manuscript.bib

@report{anderson:1987,
  title = {{{SMILES}}: {{A Line Notation}} and {{Computerized Interpreter}} for {{Chemical Structures}}},
  author = {Anderson, Eric and Veith, Gilman D. and Weininger, David},
  date = {1987-08},
  number = {EPA/600/M-87/021},
  institution = {{US Environmental Protection Agency}},
  url = {https://nepis.epa.gov/Exe/ZyPURL.cgi?Dockey=2000CAUR.TXT}
}

@article{balaban:1985,
  title = {Applications of Graph Theory in Chemistry},
  author = {Balaban, Alexandru T.},
  date = {1985-08-01},
  journaltitle = {J. Chem. Inf. Comput. Sci.},
  volume = {25},
  number = {3},
  pages = {334--343},
  issn = {0095-2338},
  doi = {10.1021/ci00047a033},
  langid = {english}
}

@online{bison,
  title = {Bison, {{The YACC-compatible Parser Generator}}},
  url = {http://dinosaur.compilertools.net/bison/index.html},
  urldate = {2022-08-21}
}

@online{cdxml,
  title = {{{CDX Format Specification}}: {{The CDXML}} Text-Based File Format},
  url = {https://www.cambridgesoft.com/services/documentation/sdk/chemdraw/cdx/IntroCDXML.htm},
  urldate = {2022-03-17}
}

@article{clark:2011,
  title = {Accurate {{Specification}} of {{Molecular Structures}}: {{The Case}} for {{Zero-Order Bonds}} and {{Explicit Hydrogen Counting}}},
  shorttitle = {Accurate {{Specification}} of {{Molecular Structures}}},
  author = {Clark, Alex M.},
  date = {2011-12-27},
  journaltitle = {J. Chem. Inf. Model.},
  volume = {51},
  number = {12},
  pages = {3149--3157},
  issn = {1549-9596, 1549-960X},
  doi = {10.1021/ci200488k},
  langid = {english}
}

@book{crockford:2008,
  title = {{{JavaScript}}: The Good Parts ; [Unearthing the Excellence in {{JavaScript}}]},
  shorttitle = {{{JavaScript}}},
  author = {Crockford, Douglas},
  date = {2008},
  series = {Unearthing the Excellence in {{JavaScript}}},
  edition = {1. ed},
  publisher = {{O'Reilly}},
  location = {{Beijing Köln}},
  isbn = {978-0-596-51774-8},
  langid = {english},
  pagetotal = {153}
}

@online{ctfileFormats,
  title = {{{CTfile Formats}} - {{Dassault Systèmes}}},
  url = {https://discover.3ds.com/ctfile-documentation-request-form},
  urldate = {2022-03-17}
}

@online{cxsmiles,
  title = {Chemaxon {{Extended SMILES}} and {{SMARTS}} - {{CXSMILES}} and {{CXSMARTS}} | {{Chemaxon Docs}}},
  url = {https://docs.chemaxon.com/display/docs/chemaxon-extended-smiles-and-smarts-cxsmiles-and-cxsmarts.md},
  urldate = {2022-03-17}
}

@online{daylightTheory,
  title = {Daylight {{Theory Manual}}},
  url = {https://www.daylight.com/dayhtml/doc/theory/},
  urldate = {2022-03-17}
}

@online{daylightToolkit,
  title = {Daylight {{Toolkit}}},
  url = {https://www.daylight.com/products/toolkit.html},
  urldate = {2022-03-17}
}

@article{degtyarenko:2007,
  title = {{{ChEBI}}: A Database and Ontology for Chemical Entities of Biological Interest},
  shorttitle = {{{ChEBI}}},
  author = {Degtyarenko, K. and de Matos, P. and Ennis, M. and Hastings, J. and Zbinden, M. and McNaught, A. and Alcantara, R. and Darsow, M. and Guedj, M. and Ashburner, M.},
  options = {useprefix=true},
  date = {2007-12-23},
  journaltitle = {Nucleic Acids Research},
  volume = {36},
  pages = {D344-D350},
  issn = {0305-1048, 1362-4962},
  doi = {10.1093/nar/gkm791},
  issue = {Database},
  langid = {english}
}

@thesis{denjoed:2010,
  title = {Parsing and {{Conversion}} of {{SMILES-strings}} to {{Molecular Graphs}}},
  author = {den Joed, Anton},
  options = {useprefix=true},
  date = {2010},
  institution = {{Leiden University}},
  location = {{Universiteit Leiden}},
  url = {https://theses.liacs.nl/203},
  langid = {english}
}

