Item talk:Q61064: Difference between revisions

From geokb
(Wrote fresh schema.org document to item wiki page)
(Update item cache)
 
Line 1: Line 1:
{"@context": "https://schema.org", "@type": "CreativeWork", "additionalType": "USGS Numbered Series", "name": "SSR_pipeline--computer software for the identification of microsatellite sequences from paired-end Illumina high-throughput DNA sequence data", "identifier": [{"@type": "PropertyValue", "propertyID": "USGS Publications Warehouse IndexID", "value": "ds778", "url": "https://pubs.usgs.gov/publication/ds778"}, {"@type": "PropertyValue", "propertyID": "USGS Publications Warehouse Internal ID", "value": 70046704}, {"@type": "PropertyValue", "propertyID": "DOI", "value": "10.3133/ds778", "url": "https://doi.org/10.3133/ds778"}], "inLanguage": "en", "isPartOf": [{"@type": "CreativeWorkSeries", "name": "Data Series"}], "datePublished": "2013", "dateModified": "2013-06-26", "abstract": "SSR_pipeline is a flexible set of programs designed to efficiently identify simple sequence repeats (SSRs; for example, microsatellites) from paired-end high-throughput Illumina DNA sequencing data. The program suite contains three analysis modules along with a fourth control module that can be used to automate analyses of large volumes of data. The modules are used to (1) identify the subset of paired-end sequences that pass quality standards, (2) align paired-end reads into a single composite DNA sequence, and (3) identify sequences that possess microsatellites conforming to user specified parameters. Each of the three separate analysis modules also can be used independently to provide greater flexibility or to work with FASTQ or FASTA files generated from other sequencing platforms (Roche 454, Ion Torrent, etc).\n\nAll modules are implemented in the Python programming language and can therefore be used from nearly any computer operating system (Linux, Macintosh, Windows). The program suite relies on a compiled Python extension module to perform paired-end alignments. Instructions for compiling the extension from source code are provided in the documentation. Users who do not have Python installed on their computers or who do not have the ability to compile software also may choose to download packaged executable files. These files include all Python scripts, a copy of the compiled extension module, and a minimal installation of Python in a single binary executable. See program documentation for more information.", "description": "HTML Document; Program Documentation; Program Executable Files", "publisher": {"@type": "Organization", "name": "U.S. Geological Survey"}, "author": [{"@type": "Person", "name": "Haig, Susan M. susan_haig@usgs.gov", "givenName": "Susan M.", "familyName": "Haig", "email": "susan_haig@usgs.gov", "identifier": {"@type": "PropertyValue", "propertyID": "ORCID", "value": "0000-0002-6616-7589", "url": "https://orcid.org/0000-0002-6616-7589"}, "affiliation": [{"@type": "Organization", "name": "Forest and Rangeland Ecosys Science Center", "url": "https://www.usgs.gov/centers/forest-and-rangeland-ecosystem-science-center"}, {"@type": "Organization", "name": "Forest and Rangeland Ecosystem Science Center", "url": "https://www.usgs.gov/centers/forest-and-rangeland-ecosystem-science-center"}]}, {"@type": "Person", "name": "Miller, Mark P. mpmiller@usgs.gov", "givenName": "Mark P.", "familyName": "Miller", "email": "mpmiller@usgs.gov", "identifier": {"@type": "PropertyValue", "propertyID": "ORCID", "value": "0000-0003-1045-1772", "url": "https://orcid.org/0000-0003-1045-1772"}, "affiliation": [{"@type": "Organization", "name": "WMA - Office of Planning and Programming", "url": "https://www.usgs.gov/mission-areas/water-resources"}]}, {"@type": "Person", "name": "Mullins, Thomas D.", "givenName": "Thomas D.", "familyName": "Mullins"}, {"@type": "Person", "name": "Knaus, Brian J.", "givenName": "Brian J.", "familyName": "Knaus"}], "funder": [{"@type": "Organization", "name": "Forest and Rangeland Ecosystem Science Center", "url": "https://www.usgs.gov/centers/forest-and-rangeland-ecosystem-science-center"}]}
{
  "USGS Publications Warehouse": {
    "schema": {
      "@context": "https://schema.org",
      "@type": "CreativeWork",
      "additionalType": "USGS Numbered Series",
      "name": "SSR_pipeline--computer software for the identification of microsatellite sequences from paired-end Illumina high-throughput DNA sequence data",
      "identifier": [
        {
          "@type": "PropertyValue",
          "propertyID": "USGS Publications Warehouse IndexID",
          "value": "ds778",
          "url": "https://pubs.usgs.gov/publication/ds778"
        },
        {
          "@type": "PropertyValue",
          "propertyID": "USGS Publications Warehouse Internal ID",
          "value": 70046704
        },
        {
          "@type": "PropertyValue",
          "propertyID": "DOI",
          "value": "10.3133/ds778",
          "url": "https://doi.org/10.3133/ds778"
        }
      ],
      "inLanguage": "en",
      "isPartOf": [
        {
          "@type": "CreativeWorkSeries",
          "name": "Data Series"
        }
      ],
      "datePublished": "2013",
      "dateModified": "2013-06-26",
      "abstract": "SSR_pipeline is a flexible set of programs designed to efficiently identify simple sequence repeats (SSRs; for example, microsatellites) from paired-end high-throughput Illumina DNA sequencing data. The program suite contains three analysis modules along with a fourth control module that can be used to automate analyses of large volumes of data. The modules are used to (1) identify the subset of paired-end sequences that pass quality standards, (2) align paired-end reads into a single composite DNA sequence, and (3) identify sequences that possess microsatellites conforming to user specified parameters. Each of the three separate analysis modules also can be used independently to provide greater flexibility or to work with FASTQ or FASTA files generated from other sequencing platforms (Roche 454, Ion Torrent, etc).\n\nAll modules are implemented in the Python programming language and can therefore be used from nearly any computer operating system (Linux, Macintosh, Windows). The program suite relies on a compiled Python extension module to perform paired-end alignments. Instructions for compiling the extension from source code are provided in the documentation. Users who do not have Python installed on their computers or who do not have the ability to compile software also may choose to download packaged executable files. These files include all Python scripts, a copy of the compiled extension module, and a minimal installation of Python in a single binary executable. See program documentation for more information.",
