Пример #1
0
bool gt_alphabet_is_dna(const GtAlphabet *alphabet)
{
  if (gt_alphabet_is_protein(alphabet))
  {
    return false;
  }
  if (alphabet->mapsize == MAPSIZEDNA)
  {
    GtUchar dnasymbolmap[GT_MAXALPHABETCHARACTER+1];

    assign_dna_symbolmap(&dnasymbolmap[0]);
    if (check_symbolmap(alphabet->symbolmap,&dnasymbolmap[0],"acgt"))
    {
      return true;
    }
  }
  return false;
}
Пример #2
0
static int gt_seqtransform_runner(int argc, const char **argv, int parsed_args,
                            void *tool_arguments, GtError *err)
{
  SeqtransformArguments *arguments = tool_arguments;
  GtBioseqIterator *bsi;
  unsigned long i;
  GtBioseq *bioseq;
  int had_err;

  gt_error_check(err);
  gt_assert(arguments);

  bsi = gt_bioseq_iterator_new(argc - parsed_args, argv + parsed_args);

  while (!(had_err = gt_bioseq_iterator_next(bsi, &bioseq, err)) && bioseq) {
    GtAlphabet *alphabet;
    bool is_protein;
    alphabet = gt_bioseq_get_alphabet(bioseq);
    is_protein = gt_alphabet_is_protein(alphabet);
    for (i = 0; i < gt_bioseq_number_of_sequences(bioseq); i++) {
      const char *desc, *suffix = NULL;
      char *seq;
      unsigned long seqlen;
      desc = gt_bioseq_get_description(bioseq, i);
      seq = gt_bioseq_get_sequence(bioseq, i);
      seqlen = gt_bioseq_get_sequence_length(bioseq, i);
      if (arguments->addstopaminos && is_protein && seqlen &&
          seq[seqlen-1] != GT_STOP_AMINO) {
        suffix = GT_STOP_AMINO_CSTR;
      }
      gt_fasta_show_entry_with_suffix(desc, seq, seqlen, suffix,
                                      arguments->width, arguments->outfp);
      gt_free(seq);
    }
    gt_bioseq_delete(bioseq);
  }

  gt_bioseq_iterator_delete(bsi);

  return had_err;
}
Пример #3
0
static int gt_encseq_info_runner(GT_UNUSED int argc, const char **argv,
                           int parsed_args, void *tool_arguments,
                           GtError *err)
{
  GtEncseqInfoArguments *arguments = tool_arguments;
  int had_err = 0;
  GtAlphabet *alpha;
  const GtUchar *chars;
  gt_error_check(err);
  gt_assert(arguments);

  if (arguments->nomap) {
    GtEncseqMetadata *emd = gt_encseq_metadata_new(argv[parsed_args], err);
    if (!emd)
      had_err = -1;

    if (!had_err) {
      if (!arguments->noindexname) {
        gt_file_xprintf(arguments->outfp, "index name: ");
        gt_file_xprintf(arguments->outfp, "%s\n", argv[parsed_args]);
      }

      gt_file_xprintf(arguments->outfp, "file format version: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
                                          gt_encseq_metadata_version(emd));

      gt_file_xprintf(arguments->outfp, "64-bit file: ");
      gt_file_xprintf(arguments->outfp, "%s\n", gt_encseq_metadata_is64bit(emd)
                                                  ? "yes"
                                                  : "no");

      gt_file_xprintf(arguments->outfp, "total length: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
                                        gt_encseq_metadata_total_length(emd));

      gt_file_xprintf(arguments->outfp, "number of sequences: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
                                      gt_encseq_metadata_num_of_sequences(emd));

      gt_file_xprintf(arguments->outfp, "number of files: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
                                        gt_encseq_metadata_num_of_files(emd));

