bionic (1) asndisc.1.gz

NAME

       asndisc - check ASN.1 biological sequence records for discrepancies

SYNOPSIS

       asndisc  [-]  [-B]  [-C N]  [-F] [-I path] [-L str] [-N filename] [-P str] [-R] [-S] [-T] [-X tests] [-Z]
       [-a str] [-b] [-c] [-d tests] [-e tests] [-f] [-i filename] [-k] [-l]  [-o filename]  [-p path]  [-r dir]
       [-s ext] [-t] [-u] [-w filename] [-x str]

DESCRIPTION

       asndisc is a command-line tool to check ASN.1-format biological sequence records for discrepancies.

OPTIONS

       A summary of options is included below.

       -      Print usage message

       -B     Big sequence report

       -C N   Max count

       -F     Fix product name list

       -I path
              Path to Indexed binary ASN.1 data

       -L str Lineage to use

       -N filename
              File with list of product names to check

       -P str RePort type
              g      Genome
              b      Big sequence
              m      MegaReport
              t      Include Tag
              s      Tag for Superuser

       -R     Remote fetching from ID

       -S     Summary report

       -T     Use threads

       -X tests
              EXpand report categories (comma-delimited list of test names as listed below or ALL).

       -Z     Remote CDS Product Fetch

       -a str ASN.1 type
              a      Any (default)
              e      seq-Entry
              b      Bioseq
              s      bioseq-Set
              m      seq-subMit
              t      baTch bioseq-set
              u      batch seq-sUbmit
              c      Catenated seq-entry

       -b     Batch file is Binary

       -c     Batch file is Compressed

       -d str Disable tests (comma-delimited list of test names as listed below).

       -e str Enable tests (comma-delimited list of test names as listed below).

       -f     Use Feature table output format

       -i filename
              Single input file (standard input by default)

       -k     Local fetching

       -l     Load components in advance

       -o filename
              Single output file

       -p path
              Path to ASN.1 files

       -r dir Output directory

       -s ext Output file Suffix (.dr by default)

       -t     Big Test Set

       -u     Recurse

       -w filename
              Suspect product rule filename

       -x str File selection substring (.sqn by default)

