bio 1.3.1 → 1.4.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (303) hide show
  1. data/ChangeLog +2105 -3728
  2. data/KNOWN_ISSUES.rdoc +35 -3
  3. data/README.rdoc +8 -2
  4. data/RELEASE_NOTES.rdoc +166 -0
  5. data/bin/bioruby +4 -1
  6. data/bioruby.gemspec +146 -1
  7. data/bioruby.gemspec.erb +3 -1
  8. data/doc/ChangeLog-before-1.3.1 +3961 -0
  9. data/doc/Tutorial.rd +154 -22
  10. data/doc/Tutorial.rd.html +125 -68
  11. data/lib/bio.rb +21 -6
  12. data/lib/bio/appl/bl2seq/report.rb +11 -202
  13. data/lib/bio/appl/blast/format0.rb +0 -193
  14. data/lib/bio/appl/blast/report.rb +2 -147
  15. data/lib/bio/appl/blast/wublast.rb +0 -208
  16. data/lib/bio/appl/fasta.rb +4 -19
  17. data/lib/bio/appl/fasta/format10.rb +0 -14
  18. data/lib/bio/appl/genscan/report.rb +0 -176
  19. data/lib/bio/appl/hmmer.rb +1 -15
  20. data/lib/bio/appl/hmmer/report.rb +0 -100
  21. data/lib/bio/appl/meme/mast.rb +156 -0
  22. data/lib/bio/appl/meme/mast/report.rb +91 -0
  23. data/lib/bio/appl/meme/motif.rb +48 -0
  24. data/lib/bio/appl/psort.rb +0 -111
  25. data/lib/bio/appl/psort/report.rb +1 -45
  26. data/lib/bio/appl/pts1.rb +2 -4
  27. data/lib/bio/appl/sosui/report.rb +5 -54
  28. data/lib/bio/appl/targetp/report.rb +1 -104
  29. data/lib/bio/appl/tmhmm/report.rb +0 -36
  30. data/lib/bio/command.rb +94 -10
  31. data/lib/bio/data/aa.rb +1 -77
  32. data/lib/bio/data/codontable.rb +1 -95
  33. data/lib/bio/data/na.rb +1 -26
  34. data/lib/bio/db/aaindex.rb +1 -38
  35. data/lib/bio/db/fasta.rb +1 -134
  36. data/lib/bio/db/fasta/format_qual.rb +204 -0
  37. data/lib/bio/db/fasta/qual.rb +102 -0
  38. data/lib/bio/db/fastq.rb +645 -0
  39. data/lib/bio/db/fastq/fastq_to_biosequence.rb +40 -0
  40. data/lib/bio/db/fastq/format_fastq.rb +175 -0
  41. data/lib/bio/db/genbank/genbank.rb +1 -86
  42. data/lib/bio/db/gff.rb +0 -17
  43. data/lib/bio/db/go.rb +4 -72
  44. data/lib/bio/db/kegg/common.rb +112 -0
  45. data/lib/bio/db/kegg/compound.rb +29 -20
  46. data/lib/bio/db/kegg/drug.rb +74 -34
  47. data/lib/bio/db/kegg/enzyme.rb +26 -5
  48. data/lib/bio/db/kegg/genes.rb +128 -15
  49. data/lib/bio/db/kegg/genome.rb +3 -41
  50. data/lib/bio/db/kegg/glycan.rb +19 -24
  51. data/lib/bio/db/kegg/orthology.rb +16 -56
  52. data/lib/bio/db/kegg/reaction.rb +81 -28
  53. data/lib/bio/db/kegg/taxonomy.rb +1 -52
  54. data/lib/bio/db/litdb.rb +1 -16
  55. data/lib/bio/db/phyloxml/phyloxml.xsd +582 -0
  56. data/lib/bio/db/phyloxml/phyloxml_elements.rb +1174 -0
  57. data/lib/bio/db/phyloxml/phyloxml_parser.rb +954 -0
  58. data/lib/bio/db/phyloxml/phyloxml_writer.rb +228 -0
  59. data/lib/bio/db/prosite.rb +2 -95
  60. data/lib/bio/db/rebase.rb +5 -6
  61. data/lib/bio/db/sanger_chromatogram/abif.rb +120 -0
  62. data/lib/bio/db/sanger_chromatogram/chromatogram.rb +133 -0
  63. data/lib/bio/db/sanger_chromatogram/chromatogram_to_biosequence.rb +32 -0
  64. data/lib/bio/db/sanger_chromatogram/scf.rb +210 -0