      "description": "HTML Document; Program Documentation; Program Executable Files",
      "publisher": {
        "@type": "Organization",
        "name": "U.S. Geological Survey"
      },
      "author": [
        {
          "@type": "Person",
          "name": "Haig, Susan M. susan_haig@usgs.gov",
          "givenName": "Susan M.",
          "familyName": "Haig",
          "email": "susan_haig@usgs.gov",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "ORCID",
            "value": "0000-0002-6616-7589",
            "url": "https://orcid.org/0000-0002-6616-7589"
          },
          "affiliation": [
            {
              "@type": "Organization",
              "name": "Forest and Rangeland Ecosystem Science Center",
              "url": "https://www.usgs.gov/centers/forest-and-rangeland-ecosystem-science-center"
            },
            {
              "@type": "Organization",
              "name": "Forest and Rangeland Ecosys Science Center",
              "url": "https://www.usgs.gov/centers/forest-and-rangeland-ecosystem-science-center"
            }
          ]
        },
        {
          "@type": "Person",
          "name": "Miller, Mark P. mpmiller@usgs.gov",
          "givenName": "Mark P.",
          "familyName": "Miller",
          "email": "mpmiller@usgs.gov",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "ORCID",
            "value": "0000-0003-1045-1772",
            "url": "https://orcid.org/0000-0003-1045-1772"
          },
          "affiliation": [
            {
              "@type": "Organization",
              "name": "WMA - Office of Planning and Programming",
              "url": "https://www.usgs.gov/mission-areas/water-resources"
            }
          ]
        },
        {
          "@type": "Person",
          "name": "Mullins, Thomas D.",
          "givenName": "Thomas D.",
          "familyName": "Mullins"
        },
        {
          "@type": "Person",
          "name": "Knaus, Brian J.",
          "givenName": "Brian J.",
          "familyName": "Knaus"
        }
      ],
      "funder": [
        {
          "@type": "Organization",
          "name": "Forest and Rangeland Ecosystem Science Center",
          "url": "https://www.usgs.gov/centers/forest-and-rangeland-ecosystem-science-center"
        }
      ]
    }
  },
  "OpenAlex": {
    "abstract_inverted_index": {
      "SSR_pipeline": [
        0
      ],
      "is": [
        1
      ],
      "a": [
        2,
        34,
        71,
        150,
        206,
        214,
        220
      ],
      "flexible": [
        3
      ],
      "set": [
        4
      ],
      "of": [
        5,
        45,
        48,
        59,
        89,
        208,
        217
      ],
      "programs": [
        6
      ],
      "designed": [
        7
      ],
      "to": [
        8,
        42,
        54,
        84,
        100,
        105,
        155,
        189,
        195
      ],
      "efficiently": [
        9
      ],
      "identify": [
        10,
        56,
        78
      ],
      "simple": [
        11
      ],
      "sequence": [
        12
      ],
      "repeats": [
        13
      ],
      "(SSRs;": [
        14
      ],
      "for": [
        15,
        160,
        227
      ],
      "example,": [
        16
      ],
      "microsatellites)": [
        17
      ],
      "from": [
        18,
        113,
        136,
        164
      ],
      "paired-end": [
        19,
        60,
        68,
        157
      ],
      "high-throughput": [
        20
      ],
      "Illumina": [
        21
      ],
      "DNA": [
        22,
        74
      ],
      "sequencing": [
        23,
        115
      ],
      "data.": [
        24,
        49
      ],
      "The": [
        25,
        50,
        145
      ],
      "program": [
        26,
        146,
        225
      ],
      "suite": [
        27,
        147
      ],
      "contains": [
        28
      ],
      "three": [
        29,
        91
      ],
      "analysis": [
        30,
        93
      ],
      "modules": [
        31,
        51,
        94,
        123
      ],
      "along": [
        32
      ],
      "with": [
        33,
        107
      ],
      "fourth": [
        35
      ],
      "control": [
        36
      ],
      "module": [
        37,
        154
      ],
      "that": [
        38,
        62,
        80
      ],
      "can": [
        39,
        96,
        132
      ],
      "be": [
        40,
        97,
        134
      ],
      "used": [
        41,
        53,
        98,
        135
      ],
      "automate": [
        43
      ],
      "analyses": [
        44
      ],
      "large": [
        46
      ],
      "volumes": [
        47
      ],
      "are": [
        52,
        124,
        167
      ],
      "(1)": [
        55
      ],
      "the": [
        57,
        90,
        127,
        162,
        170,
        187,
        209
      ],
      "subset": [
        58
      ],
      "sequences": [
        61,
        79
      ],
      "pass": [
        63
      ],
      "quality": [
        64
      ],
      "standards,": [
        65
      ],
      "(2)": [
        66
      ],
      "align": [
        67
      ],
      "reads": [
        69
      ],
      "into": [
        70
      ],
      "single": [
        72,
        221
      ],
      "composite": [
        73
      ],
      "sequence,": [
        75