@online{depictArchive,
  title = {Depict {{Archive Page}}},
  url = {https://web.archive.org/web/20070113052758/https://www.daylight.com/daycgi/depict},
  urldate = {2022-03-17}
}

@article{dietz:1995,
  title = {Yet {{Another Representation}} of {{Molecular Structure}}},
  author = {Dietz, Andreas},
  date = {1995-09-01},
  journaltitle = {J. Chem. Inf. Model.},
  volume = {35},
  number = {5},
  pages = {787--802},
  issn = {1549-9596},
  doi = {10.1021/ci00027a001},
  langid = {english},
  keywords = {dietz}
}

@article{drefahl:2011,
  title = {{{CurlySMILES}}: A Chemical Language to Customize and Annotate Encodings of Molecular and Nanodevice Structures},
  shorttitle = {{{CurlySMILES}}},
  author = {Drefahl, Axel},
  date = {2011-12},
  journaltitle = {J Cheminform},
  volume = {3},
  number = {1},
  pages = {1},
  issn = {1758-2946},
  doi = {10.1186/1758-2946-3-1},
  langid = {english}
}

@article{edmonds:1965,
  title = {Paths, {{Trees}}, and {{Flowers}}},
  author = {Edmonds, Jack},
  date = {1965},
  journaltitle = {Can. J. Math.},
  volume = {17},
  pages = {449--467},
  doi = {10.4153/CJM-1965-045-4},
  langid = {english}
}

@online{extendingVersioningLanguages,
  title = {[{{Editorial Draft}}] {{Extending}} and {{Versioning Languages}}: {{Terminology}}},
  url = {https://www.w3.org/2001/tag/doc/versioning},
  urldate = {2022-10-02}
}

@article{gasteiger:2018,
  title = {Leaving Us with Fond Memories, Smiles, {{SMILES}} and, Alas, Tears: A Tribute to {{David Weininger}}, 1952–2016},
  shorttitle = {Leaving Us with Fond Memories, Smiles, {{SMILES}} and, Alas, Tears},
  author = {Gasteiger, Johann and Martin, Yvonne and Nicholls, Anthony and Oprea, Tudor I. and Stouch, Terry},
  date = {2018-02},
  journaltitle = {J Comput Aided Mol Des},
  volume = {32},
  number = {2},
  pages = {313--319},
  issn = {0920-654X, 1573-4951},
  doi = {10.1007/s10822-018-0104-3},
  langid = {english}
}

@article{gaulton:2012,
  title = {{{ChEMBL}}: A Large-Scale Bioactivity Database for Drug Discovery},
  shorttitle = {{{ChEMBL}}},
  author = {Gaulton, A. and Bellis, L. J. and Bento, A. P. and Chambers, J. and Davies, M. and Hersey, A. and Light, Y. and McGlinchey, S. and Michalovich, D. and Al-Lazikani, B. and Overington, J. P.},
  date = {2012-01-01},
  journaltitle = {Nucleic Acids Research},
  volume = {40},
  number = {D1},
  pages = {D1100-D1107},
  issn = {0305-1048, 1362-4962},
  doi = {10.1093/nar/gkr777},
  langid = {english}
}

@article{hanson:2016,
  title = {Jmol {{SMILES}} and {{Jmol SMARTS}}: Specifications and Applications},
  shorttitle = {Jmol {{SMILES}} and {{Jmol SMARTS}}},
  author = {Hanson, Robert M.},
  date = {2016-12},
  journaltitle = {J Cheminform},
  volume = {8},
  number = {1},
  pages = {50},
  issn = {1758-2946},
  doi = {10.1186/s13321-016-0160-4},
  langid = {english}
}

@article{hatton:2007,
  title = {Language Subsetting in an Industrial Context: {{A}} Comparison of {{MISRA C}} 1998 and {{MISRA C}} 2004},
  shorttitle = {Language Subsetting in an Industrial Context},
  author = {Hatton, Les},
  date = {2007-05},
  journaltitle = {Information and Software Technology},
  volume = {49},
  number = {5},
  pages = {475--482},
  issn = {09505849},
  doi = {10.1016/j.infsof.2006.07.004},
  langid = {english}
}

@article{heller:2015,
  title = {{{InChI}}, the {{IUPAC International Chemical Identifier}}},
  author = {Heller, Stephen R and McNaught, Alan and Pletnev, Igor and Stein, Stephen and Tchekhovskoi, Dmitrii},
  date = {2015-12},
  journaltitle = {J Cheminform},
  volume = {7},
  number = {1},
  pages = {23},
  issn = {1758-2946},
  doi = {10.1186/s13321-015-0068-4},
  langid = {english}
}