      gt_file_xprintf(arguments->outfp, "length of shortest/longest "
                                        "sequence: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"/"GT_WU"\n",
                                        gt_encseq_metadata_min_seq_length(emd),
                                        gt_encseq_metadata_max_seq_length(emd));

      gt_file_xprintf(arguments->outfp, "accesstype: ");
      gt_file_xprintf(arguments->outfp, "%s\n",
                 gt_encseq_access_type_str(gt_encseq_metadata_accesstype(emd)));

      alpha = gt_encseq_metadata_alphabet(emd);
      chars = gt_alphabet_characters(alpha);
      gt_file_xprintf(arguments->outfp, "alphabet size: ");
      gt_file_xprintf(arguments->outfp, "%u\n",
                                        gt_alphabet_num_of_chars(alpha));
      gt_file_xprintf(arguments->outfp, "alphabet characters: ");
      gt_file_xprintf(arguments->outfp, "%.*s", gt_alphabet_num_of_chars(alpha),
                                        (char*) chars);
      if (gt_alphabet_is_dna(alpha))
        gt_file_xprintf(arguments->outfp, " (DNA)");
      if (gt_alphabet_is_protein(alpha))
        gt_file_xprintf(arguments->outfp, " (Protein)");
      gt_file_xprintf(arguments->outfp, "\n");
      if (arguments->show_alphabet) {
        GtStr *out = gt_str_new();
        gt_alphabet_to_str(alpha, out);
        gt_file_xprintf(arguments->outfp, "alphabet definition:\n");
        gt_file_xprintf(arguments->outfp, "%s\n", gt_str_get(out));
        gt_str_delete(out);
      }

    }
    gt_encseq_metadata_delete(emd);
  } else {
    GtEncseqLoader *encseq_loader;
    GtEncseq *encseq;

    encseq_loader = gt_encseq_loader_new();
    if (arguments->mirror)
      gt_encseq_loader_mirror(encseq_loader);
    if (!(encseq = gt_encseq_loader_load(encseq_loader,
                                         argv[parsed_args], err)))
      had_err = -1;

    if (!had_err) {
      const GtStrArray *filenames;
      GtUword i;

      if (!arguments->noindexname) {
        gt_file_xprintf(arguments->outfp, "index name: ");
        gt_file_xprintf(arguments->outfp, "%s\n", argv[parsed_args]);
      }

      gt_file_xprintf(arguments->outfp, "file format version: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"\n", gt_encseq_version(encseq));

      gt_file_xprintf(arguments->outfp, "64-bit file: ");
      gt_file_xprintf(arguments->outfp, "%s\n", gt_encseq_is_64_bit(encseq)
                                                   ? "yes"
                                                   : "no");

      gt_file_xprintf(arguments->outfp, "total length: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
                                        gt_encseq_total_length(encseq));

      gt_file_xprintf(arguments->outfp, "compressed size: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU" bytes\n",
                                        gt_encseq_sizeofrep(encseq));

      gt_file_xprintf(arguments->outfp, "number of sequences: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
                                        gt_encseq_num_of_sequences(encseq));

      gt_file_xprintf(arguments->outfp, "number of files: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
                                        gt_encseq_num_of_files(encseq));

      gt_file_xprintf(arguments->outfp, "length of shortest/longest "
                                        "sequence: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"/"GT_WU"\n",
                                      gt_encseq_min_seq_length(encseq),
                                      gt_encseq_max_seq_length(encseq));

      filenames = gt_encseq_filenames(encseq);
      gt_file_xprintf(arguments->outfp, "original filenames:\n");
      for (i = 0; i < gt_str_array_size(filenames); i++) {
        gt_file_xprintf(arguments->outfp, "\t%s ("GT_WU" characters)\n",
                                          gt_str_array_get(filenames, i),
                                          (GtUword)
                                     gt_encseq_effective_filelength(encseq, i));
      }