   AVAILABLE TESTS
       MISSING_GENES, EXTRA_GENES, MISSING_LOCUS_TAGS, DUPLICATE_LOCUS_TAGS, BAD_LOCUS_TAG_FORMAT,
       INCONSISTENT_LOCUS_TAG_PREFIX, NON_GENE_LOCUS_TAG, DISC_COUNT_NUCLEOTIDES, MISSING_PROTEIN_ID,
       INCONSISTENT_PROTEIN_ID, FEATURE_LOCATION_CONFLICT, GENE_PRODUCT_CONFLICT, DUPLICATE_GENE_LOCUS,
       EC_NUMBER_NOTE, PSEUDO_MISMATCH, JOINED_FEATURES, OVERLAPPING_GENES, OVERLAPPING_CDS, CONTAINED_CDS,
       RNA_CDS_OVERLAP, SHORT_CONTIG, INCONSISTENT_BIOSOURCE, SUSPECT_PRODUCT_NAMES, DISC_PRODUCT_NAME_TYPO,
       DISC_PRODUCT_NAME_QUICKFIX, INCONSISTENT_SOURCE_DEFLINE, PARTIAL_CDS_COMPLETE_SEQUENCE,
       EC_NUMBER_ON_UNKNOWN_PROTEIN, TAX_LOOKUP_MISSING, TAX_LOOKUP_MISMATCH, SHORT_SEQUENCES, SUSPECT_PHRASES,
       DISC_SUSPICIOUS_NOTE_TEXT, COUNT_TRNAS, FIND_DUP_TRNAS, FIND_BADLEN_TRNAS, FIND_STRAND_TRNAS,
       COUNT_RRNAS, FIND_DUP_RRNAS, RNA_NO_PRODUCT, TRANSL_NO_NOTE, NOTE_NO_TRANSL, TRANSL_TOO_LONG,
       CDS_TRNA_OVERLAP, COUNT_PROTEINS, DISC_FEAT_OVERLAP_SRCFEAT, MISSING_GENPRODSET_PROTEIN,
       DUP_GENPRODSET_PROTEIN, MISSING_GENPRODSET_TRANSCRIPT_ID, DISC_DUP_GENPRODSET_TRANSCRIPT_ID,
       DISC_PERCENT_N, N_RUNS, ZERO_BASECOUNT, ADJACENT_PSEUDOGENES, DISC_LONG_NO_ANNOTATION, NO_ANNOTATION,
       DISC_INFLUENZA_DATE_MISMATCH, DISC_SHORT_INTRON, DISC_MISSING_VIRAL_QUALS, DISC_SRC_QUAL_PROBLEM,
       DISC_MISSING_SRC_QUAL, DISC_DUP_SRC_QUAL, DISC_DUP_SRC_QUAL_DATA, DISC_HAPLOTYPE_MISMATCH,
       DISC_FEATURE_MOLTYPE_MISMATCH, DISC_CDS_WITHOUT_MRNA, DISC_EXON_INTRON_CONFLICT, DISC_FEATURE_COUNT,
       DISC_SPECVOUCHER_TAXNAME_MISMATCH, DISC_GENE_PARTIAL_CONFLICT, DISC_FLATFILE_FIND_ONCALLER,
       DISC_CDS_PRODUCT_FIND, DISC_DUP_DEFLINE, DUP_DISC_ATCC_CULTURE_CONFLICT, DISC_USA_STATE,
       DISC_INCONSISTENT_MOLTYPES, DISC_SUBMITBLOCK_CONFLICT, DISC_POSSIBLE_LINKER, DISC_TITLE_AUTHOR_CONFLICT,
       DISC_BAD_GENE_STRAND, DISC_MAP_CHROMOSOME_CONFLICT, DISC_RBS_WITHOUT_GENE, DISC_CITSUBAFFIL_CONFLICT,
       DISC_REQUIRED_CLONE, DISC_SOURCE_QUALS_ASNDISC, DISC_mRNA_ON_WRONG_SEQUENCE_TYPE, DISC_RETROVIRIDAE_DNA,
       DISC_CHECK_AUTH_CAPS, DISC_CHECK_RNA_PRODUCTS_AND_COMMENTS, DISC_MICROSATELLITE_REPEAT_TYPE,
       DISC_MITOCHONDRION_REQUIRED, DISC_UNPUB_PUB_WITHOUT_TITLE, DISC_QUALITY_SCORES,
       DISC_INTERNAL_TRANSCRIBED_SPACER_RRNA, DISC_PARTIAL_PROBLEMS,
       DISC_BACTERIAL_PARTIAL_NONEXTENDABLE_PROBLEMS, DISC_BACTERIAL_PARTIAL_NONEXTENDABLE_EXCEPTION,
       DISC_SUSPECT_RRNA_PRODUCTS, DISC_SUSPECT_MISC_FEATURES, DISC_BACTERIA_MISSING_STRAIN,
       DISC_MISSING_DEFLINES, DISC_MISSING_AFFIL, DISC_BACTERIA_SHOULD_NOT_HAVE_ISOLATE,
       DISC_BACTERIA_SHOULD_NOT_HAVE_MRNA, DISC_CDS_HAS_NEW_EXCEPTION, DISC_TRINOMIAL_SHOULD_HAVE_QUALIFIER,
       DISC_METAGENOMIC, DISC_METAGENOME_SOURCE, ONCALLER_GENE_MISSING, ONCALLER_SUPERFLUOUS_GENE,