  65. data/lib/bio/io/das.rb +0 -44
  66. data/lib/bio/io/ddbjxml.rb +1 -181
  67. data/lib/bio/io/flatfile.rb +1 -7
  68. data/lib/bio/io/flatfile/autodetection.rb +6 -0
  69. data/lib/bio/io/keggapi.rb +0 -442
  70. data/lib/bio/io/ncbirest.rb +130 -132
  71. data/lib/bio/io/ncbisoap.rb +2 -1
  72. data/lib/bio/io/pubmed.rb +0 -88
  73. data/lib/bio/location.rb +0 -73
  74. data/lib/bio/pathway.rb +0 -171
  75. data/lib/bio/sequence.rb +18 -1
  76. data/lib/bio/sequence/adapter.rb +3 -0
  77. data/lib/bio/sequence/format.rb +16 -0
  78. data/lib/bio/sequence/quality_score.rb +205 -0
  79. data/lib/bio/tree.rb +70 -5
  80. data/lib/bio/util/restriction_enzyme/single_strand.rb +3 -2
  81. data/lib/bio/util/sirna.rb +1 -23
  82. data/lib/bio/version.rb +1 -1
  83. data/sample/demo_aaindex.rb +67 -0
  84. data/sample/demo_aminoacid.rb +101 -0
  85. data/sample/demo_bl2seq_report.rb +220 -0
  86. data/sample/demo_blast_report.rb +285 -0
  87. data/sample/demo_codontable.rb +119 -0
  88. data/sample/demo_das.rb +105 -0
  89. data/sample/demo_ddbjxml.rb +212 -0
  90. data/sample/demo_fasta_remote.rb +51 -0
  91. data/sample/demo_fastaformat.rb +105 -0
  92. data/sample/demo_genbank.rb +132 -0
  93. data/sample/demo_genscan_report.rb +202 -0
  94. data/sample/demo_gff1.rb +49 -0
  95. data/sample/demo_go.rb +98 -0
  96. data/sample/demo_hmmer_report.rb +149 -0
  97. data/sample/demo_kegg_compound.rb +57 -0
  98. data/sample/demo_kegg_drug.rb +65 -0
  99. data/sample/demo_kegg_genome.rb +74 -0
  100. data/sample/demo_kegg_glycan.rb +72 -0
  101. data/sample/demo_kegg_orthology.rb +62 -0
  102. data/sample/demo_kegg_reaction.rb +66 -0
  103. data/sample/demo_kegg_taxonomy.rb +92 -0
  104. data/sample/demo_keggapi.rb +502 -0
  105. data/sample/demo_litdb.rb +42 -0
  106. data/sample/demo_locations.rb +99 -0
  107. data/sample/demo_ncbi_rest.rb +130 -0
  108. data/sample/demo_nucleicacid.rb +49 -0
  109. data/sample/demo_pathway.rb +196 -0
  110. data/sample/demo_prosite.rb +120 -0
  111. data/sample/demo_psort.rb +138 -0
  112. data/sample/demo_psort_report.rb +70 -0
  113. data/sample/demo_pubmed.rb +118 -0
  114. data/sample/demo_sirna.rb +63 -0
  115. data/sample/demo_sosui_report.rb +89 -0
  116. data/sample/demo_targetp_report.rb +135 -0
  117. data/sample/demo_tmhmm_report.rb +68 -0
  118. data/sample/pmfetch.rb +13 -4
  119. data/sample/pmsearch.rb +15 -4
  120. data/sample/test_phyloxml_big.rb +205 -0
  121. data/test/bioruby_test_helper.rb +61 -0
  122. data/test/data/KEGG/1.1.1.1.enzyme +935 -0
  123. data/test/data/KEGG/C00025.compound +102 -0
  124. data/test/data/KEGG/D00063.drug +104 -0
  125. data/test/data/KEGG/G00024.glycan +47 -0
  126. data/test/data/KEGG/G01366.glycan +18 -0
  127. data/test/data/KEGG/K02338.orthology +902 -0
  128. data/test/data/KEGG/R00006.reaction +14 -0
  129. data/test/data/fastq/README.txt +109 -0
  130. data/test/data/fastq/error_diff_ids.fastq +20 -0
  131. data/test/data/fastq/error_double_qual.fastq +22 -0
