Inverse Material Search and Synthesis Verification by Hand Drawings via Transfer Learning and Contour Detection

Abstract

Nano‐ and micromaterials of various morphologies and compositions have extensive use in many different areas. However, the search for procedures giving custom nanomaterials with the desired structure, shape, and size remains a challenge and is often implemented by manual article screening. Here, for the first time, scanning and transmission electron microscopy inverse image search and hand drawing‐based search via transfer learning are developed, namely, VGG16 convolution neural network repurposing for image features extraction and image similarity determination. Moreover, the case use of this platform is demonstrated on the calcium carbonate system, where the data are acquired by random high throughput experimental synthesis, and on Au nanoparticles data extracted from the articles. This approach can be used for advanced nanomaterials search, synthesis procedure verification, and can be further combined with machine learning solutions to provide data‐driven nanomaterials discovery.

Quantitative Prediction of Inorganic Nanomaterial Cellular Toxicity via Machine Learning

“…However, when it comes to nanoparticles, these descriptors become insufficient, as they bear no information about their structure and surficial properties. Accurate representation of nanomaterials requires various descriptors based on nanomaterial structure, [ 27 ] atom‐ and atom distance‐based parameters, [ 28 ] quantum mechanics calculations, [ 29 ] SMILES representations, [ 30 ] periodic table constants, [ 31 ] physicochemical properties such as size, shape, and surface charge, [ 32 ] and experimental data. [ 33 ] The descriptors are used to predict various bio‐properties as protein corona formation, [ 34 ] cellular uptake, [ 35 ] ecotoxic effects [ 36 ] as well as cytotoxicity,; [ 37,38 ] the latter represents a crucial parameter screened in almost any nanomaterial‐related research.…”