@article{Ricart2020,

title = {Automatic Annotation and Dereplication of Tandem Mass Spectra of Peptidic Natural Products},

author = {Emma Ricart and Maude Pupin and Markus Müller and Frédérique Lisacek},

url = {https://doi.org/10.1021/acs.analchem.0c03208},

doi = {10.1021/acs.analchem.0c03208},

issn = {0003-2700},

year  = {2020},

date = {2020-11-01},

journal = {Analytical Chemistry},

publisher = {American Chemical Society},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rampler2020,

title = {Recurrent Topics in Mass Spectrometry-Based Metabolomics and Lipidomics—Standardization, Coverage, and Throughput},

author = {Evelyn Rampler and Yasin El Abiead and Harald Schoeny and Mate Rusz and Felina Hildebrand and Veronika Fitz and Gunda Koellensperger},

url = {https://doi.org/10.1021/acs.analchem.0c04698},

doi = {10.1021/acs.analchem.0c04698},

issn = {0003-2700},

year  = {2020},

date = {2020-11-01},

journal = {Analytical Chemistry},

publisher = {American Chemical Society},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Beard2020b,

title = {ChemSchematicResolver: A Toolkit to Decode 2D Chemical Diagrams with Labels and R-Groups into Annotated Chemical Named Entities},

author = {Edward J Beard and Jacqueline M Cole},

url = {https://doi.org/10.1021/acs.jcim.0c00042},

doi = {10.1021/acs.jcim.0c00042},

year  = {2020},

date = {2020-04-01},

journal = {Journal of Chemical Information and Modeling},

volume = {0},

number = {0},

pages = {null},

note = {PMID: 32212690},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Reher0000,

title = {A Convolutional Neural Network-Based Approach for the Rapid Characterization of Molecularly Diverse Natural Products},

author = {Raphael Reher and Hyun Woo Kim and Chen Zhang and Huanru Henry Mao and Mingxun Wang and Louis-Félix Nothias and Andres Mauricio Caraballo-Rodriguez and Evgenia Glukhov and Bahar Teke and Tiago Leao and Kelsey L Alexander and Brendan M Duggan and Ezra L Van Everbroeck and Pieter C Dorrestein and Garrison W Cottrell and William H Gerwick},

url = {https://doi.org/10.1021/jacs.9b13786},

doi = {10.1021/jacs.9b13786},

year  = {2020},

date = {2020-02-26},

journal = {Journal of the American Chemical Society},

volume = {0},

number = {ja},

pages = {null},

note = {PMID: 32045230},

keywords = {},

pubstate = {forthcoming},

tppubtype = {article}

}

@article{Stumpfe2020,

title = {Current Trends, Overlooked Issues, and Unmet Challenges in Virtual Screening},

author = {Dagmar Stumpfe and Jürgen Bajorath},

url = {https://dx.doi.org/10.1021/acs.jcim.9b01101},

doi = {10.1021/acs.jcim.9b01101},

issn = {1549-9596},

year  = {2020},

date = {2020-02-01},

journal = {Journal of Chemical Information and Modeling},

publisher = {American Chemical Society (ACS)},

abstract = {Virtual compound screening focusing on hit identification is among the most popular computational approaches in pharmaceutical research. Yet, its opportunities and limitations are often not fully understood. Herein, we critically discuss several aspects of virtual screening that are thought to be of particular relevance for the field going forward.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kwon2020,

title = {Compressed graph representation for scalable molecular graph generation},

author = {Youngchun Kwon and Dongseon Lee and Youn-Suk Choi and Kyoham Shin and Seokho Kang},

doi = {10.1186/s13321-020-00463-2},

issn = {1758-2946},

year  = {2020},

date = {2020-01-01},

journal = {Journal of Cheminformatics},

abstract = {textlessptextgreaterRecently, deep learning has been successfully applied to molecular graph generation. Nevertheless, mitigating the computational complexity, which increases with the number of nodes in a graph, has been a major challenge. This has hindered the application of deep learning-based molecular graph generation to large molecules with many heavy atoms. In this study, we present a molecular graph compression method to alleviate the complexity while maintaining the capability of generating chemically valid and diverse molecular graphs. We designate six small substructural patterns that are prevalent between two atoms in real-world molecules. These relevant substructures in a molecular graph are then converted to edges by regarding them as additional edge features along with the bond types. This reduces the number of nodes significantly without any information loss. Consequently, a generative model can be constructed in a more efficient and scalable manner with large molecules on a compressed graph representation. We demonstrate the effectiveness of the proposed method for molecules with up to 88 heavy atoms using the GuacaMol benchmark.textless/ptextgreater},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Desmet2020b,

title = {Seeing the forest for the trees: retrieving plant secondary biochemical pathways from metabolome networks},

author = {Sandrien Desmet and Marlies Brouckaert and Kris Morreel and Wout Boerjan},