  132. data/test/data/fastq/error_double_seq.fastq +22 -0
  133. data/test/data/fastq/error_long_qual.fastq +20 -0
  134. data/test/data/fastq/error_no_qual.fastq +20 -0
  135. data/test/data/fastq/error_qual_del.fastq +20 -0
  136. data/test/data/fastq/error_qual_escape.fastq +20 -0
  137. data/test/data/fastq/error_qual_null.fastq +0 -0
  138. data/test/data/fastq/error_qual_space.fastq +21 -0
  139. data/test/data/fastq/error_qual_tab.fastq +21 -0
  140. data/test/data/fastq/error_qual_unit_sep.fastq +20 -0
  141. data/test/data/fastq/error_qual_vtab.fastq +20 -0
  142. data/test/data/fastq/error_short_qual.fastq +20 -0
  143. data/test/data/fastq/error_spaces.fastq +20 -0
  144. data/test/data/fastq/error_tabs.fastq +21 -0
  145. data/test/data/fastq/error_trunc_at_plus.fastq +19 -0
  146. data/test/data/fastq/error_trunc_at_qual.fastq +19 -0
  147. data/test/data/fastq/error_trunc_at_seq.fastq +18 -0
  148. data/test/data/fastq/error_trunc_in_plus.fastq +19 -0
  149. data/test/data/fastq/error_trunc_in_qual.fastq +20 -0
  150. data/test/data/fastq/error_trunc_in_seq.fastq +18 -0
  151. data/test/data/fastq/error_trunc_in_title.fastq +17 -0
  152. data/test/data/fastq/illumina_full_range_as_illumina.fastq +8 -0
  153. data/test/data/fastq/illumina_full_range_as_sanger.fastq +8 -0
  154. data/test/data/fastq/illumina_full_range_as_solexa.fastq +8 -0
  155. data/test/data/fastq/illumina_full_range_original_illumina.fastq +8 -0
  156. data/test/data/fastq/longreads_as_illumina.fastq +40 -0
  157. data/test/data/fastq/longreads_as_sanger.fastq +40 -0
  158. data/test/data/fastq/longreads_as_solexa.fastq +40 -0
  159. data/test/data/fastq/longreads_original_sanger.fastq +120 -0
  160. data/test/data/fastq/misc_dna_as_illumina.fastq +16 -0
  161. data/test/data/fastq/misc_dna_as_sanger.fastq +16 -0
  162. data/test/data/fastq/misc_dna_as_solexa.fastq +16 -0
  163. data/test/data/fastq/misc_dna_original_sanger.fastq +16 -0
  164. data/test/data/fastq/misc_rna_as_illumina.fastq +16 -0
  165. data/test/data/fastq/misc_rna_as_sanger.fastq +16 -0
  166. data/test/data/fastq/misc_rna_as_solexa.fastq +16 -0
  167. data/test/data/fastq/misc_rna_original_sanger.fastq +16 -0
  168. data/test/data/fastq/sanger_full_range_as_illumina.fastq +8 -0
  169. data/test/data/fastq/sanger_full_range_as_sanger.fastq +8 -0
  170. data/test/data/fastq/sanger_full_range_as_solexa.fastq +8 -0
  171. data/test/data/fastq/sanger_full_range_original_sanger.fastq +8 -0
  172. data/test/data/fastq/solexa_full_range_as_illumina.fastq +8 -0
  173. data/test/data/fastq/solexa_full_range_as_sanger.fastq +8 -0
  174. data/test/data/fastq/solexa_full_range_as_solexa.fastq +8 -0
  175. data/test/data/fastq/solexa_full_range_original_solexa.fastq +8 -0
  176. data/test/data/fastq/wrapping_as_illumina.fastq +12 -0
  177. data/test/data/fastq/wrapping_as_sanger.fastq +12 -0
  178. data/test/data/fastq/wrapping_as_solexa.fastq +12 -0
