Browse
Submit Data
Databases
API
Help

Dataset Information

45 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Deep Learning Insights into Lanthanides Complexation Chemistry.

ABSTRACT: Modern structure-property models are widely used in chemistry; however, in many cases, they are still a kind of a "black box" where there is no clear path from molecule structure to target property. Here we present an example of deep learning usage not only to build a model but also to determine key structural fragments of ligands influencing metal complexation. We have a series of chemically similar lanthanide ions, and we have collected data on complexes' stability, built models, predicting stability constants and decoded the models to obtain key fragments responsible for complexation efficiency. The results are in good correlation with the experimental ones, as well as modern theories of complexation. It was shown that the main influence on the constants had a mutual location of the binding centers.

SUBMITTER: Mitrofanov AA

PROVIDER: S-EPMC8198800 | biostudies-literature | 2021 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Deep Learning Insights into Lanthanides Complexation Chemistry.

Mitrofanov Artem A AA Matveev Petr I PI Yakubova Kristina V KV Korotcov Alexandru A Sattarov Boris B Tkachenko Valery V Kalmykov Stepan N SN

Molecules (Basel, Switzerland) 20210527 11

Modern structure-property models are widely used in chemistry; however, in many cases, they are still a kind of a "black box" where there is no clear path from molecule structure to target property. Here we present an example of deep learning usage not only to build a model but also to determine key structural fragments of ligands influencing metal complexation. We have a series of chemically similar lanthanide ions, and we have collected data on complexes' stability, built models, predicting st ...[more]

PMID: 34072262

Similar Datasets

The Hitchhiker's Guide to Deep Learning Driven Generative Chemistry.

Project description:This microperspective covers the most recent research outcomes of artificial intelligence (AI) generated molecular structures from the point of view of the medicinal chemist. The main focus is on studies that include synthesis and experimental in vitro validation in biochemical assays of the generated molecular structures, where we analyze the reported structures' relevance in modern medicinal chemistry and their novelty. The authors believe that this review would be appreciated by medicinal chemistry and AI-driven drug design (AIDD) communities and can be adopted as a comprehensive approach for qualifying different research outcomes in AIDD.

| S-EPMC10351082 | biostudies-literature

Fluorophore-Assisted Click Chemistry through Copper(I) Complexation.

Project description:The copper-catalyzed alkyne-azide cycloaddition (CuAAC) is one of the most powerful chemical strategies for selective fluorescent labeling of biomolecules in in vitro or biological systems. In order to accelerate the ligation process and ensure efficient formation of conjugates under diluted conditions, external copper(I) ligands or sophisticated copper(I)-chelating azides are used. This latter strategy, however, increases the bulkiness of the triazole linkage, thus perturbing the biological function or dynamic behavior of the conjugates. In a proof-of-concept study, we investigated the use of an extremely compact fluorophore-based copper(I) chelating azide in order to accelerate the CuAAC with concomitant fluorescence labeling; in our strategy, the fluorophore is able to complex copper(I) species while retaining its photophysical properties. It is believed that this unprecedented approach which was applied for the labeling of a short peptide molecule and the fluorescent labeling of live cells, could be extended to other families of nitrogen-based fluorophores in order to tune both the reaction rate and photophysical characteristics.

| S-EPMC7225998 | biostudies-literature

ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition.

Project description:Conventional machine learning approaches for predicting material properties from elemental compositions have emphasized the importance of leveraging domain knowledge when designing model inputs. Here, we demonstrate that by using a deep learning approach, we can bypass such manual feature engineering requiring domain knowledge and achieve much better results, even with only a few thousand training samples. We present the design and implementation of a deep neural network model referred to as ElemNet; it automatically captures the physical and chemical interactions and similarities between different elements using artificial intelligence which allows it to predict the materials properties with better accuracy and speed. The speed and best-in-class accuracy of ElemNet enable us to perform a fast and robust screening for new material candidates in a huge combinatorial space; where we predict hundreds of thousands of chemical systems that could contain yet-undiscovered compounds.

| S-EPMC6279928 | biostudies-literature

The Chemistry of Lanthanides in Biology: Recent Discoveries, Emerging Principles, and Technological Applications.