url = {http://www.sciencedirect.com/science/article/pii/S2001037020305171},

doi = {https://doi.org/10.1016/j.csbj.2020.11.050},

issn = {2001-0370},

year  = {2020},

date = {2020-01-01},

journal = {Computational and Structural Biotechnology Journal},

abstract = {Over the last decade, a giant leap forward has been made in resolving the main bottleneck in metabolomics, i.e., the structural characterization of the many unknowns. This has led to the next challenge in this research field: retrieving biochemical pathway information from the various types of networks that can be constructed from metabolome data. Searching putative biochemical pathways, referred to as biotransformation paths, is complicated because several flaws occur during the construction of metabolome networks. Multiple network analysis tools have been developed to deal with these flaws, while in silico retrosynthesis is appearing as an alternative approach. In this review, the different types of metabolome networks, their flaws, and the various tools to trace these biotransformation paths are discussed.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Djoumbou-Feunang2019b,

title = {CFM-ID 3.0: Significantly Improved ESI-MS/MS Prediction and Compound Identification},

author = {Yannick Djoumbou-Feunang and Allison Pon and Naama Karu and Jiamin Zheng and Carin Li and David Arndt and Maheswor Gautam and Felicity Allen and David S Wishart},

url = {https://www.mdpi.com/2218-1989/9/4/72},

doi = {10.3390/metabo9040072},

issn = {2218-1989},

year  = {2019},

date = {2019-01-01},

journal = {Metabolites},

volume = {9},

number = {4},

abstract = {Metabolite identification for untargeted metabolomics is often hampered by the lack of experimentally collected reference spectra from tandem mass spectrometry (MS/MS). To circumvent this problem, Competitive Fragmentation Modeling-ID (CFM-ID) was developed to accurately predict electrospray ionization-MS/MS (ESI-MS/MS) spectra from chemical structures and to aid in compound identification via MS/MS spectral matching. While earlier versions of CFM-ID performed very well, CFM-ID’s performance for predicting the MS/MS spectra of certain classes of compounds, including many lipids, was quite poor. Furthermore, CFM-ID’s compound identification capabilities were limited because it did not use experimentally available MS/MS spectra nor did it exploit metadata in its spectral matching algorithm. Here, we describe significant improvements to CFM-ID’s performance and speed. These include (1) the implementation of a rule-based fragmentation approach for lipid MS/MS spectral prediction, which greatly improves the speed and accuracy of CFM-ID; (2) the inclusion of experimental MS/MS spectra and other metadata to enhance CFM-ID’s compound identification abilities; (3) the development of new scoring functions that improves CFM-ID’s accuracy by 21.1%; and (4) the implementation of a chemical classification algorithm that correctly classifies unknown chemicals (based on their MS/MS spectra) in >80% of the cases. This improved version called CFM-ID 3.0 is freely available as a web server. Its source code is also accessible online.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ji2019,

title = {Deep MS/MS-Aided Structural-Similarity Scoring for Unknown Metabolite Identification},

author = {Hongchao Ji and Yamei Xu and Hongmei Lu and Zhimin Zhang},

url = {https://doi.org/10.1021/acs.analchem.8b05405},

doi = {10.1021/acs.analchem.8b05405},

issn = {15206882},

year  = {2019},

date = {2019-01-01},

journal = {Analytical Chemistry},

volume = {91},

number = {9},

pages = {5629--5637},

abstract = {Tandem mass spectrometry (MS/MS) is the workhorse for structural annotation of metabolites, because it can provide abundance of structural information. Currently, metabolite identification mainly relies on querying experimental spectra against public or in-house spectral databases. The identification is severely limited by the available spectra in the databases. Although, the metabolome consists of a huge number of different functional metabolites, the whole metabolome derives from a limited number of initial metabolites via bioreactions. In each bioreaction, the reactant and the product often change some substructures but are still structurally related. These structurally related metabolites often have related MS/MS spectra, which provide the possibility to identify unknown metabolites through known ones. However, it is challenging to explore the internal relationship between MS/MS spectra and structural similarity. In this study, we present the deep-learning-based approach for MS/MS-aided structural-similarity scoring (DeepMASS), which can score the structural similarity of unknown metabolite against the known one with MS/MS spectra and deep neural networks. We evaluated DeepMASS with leave-one-out cross-validation on MS/MS spectra of 662 compounds in KEGG and an external test on the biomarkers from male infertility study measured on Shimadzu LC-ESI-IT-TOF and Bruker Compact LC-ESI-QTOF. Results show that the identification of unknown compound is valid if its structure-related metabolite is available in the database. It provides an effective approach to extend the identification range of metabolites for existing MS/MS databases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kochev2018,

title = {Ambit-SMIRKS: a software module for reaction representation, reaction search and structure transformation},