  179. data/test/data/fastq/wrapping_original_sanger.fastq +24 -0
  180. data/test/data/meme/db +0 -0
  181. data/test/data/meme/mast +0 -0
  182. data/test/data/meme/mast.out +13 -0
  183. data/test/data/meme/meme.out +3 -0
  184. data/test/data/phyloxml/apaf.xml +666 -0
  185. data/test/data/phyloxml/bcl_2.xml +2097 -0
  186. data/test/data/phyloxml/made_up.xml +144 -0
  187. data/test/data/phyloxml/ncbi_taxonomy_mollusca_short.xml +65 -0
  188. data/test/data/phyloxml/phyloxml_examples.xml +415 -0
  189. data/test/data/sanger_chromatogram/test_chromatogram_abif.ab1 +0 -0
  190. data/test/data/sanger_chromatogram/test_chromatogram_scf_v2.scf +0 -0
  191. data/test/data/sanger_chromatogram/test_chromatogram_scf_v3.scf +0 -0
  192. data/test/functional/bio/appl/test_pts1.rb +7 -5
  193. data/test/functional/bio/io/test_ensembl.rb +4 -3
  194. data/test/functional/bio/io/test_pubmed.rb +9 -3
  195. data/test/functional/bio/io/test_soapwsdl.rb +5 -4
  196. data/test/functional/bio/io/test_togows.rb +5 -4
  197. data/test/functional/bio/sequence/test_output_embl.rb +6 -4
  198. data/test/functional/bio/test_command.rb +54 -5
  199. data/test/runner.rb +5 -3
  200. data/test/unit/bio/appl/bl2seq/test_report.rb +5 -4
  201. data/test/unit/bio/appl/blast/test_ncbioptions.rb +4 -2
  202. data/test/unit/bio/appl/blast/test_report.rb +5 -4
  203. data/test/unit/bio/appl/blast/test_rpsblast.rb +5 -4
  204. data/test/unit/bio/appl/gcg/test_msf.rb +5 -5
  205. data/test/unit/bio/appl/genscan/test_report.rb +8 -9
  206. data/test/unit/bio/appl/hmmer/test_report.rb +5 -4
  207. data/test/unit/bio/appl/iprscan/test_report.rb +6 -5
  208. data/test/unit/bio/appl/mafft/test_report.rb +6 -5
  209. data/test/unit/bio/appl/meme/mast/test_report.rb +46 -0
  210. data/test/unit/bio/appl/meme/test_mast.rb +103 -0
  211. data/test/unit/bio/appl/meme/test_motif.rb +38 -0
  212. data/test/unit/bio/appl/paml/codeml/test_rates.rb +5 -4
  213. data/test/unit/bio/appl/paml/codeml/test_report.rb +5 -4
  214. data/test/unit/bio/appl/paml/test_codeml.rb +5 -4
  215. data/test/unit/bio/appl/sim4/test_report.rb +5 -4
  216. data/test/unit/bio/appl/sosui/test_report.rb +6 -5
  217. data/test/unit/bio/appl/targetp/test_report.rb +5 -3
  218. data/test/unit/bio/appl/test_blast.rb +5 -4
  219. data/test/unit/bio/appl/test_fasta.rb +4 -2
  220. data/test/unit/bio/appl/test_pts1.rb +4 -2
  221. data/test/unit/bio/appl/tmhmm/test_report.rb +6 -5
  222. data/test/unit/bio/data/test_aa.rb +5 -3
  223. data/test/unit/bio/data/test_codontable.rb +5 -4
  224. data/test/unit/bio/data/test_na.rb +5 -3
  225. data/test/unit/bio/db/biosql/tc_biosql.rb +5 -1
  226. data/test/unit/bio/db/embl/test_common.rb +4 -2
  227. data/test/unit/bio/db/embl/test_embl.rb +6 -6
  228. data/test/unit/bio/db/embl/test_embl_rel89.rb +6 -6
  229. data/test/unit/bio/db/embl/test_embl_to_bioseq.rb +7 -8
  230. data/test/unit/bio/db/embl/test_sptr.rb +6 -8
  231. data/test/unit/bio/db/embl/test_uniprot.rb +6 -5
