Correlative analysis of metal organic framework structures through manifold learning of Hirshfeld surfaces

Shen, Xiaozhou; Zhang, Tianmu; Broderick, Scott; Rajan, Krishna

doi:10.1039/c8me00014j

Cited by 17 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While much of the work so far has focused on deep generative modeling for drug molecules, 24 there are many other application domains which are benefiting from the application of deep learning to lead generation and screening, such as organic light emitting diodes, 25 organic solar cells, 26 energetic materials, 10,27 electrochromic devices, 28 polymers, 29 polypeptides, [30][31][32] and metal organic frameworks. 33,34 Our review touches on four major issues we have observed in the field. The first is the importance and opportunities for improvement by using different molecular representations.…”

mentioning

confidence: 99%

Deep learning for molecular design—a review of the state of the art

Elton

Boukouvalas

Fuge

et al. 2019

Mol. Syst. Des. Eng.

510

516

View full text Add to dashboard Cite

In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes, researchers are now applying deep generative modeling techniques to the generation and optimization of molecules-in our review we found 45 papers on the subject published in the past two years. These works point to a future where such systems will be used to generate lead molecules, greatly reducing resources spent downstream synthesizing and characterizing bad leads in the lab. In this review we survey the increasingly complex landscape of models and representation schemes that have been proposed. The four classes of techniques we describe are recursive neural networks, autoencoders, generative adversarial networks, and reinforcement learning. After first discussing some of the mathematical fundamentals of each technique, we draw high level connections and comparisons with other techniques and expose the pros and cons of each. Several important high level themes emerge as a result of this work, including the shift away from the SMILES string representation of molecules towards more sophisticated representations such as graph grammars and 3D representations, the importance of reward function design, the need for better standards for benchmarking and testing, and the benefits of adversarial training and reinforcement learning over maximum likelihood based training.

show abstract

mentioning

confidence: 99%

Deep learning for molecular design—a review of the state of the art

Elton

Boukouvalas

Fuge

et al. 2019

Mol. Syst. Des. Eng.

510

516

View full text Add to dashboard Cite

show abstract

“…In this way, the resulting hypothetical reticular structures will be combined with experimental structures (e.g., CoRE MOFs) and subjected to high-throughput calculations for property data prediction on the level of molecular dynamics (e.g., Monte Carlo simulations for gas sorption), 147,149,150 density functional theory (e.g., point charges and band structures), 148,151,152 ab initio calculations, [153][154][155] and machine-learned models. 154,155 These calculated property data can be further used for statistical analysis (e.g., linear or non-linear regression and principal-component analysis) 149,156 or machine-learning methods (e.g., support vector machine [SVM], 157,158 random forest [RF], 155,159,160 genetic algorithm [GA], 161,162 k-nearest neighbors [k-NNs], 163,164 artificial neural networks [ANNs], 154,165,166 and other higher-level models) to decipher the properties of materials (AI-assisted property studies in Figure 3).…”

Section: The Computational Discovery Cyclementioning

confidence: 99%

Digital Reticular Chemistry

Lyu

Wuttke

et al. 2020

Chem

107

104

View full text Add to dashboard Cite

Reticular chemistry operates in an infinite space of compositions, structures, properties, and applications. Although great progress has been made in exploring this space through the development of metal-organic frameworks and covalent organic frameworks, there remains a gap between what we foresee as being possible and what can actually be accomplished with the current tools and methods. The establishment of digital reticular chemistry, where digital tools are deployed, in particular laboratory robotics and artificial intelligence, will fundamentally change the current workflow to enable discovery of this untapped chemical space and to go beyond the limits of human capacity. In so doing, long-standing challenges in reticular chemistry can finally be addressed faster and better, and more significantly, new questions, unimagined before digitization, can be articulated. The interface between human and ''machine'' is an integral part of this endeavor and one whose quality is critical to uncovering science transcending intellectual and physical borders.Scheme 1. Tools for Developing Digital Reticular Chemistry

show abstract

“…The nature of short interatomic interactions in the crystal lattice has been studied by applying the Hirshfeld surface analysis and associated pseudo-mirror 2D (two-dimensional) ngerprint plots over the surface. [47][48][49][50] Normally, the parameter d norm plot was assessed by the calculations of the d e (external) and d i (internal) distances to the nearby atoms. The existence of a red colour patch (surfaces) mark on the blue surface represented a uctuating intensity amongst the interacting atoms in the d norm surface plot, which shows the existence of interactions lesser than or equal to the summation of the van der Waals radii of the two interacting nuclei.…”

Section: Hirshfeld Surface Analysismentioning

confidence: 99%