author = {Nikolay Kochev and Svetlana Avramova and Nina Jeliazkova},

url = {https://doi.org/10.1186/s13321-018-0295-6},

doi = {10.1186/s13321-018-0295-6},

issn = {1758-2946},

year  = {2018},

date = {2018-08-20},

journal = {Journal of Cheminformatics},

volume = {10},

number = {1},

pages = {42},

abstract = {Ambit-SMIRKS is an open source software, enabling structure transformation via the SMIRKS language and implemented as an extension of Ambit-SMARTS. As part of the Ambit project it builds on top of The Chemistry Development Kit (The CDK). Ambit-SMIRKS provides the following functionalities: parsing of SMIRKS linear notations into internal reaction (transformation) representations based on The CDK objects, application of the stored reactions against target (reactant) molecules for actual transformation of the target chemical objects, reaction searching, stereo information handling, product post-processing, etc. The transformations can be applied on various sites of the reactant molecule in several modes: single, non-overlapping, non-identical, non-homomorphic or externally specified list of sites utilizing efficient substructure searching algorithm. Ambit-SMIRKS handles the molecules stereo information and supports basic chemical stereo elements implemented in The CDK library. The full SMARTS logical expressions syntax for reactions specification is supported, including recursive SMARTS expressions as well as additional syntax extensions. Since its initial development for the purpose of metabolite generation within Toxtree, the Ambit-SMIRKS module was used in various chemoinformatics projects, both developed by the authors of the package and by external teams. We show several use cases of the Ambit-SMIRKS software including standardization of large chemical databases and pathway transformation database and prediction. Ambit-SMIRKS is distributed as a Java library under LGPL license. More information on use cases and applications, including download links is available at http://ambit.sourceforge.net/smirks.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Kotov2018,

title = {Chemotion-ELN part 2: adaption of an embedded Ketcher editor to advanced research applications},

author = {Serhii Kotov and Pierre Tremouilhac and Nicole Jung and Stefan Bräse},

url = {https://doi.org/10.1186/s13321-018-0292-9},

doi = {10.1186/s13321-018-0292-9},

issn = {1758-2946},

year  = {2018},

date = {2018-08-13},

journal = {Journal of Cheminformatics},

volume = {10},

number = {1},

pages = {38},

abstract = {The Ketcher editor, available as an Open Source software package for drawing chemical structures, has been expanded to include several features that allow storage, management and application of templates, as well as the use of symbols for a planning and processing of solid phase synthesis. In addition, tools for the drawing of coordinative bonds to represent e.g. organometallic compounds were added. The editor has been implemented into an Electronic Lab Notebook (ELN) application which enables the use of the Ketcher editor for advanced operations in chemistry research. The developments of the ELN-integrated Ketcher (ketcher-rails) support the retrieval of identifiers and structure-related information from external databases and the molecule-based calculation of analytical values. The reworked editor can be used to generate molecular structures in reaction templates and to generate syntheses plans.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hähnke2018,

title = {PubChem chemical structure standardization},

author = {Volker D Hähnke and Sunghwan Kim and Evan E Bolton},

url = {https://doi.org/10.1186/s13321-018-0293-8},

doi = {10.1186/s13321-018-0293-8},

issn = {1758-2946},

year  = {2018},

date = {2018-08-10},

journal = {Journal of Cheminformatics},

volume = {10},

number = {1},

pages = {36},

abstract = {PubChem is a chemical information repository, consisting of three primary databases: Substance, Compound, and BioAssay. When individual data contributors submit chemical substance descriptions to Substance, the unique chemical structures are extracted and stored into Compound through an automated process called structure standardization. The present study describes the PubChem standardization approaches and analyzes them for their success rates, reasons that cause structures to be rejected, and modifications applied to structures during the standardization process. Furthermore, the PubChem standardization is compared to the structure normalization of the IUPAC International Chemical Identifier (InChI) software, as manifested by conversion of the InChI back into a chemical structure.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Sivakumar2018b,

title = {SimCAL: a flexible tool to compute biochemical reaction similarity},

author = {Tadi Venkata Sivakumar and Anirban Bhaduri and Rajasekhara Reddy Duvvuru Muni and Jin Hwan Park and Tae Yong Kim},

url = {https://doi.org/10.1186/s12859-018-2248-5},

doi = {10.1186/s12859-018-2248-5},

issn = {1471-2105},

year  = {2018},

date = {2018-07-03},

journal = {BMC Bioinformatics},

volume = {19},

number = {1},

pages = {254},

abstract = {Computation of reaction similarity is a pre-requisite for several bioinformatics applications including enzyme identification for specific biochemical reactions, enzyme classification and mining for specific inhibitors. Reaction similarity is often assessed at either two levels: (i) comparison across all the constituent substrates and products of a reaction, reaction level similarity, (ii) comparison at the transformation center with various degrees of neighborhood, transformation level similarity. Existing reaction similarity computation tools are designed for specific applications and use different features and similarity measures. A single system integrating these diverse features enables comparison of the impact of different molecular properties on similarity score computation.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Blazenovic:2018bv,

