comparison search_ppep.py @ 1:08678c931f5d draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 43e7a43b545c24b2dc33d039198551c032aa79be

0:dbff53e6f75f

             from UniProtKB
    """

    # Parse Command Line
    parser = argparse.ArgumentParser(
        description="Phopsphoproteomic Enrichment phosphopeptide SwissProt search (in place in SQLite DB)."
    )

    # inputs:
    #   Phosphopeptide data for experimental results, including the intensities
    #   and the mapping to kinase domains, in tabular format.

        "--phosphopeptides",
        "-p",
        nargs=1,
        required=True,
        dest="phosphopeptides",
        help="Phosphopeptide data for experimental results, generated by the Phopsphoproteomic Enrichment Localization Filter tool",
    )
    parser.add_argument(
        "--uniprotkb",
        "-u",
        nargs=1,
        required=True,
        dest="uniprotkb",
        help="UniProtKB/Swiss-Prot data, converted from FASTA format by the Phopsphoproteomic Enrichment Kinase Mapping tool",
    )
    parser.add_argument(
        "--schema",
        action="store_true",
        dest="db_schema",

    ker = con.cursor()

    cur.executescript(DROP_TABLES_SQL)

    # if options.db_schema:
    #     print("\nAfter dropping tables/views that are to be created, schema is:")
    #     cur.execute("SELECT * FROM sqlite_schema")
    #     for row in cur.fetchall():
    #         if row[4] is not None:
    #             print("%s;" % row[4])

    cur.execute("SELECT count(*) FROM (SELECT seq FROM deppep GROUP BY seq)")
    for row in cur.fetchall():
        deppep_count = row[0]

    cur.execute(
        "SELECT count(*) FROM (SELECT Sequence FROM UniProtKB GROUP BY Sequence)"
    )
    for row in cur.fetchall():
        sequence_count = row[0]

    print("%d phosphopeptides were read from input" % ppep_count)

    )
    duplicate_count = 0
    old_seq = ""
    for row in cur.fetchall():
        if duplicate_count == 0:
            print(
                "\nEach of the following sequences is associated with several accession IDs (which are listed in the first column) but the same gene ID (which is listed in the second column)."
            )
        if row[2] != old_seq:
            old_seq = row[2]
            duplicate_count += 1
            if options.warn_duplicates:
                print("\n%s\t%s\t%s" % row)

                            end_index,
                        ),
                    )
            else:
                raise ValueError(
                    "UniProtKB_id %s, but Sequence is None: Check whether SwissProt file is missing sequence for this ID"
                    % (UniProtKB_id,)
                )
    ker.execute(
        """
        SELECT   count(*) || ' accession-peptide-phosphopeptide combinations were found'
        FROM     uniprotkb_pep_ppep_view
        """
    )
    for row in ker.fetchall():
        print(row[0])

    ker.execute(
        """
      SELECT   count(*) || ' accession matches were found', count(*) AS accession_count
      FROM     (
        SELECT   accession
        FROM     uniprotkb_pep_ppep_view
        GROUP BY accession
        )

    for row in ker.fetchall():
        print(row[0])

    ker.execute(
        """
      SELECT   count(*) || ' phosphopeptide matches were found', count(*) AS phosphopeptide_count
      FROM     (
        SELECT   phosphopeptide
        FROM     uniprotkb_pep_ppep_view
        GROUP BY phosphopeptide
        )

1:08678c931f5d

             from UniProtKB
    """

    # Parse Command Line
    parser = argparse.ArgumentParser(
        description=" ".join([
            "Phopsphoproteomic Enrichment",
            "phosphopeptide SwissProt search (in place in SQLite DB)."
        ])
    )

    # inputs:
    #   Phosphopeptide data for experimental results, including the intensities
    #   and the mapping to kinase domains, in tabular format.

        "--phosphopeptides",
        "-p",
        nargs=1,
        required=True,
        dest="phosphopeptides",
        help=" ".join([
            "Phosphopeptide data for experimental results,",
            "generated by the Phopsphoproteomic Enrichment Localization",
            "Filter tool"
        ]),
    )
    parser.add_argument(
        "--uniprotkb",
        "-u",
        nargs=1,
        required=True,
        dest="uniprotkb",
        help=" ".join([
            "UniProtKB/Swiss-Prot data, converted from FASTA format by the",
            "Phopsphoproteomic Enrichment Kinase Mapping tool"
        ]),
    )
    parser.add_argument(
        "--schema",
        action="store_true",
        dest="db_schema",

    ker = con.cursor()

    cur.executescript(DROP_TABLES_SQL)

    # if options.db_schema:
    #     print("\nAfter dropping tables/views that are to be created,"
    #         + schema is:")
    #     cur.execute("SELECT * FROM sqlite_schema")
    #     for row in cur.fetchall():
    #         if row[4] is not None:
    #             print("%s;" % row[4])

    cur.execute("SELECT count(*) FROM (SELECT seq FROM deppep GROUP BY seq)")
    for row in cur.fetchall():
        deppep_count = row[0]

    cur.execute(
        """
        SELECT count(*) FROM (
          SELECT Sequence FROM UniProtKB GROUP BY Sequence
          )
        """
    )
    for row in cur.fetchall():
        sequence_count = row[0]

    print("%d phosphopeptides were read from input" % ppep_count)

    )
    duplicate_count = 0
    old_seq = ""
    for row in cur.fetchall():
        if duplicate_count == 0:
            print(" ".join([
                "\nEach of the following sequences is associated with several",
                "accession IDs (which are listed in the first column) but",
                "the same gene ID (which is listed in the second column)."
            ]))
        if row[2] != old_seq:
            old_seq = row[2]
            duplicate_count += 1
            if options.warn_duplicates:
                print("\n%s\t%s\t%s" % row)

                            end_index,
                        ),
                    )
            else:
                raise ValueError(
                    "UniProtKB_id %s, but Sequence is None: %s %s"
                    % (
                        UniProtKB_id,
                        "Check whether SwissProt file is missing",
                        "the sequence for this ID")
                )
    ker.execute(
        """
        SELECT
          count(*) ||
            ' accession-peptide-phosphopeptide combinations were found'
        FROM
          uniprotkb_pep_ppep_view
        """
    )
    for row in ker.fetchall():
        print(row[0])

    ker.execute(
        """
      SELECT
        count(*) || ' accession matches were found',
        count(*) AS accession_count
      FROM     (
        SELECT   accession
        FROM     uniprotkb_pep_ppep_view
        GROUP BY accession
        )

    for row in ker.fetchall():
        print(row[0])

    ker.execute(
        """
      SELECT
        count(*) || ' phosphopeptide matches were found',
        count(*) AS phosphopeptide_count
      FROM     (
        SELECT   phosphopeptide
        FROM     uniprotkb_pep_ppep_view
        GROUP BY phosphopeptide
        )