      ],
      "and": [
        76,
        131,
        213
      ],
      "(3)": [
        77
      ],
      "possess": [
        81
      ],
      "microsatellites": [
        82
      ],
      "conforming": [
        83
      ],
      "user": [
        85
      ],
      "specified": [
        86
      ],
      "parameters.": [
        87
      ],
      "Each": [
        88
      ],
      "separate": [
        92
      ],
      "also": [
        95,
        192
      ],
      "independently": [
        99
      ],
      "provide": [
        101
      ],
      "greater": [
        102
      ],
      "flexibility": [
        103
      ],
      "or": [
        104,
        109,
        182
      ],
      "work": [
        106
      ],
      "FASTQ": [
        108
      ],
      "FASTA": [
        110
      ],
      "files": [
        111,
        201
      ],
      "generated": [
        112
      ],
      "other": [
        114
      ],
      "platforms": [
        116
      ],
      "(Roche": [
        117
      ],
      "454,": [
        118
      ],
      "Ion": [
        119
      ],
      "Torrent,": [
        120
      ],
      "etc).": [
        121
      ],
      "All": [
        122
      ],
      "implemented": [
        125
      ],
      "in": [
        126,
        169,
        219
      ],
      "Python": [
        128,
        152,
        177,
        204,
        218
      ],
      "programming": [
        129
      ],
      "language": [
        130
      ],
      "therefore": [
        133
      ],
      "nearly": [
        137
      ],
      "any": [
        138
      ],
      "computer": [
        139
      ],
      "operating": [
        140
      ],
      "system": [
        141
      ],
      "(Linux,": [
        142
      ],
      "Macintosh,": [
        143
      ],
      "Windows).": [
        144
      ],
      "relies": [
        148
      ],
      "on": [
        149,
        179
      ],
      "compiled": [
        151,
        210
      ],
      "extension": [
        153,
        163,
        211
      ],
      "perform": [
        156
      ],
      "alignments.": [
        158
      ],
      "Instructions": [
        159
      ],
      "compiling": [
        161
      ],
      "source": [
        165
      ],
      "code": [
        166
      ],
      "provided": [
        168
      ],
      "documentation.": [
        171
      ],
      "Users": [
        172
      ],
      "who": [
        173,
        183
      ],
      "do": [
        174,
        184
      ],
      "not": [
        175,
        185
      ],
      "have": [
        176,
        186
      ],
      "installed": [
        178
      ],
      "their": [
        180
      ],
      "computers": [
        181
      ],
      "ability": [
        188
      ],
      "compile": [
        190
      ],
      "software": [
        191
      ],
      "may": [
        193
      ],
      "choose": [
        194
      ],
      "download": [
        196
      ],
      "packaged": [
        197
      ],
      "executable": [
        198
      ],
      "files.": [
        199
      ],
      "These": [
        200
      ],
      "include": [
        202
      ],
      "all": [
        203
      ],
      "scripts,": [
        205
      ],
      "copy": [
        207
      ],
      "module,": [
        212
      ],
      "minimal": [
        215
      ],
      "installation": [
        216
      ],
      "binary": [
        222
      ],
      "executable.": [
        223
      ],
      "See": [
        224
      ],
      "documentation": [
        226
      ],
      "more": [
        228
      ],
      "information.": [
        229
      ]
    },
    "apc_list": null,
    "apc_paid": null,
    "authorships": [
      {
        "author_position": "first",
        "author": {
          "id": "https://openalex.org/A5002419088",
          "display_name": "Mark P. Miller",
          "orcid": "https://orcid.org/0000-0003-1045-1772"
        },
        "institutions": [],
        "countries": [],
        "is_corresponding": false,
        "raw_author_name": "Mark P. Miller",
        "raw_affiliation_strings": [],
        "affiliations": []
      },
      {
        "author_position": "middle",
        "author": {
          "id": "https://openalex.org/A5008832881",
          "display_name": "Brian J. Knaus",
          "orcid": "https://orcid.org/0000-0003-1665-4343"
        },
        "institutions": [],
        "countries": [],
        "is_corresponding": false,
        "raw_author_name": "Brian J. Knaus",
        "raw_affiliation_strings": [],
        "affiliations": []
      },
      {
        "author_position": "middle",
        "author": {
          "id": "https://openalex.org/A5066645664",
          "display_name": "Thomas D. Mullins",
          "orcid": "https://orcid.org/0000-0001-8948-9604"
        },
        "institutions": [],
        "countries": [],
        "is_corresponding": false,
        "raw_author_name": "Thomas D. Mullins",
        "raw_affiliation_strings": [],
        "affiliations": []
      },
      {
        "author_position": "last",
        "author": {
          "id": "https://openalex.org/A5020594178",
          "display_name": "Susan M. Haig",
          "orcid": "https://orcid.org/0000-0002-6616-7589"
        },
        "institutions": [],
        "countries": [],
        "is_corresponding": false,
        "raw_author_name": "Susan M. Haig",
        "raw_affiliation_strings": [],
        "affiliations": []
      }
    ],
    "best_oa_location": null,
    "biblio": {
      "volume": null,
      "issue": null,
      "first_page": null,
      "last_page": null
    },
    "citation_normalized_percentile": null,
    "cited_by_api_url": "https://api.openalex.org/works?filter=cites:W1547475070",
    "cited_by_count": 0,
    "cited_by_percentile_year": {
      "min": 0,
      "max": 67
    },
    "concepts": [
      {
        "id": "https://openalex.org/c160145156",
        "wikidata": "https://www.wikidata.org/wiki/Q778586",
        "display_name": "Executable",
        "level": 2,
        "score": 0.8060643,