title = {Software Tools and Approaches for Compound Identification of LC-MS/MS Data in Metabolomics},

author = {Ivana Blazenovic and Tobias Kind and Jian Ji and Oliver Fiehn},

url = {http://www.mdpi.com/2218-1989/8/2/31/htm},

doi = {10.3390/metabo8020031},

year  = {2018},

date = {2018-01-01},

journal = {Metabolites},

volume = {8},

number = {2},

pages = {31},

publisher = {Multidisciplinary Digital Publishing Institute},

abstract = {The annotation of small molecules remains a major challenge in untargeted mass spectrometry-based metabolomics. We here critically discuss structured elucidation approaches and software that are designed to help during the annotation of unknown compounds. Only by elucidating unknown metabolites first is it possible to biologically interpret complex systems, to map compounds to pathways and to create reliable predictive metabolic models for translational and clinical research. These strategies include the construction and quality of tandem mass spectral databases such as the coalition of MassBank repositories and investigations of MS/MS matching confidence. We present in silico fragmentation tools such as MS-FINDER, CFM-ID, MetFrag, ChemDistiller and CSI:FingerID that can annotate compounds from existing structure databases and that have been used in the CASMI (critical assessment of small molecule identification) contests. Furthermore, the use of retention time models from liquid chromatography and the utility of collision cross-section modelling from ion mobility experiments are covered. Workflows and published examples of successfully annotated unknown compounds are included.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Chong:2018kl,

title = {MetaboAnalyst 4.0: towards more transparent and integrative metabolomics analysis},

author = {Jasmine Chong and Othman Soufan and Carin Li and Iurie Caraus and Shuzhao Li and Guillaume Bourque and David S Wishart and Jianguo Xia},

url = {https://academic.oup.com/nar/advance-article/doi/10.1093/nar/gky310/4995686},

doi = {10.1093/nar/gky310},

year  = {2018},

date = {2018-01-01},

journal = {Nucleic Acids Research},

volume = {37},

pages = {W652},

abstract = {Abstract. We present a new update to MetaboAnalyst (version 4.0) for comprehensive metabolomic data analysis, interpretation, and integration with other omics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{GeorgThiemeVerlagKG:2018kn,

title = {The Integration of Metabolomics and Next-Generation Sequencing Data to Elucidate the Pathways of Natural Product Metabolism in Medicinal Plants},

author = {Georg Thieme Verlag KG and Federico Scossa and Maria Benina and Saleh Alseekh and Youjun Zhang and Alisdair R Fernie},

url = {http://www.thieme-connect.com/products/ejournals/html/10.1055/a-0630-1899},

doi = {10.1055/a-0630-1899},

year  = {2018},

date = {2018-01-01},

journal = {Planta Medica},

number = {EFirst},

publisher = {Georg Thieme Verlag KG},

abstract = {<p>Plants have always been used as medicines since ancient times to treat diseases. The knowledge around the active components of herbal preparations has remained nevertheless fragmentary: the biosynthetic pathways of many secondary metabolites of pharmacological importance have been clarified only in a few species, while the chemodiversity present in many medicinal plants has remained largely unexplored. Despite the advancements of synthetic biology for production of medicinal compounds in heterologous hosts, the native plant species are often the most reliable and economic source for their production. It thus becomes fundamental to investigate the metabolic composition of medicinal plants to characterize their natural metabolic diversity and to define the biosynthetic routes \textit{in planta} of important compounds to develop strategies to further increase their content. We present here a number of case studies for selected classes of secondary metabolites and we review their health benefits and the historical developments in their structural elucidation and characterization of biosynthetic genes. We cover the cases of benzoisoquinoline and monoterpenoid indole alkaloids, cannabinoids, caffeine, ginsenosides, withanolides, artemisinin, and taxol; we show how the textquotedblleftearlytextquotedblright biochemical or the more recent integrative approaches–based on omics-analyses–have helped to elucidate their metabolic pathways and cellular compartmentation. We also summarize how the knowledge generated about their biosynthesis has been used to develop metabolic engineering strategies in heterologous and native hosts. We conclude that following the advent of novel, high-throughput and cost-effective analytical technologies, the secondary metabolism of medicinal plants can now be examined under the lens of systems biology.</p>},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Tanaka2018b,

title = {Physicochemical Prediction of Metabolite Fragmentation in Tandem Mass Spectrometry},

author = {Wataru Tanaka and Masanori Arita},

doi = {10.5702/massspectrometry.A0066},

year  = {2018},

date = {2018-01-01},

journal = {Mass Spectrometry},

volume = {7},

number = {1},

pages = {A0066-A0066},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Lai:2017kk,

title = {Identifying metabolites by integrating metabolome databases with mass spectrometry cheminformatics},

