Machine Learning Yield Prediction from NiCOlit, a Small-Size Literature Data Set of Nickel Catalyzed C–O Couplings

Journal of the American Chemical Society, Journal Year: 2022, Volume and Issue: 144(32), P. 14722 - 14730

Published: Aug. 8, 2022

Synthetic yield prediction using machine learning is intensively studied. Previous work has focused on two categories of data sets: high-throughput experimentation data, as an ideal case study, and sets extracted from proprietary databases, which are known to have a strong reporting bias toward high yields. However, predicting yields published reaction remains elusive. To fill the gap, we built set nickel-catalyzed cross-couplings organic publications, including scope optimization information. We demonstrate importance source failed experiments emphasize how publication constraints shape exploration chemical space by synthetic community. While models still fail perform out-of-sample predictions, this shows that adding knowledge enables fair predictions in low-data regime. Eventually, hope unique public database will foster further improvements methods for more realistic context.

Language: Английский

---

Intelligent control of nanoparticle synthesis on microfluidic chips with machine learning

NPG Asia Materials, Journal Year: 2022, Volume and Issue: 14(1)

Published: Aug. 12, 2022

Abstract Nanoparticles play irreplaceable roles in optoelectronic sensing, medical therapy, material science, and chemistry due to their unique properties. There are many synthetic pathways used for the preparation of nanoparticles, different can produce nanoparticles with Therefore, it is crucial control properties precisely impart desired functions. In general, influenced by sizes morphologies. Current technology on microfluidic chips requires repeated experimental debugging significant resources synthesize Machine learning-assisted synthesis a sensible choice addressing this challenge. paper, we review recent studies syntheses assisted machine learning. Moreover, describe working steps learning, main algorithms, ways obtain datasets. Finally, discuss current problems research provide an outlook.

Language: Английский

---

When machine learning meets molecular synthesis

Trends in Chemistry, Journal Year: 2022, Volume and Issue: 4(10), P. 863 - 885

Published: Aug. 31, 2022

Language: Английский

---

Molecular Machine Learning for Chemical Catalysis: Prospects and Challenges

Accounts of Chemical Research, Journal Year: 2023, Volume and Issue: 56(3), P. 402 - 412

Published: Jan. 30, 2023

ConspectusIn the domain of reaction development, one aims to obtain higher efficacies as measured in terms yield and/or selectivities. During empirical cycles, an admixture outcomes from low high yields/selectivities is expected. While it not easy identify all factors that might impact efficiency, complex and nonlinear dependence on nature reactants, catalysts, solvents, etc. quite likely. Developmental stages newer reactions would typically offer a few hundreds samples with variations participating molecules conditions. These "observations" their "output" can be harnessed valuable labeled data for developing molecular machine learning (ML) models. Once robust ML model built specific under predict outcome any new choice substrates/catalyst seconds/minutes thus expedite identification promising candidates experimental validation. Recent years have witnessed impressive applications world, most them aimed at predicting important chemical or biological properties. We believe integration effective workflows made richly beneficial discovery.As technology, direct adaptation used well-developed domains, such natural language processing (NLP) image recognition, unlikely succeed discovery. Some challenges stem ineffective featurization space, unavailability quality its distribution, making right technically deployment. It shall noted there no universal suitable inherently high-dimensional problem reactions. Given these backgrounds, rendering tools conducive exciting well challenging endeavor same time. With increased availability efficient algorithms, we focused tapping potential small-data discovery (a thousands samples).In this Account, describe both feature engineering approaches applied diverse contemporary interest. Among these, catalytic asymmetric hydrogenation imines/alkenes, β-C(sp3)–H bond functionalization, relay Heck employed approach using quantum-chemically derived physical organic descriptors features─all designed enantioselectivity. The selection features customize interest described, along emphasizing insights could gathered through use features. Feature methods Buchwald–Hartwig cross-coupling, deoxyfluorination alcohols, enantioselectivity N,S-acetal formation are found excellent predictions. propose transfer protocol, wherein trained large number (105–106) fine-tuned library target task reactions, alternative (102–103 reactions). exploitation deep neural network latent space method generative tasks useful substrates demonstrated strategy.