        "qid": null
      },
      {
        "id": "https://openalex.org/c519991488",
        "wikidata": "https://www.wikidata.org/wiki/Q28865",
        "display_name": "Python (programming language)",
        "level": 2,
        "score": 0.7785063,
        "qid": null
      },
      {
        "id": "https://openalex.org/c41008148",
        "wikidata": "https://www.wikidata.org/wiki/Q21198",
        "display_name": "Computer science",
        "level": 0,
        "score": 0.7685064,
        "qid": "Q158969"
      },
      {
        "id": "https://openalex.org/c199360897",
        "wikidata": "https://www.wikidata.org/wiki/Q9143",
        "display_name": "Programming language",
        "level": 1,
        "score": 0.61714745,
        "qid": "Q226303"
      },
      {
        "id": "https://openalex.org/c61423126",
        "wikidata": "https://www.wikidata.org/wiki/Q187432",
        "display_name": "Scripting language",
        "level": 2,
        "score": 0.5798254,
        "qid": null
      },
      {
        "id": "https://openalex.org/c111919701",
        "wikidata": "https://www.wikidata.org/wiki/Q9135",
        "display_name": "Operating system",
        "level": 1,
        "score": 0.5138693,
        "qid": "Q226285"
      },
      {
        "id": "https://openalex.org/c2777904410",
        "wikidata": "https://www.wikidata.org/wiki/Q7397",
        "display_name": "Software",
        "level": 2,
        "score": 0.50559735,
        "qid": "Q165907"
      },
      {
        "id": "https://openalex.org/c77088390",
        "wikidata": "https://www.wikidata.org/wiki/Q8513",
        "display_name": "Database",
        "level": 1,
        "score": 0.35823247,
        "qid": "Q165904"
      }
    ],
    "corresponding_author_ids": [],
    "corresponding_institution_ids": [],
    "countries_distinct_count": 0,
    "counts_by_year": [],
    "created_date": "2016-06-24",
    "datasets": [],
    "display_name": "SSR_pipeline--computer software for the identification of microsatellite sequences from paired-end Illumina high-throughput DNA sequence data",
    "doi": "https://doi.org/10.3133/ds778",
    "fwci": 0.0,
    "grants": [],
    "has_fulltext": false,
    "id": "https://openalex.org/W1547475070",
    "ids": {
      "openalex": "https://openalex.org/W1547475070",
      "doi": "https://doi.org/10.3133/ds778",
      "mag": "1547475070"
    },
    "indexed_in": [
      "crossref"
    ],
    "institutions_distinct_count": 0,
    "is_paratext": false,
    "is_retracted": false,
    "keywords": [
      {
        "id": "https://openalex.org/keywords/executable",
        "display_name": "Executable",
        "score": 0.8060643
      },
      {
        "id": "https://openalex.org/keywords/python",
        "display_name": "Python (programming language)",
        "score": 0.7785063
      },
      {
        "id": "https://openalex.org/keywords/secondary-structure-prediction",
        "display_name": "Secondary Structure Prediction",
        "score": 0.47806
      }
    ],
    "language": "en",
    "locations": [
      {
        "is_oa": false,
        "landing_page_url": "https://doi.org/10.3133/ds778",
        "pdf_url": null,
        "source": {
          "id": "https://openalex.org/S4210176622",
          "display_name": "Data series",
          "issn_l": "2327-638X",
          "issn": [
            "2327-638X",
            "2328-0271",
            "2333-0481"
          ],
          "is_oa": false,
          "is_in_doaj": false,
          "is_core": false,
          "host_organization": "https://openalex.org/P4310319934",
          "host_organization_name": "United States Geological Survey",
          "host_organization_lineage": [
            "https://openalex.org/P4310319934",
            "https://openalex.org/P4310316088"
          ],
          "host_organization_lineage_names": [
            "United States Geological Survey",
            "United States Department of the Interior"
          ],
          "type": "journal"
        },
        "license": null,
        "license_id": null,
        "version": null,
        "is_accepted": false,
        "is_published": false
      }
    ],
    "locations_count": 1,
    "mesh": [],
    "ngrams_url": "https://api.openalex.org/works/W1547475070/ngrams",
    "open_access": {
      "is_oa": false,
      "oa_status": "closed",
      "oa_url": null,
      "any_repository_has_fulltext": false
    },
    "primary_location": {
      "is_oa": false,
      "landing_page_url": "https://doi.org/10.3133/ds778",
      "pdf_url": null,
      "source": {
        "id": "https://openalex.org/S4210176622",
        "display_name": "Data series",
        "issn_l": "2327-638X",
        "issn": [
          "2327-638X",
          "2328-0271",
          "2333-0481"
        ],
        "is_oa": false,
        "is_in_doaj": false,
        "is_core": false,
        "host_organization": "https://openalex.org/P4310319934",
        "host_organization_name": "United States Geological Survey",
        "host_organization_lineage": [
          "https://openalex.org/P4310319934",
          "https://openalex.org/P4310316088"
        ],
        "host_organization_lineage_names": [
          "United States Geological Survey",
          "United States Department of the Interior"
        ],
        "type": "journal"
      },
      "license": null,
      "license_id": null,
      "version": null,
      "is_accepted": false,
      "is_published": false
    },
    "primary_topic": {
      "id": "https://openalex.org/T10015",
      "display_name": "RNA Sequencing Data Analysis",
      "score": 0.9983,
      "subfield": {
        "id": "https://openalex.org/subfields/1312",
        "display_name": "Molecular Biology"
      },
      "field": {
        "id": "https://openalex.org/fields/13",
        "display_name": "Biochemistry, Genetics and Molecular Biology"
      },
      "domain": {
        "id": "https://openalex.org/domains/1",
        "display_name": "Life Sciences"
      }
    },
    "publication_date": "2013-01-01",
    "publication_year": 2013,
    "referenced_works": [],
    "referenced_works_count": 0,
    "related_works": [
