Predicting inorganic dimensionality in templated metal oxides

Abstract

Amine-templated metal oxides are a class of hybrid organic–inorganic compounds with great structural diversity; by varying the compositions, 0D, 1D, 2D, and 3D inorganic dimensionalities can be achieved. In this work, we created a dataset of 3725 amine-templated metal oxides (including some metalloid oxides), their composition, amine identity, and dimensionality, extracted from the Cambridge Structure Database (CSD), which spans 71 elements, 25 main group building units, and 349 amines. We characterize the diversity of this dataset over reactants and in time. Artificial neural network models trained on this dataset can predict the most and least probable outcome dimensionalities with 71% and 95% accuracies, respectively, using only information about reactant identities, without stoichiometric information. Surprisingly, the amine identity plays only a minor role in most cases, as omitting this information only reduces the accuracy by <2%. The generality of this model is demonstrated on a time held-out test set of 36 amine-templated lanthanide oxalates, vanadium tellurites, vanadium selenites, vanadates, molybdates, and molybdenum sulfates, whose syntheses and structural characterizations are reported here for the first time, and which contain two new element combinations and four amines that are not present in the CSD.

Predicting compositional changes of organic–inorganic hybrid materials with Augmented CycleGAN

“…Crystal structures of amine-templated metal/metalloid oxides (ATMO) were collected from Cambridge Structure Database (CSD, version 5.41) following the procedures described in our previous study. 12 Briefly, a structure is considered as an ATMO if it (1) contains amine cations all of which can be neutralized to one type of amine (quaternary ammonium cations are therefore excluded), (2) contains at least one metal/metalloid atom bonded to three oxygen atoms, and (3) metal/metalloid atoms in the structure are bonded to oxygen/halogen only. Their chemical compositions were extracted using CSD API (the formula property of ccdc.crystal.Crystal), and were normalized to element fractions (sum to 1).…”

“…More details regarding dimensionality determination are available in Methods section of our previous study. 12…”

“…The pairing between chemical systems and amines can be described by a bipartite graph whose edges are the observed structures. Two noteworthy features of this bipartite graph (Figure 3) are that: the number of observed chemical systems (685, the purple arc) is much larger than that of amines (349, the green arc), 12 and, more importantly, connections are concentrated on a small portion of all available nodes for both chemical systems and amines. Only 22.64 % of all amine pairs are connected, and there is only a small probability (1.03 %) to find an edge between a randomly chosen chemical system-amine pair.…”

“…[7][8][9][10][11] The great structural diversity found in ATMOs (exemplified by the amine-templated zinc phosphate structures of four different dimensionalities), can only be matched by their compositional diversity (71 elements, 25 main group building units, and 349 amines as of 2021). 12 This immense chemical space, along with various types of possible interactions, makes it extremely challenging to predict the properties of novel ATMOs.…”

IP Analytics and Machine Learning Applied to Create Process Visualization Graphs for Chemical Utility Patents

“…ChemDataExtractor is a tool for automatically extracting chemical information from scientific documents and provides a wide range of state-of-the-art natural language processing algorithms [23,24] to interpret the English language text of scientific documents. The state-of-the-art methods include a chemistry-aware part-of-speech (POS) tagger, a Machine learning methods are used in the chemical domain and directly extract relationships among text in the raw data [15][16][17][18]. The tool Chemical Tagger is frequently used for chemical text mining [19] and parses text while classifying the chemical information (e.g., reactant, solvent) in the text files [20,21].…”