      alpha = gt_encseq_alphabet(encseq);
      chars = gt_alphabet_characters(alpha);
      gt_file_xprintf(arguments->outfp, "alphabet size: ");
      gt_file_xprintf(arguments->outfp, "%u\n",
                                        gt_alphabet_num_of_chars(alpha));
      gt_file_xprintf(arguments->outfp, "alphabet characters: ");
      gt_file_xprintf(arguments->outfp, "%.*s", gt_alphabet_num_of_chars(alpha),
                                        (char*) chars);
      if (gt_alphabet_is_dna(alpha))
        gt_file_xprintf(arguments->outfp, " (DNA)");
      if (gt_alphabet_is_protein(alpha))
        gt_file_xprintf(arguments->outfp, " (Protein)");
      gt_file_xprintf(arguments->outfp, "\n");
      if (arguments->show_alphabet) {
        GtStr *out = gt_str_new();
        gt_alphabet_to_str(alpha, out);
        gt_file_xprintf(arguments->outfp, "alphabet definition:\n");
        gt_file_xprintf(arguments->outfp, "%s\n", gt_str_get(out));
        gt_str_delete(out);
      }

      gt_file_xprintf(arguments->outfp, "character distribution:\n");
      for (i = 0; i < gt_alphabet_num_of_chars(alpha); i++) {
        GtUword cc;
        cc = gt_encseq_charcount(encseq, gt_alphabet_encode(alpha, chars[i]));
        gt_file_xprintf(arguments->outfp, "\t%c: "GT_WU" (%.2f%%)\n",
                                          (char) chars[i],
                                          cc,
                             (cc /(double) (gt_encseq_total_length(encseq)
                                  - gt_encseq_num_of_sequences(encseq)+1))*100);
      }

      gt_file_xprintf(arguments->outfp, "number of wildcards: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU" ("GT_WU" range(s))\n",
                                        gt_encseq_wildcards(encseq),
                                        gt_encseq_realwildcardranges(encseq));

      gt_file_xprintf(arguments->outfp, "number of special characters: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU" ("GT_WU" range(s))\n",
                                        gt_encseq_specialcharacters(encseq),
                                        gt_encseq_realspecialranges(encseq));

      gt_file_xprintf(arguments->outfp, "length of longest non-special "
                                        "character stretch: ");
      gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
                                   gt_encseq_lengthoflongestnonspecial(encseq));

      gt_file_xprintf(arguments->outfp, "accesstype: ");
      gt_file_xprintf(arguments->outfp, "%s\n",
                   gt_encseq_access_type_str(gt_encseq_accesstype_get(encseq)));

      gt_file_xprintf(arguments->outfp, "bits used per character: ");
      gt_file_xprintf(arguments->outfp, "%f\n",
        (double) ((uint64_t) CHAR_BIT *
                  (uint64_t) gt_encseq_sizeofrep(encseq)) /
        (double) gt_encseq_total_length(encseq));

      gt_file_xprintf(arguments->outfp, "has special ranges: ");
      gt_file_xprintf(arguments->outfp, "%s\n",
                                        gt_encseq_has_specialranges(encseq)
                                          ? "yes"
                                          : "no");

      gt_file_xprintf(arguments->outfp, "has description support: ");
      gt_file_xprintf(arguments->outfp, "%s\n",
                                       gt_encseq_has_description_support(encseq)
                                          ? "yes"
                                          : "no");

      if (gt_encseq_has_description_support(encseq)) {
        gt_file_xprintf(arguments->outfp, "length of longest description: ");
        gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
                                          gt_encseq_max_desc_length(encseq));
      }

      gt_file_xprintf(arguments->outfp, "has multiple sequence support: ");
      gt_file_xprintf(arguments->outfp, "%s\n",
                                        gt_encseq_has_multiseq_support(encseq)
                                          ? "yes"
                                          : "no");
    }
    gt_encseq_delete(encseq);
    gt_encseq_loader_delete(encseq_loader);
  }

  return had_err;
}