author = {Zijuan Lai and Hiroshi Tsugawa and Gert Wohlgemuth and Sajjan Mehta and Matthew Mueller and Yuxuan Zheng and Atsushi Ogiwara and John Meissen and Megan Showalter and Kohei Takeuchi and Tobias Kind and Peter Beal and Masanori Arita and Oliver Fiehn},

url = {https://www.nature.com/articles/nmeth.4512},

doi = {10.1038/nmeth.4512},

year  = {2017},

date = {2017-11-01},

journal = {Nature Methods},

volume = {122},

number = {1},

pages = {769--56},

publisher = {Nature Publishing Group},

abstract = {<p>An integrated cheminformatics workflow aids the functional and structural annotation of unknown metabolites found across multiple biological systems.</p>},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Alden:2017ce,

title = {Biologically Consistent Annotation of Metabolomics Data},

author = {Nicholas Alden and Smitha Krishnan and Vladimir Porokhin and Ravali Raju and Kyle McElearney and Alan Gilbert and Kyongbum Lee},

url = {http://pubs.acs.org/doi/10.1021/acs.analchem.7b02162},

doi = {10.1021/acs.analchem.7b02162},

year  = {2017},

date = {2017-01-01},

journal = {Analytical Chemistry},

volume = {89},

number = {24},

pages = {acs.analchem.7b02162--13104},

publisher = {American Chemical Society},

abstract = {Annotation of metabolites remains a major challenge in liquid chromatography–mass spectrometry (LC–MS) based untargeted metabolomics. The current gold standard for metabolite identification is to match the detected feature with an authentic standard analyzed on the same equipment and using the same method as the experimental samples. However, there are substantial practical challenges in applying this approach to large data sets. One widely used annotation approach is to search spectral libraries in reference databases for matching metabolites; however, this approach is limited by the incomplete coverage of these libraries. An alternative computational approach is to match the detected features to candidate chemical structures based on their mass and predicted fragmentation pattern. Unfortunately, both of these approaches can match multiple identities with a single feature. Another issue is that annotations from different tools often disagree. This paper presents a novel LC–MS data annotation method, term...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Naake:2017jp,

title = {MetCirc: navigating mass spectral similarity in high-resolution MS/MS metabolomics data},

author = {Thomas Naake and Emmanuel Gaquerel},

url = {http://academic.oup.com/bioinformatics/article/33/15/2419/3574598/MetCirc-navigating-mass-spectral-similarity-in},

doi = {10.1093/bioinformatics/btx159},

year  = {2017},

date = {2017-01-01},

journal = {Bioinformatics},

volume = {33},

number = {15},

pages = {2419--2420},

publisher = {Oxford University Press},

abstract = {Abstract. Summary: Among the main challenges in metabolomics are the rapid dereplication of previously characterized metabolites across a range of biological s},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Sahoo2016b,

title = {A Short Review of the Generation of Molecular Descriptors and Their Applications in Quantitative Structure Property/Activity Relationships},

author = {Sagarika Sahoo and Chandana Adhikari and Minati Kuanar Mishra and Bijay K.},

url = {http://www.eurekaselect.com/node/142484/article},

year  = {2016},

date = {2016-01-01},

journal = {Current Computer-Aided Drug Design},

volume = {12},

number = {3},

pages = {181-205},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Heller2015b,

title = {InChI, the IUPAC International Chemical Identifier},

author = {Stephen R Heller and Alan McNaught and Igor Pletnev and Stephen Stein and Dmitrii Tchekhovskoi},

url = {https://doi.org/10.1186/s13321-015-0068-4},

doi = {10.1186/s13321-015-0068-4},

issn = {1758-2946},

year  = {2015},

date = {2015-05-30},

journal = {Journal of Cheminformatics},

volume = {7},

number = {1},

pages = {23},

abstract = {This paper documents the design, layout and algorithms of the IUPAC International Chemical Identifier, InChI.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Willoughby:2014ix,

title = {A guide to small-molecule structure assignment through computation of (1H and 13C) NMR chemical shifts},

author = {Patrick H Willoughby and Matthew J Jansma and Thomas R Hoye},

url = {http://www.nature.com/doifinder/10.1038/nprot.2014.042},

doi = {10.1038/nprot.2014.042},

year  = {2014},

date = {2014-01-01},

journal = {Nature protocols},

volume = {9},

number = {3},

pages = {643--660},

publisher = {Nature Publishing Group},

abstract = {A guide to small-molecule structure assignment through computation of (^{1}H and ^{13}C) NMR chemical shifts},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Plainchont2013,

title = {Recent advances in the structure elucidation of small organic molecules by the LSD software},

author = {Bertrand Plainchont and Vicente de Paulo Emerenciano and Jean-Marc Nuzillard},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/mrc.3965},

