Chemical space

Kirkpatrick, Peter; Ellis, Clare

doi:10.1038/432823a

Cited by 318 publications

(260 citation statements)

References 0 publications

Supporting

Mentioning

252

Contrasting

Unclassified

Order By: Relevance

“…[1] Stated more precisely, CCS refers to the combinatorial set of all compounds that can be isolated and constructed from possible combinations and configurations of N I atoms and N e electrons in real space. In absence of external fields and for given N e and N I atom-types fZ I g and spatial configurations fR I g, not only covalent, ionic, and metallic bonding result, but also the much weaker hydrogen and van-der-Waals (vdW)-bonding, responsible for the physics and chemistry of molecular crystals, liquids, and other supramolecular aggregates.…”

Section: Introductionmentioning

confidence: 99%

First principles view on chemical compound space: Gaining rigorous atomistic control of molecular properties

Lilienfeld

2013

Int J of Quantum Chemistry

139

160

View full text Add to dashboard Cite

A well‐defined notion of chemical compound space (CCS) is essential for gaining rigorous control of properties through variation of elemental composition and atomic configurations. Here, we give an introduction to an atomistic first principles perspective on CCS. First, CCS is discussed in terms of variational nuclear charges in the context of conceptual density functional and molecular grand‐canonical ensemble theory. Thereafter, we revisit the notion of compound pairs, related to each other via “alchemical” interpolations involving fractional nuclear charges in the electronic Hamiltonian. We address Taylor expansions in CCS, property nonlinearity, improved predictions using reference compound pairs, and the ounce‐of‐gold prize challenge to linearize CCS. Finally, we turn to machine learning of analytical structure property relationships in CCS. These relationships correspond to inferred, rather than derived through variational principle, solutions of the electronic Schrödinger equation. © 2013 Wiley Periodicals, Inc.

show abstract

Section: Introductionmentioning

confidence: 99%

First principles view on chemical compound space: Gaining rigorous atomistic control of molecular properties

Lilienfeld

2013

Int J of Quantum Chemistry

139

160

View full text Add to dashboard Cite

show abstract

“…1 Alternatively, Kernel-Ridge-Regression (KRR) based machine learning (ML) models 2 can also infer the observable in terms of a linear expansion in chemical compound space. [3][4][5][6] More specifically, any observable can be estimated using O inf (M) =  N i α i k(d(M, M i )), where k is the kernel function (e.g., Laplacian with training set dependent width), M is the molecular representation (typically in matrix or vector format), 7,8 and d is a metric (often the L 1 -norm). The sum runs over all reference molecules i used for training to obtain regression weights {α i }.…”

mentioning

confidence: 99%

Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity

Huang¹,

Lilienfeld²

2016

The Journal of Chemical Physics

308

342

View full text Add to dashboard Cite

The predictive accuracy of Machine Learning (ML) models of molecular properties depends on the choice of the molecular representation. Based on the postulates of quantum mechanics, we introduce a hierarchy of representations which meet uniqueness and target similarity criteria. To systematically control target similarity, we rely on interatomic many body expansions, as implemented in universal force-fields, including Bonding, Angular, and higher order terms (BA). Addition of higher order contributions systematically increases similarity to the true potential energy and predictive accuracy of the resulting ML models. We report numerical evidence for the performance of BAML models trained on molecular properties pre-calculated at electron-correlated and density functional theory level of theory for thousands of small organic molecules. Properties studied include enthalpies and free energies of atomization, heatcapacity, zero-point vibrational energies, dipole-moment, polarizability, HOMO/LUMO energies and gap, ionization potential, electron affinity, and electronic excitations. After training, BAML predicts energies or electronic properties of out-of-sample molecules with unprecedented accuracy and speed.

show abstract

“…[86][87][88][89][90][91][92][93][94] and predictive studies. [95][96][97][98][99][100][101][102][103][104] To gain a better understanding of the polymerization processes discussed above, detailed theoretical studies were essential. Our group previously reported DFT calculations on redox switchable polymerization by cerium.…”

mentioning

confidence: 99%

A Comparison of Gallium and Indium Alkoxide Complexes as Catalysts for Ring-Opening Polymerization of Lactide

et al. 2017

View full text Add to dashboard Cite

ABSTRACT:The synthesis, characterization, and reactivity of an aluminum alkoxide complex supported by a ferrocene-based ligand, (thiolfan*)Al(O t Bu) (1 red , thiolfan* = 1,1'-di(2,4-di-tert-butyl-6-thiophenoxy)ferrocene), are reported. The homopolymers of L-lactide (LA), ε-caprolactone (CL), δ-valerolactone (VL), cyclohexene oxide (CHO), trimethylene carbonate (TMC), and their copolymers were obtained in a controlled manner by using redox reagents. Detailed DFT calculations and experimental studies were performed to investigate the mechanism. Mechanistic studies show that after the insertion of the first monomer, the coordination effect of the carbonyl group, which has usually been ignored in previous reports, can significantly change the energy barrier of the propagation steps, thus playing an important role in polymerization and copolymerization processes.

show abstract

Chemical space

Cited by 318 publications

References 0 publications

First principles view on chemical compound space: Gaining rigorous atomistic control of molecular properties

First principles view on chemical compound space: Gaining rigorous atomistic control of molecular properties

Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity

A Comparison of Gallium and Indium Alkoxide Complexes as Catalysts for Ring-Opening Polymerization of Lactide

Contact Info

Product

Resources

About