A transfer learning protocol for chemical catalysis using a recurrent neural network adapted from natural language processing

Singh, Sukriti; Sunoj, Raghavan B.

doi:10.1039/d1dd00052g

Cited by 17 publications

(22 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have performed principal component analysis (PCA) on the encoder output (Figure 4b) followed by k-means clustering on the first two principal components. 34 Interestingly, distinct clusters were obtained in each reaction type. For example, structurally similar chiral ligands/catalysts in the case of the asymmetric hydrogenation reaction were found to remain in the same cluster.…”

Section: Modelsmentioning

confidence: 99%

“…33 On this front, we have utilized the tools from the domain of NLP to predict % ee/yield of three diverse catalytic reactions (Figure 4a). 34 The diverse reaction types comprise both transition-metal-catalyzed and organocatalytic transformations with varying data sizes and distributions. SMILES strings were employed to express the molecules as linear strings of characters conducive for language models (LMs).…”

Section: Reaction Outcome Predictionmentioning

confidence: 99%

“…(b) Example illustrating the conversion of SMILES strings to machine-readable input. From ref . CC BY-NC 3.0.…”

Section: Learned Molecular Representations For Reaction Outcome Predi...mentioning

confidence: 99%

“…However, additional analyses of the language model built on the composite SMILES representation of the catalytic reactions shown in Figure a could provide meaningful details. We have performed principal component analysis (PCA) on the encoder output (Figure b) followed by k -means clustering on the first two principal components . Interestingly, distinct clusters were obtained in each reaction type.…”

Section: Control Experiments To Evaluate ML Modelsmentioning

confidence: 99%

See 3 more Smart Citations

Molecular Machine Learning for Chemical Catalysis: Prospects and Challenges

Singh

Sunoj

2023

Acc. Chem. Res.

Self Cite

View full text Add to dashboard Cite

Conspectus In the domain of reaction development, one aims to obtain higher efficacies as measured in terms of yield and/or selectivities. During the empirical cycles, an admixture of outcomes from low to high yields/selectivities is expected. While it is not easy to identify all of the factors that might impact the reaction efficiency, complex and nonlinear dependence on the nature of reactants, catalysts, solvents, etc. is quite likely. Developmental stages of newer reactions would typically offer a few hundreds of samples with variations in participating molecules and/or reaction conditions. These “observations” and their “output” can be harnessed as valuable labeled data for developing molecular machine learning (ML) models. Once a robust ML model is built for a specific reaction under development, it can predict the reaction outcome for any new choice of substrates/catalyst in a few seconds/minutes and thus can expedite the identification of promising candidates for experimental validation. Recent years have witnessed impressive applications of ML in the molecular world, most of them aimed at predicting important chemical or biological properties. We believe that an integration of effective ML workflows can be made richly beneficial to reaction discovery. As with any new technology, direct adaptation of ML as used in well-developed domains, such as natural language processing (NLP) and image recognition, is unlikely to succeed in reaction discovery. Some of the challenges stem from ineffective featurization of the molecular space, unavailability of quality data and its distribution, in making the right choice of ML model and its technically robust deployment. It shall be noted that there is no universal ML model suitable for an inherently high-dimensional problem such as chemical reactions. Given these backgrounds, rendering ML tools conducive for reactions is an exciting as well as challenging endeavor at the same time. With the increased availability of efficient ML algorithms, we focused on tapping their potential for small-data reaction discovery (a few hundreds to thousands of samples). In this Account, we describe both feature engineering and feature learning approaches for molecular ML as applied to diverse reactions of high contemporary interest. Among these, catalytic asymmetric hydrogenation of imines/alkenes, β-C(sp3)–H bond functionalization, and relay Heck reaction employed a feature engineering approach using the quantum-chemically derived physical organic descriptors as the molecular featuresall designed to predict the enantioselectivity. The selection of molecular features to customize it for a reaction of interest is described, along with emphasizing the chemical insights that could be gathered through the use of such features. Feature learning methods for predicting the yield of Buchwald–Hartwig cross-coupling, deoxyfluorination of alcohols, and enantioselectivity of N,S-acetal formation are found to offer excellent predictions. We propose a transfer learning protocol, wherein an ML model...

show abstract

Section: Modelsmentioning

confidence: 99%

Section: Reaction Outcome Predictionmentioning

confidence: 99%

“…(b) Example illustrating the conversion of SMILES strings to machine-readable input. From ref . CC BY-NC 3.0.…”

Section: Learned Molecular Representations For Reaction Outcome Predi...mentioning

confidence: 99%

Section: Control Experiments To Evaluate ML Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Molecular Machine Learning for Chemical Catalysis: Prospects and Challenges

Singh

Sunoj

2023

Acc. Chem. Res.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The use of DL for molecular discovery can broadly be categorized into reaction outcome prediction and molecule generation ( Gomez-Bombarelli et al., 2018 ; Miljkovic et al., 2021 ; Walters and Barzilay, 2021 ). The predictive DL models, consisting of multiple hidden layers, have been used for predictions of molecular properties as well as the yield/selectivities of reactions ( Schwaller et al., 2021 ; Senior et al., 2020 ; Singh and Sunoj, 2022 ). First, DL methods can take molecular structures to learn the data-driven feature representation with minimal feature engineering ( Winter et al., 2019 ; Li et al., 2021 ; Atz et al., 2021 ; Mi et al., 2021 ; Lim and Jung, 2019 ).…”

Section: Introductionmentioning

confidence: 99%

A transfer learning approach for reaction discovery in small data situations using generative model

Singh

Sunoj

2022

iScience

Self Cite

View full text Add to dashboard Cite

Paving the road towards automated homogeneous catalyst design

Kalikadien,

Mirza,

Hossaini

et al. 2024

ChemPlusChem

View full text Add to dashboard Cite

In the past decade, computational tools have become integral to catalyst design. They continue to offer significant support to experimental organic synthesis and catalysis researchers aiming for optimal reaction outcomes. More recently, data‐driven approaches utilizing machine learning have garnered considerable attention for their expansive capabilities. This Perspective provides an overview of diverse initiatives in the realm of computational catalyst design and introduces our automated tools tailored for high‐throughput in silico exploration of the chemical space. While valuable insights are gained through methods for high‐throughput in silico exploration and analysis of chemical space, their degree of automation and modularity are key. We argue that the integration of data‐driven, automated and modular workflows is key to enhancing homogeneous catalyst design on an unprecedented scale, contributing to the advancement of catalysis research.

show abstract

A transfer learning protocol for chemical catalysis using a recurrent neural network adapted from natural language processing

Abstract: Minimizing the time and material investments in discovering molecular catalysis would be immensely beneficial. Given the high contemporary importance of homogeneous catalysis in general, and asymmetric catalysis in particular, makes...

Cited by 17 publications

References 49 publications

Molecular Machine Learning for Chemical Catalysis: Prospects and Challenges

Molecular Machine Learning for Chemical Catalysis: Prospects and Challenges

A transfer learning approach for reaction discovery in small data situations using generative model

Paving the road towards automated homogeneous catalyst design

Contact Info

Product

Resources

About