doi = {10.1002/mrc.3965},

year  = {2013},

date = {2013-01-01},

journal = {Magnetic Resonance in Chemistry},

volume = {51},

number = {8},

pages = {447-453},

abstract = {The LSD software proposes the structures of small organic molecules that fit with structural constraints from 1D and 2D NMR spectroscopy. Its initial design introduced limits that needed to be eliminated to extend its scope and help its users choose the most likely structure among those proposed. The LSD software code has been improved, so that it recognizes a wider set of atom types to build molecules. More flexibility has been given in the interpretation of 2D NMR data, including the automatic detection of very long-range correlations. A program named pyLSD was written to deal with problems in which atom types are ambiguously defined. It also provides a 13C NMR chemical shift-based solution ranking algorithm. PyLSD was able to propose the correct structure of hexacyclinol, a natural product whose structure determination has been highly controversal. The solution was ranked first within a list of ten structures that were produced by pyLSD from the literature NMR data. The structure of an aporphin natural product was determined by pyLSD, taking advantage of the possibility of handling electrically charged atoms. The structure generation of the insect antifeedant azadirachtin by LSD was reinvestigated by pyLSD, considering that three 13C resonances did not lead to univocal hybridization states. Copyright © 2013 John Wiley & Sons, Ltd.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Heller2013b,

title = {InChI - the worldwide chemical structure identifier standard},

author = {Stephen Heller and Alan McNaught and Stephen Stein and Dmitrii Tchekhovskoi and Igor Pletnev},

url = {https://doi.org/10.1186/1758-2946-5-7},

doi = {10.1186/1758-2946-5-7},

issn = {1758-2946},

year  = {2013},

date = {2013-01-01},

journal = {Journal of Cheminformatics},

volume = {5},

number = {1},

pages = {7},

abstract = {Since its public introduction in 2005 the IUPAC InChI chemical structure identifier standard has become the international, worldwide standard for defined chemical structures. This article will describe the extensive use and dissemination of the InChI and InChIKey structure representations by and for the world-wide chemistry community, the chemical information community, and major publishers and disseminators of chemical and related scientific offerings in manuscripts and databases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Schymanski2012,

title = {Consensus Structure Elucidation Combining GC/EI-MS, Structure Generation, and Calculated Properties},

author = {Emma L Schymanski and Christine M J Gallampois and Martin Krauss and Markus Meringer and Steffen Neumann and Tobias Schulze and Sebastian Wolf and Werner Brack},

url = {https://doi.org/10.1021/ac203471y},

doi = {10.1021/ac203471y},

year  = {2012},

date = {2012-01-01},

journal = {Analytical Chemistry},

volume = {84},

number = {7},

pages = {3287-3295},

note = {PMID: 22414024},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1002/wcms.1104,

title = {The enumeration of chemical space},

author = {Jean-Louis Reymond and Lars Ruddigkeit and Lorenz Blum and Ruud van Deursen},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/wcms.1104},

doi = {10.1002/wcms.1104},

year  = {2012},

date = {2012-01-01},

journal = {Wiley Interdisciplinary Reviews: Computational Molecular Science},

volume = {2},

number = {5},

pages = {717-733},

abstract = {Abstract In the field of medicinal chemistry, the chemical space describes the ensemble of all organic molecules to be considered when searching for new drugs (estimated >1060 molecules), as well as the property spaces in which these molecules are placed for the sake of describing them. Molecules can be enumerated computationally by the millions, which was first undertaken in the field of computer-aided structure elucidation. Scoring the enumerated virtual libraries by virtual screening has recently become an attractive strategy to prioritize compounds for synthesis and testing. Enumeration methods include combinatorial linking of fragments, genetic algorithms based on cycles of enumeration and selection by ligand-based or target-based scoring functions, and exhaustive enumeration from first principles. The chemical space of molecules following simple rules of chemical stability and synthetic feasibility has been enumerated up to 13 atoms of C, N, O, Cl, S, forming the GDB-13 database with 977 million structures. The database has been organized in a 42-dimensional chemical space using molecular quantum numbers (MQN) as descriptors, which can be visualized by projection in two dimensions by principal component analysis, and searched within seconds using a Web browser available at www.gdb.unibe.ch. © 2012 John Wiley & Sons, Ltd. This article is categorized under: Computer and Information Science > Chemoinformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{doi:10.1021/ci0341060,

title = {Structure Elucidator:  A Versatile Expert System for Molecular Structure Elucidation from 1D and 2D NMR Data and Molecular Fragments},

author = {Mikhail E Elyashberg and Kirill A Blinov and Antony J Williams and Sergey G Molodtsov and Gary E Martin and Eduard R Martirosian},

url = {https://doi.org/10.1021/ci0341060},

doi = {10.1021/ci0341060},

year  = {2004},

date = {2004-01-01},

journal = {Journal of Chemical Information and Computer Sciences},

volume = {44},

number = {3},

pages = {771-792},

note = {PMID: 15154743},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Schulz2003,