  232. data/test/unit/bio/db/fasta/test_format_qual.rb +346 -0
  233. data/test/unit/bio/db/kegg/test_compound.rb +146 -0
  234. data/test/unit/bio/db/kegg/test_drug.rb +194 -0
  235. data/test/unit/bio/db/kegg/test_enzyme.rb +241 -0
  236. data/test/unit/bio/db/kegg/test_genes.rb +32 -4
  237. data/test/unit/bio/db/kegg/test_glycan.rb +260 -0
  238. data/test/unit/bio/db/kegg/test_orthology.rb +50 -0
  239. data/test/unit/bio/db/kegg/test_reaction.rb +96 -0
  240. data/test/unit/bio/db/pdb/test_pdb.rb +4 -2
  241. data/test/unit/bio/db/sanger_chromatogram/test_abif.rb +76 -0
  242. data/test/unit/bio/db/sanger_chromatogram/test_scf.rb +98 -0
  243. data/test/unit/bio/db/test_aaindex.rb +6 -6
  244. data/test/unit/bio/db/test_fasta.rb +5 -46
  245. data/test/unit/bio/db/test_fastq.rb +829 -0
  246. data/test/unit/bio/db/test_gff.rb +4 -2
  247. data/test/unit/bio/db/test_lasergene.rb +7 -5
  248. data/test/unit/bio/db/test_medline.rb +4 -2
  249. data/test/unit/bio/db/test_newick.rb +6 -6
  250. data/test/unit/bio/db/test_nexus.rb +4 -2
  251. data/test/unit/bio/db/test_phyloxml.rb +769 -0
  252. data/test/unit/bio/db/test_phyloxml_writer.rb +328 -0
  253. data/test/unit/bio/db/test_prosite.rb +6 -5
  254. data/test/unit/bio/db/test_qual.rb +63 -0
  255. data/test/unit/bio/db/test_rebase.rb +5 -3
  256. data/test/unit/bio/db/test_soft.rb +7 -6
  257. data/test/unit/bio/io/flatfile/test_autodetection.rb +6 -7
  258. data/test/unit/bio/io/flatfile/test_buffer.rb +6 -5
  259. data/test/unit/bio/io/flatfile/test_splitter.rb +4 -4
  260. data/test/unit/bio/io/test_ddbjxml.rb +4 -3
  261. data/test/unit/bio/io/test_ensembl.rb +5 -3
  262. data/test/unit/bio/io/test_fastacmd.rb +4 -3
  263. data/test/unit/bio/io/test_flatfile.rb +6 -5
  264. data/test/unit/bio/io/test_soapwsdl.rb +4 -3
  265. data/test/unit/bio/io/test_togows.rb +4 -2
  266. data/test/unit/bio/sequence/test_aa.rb +5 -3
  267. data/test/unit/bio/sequence/test_common.rb +4 -2
  268. data/test/unit/bio/sequence/test_compat.rb +4 -2
  269. data/test/unit/bio/sequence/test_dblink.rb +5 -3
  270. data/test/unit/bio/sequence/test_na.rb +4 -2
  271. data/test/unit/bio/sequence/test_quality_score.rb +330 -0
  272. data/test/unit/bio/shell/plugin/test_seq.rb +5 -3
  273. data/test/unit/bio/test_alignment.rb +5 -3
  274. data/test/unit/bio/test_command.rb +4 -3
  275. data/test/unit/bio/test_db.rb +5 -3
  276. data/test/unit/bio/test_feature.rb +4 -2
  277. data/test/unit/bio/test_location.rb +4 -2
  278. data/test/unit/bio/test_map.rb +5 -3
  279. data/test/unit/bio/test_pathway.rb +4 -2
  280. data/test/unit/bio/test_reference.rb +4 -2
  281. data/test/unit/bio/test_sequence.rb +5 -3
  282. data/test/unit/bio/test_shell.rb +5 -3
  283. data/test/unit/bio/test_tree.rb +6 -6
  284. data/test/unit/bio/util/restriction_enzyme/analysis/test_calculated_cuts.rb +4 -2
  285. data/test/unit/bio/util/restriction_enzyme/analysis/test_cut_ranges.rb +4 -2
