Filters








16,320 Hits in 5.2 sec

Application of Chemical Graph Theory for Automated Mechanism Generation

Artur Ratkiewicz, Thanh N. Truong
2003 Journal of chemical information and computer sciences  
The mechanism is generated using a set of reaction patterns (sub-graphs).  ...  We present an application of the chemical graph theory approach for generating elementary reactions of complex systems.  ...  The program relies on a graph-theory based molecular tree isomorphism algorithm to find the matching positions in the molecule (see Figure 1 , with more than one match when the pattern is applied).  ... 
doi:10.1021/ci020297f pmid:12546535 fatcat:xafan33pmvbuddh2v2p3a7nmze

Pattern recognition tools for proteomics

Virginio Cantoni
2014 The European Physical Journal Plus  
Binding sites recognition is generally based on geometry and combined with physico-chemical properties, since the conformation, size and chemical composition of the protein surface are all relevant for  ...  The problem is usually pursued by ad hoc pattern descriptors which are often point-based and cumbersome for management and processing.  ...  Binding sites recognition is generally based on geometry and combined with physico-chemical properties, since the conformation, size and chemical composition of the protein surface are all relevant for  ... 
doi:10.1140/epjp/i2014-14130-3 fatcat:sddaw3sbo5eb7mkkib6o23hpge

Automated extraction of chemical structure information from digital raster images

Jungkap Park, Gus R Rosania, Kerby A Shedden, Mandee Nguyen, Naesung Lyu, Kazuhiro Saitou
2009 Chemistry Central Journal  
To search for chemical structures in research articles, diagrams or text representing molecules need to be translated to a standard chemical file format compatible with cheminformatic search engines.  ...  Based on its stable performance and high accuracy, ChemReader may be sufficiently accurate for annotating the chemical database with links to scientific research articles.  ...  The most interesting features, at the post-processing stage, is that chemOCR uses a graph-matching algorithm to select the best-matching chemical structure fragment against sub-graphs of chemical structures  ... 
doi:10.1186/1752-153x-3-4 pmid:19196483 pmcid:PMC2648963 fatcat:5m4e3xvydng4pbow6asgeeuw3u

Searching for pharmacophoric patterns in databases of three-dimensional chemical structures

Peter Willett
1995 Journal of Molecular Recognition  
JOURNAL OF MOLECULAR RECOGNITION, VOL. 8, 290-303 (1995) Searching for Pharmacophoric Patterns in Databases of Three-dimensional Chemical Structures Peter Willett Krebs Institute for Biomolecular Research  ...  A graph-theoretic algorithm for match- ing chemical structures. J. Chem. Documentation 5, 36-43. Trinajstic, N. (ed.) (1983). Chemical Graph Theory. Ellis Horwood, Chichester. Ullmann, J. R. (1976).  ... 
doi:10.1002/jmr.300080503 pmid:8619950 fatcat:zrw25m53obdyjp5posqipup26a

An approach for extracting chemical data from molecular representations

Amena Mahmoud, Taher Hamza, M. Z. Rashad
2020 International Journal of Advanced Computer Research  
as an intelligent module for converting chemical molecule structures to computerized structures.  ...  Finally, a comparison between related approaches and the current proposed one at their precision rates for classification of substructure patterns was conducted.  ...  Template based recognition approach can recognize those patterns.  ... 
doi:10.19101/ijacr.2019.940105 fatcat:27jr23zjlvcgtg7hc7l22pkcd4

Implicit and Explicit Graph Embedding: Comparison of Both Approaches on Chemoinformatics Applications [chapter]

Benoit Gaüzère, Makoto Hasegawa, Luc Brun, Salvatore Tabbone
2012 Lecture Notes in Computer Science  
Defining similarities or distances between graphs is one of the bases of the structural pattern recognition field.  ...  The first one is based on the notion of graph edit distance which aims to catch a global dissimilarity between graphs.  ...  Acknowledgments The authors thanks Salim Jouili for providing the graph embedding code.  ... 
doi:10.1007/978-3-642-34166-3_56 fatcat:k4vomhhm6bfi7fj7el66pabdi4

DIGITAL REPRESENTATION TECHNIQUES FOR OLFACTORY FEATURES

Dewanand A. Meshram, Dipti D. Patil
2021 Information Technology in Industry  
The system is applied to perform Machine-learned odor recognition from physico-chemical properties of volatile molecules.  ...  The properties of volatile molecules are to match the pattern of chemosensory organisms. Artificial intelligence is used to predict the molecule of smell by applying neural network.  ...  The researchers are developing a neural network to identify artificial vanilla flavor by odor molecule pattern recognition system. intended to operate on graph as input to honestly predict the odor descriptor  ... 
doi:10.17762/itii.v9i1.131 fatcat:nzchuvivgbdafjhorzzivvaqky

A Survey on Applications of Bipartite Graph Edit Distance [chapter]