Language: Английский

---

Bayesian-optimization-assisted discovery of stereoselective aluminum complexes for ring-opening polymerization of racemic lactide

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: June 20, 2023

Stereoselective ring-opening polymerization catalysts are used to produce degradable stereoregular poly(lactic acids) with thermal and mechanical properties that superior those of atactic polymers. However, the process discovering highly stereoselective is still largely empirical. We aim develop an integrated computational experimental framework for efficient, predictive catalyst selection optimization. As a proof principle, we have developed Bayesian optimization workflow on subset literature results lactide polymerization, using algorithm, identify multiple new Al complexes catalyze either isoselective or heteroselective polymerization. In addition, feature attribution analysis uncovers mechanistically meaningful ligand descriptors, such as percent buried volume (%Vbur) highest occupied molecular orbital energy (EHOMO), can access quantitative models development.

Language: Английский

---

A Data-Driven Workflow for Assigning and Predicting Generality in Asymmetric Catalysis

Journal of the American Chemical Society, Journal Year: 2023, Volume and Issue: 145(23), P. 12870 - 12883

Published: June 2, 2023

The development of chiral catalysts that can provide high enantioselectivities across a wide assortment substrates or reaction range is priority for many catalyst design efforts. While several approaches are available to aid in the identification general systems, there currently no simple procedure directly measuring how given could be. Herein, we present catalyst-agnostic workflow centered on unsupervised machine learning enables rapid assessment and quantification generality. uses curated literature data sets descriptors visualize cluster chemical space coverage. This network then be applied derive generality metric through designer equations interfaced with other regression techniques prediction. As validating case studies, have successfully this method identify-through-quantification most chemotype an organocatalytic asymmetric Mannich predicted phosphoric acid addition nucleophiles imines. mechanistic basis gleaned from calculated values by deconstructing contributions enantiomeric excess overall result. Finally, our permitted mechanistically informative screening allow experimentalists rationally select highest probability achieving good result first round development. Overall, findings represent framework interrogating generality, strategy should relevant catalytic systems widely synthesis.

Language: Английский

---

A Review on Artificial Intelligence Enabled Design, Synthesis, and Process Optimization of Chemical Products for Industry 4.0

Processes, Journal Year: 2023, Volume and Issue: 11(2), P. 330 - 330

Published: Jan. 19, 2023

With the development of Industry 4.0, artificial intelligence (AI) is gaining increasing attention for its performance in solving particularly complex problems industrial chemistry and chemical engineering. Therefore, this review provides an overview application AI techniques, particular machine learning, design, synthesis, process optimization over past years. In review, focus on structure-function relationship analysis, synthetic route planning, automated synthesis. Finally, we discuss challenges future making products.

Language: Английский

---

Rapid planning and analysis of high-throughput experiment arrays for reaction discovery

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: July 3, 2023

High-throughput experimentation (HTE) is an increasingly important tool in reaction discovery. While the hardware for running HTE chemical laboratory has evolved significantly recent years, there remains a need software solutions to navigate data-rich experiments. Here we have developed phactor™, that facilitates performance and analysis of laboratory. phactor™ allows experimentalists rapidly design arrays reactions or direct-to-biology experiments 24, 96, 384, 1,536 wellplates. Users can access online reagent data, such as inventory, virtually populate wells with produce instructions perform array manually, assistance liquid handling robot. After completion array, analytical results be uploaded facile evaluation, guide next series All metadata, are stored machine-readable formats readily translatable various software. We also demonstrate use discovery several chemistries, including identification low micromolar inhibitor SARS-CoV-2 main protease. Furthermore, been made available free academic 24- 96-well via interface.

Language: Английский

---

Reaction performance prediction with an extrapolative and interpretable graph model based on chemical knowledge

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: June 15, 2023

Accurate prediction of reactivity and selectivity provides the desired guideline for synthetic development. Due to high-dimensional relationship between molecular structure function, it is challenging achieve predictive modelling transformation with required extrapolative ability chemical interpretability. To meet gap rich domain knowledge chemistry advanced graph model, herein we report a knowledge-based model that embeds digitalized steric electronic information. In addition, interaction module developed enable learning synergistic influence reaction components. this study, demonstrate achieves excellent predictions yield stereoselectivity, whose corroborated by additional scaffold-based data splittings experimental verifications new catalysts. Because embedding local environment, allows atomic level interpretation on overall performance, which serves as useful guide engineering towards target function. This offers an interpretable approach performance prediction, pointing out importance knowledge-constrained purpose.

Language: Английский

---

Paving the road towards automated homogeneous catalyst design

ChemPlusChem, Journal Year: 2024, Volume and Issue: 89(7)

Published: Jan. 26, 2024

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

Language: Английский

---