      "https://openalex.org/W4389470870",
      "https://openalex.org/W4300438041",
      "https://openalex.org/W3084909426",
      "https://openalex.org/W3023169329",
      "https://openalex.org/W2782165897",
      "https://openalex.org/W2761254753",
      "https://openalex.org/W2188981919",
      "https://openalex.org/W2139703748",
      "https://openalex.org/W2054104202",
      "https://openalex.org/W1024825291"
    ],
    "sustainable_development_goals": [],
    "title": "SSR_pipeline--computer software for the identification of microsatellite sequences from paired-end Illumina high-throughput DNA sequence data",
    "topics": [
      {
        "id": "https://openalex.org/T10015",
        "display_name": "RNA Sequencing Data Analysis",
        "score": 0.9983,
        "subfield": {
          "id": "https://openalex.org/subfields/1312",
          "display_name": "Molecular Biology"
        },
        "field": {
          "id": "https://openalex.org/fields/13",
          "display_name": "Biochemistry, Genetics and Molecular Biology"
        },
        "domain": {
          "id": "https://openalex.org/domains/1",
          "display_name": "Life Sciences"
        }
      },
      {
        "id": "https://openalex.org/T10521",
        "display_name": "Ribosome Structure and Translation Mechanisms",
        "score": 0.9847,
        "subfield": {
          "id": "https://openalex.org/subfields/1312",
          "display_name": "Molecular Biology"
        },
        "field": {
          "id": "https://openalex.org/fields/13",
          "display_name": "Biochemistry, Genetics and Molecular Biology"
        },
        "domain": {
          "id": "https://openalex.org/domains/1",
          "display_name": "Life Sciences"
        }
      },
      {
        "id": "https://openalex.org/T12858",
        "display_name": "Genetics and Epidemiology of Plant Pathogens",
        "score": 0.9689,
        "subfield": {
          "id": "https://openalex.org/subfields/1110",
          "display_name": "Plant Science"
        },
        "field": {
          "id": "https://openalex.org/fields/11",
          "display_name": "Agricultural and Biological Sciences"
        },
        "domain": {
          "id": "https://openalex.org/domains/1",
          "display_name": "Life Sciences"
        }
      }
    ],
    "type": "article",
    "type_crossref": "journal-article",
    "updated_date": "2024-08-12T07:56:58.895182",
    "versions": [],
    "qid": "Q61064"
  }
}

Latest revision as of 00:40, 15 August 2024

{

 "USGS Publications Warehouse": {
   "schema": {
     "@context": "https://schema.org",
     "@type": "CreativeWork",
     "additionalType": "USGS Numbered Series",
     "name": "SSR_pipeline--computer software for the identification of microsatellite sequences from paired-end Illumina high-throughput DNA sequence data",
     "identifier": [
       {
         "@type": "PropertyValue",
         "propertyID": "USGS Publications Warehouse IndexID",
         "value": "ds778",
         "url": "https://pubs.usgs.gov/publication/ds778"
       },
       {
         "@type": "PropertyValue",
         "propertyID": "USGS Publications Warehouse Internal ID",
         "value": 70046704
       },
       {
         "@type": "PropertyValue",
         "propertyID": "DOI",
         "value": "10.3133/ds778",
         "url": "https://doi.org/10.3133/ds778"
       }
     ],
     "inLanguage": "en",
     "isPartOf": [
       {
         "@type": "CreativeWorkSeries",
         "name": "Data Series"
       }
     ],
     "datePublished": "2013",
     "dateModified": "2013-06-26",
     "abstract": "SSR_pipeline is a flexible set of programs designed to efficiently identify simple sequence repeats (SSRs; for example, microsatellites) from paired-end high-throughput Illumina DNA sequencing data. The program suite contains three analysis modules along with a fourth control module that can be used to automate analyses of large volumes of data. The modules are used to (1) identify the subset of paired-end sequences that pass quality standards, (2) align paired-end reads into a single composite DNA sequence, and (3) identify sequences that possess microsatellites conforming to user specified parameters. Each of the three separate analysis modules also can be used independently to provide greater flexibility or to work with FASTQ or FASTA files generated from other sequencing platforms (Roche 454, Ion Torrent, etc).\n\nAll modules are implemented in the Python programming language and can therefore be used from nearly any computer operating system (Linux, Macintosh, Windows). The program suite relies on a compiled Python extension module to perform paired-end alignments. Instructions for compiling the extension from source code are provided in the documentation. Users who do not have Python installed on their computers or who do not have the ability to compile software also may choose to download packaged executable files. These files include all Python scripts, a copy of the compiled extension module, and a minimal installation of Python in a single binary executable. See program documentation for more information.",
     "description": "HTML Document; Program Documentation; Program Executable Files",
     "publisher": {
       "@type": "Organization",
       "name": "U.S. Geological Survey"
     },
     "author": [
       {
         "@type": "Person",
         "name": "Haig, Susan M. susan_haig@usgs.gov",
         "givenName": "Susan M.",
         "familyName": "Haig",
         "email": "susan_haig@usgs.gov",
         "identifier": {
           "@type": "PropertyValue",
           "propertyID": "ORCID",
           "value": "0000-0002-6616-7589",
           "url": "https://orcid.org/0000-0002-6616-7589"
         },
         "affiliation": [
           {
             "@type": "Organization",
             "name": "Forest and Rangeland Ecosystem Science Center",
             "url": "https://www.usgs.gov/centers/forest-and-rangeland-ecosystem-science-center"
           },
           {
             "@type": "Organization",
