Inorganic-organic hybrid materials such as organically templated metal oxides, metal-organic frameworks (MOFs) and organohalide perovskites have been studied for decades, and hydrothermal and (non-aqueous) solvothermal syntheses have produced thousands of new materials that collectively contain nearly all the metals in the periodic table. Nevertheless, the formation of these compounds is not fully understood, and development of new compounds relies primarily on exploratory syntheses. Simulation- and data-driven approaches (promoted by efforts such as the Materials Genome Initiative) provide an alternative to experimental trial-and-error. Three major strategies are: simulation-based predictions of physical properties (for example, charge mobility, photovoltaic properties, gas adsorption capacity or lithium-ion intercalation) to identify promising target candidates for synthetic efforts; determination of the structure-property relationship from large bodies of experimental data, enabled by integration with high-throughput synthesis and measurement tools; and clustering on the basis of similar crystallographic structure (for example, zeolite structure classification or gas adsorption properties). Here we demonstrate an alternative approach that uses machine-learning algorithms trained on reaction data to predict reaction outcomes for the crystallization of templated vanadium selenites. We used information on 'dark' reactions--failed or unsuccessful hydrothermal syntheses--collected from archived laboratory notebooks from our laboratory, and added physicochemical property descriptions to the raw notebook information using cheminformatics techniques. We used the resulting data to train a machine-learning model to predict reaction success. When carrying out hydrothermal synthesis experiments using previously untested, commercially available organic building blocks, our machine-learning model outperformed traditional human strategies, and successfully predicted conditions for new organically templated inorganic product formation with a success rate of 89 per cent. Inverting the machine-learning model reveals new hypotheses regarding the conditions for successful product formation.
Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior, and in particular how different features influence the model prediction. This is important when interpreting the behavior of complex models, or asserting that certain problematic attributes (like race or gender) are not unduly influencing decisions.In this paper, we present a technique for auditing black-box models, which lets us study the extent to which existing models take advantage of particular features in the dataset, without knowing how the models work. Our work focuses on the problem of indirect influence: how some features might indirectly influence outcomes via other, related features. As a result, we can find attribute influences even in cases where, upon further direct examination of the model, the attribute is not referred to by the model at all.Our approach does not require the black-box model to be retrained. This is important if (for example) the model is only accessible via an API, and contrasts our work with other methods that investigate feature influence like feature selection. We present experimental evidence for the effectiveness of our procedure using a variety of publicly available datasets and models. We also validate our procedure using techniques from interpretable learning and feature selection, as well as against other black-box auditing procedures.
Abstract-Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior, and in particular how different features influence the model prediction. This is important when interpreting the behavior of complex models, or asserting that certain problematic attributes (like race or gender) are not unduly influencing decisions.In this paper, we present a technique for auditing black-box models, which lets us study the extent to which existing models take advantage of particular features in the dataset, without knowing how the models work. Our work focuses on the problem of indirect influence: how some features might indirectly influence outcomes via other, related features. As a result, we can find attribute influences even in cases where, upon further direct examination of the model, the attribute is not referred to by the model at all.Our approach does not require the black-box model to be retrained. This is important if (for example) the model is only accessible via an API, and contrasts our work with other methods that investigate feature influence like feature selection. We present experimental evidence for the effectiveness of our procedure using a variety of publicly available datasets and models. We also validate our procedure using techniques from interpretable learning and feature selection, as well as against other black-box auditing procedures.
The structural and electronic adaptability of a vanadium selenite framework is determined using cheminformatics data and machine learning algorithms.
The structural adaptability of [V 3 O 5 (SeO 3 ) 3 ] n 2nlayers in organically templated vanadium selenites was determined using a three step approach involving (i) 84 reaction study with 14 distinct organic amines and 6 different reaction conditions, (ii) decision tree construction using both dependent and independent variables, and (iii) the derivation of chemical hypotheses.Formation of [V 3 O 5 (SeO 3 ) 3 ] n 2nlayers requires that three criteria be met. First, compound stabilization through hydrogen-bonding with specific nucleophilic oxide ions is needed, requiring the presence of a primary ammonium site on the respective organic amine. Second, layer formation is facilitated through the use of compact ammonium cations that are able to achieve charge density matching with the anionic layers. Third, competition between organic ammonium cations and NH 4 + , which affects product formation, can be controlled through reagent choice and initial reactant concentrations. This approach to elucidate structural adaptability is generalizable and can be applied to a range of chemical systems.
Mit Hilfe einer beheizten Ionisationskammer wurde der Ionisierungsaufwand W von 78 aliphatischen Verbindungen sowie OEs zeigte sich, daß für homologe Reihen W proportional dem niedrigsten Ionisierungspotential lEine Abschätzung ergibt, daß vor allem die zur Anregung der Moleküle verbrauchte Energie von der Art der Substituenten abhängt, während die für die Ionisation verbrauchte Energie unabhängig von der Molekülstruktur einen Wert um 1,2 ·I
The pseudo-tetrahedral complexes [CuL 2 ]PF 6 ·7H 2 O·CH 3 OH (1) and [AgL 2 ]CF 3 SO 3 ·H 2 O (2) (L = 3,3′-bis(2-benzimidazolyl)-2,2′-bipyridine) have been synthesized and characterized through crystal structure analyses, electrochemistry, and spectroscopic methods. X-ray structural analyses of 1 and 2 indicate that sterically constrained N 4 ligands L are cis and behave as bidentate chelates to a single metal ion in a pseudo-tetrahedral fashion through the benzimidazole. As two benzimidazolyl rings exhibit considerable steric hindrance, the bipyridine unit of L remains uncoordinated. The pseudo-tetrahedral cation [CuL 2 ] + shows a quasi-reversible Cu I /Cu II oxidation-reduction wave in the CV in DMF (counter-ion PF 6 − ). The fluorescence titration of L with copper(I), silver(I), and also with pH have been conducted to examine the selectivity. The ligand shows remarkably high selectivity and sensitivity for Ag(I).
In the title compound, C22H18Cl2N2O, the indazole ring system is approximately planar [maximum deviation = 0.031 (2) Å], its mean plane is oriented at 3.17 (4) and 19.34 (4)° with respect to the phenyl and benzene rings. In the crystal, weak C—H...π interactions link the molecules into supramolecular chains running along theb-axis direction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.