  286. data/test/unit/bio/util/restriction_enzyme/analysis/test_sequence_range.rb +4 -2
  287. data/test/unit/bio/util/restriction_enzyme/double_stranded/test_aligned_strands.rb +4 -2
  288. data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_location_pair.rb +4 -2
  289. data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_location_pair_in_enzyme_notation.rb +4 -2
  290. data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_locations.rb +4 -2
  291. data/test/unit/bio/util/restriction_enzyme/double_stranded/test_cut_locations_in_enzyme_notation.rb +4 -2
  292. data/test/unit/bio/util/restriction_enzyme/single_strand/test_cut_locations_in_enzyme_notation.rb +4 -2
  293. data/test/unit/bio/util/restriction_enzyme/test_analysis.rb +4 -2
  294. data/test/unit/bio/util/restriction_enzyme/test_cut_symbol.rb +4 -2
  295. data/test/unit/bio/util/restriction_enzyme/test_double_stranded.rb +4 -2
  296. data/test/unit/bio/util/restriction_enzyme/test_single_strand.rb +17 -13
  297. data/test/unit/bio/util/restriction_enzyme/test_single_strand_complement.rb +17 -13
  298. data/test/unit/bio/util/restriction_enzyme/test_string_formatting.rb +4 -2
  299. data/test/unit/bio/util/test_color_scheme.rb +5 -3
  300. data/test/unit/bio/util/test_contingency_table.rb +5 -3
  301. data/test/unit/bio/util/test_restriction_enzyme.rb +4 -2
  302. data/test/unit/bio/util/test_sirna.rb +6 -4
  303. metadata +147 -2
data/test/data/KEGG/R00006.reaction ADDED
@@ -0,0 +1,14 @@
1
+ ENTRY R00006 Reaction
2
+ NAME pyruvate:pyruvate acetaldehydetransferase (decarboxylating);
3
+ 2-acetolactate pyruvate-lyase (carboxylating)
4
+ DEFINITION 2-Acetolactate + CO2 <=> 2 Pyruvate
5
+ EQUATION C00900 + C00011 <=> 2 C00022
6
+ COMMENT TPP-dependent enzymatic reaction (R00014+R03050)
7
+ RPAIR RP: RP00440 C00022_C00900 main
8
+ RP: RP05698 C00011_C00022 leave
9
+ RP: RP12733 C00022_C00900 trans
10
+ PATHWAY PATH: rn00770 Pantothenate and CoA biosynthesis
11
+ ENZYME 2.2.1.6
12
+ ORTHOLOGY KO: K01652 acetolactate synthase I/II/III large subunit
13
+ [EC:2.2.1.6]
14
+ KO: K01653 acetolactate synthase I/III small subunit [EC:2.2.1.6]
data/test/data/fastq/README.txt ADDED
@@ -0,0 +1,109 @@
1
+ This README file describes the FASTQ example files provided as supplementary
2
+ information to the open-access publication:
3
+
4
+ P.J.A. Cock, C.J. Fields, N. Goto, M.L. Heuer and P.M. Rice (2009). The Sanger
5
+ FASTQ file format for sequences with quality scores, and the Solexa/Illumina
6
+ FASTQ variants.
7
+
8
+ These files are provided freely and we encourage anyone writing a FASTQ parser
9
+ to use them as part of your test suite. Permission is granted to freely
10
+ distribute and modify the files. We request (but do not insist) that this
11
+ README file is included, or at least a reference to the above paper. Please
12
+ cite the above paper if appropriate. We also request (but do not insist) that
13
+ the example files are not modified, in order that they may serve as a common
14
+ reference.