             "name": "Forest and Rangeland Ecosys Science Center",
             "url": "https://www.usgs.gov/centers/forest-and-rangeland-ecosystem-science-center"
           }
         ]
       },
       {
         "@type": "Person",
         "name": "Miller, Mark P. mpmiller@usgs.gov",
         "givenName": "Mark P.",
         "familyName": "Miller",
         "email": "mpmiller@usgs.gov",
         "identifier": {
           "@type": "PropertyValue",
           "propertyID": "ORCID",
           "value": "0000-0003-1045-1772",
           "url": "https://orcid.org/0000-0003-1045-1772"
         },
         "affiliation": [
           {
             "@type": "Organization",
             "name": "WMA - Office of Planning and Programming",
             "url": "https://www.usgs.gov/mission-areas/water-resources"
           }
         ]
       },
       {
         "@type": "Person",
         "name": "Mullins, Thomas D.",
         "givenName": "Thomas D.",
         "familyName": "Mullins"
       },
       {
         "@type": "Person",
         "name": "Knaus, Brian J.",
         "givenName": "Brian J.",
         "familyName": "Knaus"
       }
     ],
     "funder": [
       {
         "@type": "Organization",
         "name": "Forest and Rangeland Ecosystem Science Center",
         "url": "https://www.usgs.gov/centers/forest-and-rangeland-ecosystem-science-center"
       }
     ]
   }
 },
 "OpenAlex": {
   "abstract_inverted_index": {
     "SSR_pipeline": [
       0
     ],
     "is": [
       1
     ],
     "a": [
       2,
       34,
       71,
       150,
       206,
       214,
       220
     ],
     "flexible": [
       3
     ],
     "set": [
       4
     ],
     "of": [
       5,
       45,
       48,
       59,
       89,
       208,
       217
     ],
     "programs": [
       6
     ],
     "designed": [
       7
     ],
     "to": [
       8,
       42,
       54,
       84,
       100,
       105,
       155,
       189,
       195
     ],
     "efficiently": [
       9
     ],
     "identify": [
       10,
       56,
       78
     ],
     "simple": [
       11
     ],
     "sequence": [
       12
     ],
     "repeats": [
       13
     ],
     "(SSRs;": [
       14
     ],
     "for": [
       15,
       160,
       227
     ],
     "example,": [
       16
     ],
     "microsatellites)": [
       17
     ],
     "from": [
       18,
       113,
       136,
       164
     ],
     "paired-end": [
       19,
       60,
       68,
       157
     ],
     "high-throughput": [
       20
     ],
     "Illumina": [
       21
     ],
     "DNA": [
       22,
       74
     ],
     "sequencing": [
       23,
       115
     ],
     "data.": [
       24,
       49
     ],
     "The": [
       25,
       50,
       145
     ],
     "program": [
       26,
       146,
       225
     ],
     "suite": [
       27,
       147
     ],
     "contains": [
       28
     ],
     "three": [
       29,
       91
     ],
     "analysis": [
       30,
       93
     ],
     "modules": [
       31,
       51,
       94,
       123
     ],
     "along": [
       32
     ],
     "with": [
       33,
       107
     ],
     "fourth": [
       35
     ],
     "control": [
       36
     ],
     "module": [
       37,
       154
     ],
     "that": [
       38,
       62,
       80
     ],
     "can": [
       39,
       96,
       132
     ],
     "be": [
       40,
       97,
       134
     ],
     "used": [
       41,
       53,
       98,
       135
     ],
     "automate": [
       43
     ],
     "analyses": [
       44
     ],
     "large": [
       46
     ],
     "volumes": [
       47
     ],
     "are": [
       52,
       124,
       167
     ],
     "(1)": [
       55
     ],
     "the": [
       57,
       90,
       127,
       162,
       170,
       187,
       209
     ],
     "subset": [
       58
     ],
     "sequences": [
       61,
       79
     ],
     "pass": [
       63
     ],
     "quality": [
       64
     ],
     "standards,": [
       65
     ],
     "(2)": [
       66
     ],
     "align": [
       67
     ],
     "reads": [
       69
     ],
     "into": [
       70
     ],
     "single": [
       72,
       221
     ],
     "composite": [
       73
     ],
     "sequence,": [
       75
     ],
     "and": [
       76,
       131,
       213
     ],
     "(3)": [
       77
     ],
     "possess": [
       81
     ],
     "microsatellites": [
       82
     ],
     "conforming": [
       83
     ],
     "user": [
       85
     ],
     "specified": [
       86
     ],
     "parameters.": [
       87
     ],
     "Each": [
       88
     ],
     "separate": [
       92
     ],
     "also": [
       95,
       192
     ],
     "independently": [
       99
     ],
     "provide": [
       101
     ],
     "greater": [
       102
     ],
     "flexibility": [
       103
     ],
     "or": [
       104,
       109,
       182
     ],
     "work": [
       106
     ],
     "FASTQ": [
       108
     ],
     "FASTA": [
       110
     ],
     "files": [
       111,
       201
     ],
     "generated": [
       112
     ],
     "other": [
       114
     ],
     "platforms": [
       116
     ],
     "(Roche": [
       117
     ],
     "454,": [
       118
     ],
     "Ion": [
       119
     ],
     "Torrent,": [
       120
     ],
     "etc).": [
       121
     ],
     "All": [
       122
     ],
     "implemented": [
       125
     ],
     "in": [
       126,
       169,
       219
     ],
     "Python": [
       128,
       152,
       177,
       204,
       218
     ],
     "programming": [
       129
     ],
     "language": [
       130
     ],
     "therefore": [
       133
     ],
     "nearly": [
       137
     ],
     "any": [
       138
     ],
     "computer": [
       139
     ],
     "operating": [
       140
     ],
     "system": [
       141
     ],
     "(Linux,": [
       142
     ],
     "Macintosh,": [
       143
     ],
     "Windows).": [
       144
     ],
     "relies": [
       148
     ],
     "on": [
       149,
       179
     ],
     "compiled": [
       151,
       210
     ],