title = {Applications of a HOUDINI-Based Structure Elucidation System},

author = {K -P Schulz and A Korytko and M E Munk},

url = {https://doi.org/10.1021/ci034058j},

doi = {10.1021/ci034058j},

year  = {2003},

date = {2003-01-01},

journal = {Journal of Chemical Information and Computer Sciences},

volume = {43},

number = {5},

pages = {1447-1456},

note = {PMID: 14502477},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Munk1998,

title = {Computer-Based Structure Determination:  Then and Now},

author = {Morton E Munk},

url = {https://doi.org/10.1021/ci980083r},

doi = {10.1021/ci980083r},

year  = {1998},

date = {1998-01-01},

journal = {Journal of Chemical Information and Computer Sciences},

volume = {38},

number = {6},

pages = {997-1009},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Funatsu1996,

title = {Recent Advances in the Automated Structure Elucidation System, CHEMICS. Utilization of Two-Dimensional NMR Spectral Information and Development of Peripheral Functions for Examination of Candidates},

author = {Kimito Funatsu and Shin-ichi Sasaki},

url = {https://doi.org/10.1021/ci950152r},

doi = {10.1021/ci950152r},

year  = {1996},

date = {1996-01-01},

journal = {Journal of Chemical Information and Computer Sciences},

volume = {36},

number = {2},

pages = {190-204},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Peng1994,

title = {Efficient Application of 2D NMR Correlation Information in Computer-Assisted Structure Elucidation of Complex Natural Products},

author = {Chen Peng and Shengang Yuan and Chongzhi Zheng and Yongzheng Hui},

url = {https://pubs.acs.org/doi/abs/10.1021/ci00020a013},

doi = {10.1021/ci00020a013},

year  = {1994},

date = {1994-01-01},

journal = {Journal of Chemical Information and Computer Sciences},

volume = {34},

number = {4},

pages = {805-813},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Razinger1993,

title = {Graph automorphism perception algorithms in computer-enhanced structure elucidation},

author = {Marko Razinger and K Balasubramanian and Morton Munk},

doi = {10.1021/ci00012a003},

year  = {1993},

date = {1993-01-01},

journal = {Journal of chemical information and computer sciences},

volume = {33},

pages = {197-201},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Gasteiger1990b,

title = {Automatic generation of 3D-atomic coordinates for organic molecules},

author = {J Gasteiger and C Rudolph and J Sadowski},

url = {http://www.sciencedirect.com/science/article/pii/0898552990901563},

doi = {https://doi.org/10.1016/0898-5529(90)90156-3},

issn = {0898-5529},

year  = {1990},

date = {1990-01-01},

journal = {Tetrahedron Computer Methodology},

volume = {3},

number = {6, Part C},

pages = {537 - 547},

abstract = {A system has been developed that can automatically generate three-dimensional atomic coordinates from the constitution of a molecule as expressed by a connection table. The program, CORINA, is applicable to the entire range of organic chemistry. It can also handle structures that are beyond the scope of some other programs, e.g., macrocyclic and polymacrocyclic molecules. Computation times are short and the results compare favorably with data from X-ray crystallography and with those of molecular mechanics calculations.},

note = {Three-dimensional chemical structure handling},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Weininger1989b,

title = {SMILES. 2. Algorithm for generation of unique SMILES notation},

author = {David Weininger and Arthur Weininger and Joseph L Weininger},

url = {https://pubs.acs.org/doi/abs/10.1021/ci00062a008},

doi = {10.1021/ci00062a008},

year  = {1989},

date = {1989-01-01},

journal = {Journal of Chemical Information and Computer Sciences},

volume = {29},

number = {2},

pages = {97-101},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Weininger1988,

title = {SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules},

author = {David Weininger},

url = {https://pubs.acs.org/doi/abs/10.1021/ci00057a005},

doi = {10.1021/ci00057a005},

year  = {1988},

date = {1988-01-01},

journal = {Journal of Chemical Information and Computer Sciences},

volume = {28},

number = {1},

pages = {31-36},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Balaban1985,

title = {Unique description of chemical structures based on hierarchically ordered extended connectivities (HOC procedures). I. Algorithms for finding graph orbits and canonical numbering of atoms},

author = {Alexandru T Balaban and Ovanes Mekenyan and Danail Bonchev},

url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/jcc.540060606},

doi = {10.1002/jcc.540060606},

year  = {1985},

date = {1985-01-01},

journal = {Journal of Computational Chemistry},

volume = {6},

number = {6},

pages = {538-551},

abstract = {Abstract An iterative algorithm is described for finding topological equivalence, ordering, and canonical numbering of vertexes (atoms) in molecular graphs. Like the Morgan algorithm, it is based on extended connectivities but: (i) the latter are used hierarchically, i. e., the discrimination in the next iteration is carried out only for the vertices having the same extended connectivities (ranks) at the previous iteration; (ii) at equal extended connectivities, additional discrimination is introduced by the ranks of adjacent vertices; (iii) there is no “best name” search; (iv) three levels of complexity of chemical structures are distinguished and handled by different procedures. Two schemes of application of HOC procedures are presented: one directed towards a fast canonical numbering for coding systems, and another one yielding levels of topological equivalence allowing a unique topological representation of the molecule with possible applications to similarity search, structure-activity correlations, etc.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{SHELLEY1981507,

