Influence of Template Size, Canonicalization, and Exclusivity for Retrosynthesis and Reaction Prediction Applications

An effective and rapid deep learning method to predict chemical reactions contributes to the research and development of organic chemistry and drug discovery.

Download Full-text

Synergies Between Quantum Mechanics and Machine Learning in Reaction Prediction

Journal of Chemical Information and Modeling ◽

10.1021/acs.jcim.6b00351 ◽

2016 ◽

Vol 56 (11) ◽

pp. 2125-2128 ◽

Cited By ~ 26

Author(s):

Peter Sadowski ◽

David Fooshee ◽

Niranjan Subrahmanya ◽

Pierre Baldi

Keyword(s):

Machine Learning ◽

Quantum Mechanics ◽

Reaction Prediction

Download Full-text

Elastodynamic modeling and joint reaction prediction for 3-PRS PKM

Journal of Central South University ◽

10.1007/s11771-015-2833-y ◽

2015 ◽

Vol 22 (8) ◽

pp. 2971-2979 ◽

Cited By ~ 2

Author(s):

Jun Zhang ◽

Yan-qin Zhao

Keyword(s):

Reaction Prediction ◽

Elastodynamic Modeling ◽

Joint Reaction

Download Full-text

Reaction Prediction via Atomistic Simulation: from Quantum Mechanics to Machine Learning

iScience ◽

10.1016/j.isci.2020.102013 ◽

2020 ◽

pp. 102013

Author(s):

Pei-Lin Kang ◽

Zhi-Pan Liu

Keyword(s):

Machine Learning ◽

Quantum Mechanics ◽

Atomistic Simulation ◽

Reaction Prediction

Download Full-text

Controlling the Size of Interior Core of Silicon Nanowires

Journal of Nano Research ◽

10.4028/www.scientific.net/jnanor.45.193 ◽

2017 ◽

Vol 45 ◽

pp. 193-198 ◽

Cited By ~ 2

Author(s):

Ankur Soam ◽

Rajiv Dusane

Keyword(s):

Electrical Properties ◽

Silicon Nanowires ◽

Thermal Evaporation ◽

Silicon Film ◽

Chemical Vapor ◽

Hot Wire ◽

Vapor Liquid Solid ◽

Thermal Evaporation Method ◽

Evaporation Method ◽

Template Size

As the physical and electrical properties of silicon nanowires (SiNWs) are determined by their dimension, it is necessary to control their dimension to integrate them in a device. SiNWs were synthesized via Vapor-Liquid-Solid (VLS) mechanism in hot-wire chemical vapor process (HWCVP) technique using silane as a Si source and Sn as a catalyst. Different sizes of nano-template have been made by depositing of different amount of Sn using thermal evaporation method. The size of nano-template is found to be increased with the quantity of Sn. The diameter of resulted SiNWs depends on the size of the nano-template and it increases with the nano-template size. However, the diameter of SiNWs is found to be much larger than the used nano-template which is due to the deposition of silicon film on the sidewalls of the growing SiNWs. It is demonstrated here that the diameter of the interior core of SiNWs can be controlled desirable by adjusting the size of the nano-template.

Download Full-text

Spectral Minutiae Fingerprint Recognition System

International Journal of Computer and Communication Technology ◽

10.47893/ijcct.2014.1228 ◽

2014 ◽

pp. 103-108

Author(s):

S. Shanawaz Basha ◽

N. Musrat Sultana

Keyword(s):

Large Scale ◽

Reduction Rate ◽

Principal Component ◽

Rejection Rate ◽

Recognition System ◽

Feature Reduction ◽

Fingerprint Recognition ◽

Identification System ◽

Behavioral Characteristics ◽

Template Size

Biometrics refers to the automatic recognition of individuals based on their physiological and/or behavioral characteristics, such as faces, finger prints, iris, and gait. In this paper, we focus on the application of finger print recognition system. The spectral minutiae fingerprint recognition is a method to represent a minutiae set as a fixedlength feature vector, which is invariant to translation, and in which rotation and scaling become translations, so that they can be easily compensated for. Based on the spectral minutiae features, this paper introduces two feature reduction algorithms: the Column Principal Component Analysis and the Line Discrete Fourier Transform feature reductions, which can efficiently compress the template size with a reduction rate of 94%.With reduced features, we can also achieve a fast minutiae-based matching algorithm. This paper presents the performance of the spectral minutiae fingerprint recognition system, this fast operation renders our system suitable for a large-scale fingerprint identification system, thus significantly reducing the time to perform matching, especially in systems like, police patrolling, airports etc,. The spectral minutiae representation system tends to significantly reduce the false acceptance rate with a marginal increase in the false rejection rate.

Download Full-text

More and Faster: Simultaneously Improving Reaction Coverage and Computational Cost in Automated Reaction Prediction Tasks

10.26434/chemrxiv.13076087 ◽

2020 ◽

Author(s):

Qiyuan Zhao ◽

Brett Savoie

Keyword(s):

Transition State ◽

Domain Knowledge ◽

Low Cost ◽

Computational Cost ◽

Chemical Degradation ◽

Reaction Pathways ◽

Reaction Networks ◽

Complex Reaction ◽

Success Rates ◽

Reaction Prediction

<div> <div> <div> <p>Automated reaction prediction has the potential to elucidate complex reaction networks for applications ranging from combustion to materials degradation. Although substantial progress has been made in predicting specific reaction pathways and resolving mechanisms, the computational cost and inconsistent reaction coverage of automated prediction are still obstacles to exploring deep reaction networks without using heuristics. Here we show that cost can be reduced and reaction coverage can be increased simultaneously by relatively straight- forward modifications of the reaction enumeration, geometry initialization, and transition state convergence algorithms that are common to many emerging prediction methodologies. These changes are implemented in the context of Yet Another Reaction Program (YARP), our reaction prediction package, for which we report a head-to-head comparison with prevailing methods for two benchmark reaction prediction tasks. In all cases, we observe near perfect recapitulation of established reaction pathways and products by YARP, without the use of heuristics or other domain knowledge to guide reaction selection. In addition, YARP also discovers many new kinetically relevant pathways and products reported here for the first time. This is achieved while simultaneously reducing the cost of reaction characterization nearly 100-fold and increasing transition state success rates and intended rates over 2-fold and 10-fold, respectively, compared with recent benchmarks. This combination of ultra-low cost and high reaction-coverage creates opportunities to explore the reactivity of larger sys- tems and more complex reaction networks for applications like chemical degradation, where approaches based on domain heuristics fail. </p> </div> </div> </div>

Download Full-text