     "extension": [
       153,
       163,
       211
     ],
     "perform": [
       156
     ],
     "alignments.": [
       158
     ],
     "Instructions": [
       159
     ],
     "compiling": [
       161
     ],
     "source": [
       165
     ],
     "code": [
       166
     ],
     "provided": [
       168
     ],
     "documentation.": [
       171
     ],
     "Users": [
       172
     ],
     "who": [
       173,
       183
     ],
     "do": [
       174,
       184
     ],
     "not": [
       175,
       185
     ],
     "have": [
       176,
       186
     ],
     "installed": [
       178
     ],
     "their": [
       180
     ],
     "computers": [
       181
     ],
     "ability": [
       188
     ],
     "compile": [
       190
     ],
     "software": [
       191
     ],
     "may": [
       193
     ],
     "choose": [
       194
     ],
     "download": [
       196
     ],
     "packaged": [
       197
     ],
     "executable": [
       198
     ],
     "files.": [
       199
     ],
     "These": [
       200
     ],
     "include": [
       202
     ],
     "all": [
       203
     ],
     "scripts,": [
       205
     ],
     "copy": [
       207
     ],
     "module,": [
       212
     ],
     "minimal": [
       215
     ],
     "installation": [
       216
     ],
     "binary": [
       222
     ],
     "executable.": [
       223
     ],
     "See": [
       224
     ],
     "documentation": [
       226
     ],
     "more": [
       228
     ],
     "information.": [
       229
     ]
   },
   "apc_list": null,
   "apc_paid": null,
   "authorships": [
     {
       "author_position": "first",
       "author": {
         "id": "https://openalex.org/A5002419088",
         "display_name": "Mark P. Miller",
         "orcid": "https://orcid.org/0000-0003-1045-1772"
       },
       "institutions": [],
       "countries": [],
       "is_corresponding": false,
       "raw_author_name": "Mark P. Miller",
       "raw_affiliation_strings": [],
       "affiliations": []
     },
     {
       "author_position": "middle",
       "author": {
         "id": "https://openalex.org/A5008832881",
         "display_name": "Brian J. Knaus",
         "orcid": "https://orcid.org/0000-0003-1665-4343"
       },
       "institutions": [],
       "countries": [],
       "is_corresponding": false,
       "raw_author_name": "Brian J. Knaus",
       "raw_affiliation_strings": [],
       "affiliations": []
     },
     {
       "author_position": "middle",
       "author": {
         "id": "https://openalex.org/A5066645664",
         "display_name": "Thomas D. Mullins",
         "orcid": "https://orcid.org/0000-0001-8948-9604"
       },
       "institutions": [],
       "countries": [],
       "is_corresponding": false,
       "raw_author_name": "Thomas D. Mullins",
       "raw_affiliation_strings": [],
       "affiliations": []
     },
     {
       "author_position": "last",
       "author": {
         "id": "https://openalex.org/A5020594178",
         "display_name": "Susan M. Haig",
         "orcid": "https://orcid.org/0000-0002-6616-7589"
       },
       "institutions": [],
       "countries": [],
       "is_corresponding": false,
       "raw_author_name": "Susan M. Haig",
       "raw_affiliation_strings": [],
       "affiliations": []
     }
   ],
   "best_oa_location": null,
   "biblio": {
     "volume": null,
     "issue": null,
     "first_page": null,
     "last_page": null
   },
   "citation_normalized_percentile": null,
   "cited_by_api_url": "https://api.openalex.org/works?filter=cites:W1547475070",
   "cited_by_count": 0,
   "cited_by_percentile_year": {
     "min": 0,
     "max": 67
   },
   "concepts": [
     {
       "id": "https://openalex.org/c160145156",
       "wikidata": "https://www.wikidata.org/wiki/Q778586",
       "display_name": "Executable",
       "level": 2,
       "score": 0.8060643,
       "qid": null
     },
     {
       "id": "https://openalex.org/c519991488",
       "wikidata": "https://www.wikidata.org/wiki/Q28865",
       "display_name": "Python (programming language)",
       "level": 2,
       "score": 0.7785063,
       "qid": null
     },
     {
       "id": "https://openalex.org/c41008148",
       "wikidata": "https://www.wikidata.org/wiki/Q21198",
       "display_name": "Computer science",
       "level": 0,
       "score": 0.7685064,
       "qid": "Q158969"
     },
     {
       "id": "https://openalex.org/c199360897",
       "wikidata": "https://www.wikidata.org/wiki/Q9143",
       "display_name": "Programming language",
       "level": 1,
       "score": 0.61714745,
       "qid": "Q226303"
     },
     {
       "id": "https://openalex.org/c61423126",
       "wikidata": "https://www.wikidata.org/wiki/Q187432",
       "display_name": "Scripting language",
       "level": 2,
       "score": 0.5798254,
       "qid": null
     },
     {
       "id": "https://openalex.org/c111919701",
       "wikidata": "https://www.wikidata.org/wiki/Q9135",
       "display_name": "Operating system",
       "level": 1,
       "score": 0.5138693,
       "qid": "Q226285"
     },
     {
       "id": "https://openalex.org/c2777904410",
       "wikidata": "https://www.wikidata.org/wiki/Q7397",
       "display_name": "Software",
       "level": 2,
       "score": 0.50559735,
       "qid": "Q165907"
     },
     {
       "id": "https://openalex.org/c77088390",
       "wikidata": "https://www.wikidata.org/wiki/Q8513",
       "display_name": "Database",
       "level": 1,
       "score": 0.35823247,
       "qid": "Q165904"
     }
   ],
   "corresponding_author_ids": [],
   "corresponding_institution_ids": [],
   "countries_distinct_count": 0,
   "counts_by_year": [],
   "created_date": "2016-06-24",
   "datasets": [],
   "display_name": "SSR_pipeline--computer software for the identification of microsatellite sequences from paired-end Illumina high-throughput DNA sequence data",
   "doi": "https://doi.org/10.3133/ds778",
   "fwci": 0.0,
   "grants": [],
   "has_fulltext": false,
   "id": "https://openalex.org/W1547475070",
   "ids": {
     "openalex": "https://openalex.org/W1547475070",