title = {Case, a computer model of the structure elucidation process},

author = {CraigA. Shelley and MortonE. Munk},

url = {http://www.sciencedirect.com/science/article/pii/S0003267001954169},

doi = {https://doi.org/10.1016/S0003-2670(01)95416-9},

issn = {0003-2670},

year  = {1981},

date = {1981-01-01},

journal = {Analytica Chimica Acta},

volume = {133},

number = {4},

pages = {507 - 516},

abstract = {CASE (computer-assisted structure elucidation) is an outgrowth of an effort to develop a computer model of structure elucidation. The current capability of CASE in assembling molecules compatible with the structural information entered and in providing interactive user access to the file of assembled molecules is discussed. Of central importance to the effective application of the system to real-world structure problems are the design of the communication link that accepts structural-constraints information and the efficiency of molecule assembly. The chemist—computer interface is designed to accommodate the great and ever-increasing diversity of available structural information. Molecule assembly proceeds by stepwise bond making. Efficient program execution requires the evaluation of each node in the tree against the structural constraints imposed. However, program response time can be improved by heuristic implementation of constraints during molecule assembly and prospective pruning of unproductive branches from the search space as early as possible. CASE must perceive the significance, not only of the individual constraints themselves, but of their interaction as well. A newly added program to edit, analyze, and peruse the constructed list of molecules provides invaluable guidance in the design of the new experiments required to limit further the number of valid candidates. Such fine tuning of the CASE program enhances its utility and ensures that no plausible structures escape consideration.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Nourse1979,

title = {Applications of artificial intelligence for chemical inference. 29. Exhaustive generation of stereoisomers for structure elucidation},

author = {James G Nourse and Raymond E Carhart and Dennis H Smith and Carl Djerassi},

url = {https://doi.org/10.1021/ja00499a028},

doi = {10.1021/ja00499a028},

year  = {1979},

date = {1979-01-01},

journal = {Journal of the American Chemical Society},

volume = {101},

number = {5},

pages = {1216-1223},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Woodruff1977,

title = {Computer-assisted interpretation of carbon-13 nuclear magnetic resonance spectra applied to structure elucidation of natural products},

author = {Hugh B. Woodruff and Charles R. Snelling and Craig A. Shelley and Morton Munk},

doi = {10.1021/ac50021a045},

year  = {1977},

date = {1977-01-01},

journal = {Analytical Chemistry - ANAL CHEM},

volume = {49},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ullmann1976,

title = {An Algorithm for Subgraph Isomorphism},

author = {J R Ullmann},

url = {https://doi.org/10.1145/321921.321925},

doi = {10.1145/321921.321925},

issn = {0004-5411},

year  = {1976},

date = {1976-01-01},

journal = {J. ACM},

volume = {23},

number = {1},

pages = {31–42},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Morgan1965b,

title = {The Generation of a Unique Machine Description for Chemical Structures-A Technique Developed at Chemical Abstracts Service.},

author = {H L Morgan},

url = {https://doi.org/10.1021/c160017a018},

doi = {10.1021/c160017a018},

year  = {1965},

date = {1965-01-01},

journal = {Journal of Chemical Documentation},

volume = {5},

number = {2},

pages = {107-113},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Tanimoto1958,

title = {An Elementary Mathematical theory of Classification and Prediction},

author = {T T Tanimoto},

url = {http://dalkescientific.com/tanimoto.pdf},

year  = {1958},

date = {1958-01-01},

volume = {126},

number = {3278},

pages = {814--819},

publisher = {International Business Machines Corp},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ray1957,

title = {Finding Chemical Records by Digital Computers},

author = {Louis C Ray and Russell A Kirsch},

url = {https://science.sciencemag.org/content/126/3278/814},

doi = {10.1126/science.126.3278.814},

issn = {0036-8075},

year  = {1957},

date = {1957-01-01},

journal = {Science},

volume = {126},

number = {3278},

pages = {814--819},

publisher = {American Association for the Advancement of Science},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Wiener1947,

title = {Structural Determination of Paraffin Boiling Points},

author = {Harry Wiener},

url = {https://doi.org/10.1021/ja01193a005},

doi = {10.1021/ja01193a005},

year  = {1947},

date = {1947-01-01},

journal = {Journal of the American Chemical Society},

volume = {69},

number = {1},

pages = {17-20},

note = {PMID: 20291038},

keywords = {},

pubstate = {published},

tppubtype = {article}

}