Michael Stauffer, Thomas Tschachtli, Andreas Fischer, Kaspar Riesen
2017 Lecture Notes in Computer Science  
About ten years ago, a novel graph edit distance framework based on bipartite graph matching has been introduced.  ...  Besides various extensions from the methodological point of view, we also observe a great variety of applications that make use of the bipartite graph matching framework.  ...  The availability of a dissimilarity or similarity measure is a basic requirement for pattern recognition and analysis.  ... 
doi:10.1007/978-3-319-58961-9_22 fatcat:dlgewedu2rd6zpkqshzpv6oe3u

Recognition of Binding Patterns Common to a Set of Protein Structures [chapter]

Maxim Shatsky, Alexandra Shulman-Peleg, Ruth Nussinov, Haim J. Wolfson
2005 Lecture Notes in Computer Science  
We present a novel computational method, MultiBind, for recognition of binding patterns common to a set of protein structures.  ...  The method recognizes patterns which are responsible for binding small molecules such as estradiol, ATP/ANP and transition state analogues.  ...  Conclusions We have presented a novel computational method, MultiBind, for recognition of physico-chemical binding patterns.  ... 
doi:10.1007/11415770_33 fatcat:tosd5tf5r5bjplfdnwxjwu6aoa

Graph theoretic methods for the analysis of structural relationships in biological macromolecules

Peter J. Artymiuk, Ruth V. Spriggs, Peter Willett
2005 Journal of the American Society for Information Science and Technology  
They thus provide a natural complement to the pattern matching algorithms that are used in bioinformatics to identify sequence relationships.  ...  ., Spriggs, R.V. and Willett, P. (2005) Graph theoretic methods for the analysis of structural relationships in biological macromolecules, Journal of the Abstract Subgraph isomorphism and maximum common  ...  A graph provides a simple and direct way of encoding the topology of a two-dimensional (2D) chemical structure diagram, by using the nodes and edges of a graph to represent the atoms and bonds of a molecule  ... 
doi:10.1002/asi.20140 fatcat:two4d7f4p5g5fgdhhbke2agvcq

Graph embedding in SYNCHEM2, an expert system for organic synthesis discovery

Joseph D Benstock, Donald J Berndt, Krishna K Agarwal
1988 Discrete Applied Mathematics  
The expert system SYNCHEM~ searches for synthesis routes of organic molecules without the online guidance of a user, and this paper examines how embedding information helps to implement the central operations  ...  The paper also outlines the architecture of SYNCHEM~, analyzes the computational time complexity of embedding and related problems in graph isomorphism and canonical chemical naming, and suggests topics  ...  Miller for suggestions and helpful discussions, and Noglle Benstock for assistance with the diagrams.  ... 
doi:10.1016/0166-218x(88)90005-4 fatcat:rfpihledazhynnrosdbapqc4mm

A Comparative Study of Graph Isomorphism Applications

Rachna Somkunwar, Vinod Moreshwar
2017 International Journal of Computer Applications  
Graph isomorphism is the area of pattern matching and widely used in various applications such as image processing, protein structure, computer and information system, chemical bond structure, Social Networks  ...  Number of real world problems is represented by graph.  ...  Handling such types of graphs is a very time consuming method. Pattern recognition is the area where two different objects are matched on the basis of some features.  ... 
doi:10.5120/ijca2017913414 fatcat:5v2fwtliynd6vlw5bd7w4juoce

A review of three-dimensional chemical structure retrieval systems

Peter Willett
1992 Journal of Chemometrics  
Given such a graph-based representation, Gund ef al. noted that a search for a pharmacophore in a 3D molecule is entirely analogous to an atom-by-atom search for a query substructure in a 2D molecule and  ...  MOLPAT allowed a chemist to specify a query pattern and a drug molecule and the programme then searched for the occurrence of the pattern in the molecule.  ... 
doi:10.1002/cem.1180060602 fatcat:qacctiu6pvfa5aoqv3h2xhpht4

Robust Molecular Image Recognition: A Graph Generation Approach [article]

Yujie Qian, Zhengkai Tu, Jiang Guo, Connor W. Coley, Regina Barzilay
2022 arXiv   pre-print
Molecular image recognition is a fundamental task in information extraction from chemistry literature.  ...  Although they perform adequately on certain benchmarks, these models are not robust in real-world situations, where molecular images differ in style, quality, and chemical patterns.  ...  In this paper, we propose a graph generation approach for molecular image recognition.  ... 
arXiv:2205.14311v1 fatcat:75msfptsmzbrxlr7uzz74jiqau

EMBEDDING OF GRAPHS WITH DISCRETE ATTRIBUTES VIA LABEL FREQUENCIES

JAUME GIBERT, ERNEST VALVENY, HORST BUNKE
2013 International journal of pattern recognition and artificial intelligence  
Embedding a graph into a vector space solves this problem since graphs are turned into feature vectors and thus all the statistical learning machinery becomes available for graph input patterns.  ...  Graph-based representations of patterns are very flexible and powerful, but they are not easily processed due to the lack of learning algorithms in the domain of graphs.  ...  them an attractive new tool for graph-based pattern recognition problems.  ... 
doi:10.1142/s0218001413600021 fatcat:mhfocovaprgt3or4jaqa7kno7i
« Previous Showing results 1 — 15 out of 16,320 results