15
+
16
+ Invalid FASTQ files
17
+ ===================
18
+
19
+ The archive contains the following sample FASTQ files with names of the form
20
+ error_NAME.fastq, which all contain errors and should be rejected (if parsed
21
+ as any of the three FASTQ variants):
22
+
23
+ error_diff_ids.fastq
24
+ error_double_qual.fastq
25
+ error_double_seq.fastq
26
+ error_long_qual.fastq
27
+ error_no_qual.fastq
28
+ error_qual_del.fastq
29
+ error_qual_escape.fastq
30
+ error_qual_null.fastq
31
+ error_qual_space.fastq
32
+ error_qual_tab.fastq
33
+ error_qual_unit_sep.fastq
34
+ error_qual_vtab.fastq
35
+ error_short_qual.fastq
36
+ error_spaces.fastq
37
+ error_tabs.fastq
38
+ error_trunc_at_seq.fastq
39
+ error_trunc_at_plus.fastq
40
+ error_trunc_at_qual.fastq
41
+ error_trunc_in_title.fastq
42
+ error_trunc_in_seq.fastq
43
+ error_trunc_in_plus.fastq
44
+ error_trunc_in_qual.fastq
45
+
46
+ Of these, those with names error_qual_XXX.fastq would be valid except for the
47
+ inclusion of spaces or non-printing ASCII characters outside the range allowed
48
+ in the quality string. The files named error_trunc_XXX.fastq would be valid
49
+ but for being truncated (e.g. simulating a partial copy over the network).
50
+
51
+ The special cases of FASTQ files which would be valid as one variant, but not
52
+ another, are covered below.
53
+
54
+ Valid FASTQ
55
+ ===========
56
+
57
+ The archive contains the following valid sample FASTQ input files for testing:
58
+
59
+ longreads_original_sanger.fastq
60
+ wrapping_original_sanger.fastq
61
+ illumina_full_range_original_illumina.fastq
62
+ sanger_full_range_original_sanger.fastq
63
+ solexa_full_range_original_solexa.fastq
64
+ misc_dna_original_sanger.fastq
65
+ misc_rna_original_sanger.fastq
66
+
67
+ These all have the form NAME_original_FORMAT.fastq, where NAME is a prefix for
68
+ that example, and FORMAT is one of sanger, solexa or illumina indicating which
69
+ FASTQ variant that example is using. There are three matching files called
70
+ NAME_as_FORMAT.fastq showing how the original file should be converted into
71
+ each of the three FASTQ variants. These converted files are standardised not
72
+ to use line wrapping (so each record has exactly four lines), and omit the
73
+ optional repetition of the read titles on the plus line.
74
+
75
+ The file longreads_original_sanger.fastq is based on real Roche 454 reads from
76
+ the Sanger Institute for the the potato cyst nematodes Globodera pallida. Ten
77
+ of the reads have been presented as FASTQ records, wrapping the sequence and
78
+ the quality lines at 80 characters. This means some of the quality lines start
79
+ with "@" or "+" characters, which may cause problems with naive parsers. Also
80
+ note that the sequence is mixed case (with upper case denoting the trimmed
81
+ region), and furthermore the free format title lines are over 100 characters
82
+ and encode assorted read information (and are repeated on the "+" lines).
83
+
84
+ The wrapping_original_sanger.fastq is based on three real reads from the NCBI
85
+ Short Read Archive, but has been carefully edited to use line wrapping for the
86
+ quality lines (but not the sequence lines) such that the due to the occurrence
87
+ of "@" and "+" on alternating lines, the file may be misinterpreted by a
88
+ simplistic parser. While this is therefore a very artificial example, it
89
+ remains a valid FASTQ file, and is useful for testing purposes.
90
+
91
+ The sanger_full_range_original_sanger.fastq file uses PHRED scores from 0 to
92
+ 93 inclusive, covering ASCII characters from 33 (!) to 126 (~). This means it
93
+ cannot be treated as a Solexa or Illumina 1.3+ FASTQ file, and attempting to
94
+ parse it as such should raise an error.
95
+
96
+ The solexa_full_range_original_solexa.fastq file uses Solexa scores from -5 to
97
+ 62 inclusive, covering ASCII characters from 59 (;) to 126 (~). This means it
98
+ cannot be treated as a Illumina 1.3+ FASTQ file, and attempting to parse it as
99
+ such should raise an error. On the basis of the quality characters, the file
100
+ would also qualify as a valid Sanger FASTQ file.