@article{irwin:2005,
  title = {{{ZINC}} − {{A Free Database}} of {{Commercially Available Compounds}} for {{Virtual Screening}}},
  author = {Irwin, John J. and Shoichet, Brian K.},
  date = {2005-01-01},
  journaltitle = {J. Chem. Inf. Model.},
  volume = {45},
  number = {1},
  pages = {177--182},
  issn = {1549-9596, 1549-960X},
  doi = {10.1021/ci049714+},
  langid = {english}
}

@online{jchembase,
  title = {{{JChem Base}} | {{Chemaxon Docs}}},
  url = {https://docs.chemaxon.com/display/docs/jchem-base.md},
  urldate = {2022-03-17}
}

@article{kerber:2006,
  title = {If {{It}}'s {{Resonance}}, {{What Is Resonating}}?},
  author = {Kerber, Robert C.},
  date = {2006-02},
  journaltitle = {J. Chem. Educ.},
  volume = {83},
  number = {2},
  pages = {223},
  issn = {0021-9584, 1938-1328},
  doi = {10.1021/ed083p223},
  langid = {english}
}

@article{kim:2016,
  title = {{{PubChem Substance}} and {{Compound}} Databases},
  author = {Kim, Sunghwan and Thiessen, Paul A. and Bolton, Evan E. and Chen, Jie and Fu, Gang and Gindulyte, Asta and Han, Lianyi and He, Jane and He, Siqian and Shoemaker, Benjamin A. and Wang, Jiyao and Yu, Bo and Zhang, Jian and Bryant, Stephen H.},
  date = {2016-01-04},
  journaltitle = {Nucleic Acids Res},
  volume = {44},
  number = {D1},
  pages = {D1202-D1213},
  issn = {0305-1048, 1362-4962},
  doi = {10.1093/nar/gkv951},
  langid = {english}
}

@article{lewis:1916,
  title = {The {{Atom}} and the {{Molecule}}},
  author = {Lewis, Gilbert},
  date = {1916},
  journaltitle = {J. Am. Chem. Soc.},
  number = {38},
  pages = {672},
  doi = {10.1021/ja02261a002}
}

@article{lin:2019,
  title = {{{BigSMILES}}: {{A Structurally-Based Line Notation}} for {{Describing Macromolecules}}},
  shorttitle = {{{BigSMILES}}},
  author = {Lin, Tzyy-Shyang and Coley, Connor W. and Mochigase, Hidenobu and Beech, Haley K. and Wang, Wencong and Wang, Zi and Woods, Eliot and Craig, Stephen L. and Johnson, Jeremiah A. and Kalow, Julia A. and Jensen, Klavs F. and Olsen, Bradley D.},
  date = {2019-09-25},
  journaltitle = {ACS Cent. Sci.},
  volume = {5},
  number = {9},
  pages = {1523--1531},
  issn = {2374-7943, 2374-7951},
  doi = {10.1021/acscentsci.9b00476},
  langid = {english}
}

@online{mayfield:2022,
  title = {{{CXSMILES Gotchas}} – {{Part}} 1: {{Bond Indexes}} – {{NextMove Software}}},
  author = {Mayfield, John},
  url = {https://nextmovesoftware.com/blog/2022/04/08/cxsmiles-gotchas-part-1-bond-indexes/},
  urldate = {2022-09-11},
  organization = {{NextMove Software Blog}}
}

@article{mislow:1984,
  title = {Stereoisomerism and Local Chirality},
  author = {Mislow, Kurt and Siegel, Jay},
  date = {1984-05},
  journaltitle = {J. Am. Chem. Soc.},
  volume = {106},
  number = {11},
  pages = {3319--3328},
  issn = {0002-7863, 1520-5126},
  doi = {10.1021/ja00323a043},
  langid = {english}
}

@online{misraC,
  title = {{{MISRA Website}}},
  url = {https://www.misra.org.uk/},
  urldate = {2022-03-18}
}

@article{murray-rust:2011,
  title = {{{CML}}: {{Evolution}} and Design},
  shorttitle = {{{CML}}},
  author = {Murray-Rust, Peter and Rzepa, Henry S},
  date = {2011-12},
  journaltitle = {J Cheminform},
  volume = {3},
  number = {1},
  pages = {44},
  issn = {1758-2946},
  doi = {10.1186/1758-2946-3-44},
  langid = {english}
}

