scholarly journals Predicting Potentially Hazardous Chemical Reactions Using Explainable Neural Network

2021 ◽  
Author(s):  
Juhwan Kim ◽  
Geun Ho Gu ◽  
Juhwan Noh ◽  
Seongun Kim ◽  
Suji Gim ◽  
...  
Keyword(s):  
Neural Network ◽  
Experimental Investigation ◽  
Chemical Reactions ◽  
Laboratory Safety ◽  
Reaction Conditions ◽  
Hazardous Chemical ◽  
Critical Task

Predicting potentially dangerous chemical reactions is a critical task for the laboratory safety. However, traditional experimental investigation of reaction conditions for the possible hazardous or explosive byproducts entails substantial time...

scholarly journals Visible Light Photochemical Reactions for Nucleic Acid-Based Technologies

Molecules ◽  
2021 ◽  
Vol 26 (3) ◽  
pp. 556
Author(s):  
Bonwoo Koo ◽  
Haneul Yoo ◽  
Ho Jeong Choi ◽  
Min Kim ◽  
Cheoljae Kim ◽  
...  
Keyword(s):  
Nucleic Acid ◽  
Nucleic Acids ◽  
Visible Light ◽  
Chemical Reactions ◽  
Chemical Biology ◽  
Photochemical Reactions ◽  
Reaction Conditions ◽  
Promising Tool ◽  
Recent Developments ◽  
Visible Light Driven

The expanding scope of chemical reactions applied to nucleic acids has diversified the design of nucleic acid-based technologies that are essential to medicinal chemistry and chemical biology. Among chemical reactions, visible light photochemical reaction is considered a promising tool that can be used for the manipulations of nucleic acids owing to its advantages, such as mild reaction conditions and ease of the reaction process. Of late, inspired by the development of visible light-absorbing molecules and photocatalysts, visible light-driven photochemical reactions have been used to conduct various molecular manipulations, such as the cleavage or ligation of nucleic acids and other molecules as well as the synthesis of functional molecules. In this review, we describe the recent developments (from 2010) in visible light photochemical reactions involving nucleic acids and their applications in the design of nucleic acid-based technologies including DNA photocleaving, DNA photoligation, nucleic acid sensors, the release of functional molecules, and DNA-encoded libraries.

scholarly journals Stochastic modeling of microstructure of homopolymers and copolymers in batch reactor

2020 ◽  
Vol 9 (2) ◽  
pp. e04921930
Author(s):  
Matheus Dias Carvalho ◽  
Jorge David Alguiar Beliido ◽  
Antonio Marcos de Oliveira Siqueira ◽  
Júlio Cesar Costa Campos
Keyword(s):  
Stochastic Modeling ◽  
Chemical Reactions ◽  
Batch Reactor ◽  
Polymer Chains ◽  
Stochastic Methods ◽  
Batch Reactors ◽  
Straight Chain ◽  
Reaction Conditions ◽  
C Language ◽  
Methyl Styrene

Find the microstructure of the product generated in a reaction of polymerization is desirable from a material science standpoint, due to the association between the microstructure and the physical properties. For the science of this fact, this paper aims to use stochastic modeling to obtain the microstructure and key information from a set of polymer chains generated during a reaction. From this data, the present article contributes to the minimization of experimental expenses, besides the saving of time, since no experiments are necessary to discover the characteristics of the polymer obtained under certain reaction conditions. This information cannot be found by other usual methodologies for modeling chemical reactions, such as the deterministic form. Also, from a given desired structure, the initial concentration and temperature conditions for forming that product can be obtained. This study was conducted based on Monte Carlo stochastic methods, by which we seek to replicate the randomness present in chemical reactions. The algorithm created in C ++ language determines the variation of the number of molecules of each species with time, besides the chemical composition, the sequence of mere and size of the generated chains. This approach applies to straight-chain homopolymerizations and copolymerizations. In this paper, we studied the polymerization in styrene batch reactors to form polystyrene, in addition to the copolymerization of styrene with alpha-methyl styrene. These simulations were characterized by forming chains with small blocks of monomers.

Predicting chemical reactions with a neural network

1991 ◽  
pp. 392-398
Author(s):  
David W. Elrod ◽  
Gerry M. Maggiora ◽  
Robert G. Trenary
Keyword(s):  
Neural Network ◽  
Chemical Reactions

ENSEMBLES OF NEURAL NETWORKS BASED ON THE ALTERATION OF INPUT FEATURE VALUES

2012 ◽  
Vol 22 (01) ◽  
pp. 77-87 ◽  
Author(s):  
M. A. H. AKHAND ◽  
K. MURASE
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Experimental Investigation ◽  
Pattern Generation ◽  
Neural Network Ensemble ◽  
Classification Problems ◽  
Input Feature ◽  
A New Technique ◽  
Feature Values ◽  
Better Than

An ensemble performs well when the component classifiers are diverse yet accurate, so that the failure of one is compensated for by others. A number of methods have been investigated for constructing ensemble in which some of them train classifiers with the generated patterns. This study investigates a new technique of training pattern generation. The method alters input feature values of some patterns using the values of other patterns to generate different patterns for different classifiers. The effectiveness of neural network ensemble based on the proposed technique was evaluated using a suite of 25 benchmark classification problems, and was found to achieve performance better than or competitive with related conventional methods. Experimental investigation of different input values alteration techniques finds that alteration with pattern values in the same class is better for generalization, although other alteration techniques may offer more diversity.

Experimental investigation of the performance of an optical two-layer neural network

1994 ◽  
Author(s):  
Nikolay N. Evtihiev ◽  
Rostislav S. Starikov ◽  
Boris N. Onyky ◽  
Vadim V. Perepelitsa ◽  
Igor B. Scherbakov
Keyword(s):  
Neural Network ◽  
Experimental Investigation
Sign in / Sign up

Export Citation Format

Share Document