Project description:The essential biological role of rare earth elements lay hidden until the discovery in 2011 that lanthanides are specifically incorporated into a bacterial methanol dehydrogenase. Only recently has this observation gone from a curiosity to a major research area, with the appreciation for the widespread nature of lanthanide-utilizing organisms in the environment and the discovery of other lanthanide-binding proteins and systems for selective uptake. While seemingly exotic at first glance, biological utilization of lanthanides is very logical from a chemical perspective. The early lanthanides (La, Ce, Pr, Nd) primarily used by biology are abundant in the environment, perform similar chemistry to other biologically useful metals and do so more efficiently due to higher Lewis acidity, and possess sufficiently distinct coordination chemistry to allow for selective uptake, trafficking, and incorporation into enzymes. Indeed, recent advances in the field illustrate clear analogies with the biological coordination chemistry of other metals, particularly CaII and FeIII, but with unique twists-including cooperative metal binding to magnify the effects of small ionic radius differences-enabling selectivity. This Outlook summarizes the recent developments in this young but rapidly expanding field and looks forward to potential future discoveries, emphasizing continuity with principles of bioinorganic chemistry established by studies of other metals. We also highlight how a more thorough understanding of the central chemical question-selective lanthanide recognition in biology-may impact the challenging problems of sensing, capture, recycling, and separations of rare earths.

| S-EPMC6764073 | biostudies-literature

pH Responsive Antibacterial Hydrogel Utilizing Catechol-Boronate Complexation Chemistry.

Project description:Bacteria such as Methicillin-resistant Staphylococcus aureus (MRSA) causes acidic microenvironment during infection. A biomaterial that exhibits tunable antimicrobial property in a pH dependent manner is potentially attractive. Herein, we presented a novel antibacterial hydrogel consisting of pH responsive and reversible catechol-boronate linkage formed between intrinsically bactericidal chlorinated catechol (catechol-Cl) and phenylboronic acid. Fourier transformed infrared spectroscopy (FTIR), oscillatory rheometry, and Johnson Kendall Roberts (JKR) contact mechanics testing confirmed the formation and dissociation of the complex in a pH dependent manner. When the hydrogel was treated with an acidic buffer (pH 3), the hydrogel exhibited excellent antimicrobial property against multiple strains of Gram-positive and negative bacteria including MRSA (up to 4 log10 reduction from 108 colony forming units/mL). At an acidic pH, catechol-Cl was unbound from the phenylboronic acid and available for killing bacteria. Conversely, when the hydrogel was treated with a basic buffer (pH 8.5), the hydrogel lost its antimicrobial property but also became non-cytotoxic. At a basic pH, the formation of catechol-boronate complex effectively reduce the exposure of the cytotoxic catechol-Cl to the surrounding. When further incubating the hydrogel in an acidic pH, the reversible complex dissociated to re-expose catechol-Cl and the hydrogel recovered its antibacterial property. Overall, the combination of catechol-Cl and phenylboronic acid provide a new strategy for designing hydrogels with pH responsive antibacterial activity and reduced cytotoxicity.

| S-EPMC9015688 | biostudies-literature

Deep learning approach for chemistry and processing history prediction from materials microstructure.

Project description:Finding the chemical composition and processing history from a microstructure morphology for heterogeneous materials is desired in many applications. While the simulation methods based on physical concepts such as the phase-field method can predict the spatio-temporal evolution of the materials' microstructure, they are not efficient techniques for predicting processing and chemistry if a specific morphology is desired. In this study, we propose a framework based on a deep learning approach that enables us to predict the chemistry and processing history just by reading the morphological distribution of one element. As a case study, we used a dataset from spinodal decomposition simulation of Fe-Cr-Co alloy created by the phase-field method. The mixed dataset, which includes both images, i.e., the morphology of Fe distribution, and continuous data, i.e., the Fe minimum and maximum concentration in the microstructures, are used as input data, and the spinodal temperature and initial chemical composition are utilized as the output data to train the proposed deep neural network. The proposed convolutional layers were compared with pretrained EfficientNet convolutional layers as transfer learning in microstructure feature extraction. The results show that the trained shallow network is effective for chemistry prediction. However, accurate prediction of processing temperature requires more complex feature extraction from the morphology of the microstructure. We benchmarked the model predictive accuracy for real alloy systems with a Fe-Cr-Co transmission electron microscopy micrograph. The predicted chemistry and heat treatment temperature were in good agreement with the ground truth.

| S-EPMC8927426 | biostudies-literature

Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems.

Project description:Machine learning models are poised to make a transformative impact on chemical sciences by dramatically accelerating computational algorithms and amplifying insights available from computational chemistry methods. However, achieving this requires a confluence and coaction of expertise in computer science and physical sciences. This Review is written for new and experienced researchers working at the intersection of both fields. We first provide concise tutorials of computational chemistry and machine learning methods, showing how insights involving both can be achieved. We follow with a critical review of noteworthy applications that demonstrate how computational chemistry and machine learning can be used together to provide insightful (and useful) predictions in molecular and materials modeling, retrosyntheses, catalysis, and drug design.

| S-EPMC8391798 | biostudies-literature

Insights and approaches using deep learning to classify wildlife.