@article{oboyle:2011,
  title = {Open {{Babel}}: {{An}} Open Chemical Toolbox},
  shorttitle = {Open {{Babel}}},
  author = {O'Boyle, Noel M and Banck, Michael and James, Craig A and Morley, Chris and Vandermeersch, Tim and Hutchison, Geoffrey R},
  date = {2011-12},
  journaltitle = {J. Cheminform.},
  volume = {3},
  number = {1},
  pages = {33},
  issn = {1758-2946},
  doi = {10.1186/1758-2946-3-33},
  langid = {english}
}

@article{oboyle:2012,
  title = {Towards a {{Universal SMILES}} Representation - {{A}} Standard Method to Generate Canonical {{SMILES}} Based on the {{InChI}}},
  author = {O’Boyle, Noel M},
  date = {2012},
  journaltitle = {J. Cheminform.},
  volume = {4},
  number = {1},
  pages = {22},
  issn = {1758-2946},
  doi = {10.1186/1758-2946-4-22},
  langid = {english}
}

@online{oetk,
  title = {{{OEChem TK}} | {{OEChem Toolkit}} | {{Cheminformatics}}},
  url = {https://www.eyesopen.com/oechem-tk},
  urldate = {2022-03-17}
}

@online{opensmiles,
  title = {{{OpenSMILES Home Page}}},
  url = {http://opensmiles.org/},
  urldate = {2022-03-17}
}

@article{parr:2014,
  title = {Adaptive {{LL}}(*) {{Parsing}}: {{The Power}} of {{Dynamic Analysis}}},
  author = {Parr, Terence and Harwell, Sam and Fisher, Kathleen},
  date = {2014-10-15},
  journaltitle = {ACM SIGPLAN Not.},
  volume = {49},
  number = {10},
  pages = {579--598},
  doi = {10.1145/2714064.2660202},
  langid = {english}
}

@online{periodicTable,
  title = {Periodic {{Table}} of {{Elements}} - {{IUPAC}} | {{International Union}} of {{Pure}} and {{Applied Chemistry}}},
  url = {https://iupac.org/what-we-do/periodic-table-of-elements/},
  urldate = {2022-03-18}
}

@incollection{randic:2018,
  title = {Aromaticity {{Revisited}}},
  booktitle = {Advances in {{Quantum Chemistry}}},
  author = {Randić, Milan},
  date = {2018},
  volume = {77},
  pages = {167--199},
  publisher = {{Elsevier}},
  doi = {10.1016/bs.aiq.2017.09.001},
  isbn = {978-0-12-813710-9},
  langid = {english}
}

@online{rdkit,
  title = {{{RDKit}}},
  url = {https://www.rdkit.org/},
  urldate = {2022-03-17}
}

@article{sageson:1997,
  title = {Names and Symbols of Transfermium Elements ({{IUPAC Recommendations}} 1997)},
  author = {Sageson, A. M.},
  date = {1997-01-01},
  journaltitle = {Pure Appl. Chem.},
  volume = {69},
  number = {12},
  pages = {2471--2474},
  issn = {1365-3075, 0033-4545},
  doi = {10.1351/pac199769122471},
  langid = {english}
}

@online{smilesPlusGitHub,
  title = {{{IUPAC SMILES}}+},
  url = {https://github.com/IUPAC/IUPAC_SMILES_plus},
  urldate = {2022-03-17}
}

@online{smilesPlusSpecification,
  title = {{{IUPAC SMILES}}+ {{Specification}}},
  url = {https://iupac.org/projects/project-details/?project_nr=2019-002-2-024},
  urldate = {2022-03-17}
}

@article{sousa:2021,
  title = {Generative {{Deep Learning}} for {{Targeted Compound Design}}},
  author = {Sousa, Tiago and Correia, João and Pereira, Vítor and Rocha, Miguel},
  date = {2021-11-22},
  journaltitle = {J. Chem. Inf. Model.},
  volume = {61},
  number = {11},
  pages = {5343--5361},
  issn = {1549-9596, 1549-960X},
  doi = {10.1021/acs.jcim.0c01496},
  langid = {english}
}

@article{steinbeck:2003,
  title = {The {{Chemistry Development Kit}} ({{CDK}}): {{An Open-Source Java Library}} for {{Chemo-}} and {{Bioinformatics}}},
  shorttitle = {The {{Chemistry Development Kit}} ({{CDK}})},
  author = {Steinbeck, Christoph and Han, Yongquan and Kuhn, Stefan and Horlacher, Oliver and Luttmann, Edgar and Willighagen, Egon},
  date = {2003-03-01},
  journaltitle = {J. Chem. Inf. Comput. Sci.},
  volume = {43},
  number = {2},
  pages = {493--500},
  issn = {0095-2338},
  doi = {10.1021/ci025584y},
  langid = {english}
}

