This work presents a machine learning approach for the computer vision-based recognition of materials inside vessels in the chemistry lab and other settings. In addition, we release a data set associated with the training of the model for further model development. The task to learn is finding the region, boundaries, and category for each material phase and vessel in an image. Handling materials inside mostly transparent containers is the main activity performed by human and robotic chemists in the laboratory. Visual recognition of vessels and their contents is essential for performing this task. Modern machine-vision methods learn recognition tasks by using data sets containing a large number of annotated images. This work presents the Vector-LabPics data set, which consists of 2187 images of materials within mostly transparent vessels in a chemistry lab and other general settings. The images are annotated for both the vessels and the individual material phases inside them, and each instance is assigned one or more classes (liquid, solid, foam, suspension, powder, ...). The fill level, labels, corks, and parts of the vessel are also annotated. Several convolutional nets for semantic and instance segmentation were trained on this data set. The trained neural networks achieved good accuracy in detecting and segmenting vessels and material phases, and in classifying liquids and solids, but relatively low accuracy in segmenting multiphase systems such as phase-separating liquids.
Computer-based de-novo design of functional molecules is one of the most prominent challenges in cheminformatics today. As a result, generative and evolutionary inverse designs from the field of artificial intelligence have emerged at a rapid pace, with aims to optimize molecules for a particular chemical property. These models ‘indirectly’ explore the chemical space; by learning latent spaces, policies, and distributions, or by applying mutations on populations of molecules. However, the recent development of the SELFIES (Krenn 2020 Mach. Learn.: Sci. Technol. 1 045024) string representation of molecules, a surjective alternative to SMILES, have made possible other potential techniques. Based on SELFIES, we therefore propose PASITHEA, a direct gradient-based molecule optimization that applies inceptionism (Mordvintsev 2015) techniques from computer vision. PASITHEA exploits the use of gradients by directly reversing the learning process of a neural network, which is trained to predict real-valued chemical properties. Effectively, this forms an inverse regression model, which is capable of generating molecular variants optimized for a certain property. Although our results are preliminary, we observe a shift in distribution of a chosen property during inverse-training, a clear indication of PASITHEA’s viability. A striking property of inceptionism is that we can directly probe the model’s understanding of the chemical space on which it is trained. We expect that extending PASITHEA to larger datasets, molecules and more complex properties will lead to advances in the design of new functional molecules as well as the interpretation and explanation of machine learning models.
Lead iodide−organic hybrids (iodoplumbates) have emerged as a class of materials with promising electronic and optical properties, and potential applications in photovoltaics and electronic devices. Hybrid iodoplumbates are composed of organic cations and lead iodide anions that exhibit diverse morphologies which determine the optical and electronic properties of the crystal. However, the diversity of the iodoplumbates is limited by the types of organic cations amenable for integration into the structure. Amides represent one of the largest groups of organic molecules, yet no examples of iodoplumbates based on protonated amide cations have been demonstrated so far. In this work, we show that it is possible to consistently grow iodoplumbates from amides following two distinct pathways. The first pathway involves growing iodoplumbates using amidium (protonated amides) as the organic cation in the crystal, which occurs for tertiary amides and urea. The second pathway involves growing iodoplumbates from primary and secondary amides, resulting in crystals containing the ammonium hydrolysis product of the amide. This path also leads to an interesting case of ring opening crystallization. The lead iodide one-dimensional chain motif composes most of the resulting structures. The large number of available amide molecules suggests that this method considerably expands the range of possible iodoplumbate structures. ■ INTRODUCTIONLead(II) iodide−organic hybrid materials (iodoplumbates) have been extensively explored owing to their diverse range of structural motifs which induce a variety of optical and electronic properties. Iodoplumbate optical properties include photoluminescence, 1,2 photochromic, 3,4 and nonlinear optics, 5−9 while the electronic features include semiconductivity 4,5,10−12 and dielectric 13 behaviors. These properties make iodoplumbate materials promising candidates for various applications including solar cell, 14−16 light emitting diodes, 17 and dielectric media. 13 The optical and electrical properties of iodoplumbates are mainly determined by the topology of the inorganic lead(II) iodide component. 12 The overall crystal structure of iodoplumbates is determined by the interplay between the negatively charged lead(II) iodide octahedral complex and the positively charged organic cations. 4,12 The geometry and topology of the lead(II) iodide component are, therefore, controlled by the type of organic cation used to form the crystals. Namely, the organic cation acts as a template, which controls the topology, dimensionality, and geometry of the inorganic lead-iodide complex and by this controls the optical and electronic properties of these materials. It is, therefore, possible to control and tune the material properties by changing the type of organic cations used for the crystallization. 4,12 It has been demonstrated that depending on the type of organic cation, the topology of the lead(II) iodide complex can obtain a range of structural motifs with various dimensionalities including one-dimensional (1...
A statistical survey was carried out to examine the connection between hydrogen-bond ring motifs (synthons) and crystallographic special symmetry positions. In the first part, the probability of common hydrogen-bond ring motifs to occupy specific crystallographic symmetry positions of inversion centers, rotation axes and mirror planes was examined. In the second part the probability of the occurrence of hydrogen-bond ring motifs was compared between crystals of chiral molecules (which cannot form inversion or mirror symmetry) to crystals of achiral molecules and racemic crystals. The results show that the crystallographic inversion center is a very significant component in the formation of hydrogen-bond ring motifs.
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.