Project description:The implementation of intelligent software to identify and classify objects and individuals in visual fields is a technology of growing importance to operatives in many fields, including wildlife conservation and management. To non-experts, the methods can be abstruse and the results mystifying. Here, in the context of applying cutting edge methods to classify wildlife species from camera-trap data, we shed light on the methods themselves and types of features these methods extract to make efficient identifications and reliable classifications. The current state of the art is to employ convolutional neural networks (CNN) encoded within deep-learning algorithms. We outline these methods and present results obtained in training a CNN to classify 20 African wildlife species with an overall accuracy of 87.5% from a dataset containing 111,467 images. We demonstrate the application of a gradient-weighted class-activation-mapping (Grad-CAM) procedure to extract the most salient pixels in the final convolution layer. We show that these pixels highlight features in particular images that in some cases are similar to those used to train humans to identify these species. Further, we used mutual information methods to identify the neurons in the final convolution layer that consistently respond most strongly across a set of images of one particular species. We then interpret the features in the image where the strongest responses occur, and present dataset biases that were revealed by these extracted features. We also used hierarchical clustering of feature vectors (i.e., the state of the final fully-connected layer in the CNN) associated with each image to produce a visual similarity dendrogram of identified species. Finally, we evaluated the relative unfamiliarity of images that were not part of the training set when these images were one of the 20 species "known" to our CNN in contrast to images of the species that were "unknown" to our CNN.

| S-EPMC6544615 | biostudies-literature

Rapidly responsive smart adhesive-coated micropillars utilizing catechol-boronate complexation chemistry.

Project description:Smart adhesive hydrogels containing 10 mol% each of dopamine methacrylamide (DMA) and 3-acrylamido phenylboronic acid (APBA) were polymerized in situ onto polydimethylsiloxane (PMDS) micropillars with different aspect ratios (AR = 0.4, 1 and 2). Using Johnson-Kendall-Roberts (JKR) contact mechanics tests, the adhesive-coated pillars demonstrated strong wet adhesion at pH 3 (Wadh = 420 mJ m-2) and can be repeatedly deactivated and reactivated by changing the pH value (pH 9 and 3, respectively). When compared to the bulk adhesive hydrogel of the same composition, the adhesive-coated pillars exhibited a significantly faster rate of transition (1 min) between strong and weak adhesion. This was attributed to an increased surface area to volume ratio of the adhesive hydrogel-coated pillars, which permitted rapid diffusion of ions into the adhesive matrix to form or break the catechol-boronate complex.

| S-EPMC6776246 | biostudies-literature

Advancing understanding of actinide(iii) (Ac, Am, Cm) aqueous complexation chemistry.

Project description:The positive impact of having access to well-defined starting materials for applied actinide technologies - and for technologies based on other elements - cannot be overstated. Of numerous relevant 5f-element starting materials, those in complexing aqueous media find widespread use. Consider acetic acid/acetate buffered solutions as an example. These solutions provide entry into diverse technologies, from small-scale production of actinide metal to preparing radiolabeled chelates for medical applications. However, like so many aqueous solutions that contain actinides and complexing agents, 5f-element speciation in acetic acid/acetate cocktails is poorly defined. Herein, we address this problem and characterize Ac3+ and Cm3+ speciation as a function of increasing acetic acid/acetate concentrations (0.1 to 15 M, pH = 5.5). Results obtained via X-ray absorption and optical spectroscopy show the aquo ion dominated in dilute acetic acid/acetate solutions (0.1 M). Increasing acetic acid/acetate concentrations to 15 M increased complexation and revealed divergent reactivity between early and late actinides. A neutral Ac(H2O)6 (1)(O2CMe)3 (1) compound was the major species in solution for the large Ac3+. In contrast, smaller Cm3+ preferred forming an anion. There were approximately four bound O2CMe1- ligands and one to two inner sphere H2O ligands. The conclusion that increasing acetic acid/acetate concentrations increased acetate complexation was corroborated by characterizing (NH4)2M(O2CMe)5 (M = Eu3+, Am3+ and Cm3+) using single crystal X-ray diffraction and optical spectroscopy (absorption, emission, excitation, and excited state lifetime measurements).

| S-EPMC8179631 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data