Machine learning modelling of chemical reaction characteristics: yesterday, today, tomorrow

Madzhidov, Timur; Rakhimbekova, Assima; Afonina, Valentina A.; Gimadiev, Timur; Mukhametgaleev, Ravil; Nugmanov, Ramil; Baskin, Igor I.; Varnek, Alexandre

doi:10.1016/j.mencom.2021.11.003

Cited by 13 publications

(9 citation statements)

References 148 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Molecular modeling gives an opportunity to predict the biological activity level and bioavailability of small molecules [ 23 , 24 , 25 ]. Quinidine was chosen as a reference compound due to its antiarrhythmic effect resulting in Na V 1.5 inhibition [ 26 ].…”

Section: Discussionmentioning

confidence: 99%

Insights into the Cardiotoxic Effects of Veratrum Lobelianum Alkaloids: Pilot Study

Taldaev

Terekhov

Melnik

et al. 2022

Toxins

View full text Add to dashboard Cite

Jervine, protoveratrine A (proA), and protoveratrine B (proB) are Veratrum alkaloids that are presented in some remedies obtained from Veratrum lobelianum, such as Veratrum aqua. This paper reports on a single-center pilot cardiotoxic mechanism study of jervine, proA, and proB in case series. The molecular aspects were studied via molecular dynamic simulation, molecular docking with cardiac sodium channel NaV1.5, and machine learning-based structure–activity relationship modeling. HPLC-MS/MS method in combination with clinical events were used to analyze Veratrum alkaloid cardiotoxicity in patients. Jervine demonstrates the highest docking score (−10.8 kcal/mol), logP value (4.188), and pKa value (9.64) compared with proA and proB. Also, this compound is characterized by the lowest calculated IC50. In general, all three analyzed alkaloids show the affinity to NaV1.5 that highly likely results in cardiotoxic action. The clinical data of seven cases of intoxication by Veratrum aqua confirms the results of molecular modeling. Patients exhibited nausea, muscle weakness, bradycardia, and arterial hypotension. The association between alkaloid concentrations in blood and urine and severity of patient condition is described. These experiments, while primary, confirmed that jervine, proA, and proB contribute to cardiotoxicity by NaV1.5 inhibition.

show abstract

Section: Discussionmentioning

confidence: 99%

Insights into the Cardiotoxic Effects of Veratrum Lobelianum Alkaloids: Pilot Study

Taldaev

Terekhov

Melnik

et al. 2022

Toxins

View full text Add to dashboard Cite

show abstract

“…These quantities are generally dependent on quantitative conditions, so they are used within reaction family-specic pipelines rather than general synthesis planning pipelines. We refer readers to Madzhidov et al 106 for a detailed review on quantitative prediction. Most notably, hybrid DFT/ML models have been developed to model the activation energies of nucleophilic aromatic substitution, 107,108 one of the most well-studied reactions in organic synthesis.…”

Section: Reaction Outcome Predictionmentioning

confidence: 99%

Predictive chemistry: machine learning for reaction deployment, reaction development, and reaction discovery

Stuyver

Coley

2023

Chem. Sci.

View full text Add to dashboard Cite

show abstract

“…Recently, machine learning, lying at the core of artificial intelligence and data science, has emerged as a promising method to yield highly reliable reaction rate constants. − The machine learning methods can be in principle clarified into three categories: supervised learning, unsupervised learning, and reinforcement learning, in which the supervised machine learning is usually applied in predicting chemical reaction properties by using different molecular representations as inputs. , In this regard, many pioneering works have been performed to learn activation energies and minimum energy paths of chemical reactions. ,− Meanwhile, some efforts have been made to directly predict rate constants …”

Section: Introductionmentioning

confidence: 99%

Structure-Based Reaction Descriptors for Predicting Rate Constants by Machine Learning: Application to Hydrogen Abstraction from Alkanes by CH₃/H/O Radicals

Song

Yang

2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Accurate determination of the thermal rate constants for combustion reactions is a highly challenging task, both experimentally and theoretically. Machine learning has been proven to be a powerful tool to predict reaction rate constants in recent years. In this work, three supervised machine learning algorithms, including XGB, FNN, and XGB-FNN, are used to develop quantitative structure−property relationship models for the estimation of the rate constants of hydrogen abstraction reactions from alkanes by the free radicals CH 3 , H, and O. The molecular similarity based on Morgan molecular fingerprints combined with the topological indices are proposed to represent chemical reactions in the machine learning models. Using the newly constructed descriptors, the hybrid XGB-FNN algorithm yields average deviations of 65.4%, 12.1%, and 64.5% on the prediction sets of alkanes + CH 3 , H, and O, respectively, whose performance is comparable and even superior to the corresponding one using the activation energy as a descriptor. The use of activation energy as a descriptor has previously been shown to significantly improve prediction accuracy (Fuel 2022, 322, 124150) but typically requires cumbersome ab initio calculations. In addition, the XGB-FNN models could reasonably predict reaction rate constants of hydrogen abstractions from different sites of alkanes and their isomers, indicating a good generalization ability. It is expected that the reaction descriptors proposed in this work can be applied to build machine learning models for other reactions.

show abstract

Machine learning modelling of chemical reaction characteristics: yesterday, today, tomorrow

Cited by 13 publications

References 148 publications

Insights into the Cardiotoxic Effects of Veratrum Lobelianum Alkaloids: Pilot Study

Insights into the Cardiotoxic Effects of Veratrum Lobelianum Alkaloids: Pilot Study

Predictive chemistry: machine learning for reaction deployment, reaction development, and reaction discovery

Structure-Based Reaction Descriptors for Predicting Rate Constants by Machine Learning: Application to Hydrogen Abstraction from Alkanes by CH₃/H/O Radicals

Contact Info

Product

Resources

About

Machine learning modelling of chemical reaction characteristics: yesterday, today, tomorrow

Cited by 13 publications

References 148 publications

Insights into the Cardiotoxic Effects of Veratrum Lobelianum Alkaloids: Pilot Study

Insights into the Cardiotoxic Effects of Veratrum Lobelianum Alkaloids: Pilot Study

Predictive chemistry: machine learning for reaction deployment, reaction development, and reaction discovery

Structure-Based Reaction Descriptors for Predicting Rate Constants by Machine Learning: Application to Hydrogen Abstraction from Alkanes by CH3/H/O Radicals

Contact Info

Product

Resources

About

Structure-Based Reaction Descriptors for Predicting Rate Constants by Machine Learning: Application to Hydrogen Abstraction from Alkanes by CH₃/H/O Radicals