@book{thain:2020,
  title = {Introduction to Compilers and Language Design},
  author = {Thain, Douglas},
  date = {2020},
  edition = {Second Edition},
  publisher = {{University of Notre Dame}},
  url = {https://www3.nd.edu/~dthain/compilerbook/},
  isbn = {9798655180260},
  langid = {english},
  annotation = {OCLC: 1236392116}
}

@article{weininger:1988,
  title = {{{SMILES}}, a Chemical Language and Information System. 1. {{Introduction}} to Methodology and Encoding Rules},
  author = {Weininger, David},
  date = {1988-02-01},
  journaltitle = {J. Chem. Inf. Model.},
  volume = {28},
  number = {1},
  pages = {31--36},
  issn = {1549-9596},
  doi = {10.1021/ci00057a005},
  langid = {english}
}

@article{weininger:1989,
  title = {{{SMILES}}. 2. {{Algorithm}} for Generation of Unique {{SMILES}} Notation},
  author = {Weininger, David and Weininger, Arthur and Weininger, Joseph L.},
  date = {1989-05-01},
  journaltitle = {J. Chem. Inf. Model.},
  volume = {29},
  number = {2},
  pages = {97--101},
  issn = {1549-9596},
  doi = {10.1021/ci00062a008},
  langid = {english}
}

@incollection{weininger:2003,
  title = {{{SMILES-A Language}} for {{Molecules}} and {{Reactions}}},
  booktitle = {Handbook of {{Chemoinformatics}}},
  author = {Weininger, David},
  editor = {Gasteiger, Johann},
  date = {2003},
  pages = {80--102},
  publisher = {{Wiley-VCH Verlag GmbH}},
  location = {{Weinheim, Germany}},
  doi = {10.1002/9783527618279.ch5},
  isbn = {978-3-527-61827-9 978-3-527-30680-0},
  langid = {english}
}

@online{wikipediaCAS,
  title = {Talk:{{CAS Registry Number}} - {{Wikipedia}}},
  url = {https://en.wikipedia.org/wiki/Talk:CAS_Registry_Number},
  urldate = {2022-03-17}
}

@article{wilkinson:2016,
  title = {The {{FAIR Guiding Principles}} for Scientific Data Management and Stewardship},
  author = {Wilkinson, Mark D. and Dumontier, Michel and Aalbersberg, IJsbrand Jan and Appleton, Gabrielle and Axton, Myles and Baak, Arie and Blomberg, Niklas and Boiten, Jan-Willem and da Silva Santos, Luiz Bonino and Bourne, Philip E. and Bouwman, Jildau and Brookes, Anthony J. and Clark, Tim and Crosas, Mercè and Dillo, Ingrid and Dumon, Olivier and Edmunds, Scott and Evelo, Chris T. and Finkers, Richard and Gonzalez-Beltran, Alejandra and Gray, Alasdair J.G. and Groth, Paul and Goble, Carole and Grethe, Jeffrey S. and Heringa, Jaap and ’t Hoen, Peter A.C and Hooft, Rob and Kuhn, Tobias and Kok, Ruben and Kok, Joost and Lusher, Scott J. and Martone, Maryann E. and Mons, Albert and Packer, Abel L. and Persson, Bengt and Rocca-Serra, Philippe and Roos, Marco and van Schaik, Rene and Sansone, Susanna-Assunta and Schultes, Erik and Sengstag, Thierry and Slater, Ted and Strawn, George and Swertz, Morris A. and Thompson, Mark and van der Lei, Johan and van Mulligen, Erik and Velterop, Jan and Waagmeester, Andra and Wittenburg, Peter and Wolstencroft, Katherine and Zhao, Jun and Mons, Barend},
  options = {useprefix=true},
  date = {2016-12},
  journaltitle = {Sci Data},
  volume = {3},
  number = {1},
  pages = {160018},
  issn = {2052-4463},
  doi = {10.1038/sdata.2016.18},
  langid = {english}
}

@article{wiswesser:1968,
  title = {107 {{Years}} of {{Line-Formula Notations}} (1861-1968)},
  author = {Wiswesser, William J.},
  date = {1968-08},
  journaltitle = {J. Chem. Doc.},
  volume = {8},
  number = {3},
  pages = {146--150},
  issn = {0021-9576, 1541-5732},
  doi = {10.1021/c160030a007},
  langid = {english}
}

@online{xmlspec,
  title = {Extensible {{Markup Language}} ({{XML}}) 1.0 ({{Fifth Edition}})},
  url = {https://www.w3.org/TR/REC-xml/},
  urldate = {2023-01-20}
}