, including the identification of cyclic pathways, [141] the optimization of process cost, [142] and the optimization of estimated process mass intensity. [143] Generating yet-unseen chemical reactions for asynthesis plan-a necessity for the synthesis of novel molecules-is ah arder search problem than when searching within af ixed reaction network.…”

Section: Noniterative Discovery Of Chemical Processes 431 Discovermentioning

confidence: 99%

Autonomous Discovery in the Chemical Sciences Part I: Progress

2020

View full text Add to dashboard Cite

This two‐part Review examines how automation has contributed to different aspects of discovery in the chemical sciences. In this first part, we describe a classification for discoveries of physical matter (molecules, materials, devices), processes, and models and how they are unified as search problems. We then introduce a set of questions and considerations relevant to assessing the extent of autonomy. Finally, we describe many case studies of discoveries accelerated by or resulting from computer assistance and automation from the domains of synthetic chemistry, drug discovery, inorganic chemistry, and materials science. These illustrate how rapid advancements in hardware automation and machine learning continue to transform the nature of experimentation and modeling. Part two reflects on these case studies and identifies a set of open challenges for the field.

show abstract

Automatized Assessment of Protective Group Reactivity: A Step Toward Big Reaction Data Analysis

Cited by 49 publications

References 26 publications

Bimolecular Nucleophilic Substitution Reactions: Predictive Models for Rate Constants and Molecular Reaction Pairs Analysis

Bimolecular Nucleophilic Substitution Reactions: Predictive Models for Rate Constants and Molecular Reaction Pairs Analysis

Using Machine Learning To Predict Suitable Conditions for Organic Reactions

Autonomous Discovery in the Chemical Sciences Part I: Progress

Contact Info

Product

Resources

About