       DISC_SHORT_RRNA, ONCALLER_CHECK_AUTHORITY, ONCALLER_CONSORTIUM,
       ONCALLER_STRAIN_CULTURE_COLLECTION_MISMATCH, ONCALLER_MULTISRC, ONCALLER_MULTIPLE_CULTURE_COLLECTION,
       DISC_SEGSETS_PRESENT, DISC_NONWGS_SETS_PRESENT, DISC_FEATURE_LIST, DISC_CATEGORY_HEADER,
       DISC_MISMATCHED_COMMENTS, DISC_STRAIN_TAXNAME_MISMATCH, DISC_HUMAN_HOST, DISC_BAD_BACTERIAL_GENE_NAME,
       TEST_BAD_GENE_NAME, ONCALLER_ORDERED_LOCATION, ONCALLER_COMMENT_PRESENT, ONCALLER_DEFLINE_ON_SET,
       ONCALLER_HIV_RNA_INCONSISTENT, SHORT_PROT_SEQUENCES, TEST_EXON_ON_MRNA, TEST_HAS_PROJECT_ID,
       ONCALLER_HAS_STANDARD_NAME, ONCALLER_MISSING_STRUCTURED_COMMENTS, DISC_REQUIRED_STRAIN,
       MISSING_GENOMEASSEMBLY_COMMENTS, DISC_BACTERIAL_TAX_STRAIN_MISMATCH, TEST_CDS_HAS_CDD_XREF,
       TEST_UNUSUAL_NT, TEST_LOW_QUALITY_REGION, TEST_ORGANELLE_NOT_GENOMIC, TEST_UNWANTED_SPACER,
       TEST_ORGANELLE_PRODUCTS, TEST_SP_NOT_UNCULTURED, TEST_BAD_MRNA_QUAL, TEST_UNNECESSARY_ENVIRONMENTAL,
       TEST_UNNECESSARY_VIRUS_GENE, TEST_UNWANTED_SET_WRAPPER, TEST_MISSING_PRIMER, TEST_UNUSUAL_MISC_RNA,
       TEST_AMPLIFIED_PRIMERS_NO_ENVIRONMENTAL_SAMPLE, TEST_DUP_GENES_OPPOSITE_STRANDS,
       TEST_SMALL_GENOME_SET_PROBLEM, TEST_OVERLAPPING_RRNAS, TEST_MRNA_SEQUENCE_MINUS_STRAND_FEATURES,
       TEST_TAXNAME_NOT_IN_DEFLINE, TEST_COUNT_UNVERIFIED, SHOW_TRANSL_EXCEPT,
       SHOW_HYPOTHETICAL_CDS_HAVING_GENE_NAME, TEST_DEFLINE_PRESENT, TEST_MRNA_OVERLAPPING_PSEUDO_GENE,
       FIND_OVERLAPPED_GENES, DISC_BIOMATERIAL_TAXNAME_MISMATCH, DISC_CULTURE_TAXNAME_MISMATCH,
       DISC_CHECK_AUTH_NAME, NON_RETROVIRIDAE_PROVIRAL, RNA_PROVIRAL, SHORT_SEQUENCES_200, DISC_10_PERCENTN,
       N_RUNS_14, MOLTYPE_NOT_MRNA, TECHNIQUE_NOT_TSA, MISSING_STRUCTURED_COMMENT, MISSING_PROJECT,
       MULTIPLE_CDS_ON_MRNA, DUP_DISC_CBS_CULTURE_CONFLICT, DIVISION_CODE_CONFLICTS, RRNA_NAME_CONFLICTS,
       EUKARYOTE_SHOULD_HAVE_MRNA, MRNA_SHOULD_HAVE_PROTEIN_TRANSCRIPT_IDS, ONCALLER_COUNTRY_COLON,
       ONCALLER_BIOPROJECT_ID, ONCALLER_STRAIN_TAXNAME_CONFLICT, ONCALLER_MORE_NAMES_COLLECTED_BY,
       ONCALLER_MORE_OR_SPEC_NAMES_IDENTIFIED_BY, ONCALLER_SUSPECTED_ORG_IDENTIFIED,
       ONCALLER_SUSPECTED_ORG_COLLECTED, ONCALLER_SWITCH_STRUCTURED_COMMENT_PREFIX, DISC_CITSUB_AFFIL_DUP_TEXT,
       ONCALLER_DUPLICATE_PRIMER_SET, END_COLON_IN_COUNTRY, DISC_PROTEIN_NAMES, DISC_TITLE_ENDS_WITH_SEQUENCE,
       DISC_INCONSISTENT_STRUCTURED_COMMENTS, DISC_INCONSISTENT_DBLINK, DISC_INCONSISTENT_MOLINFO_TECH,
       DISC_GAPS, DISC_BAD_BGPIPE_QUALS, TEST_SHORT_LNCRNA, TEST_TERMINAL_NS, TEST_ALIGNMENT_HAS_SCORE,
       UNCULTURED_NOTES_ONCALLER, SEQ_ID_PHRASES, NO_PRODUCT_STRING

AUTHOR

       The National Center for Biotechnology Information.

SEE ALSO

       asnval(1), cleanasn(1).