     "doi": "https://doi.org/10.3133/ds778",
     "mag": "1547475070"
   },
   "indexed_in": [
     "crossref"
   ],
   "institutions_distinct_count": 0,
   "is_paratext": false,
   "is_retracted": false,
   "keywords": [
     {
       "id": "https://openalex.org/keywords/executable",
       "display_name": "Executable",
       "score": 0.8060643
     },
     {
       "id": "https://openalex.org/keywords/python",
       "display_name": "Python (programming language)",
       "score": 0.7785063
     },
     {
       "id": "https://openalex.org/keywords/secondary-structure-prediction",
       "display_name": "Secondary Structure Prediction",
       "score": 0.47806
     }
   ],
   "language": "en",
   "locations": [
     {
       "is_oa": false,
       "landing_page_url": "https://doi.org/10.3133/ds778",
       "pdf_url": null,
       "source": {
         "id": "https://openalex.org/S4210176622",
         "display_name": "Data series",
         "issn_l": "2327-638X",
         "issn": [
           "2327-638X",
           "2328-0271",
           "2333-0481"
         ],
         "is_oa": false,
         "is_in_doaj": false,
         "is_core": false,
         "host_organization": "https://openalex.org/P4310319934",
         "host_organization_name": "United States Geological Survey",
         "host_organization_lineage": [
           "https://openalex.org/P4310319934",
           "https://openalex.org/P4310316088"
         ],
         "host_organization_lineage_names": [
           "United States Geological Survey",
           "United States Department of the Interior"
         ],
         "type": "journal"
       },
       "license": null,
       "license_id": null,
       "version": null,
       "is_accepted": false,
       "is_published": false
     }
   ],
   "locations_count": 1,
   "mesh": [],
   "ngrams_url": "https://api.openalex.org/works/W1547475070/ngrams",
   "open_access": {
     "is_oa": false,
     "oa_status": "closed",
     "oa_url": null,
     "any_repository_has_fulltext": false
   },
   "primary_location": {
     "is_oa": false,
     "landing_page_url": "https://doi.org/10.3133/ds778",
     "pdf_url": null,
     "source": {
       "id": "https://openalex.org/S4210176622",
       "display_name": "Data series",
       "issn_l": "2327-638X",
       "issn": [
         "2327-638X",
         "2328-0271",
         "2333-0481"
       ],
       "is_oa": false,
       "is_in_doaj": false,
       "is_core": false,
       "host_organization": "https://openalex.org/P4310319934",
       "host_organization_name": "United States Geological Survey",
       "host_organization_lineage": [
         "https://openalex.org/P4310319934",
         "https://openalex.org/P4310316088"
       ],
       "host_organization_lineage_names": [
         "United States Geological Survey",
         "United States Department of the Interior"
       ],
       "type": "journal"
     },
     "license": null,
     "license_id": null,
     "version": null,
     "is_accepted": false,
     "is_published": false
   },
   "primary_topic": {
     "id": "https://openalex.org/T10015",
     "display_name": "RNA Sequencing Data Analysis",
     "score": 0.9983,
     "subfield": {
       "id": "https://openalex.org/subfields/1312",
       "display_name": "Molecular Biology"
     },
     "field": {
       "id": "https://openalex.org/fields/13",
       "display_name": "Biochemistry, Genetics and Molecular Biology"
     },
     "domain": {
       "id": "https://openalex.org/domains/1",
       "display_name": "Life Sciences"
     }
   },
   "publication_date": "2013-01-01",
   "publication_year": 2013,
   "referenced_works": [],
   "referenced_works_count": 0,
   "related_works": [
     "https://openalex.org/W4389470870",
     "https://openalex.org/W4300438041",
     "https://openalex.org/W3084909426",
     "https://openalex.org/W3023169329",
     "https://openalex.org/W2782165897",
     "https://openalex.org/W2761254753",
     "https://openalex.org/W2188981919",
     "https://openalex.org/W2139703748",
     "https://openalex.org/W2054104202",
     "https://openalex.org/W1024825291"
   ],
   "sustainable_development_goals": [],
   "title": "SSR_pipeline--computer software for the identification of microsatellite sequences from paired-end Illumina high-throughput DNA sequence data",
   "topics": [
     {
       "id": "https://openalex.org/T10015",
       "display_name": "RNA Sequencing Data Analysis",
       "score": 0.9983,
       "subfield": {
         "id": "https://openalex.org/subfields/1312",
         "display_name": "Molecular Biology"
       },
       "field": {
         "id": "https://openalex.org/fields/13",
         "display_name": "Biochemistry, Genetics and Molecular Biology"
       },
       "domain": {
         "id": "https://openalex.org/domains/1",
         "display_name": "Life Sciences"
       }
     },
     {
       "id": "https://openalex.org/T10521",
       "display_name": "Ribosome Structure and Translation Mechanisms",
       "score": 0.9847,
       "subfield": {
         "id": "https://openalex.org/subfields/1312",
         "display_name": "Molecular Biology"
       },
       "field": {
         "id": "https://openalex.org/fields/13",
         "display_name": "Biochemistry, Genetics and Molecular Biology"
       },
       "domain": {
         "id": "https://openalex.org/domains/1",
         "display_name": "Life Sciences"
       }
     },
     {
       "id": "https://openalex.org/T12858",
       "display_name": "Genetics and Epidemiology of Plant Pathogens",
       "score": 0.9689,
       "subfield": {
         "id": "https://openalex.org/subfields/1110",
         "display_name": "Plant Science"
       },
       "field": {
         "id": "https://openalex.org/fields/11",
         "display_name": "Agricultural and Biological Sciences"
       },
       "domain": {
         "id": "https://openalex.org/domains/1",
         "display_name": "Life Sciences"
       }
     }
   ],
   "type": "article",
   "type_crossref": "journal-article",
   "updated_date": "2024-08-12T07:56:58.895182",
   "versions": [],
   "qid": "Q61064"
 }

}