101
+
102
+ The illumina_full_range_original_illumina.fastq file uses PHRED scores from 0
103
+ to 62 inclusive, covering ASCII characters from 64 (@) to 126 (~). On the
104
+ basis of the quality characters, the file would also qualify as a valid Sanger
105
+ or Solexa FASTQ file.
106
+
107
+ The misc_dna_original_sanger.fastq and misc_rna_original_sanger.fastq files
108
+ are artificial reads using the full range of IUPAC DNA or RNA letters,
109
+ including ambiguous character codes, and both cases.
data/test/data/fastq/error_diff_ids.fastq ADDED
@@ -0,0 +1,20 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_124
12
+ YYYYYYYYYYYYYWYYWYYSYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYYYYYYYYYYYWWWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYYYWYYYYWYWWUWWWQQ
data/test/data/fastq/error_double_qual.fastq ADDED
@@ -0,0 +1,22 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYYWYYWYYSYYYSY
13
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
14
+ YYYYYYYYYYYYYWYYWYYSYYYSY
15
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ GGAAACAAAGTTTTTCTCAACATAG
17
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
18
+ YYYYYYYYYYYYYYYYYYWWWWYWY
19
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ GTATTATTTAATGGCATACACTCAA
21
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
22
+ YYYYYYYYYYWYYYYWYWWUWWWQQ
data/test/data/fastq/error_double_seq.fastq ADDED
@@ -0,0 +1,22 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYYWYYWYYSYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ GGAAACAAAGTTTTTCTCAACATAG
17
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
18
+ YYYYYYYYYYYYYYYYYYWWWWYWY
19
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ GTATTATTTAATGGCATACACTCAA
21
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
22
+ YYYYYYYYYYWYYYYWYWWUWWWQQ
data/test/data/fastq/error_long_qual.fastq ADDED
@@ -0,0 +1,20 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYYWYYWYYSYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYYYYYYYYYYYWWWWYWYY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYYYWYYYYWYWWUWWWQQ
data/test/data/fastq/error_no_qual.fastq ADDED
@@ -0,0 +1,20 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGC
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+
data/test/data/fastq/error_qual_del.fastq ADDED
@@ -0,0 +1,20 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYYWYYWYYSYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYYYYYYYYYYWWWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYYYWYYYYWYWWUWWWQQ
data/test/data/fastq/error_qual_escape.fastq ADDED
@@ -0,0 +1,20 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYYWYYWYYSYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYYYYYYYYYYYWWWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYYWYYYYWYWWUWWWQQ
data/test/data/fastq/error_qual_space.fastq ADDED
@@ -0,0 +1,21 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYYWYYWYYSYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYYYYYYYYYYY WWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYYYWYYYYWYWWUWWWQQ
21
+
data/test/data/fastq/error_qual_tab.fastq ADDED
@@ -0,0 +1,21 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYYWYYWYYSYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYYYYYYYYYYYWWWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYYY YYYYWYWWUWWWQQ
21
+
data/test/data/fastq/error_qual_unit_sep.fastq ADDED
@@ -0,0 +1,20 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYWYYWYYSYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYYYYYYYYYYYWWWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYYYWYYYYWYWWUWWWQQ
data/test/data/fastq/error_qual_vtab.fastq ADDED
@@ -0,0 +1,20 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYY YYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYYWYYWYYSYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYYYYYYYYYYYWWWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYYYWYYYYWYWWUWWWQQ
data/test/data/fastq/error_short_qual.fastq ADDED
@@ -0,0 +1,20 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYYWYYWYYSYYYS
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYYYYYYYYYYYWWWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYYYWYYYYWYWWUWWWQQ
data/test/data/fastq/error_spaces.fastq ADDED
@@ -0,0 +1,20 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAA TACCTTTGTA GAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYY YYYYYYYYYW YWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGA AAGAGAAATG AGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYY WYYYYWWYYY WYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTT GATCATGATG ATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYY YYYYWYYWYY SYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAA GTTTTTCTCA ACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYY YYYYYYYYYW WWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTT AATGGCATAC ACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYY YWYYYYWYWW UWWWQQ
data/test/data/fastq/error_tabs.fastq ADDED
@@ -0,0 +1,21 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAA TACCTTTGTA GAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYY YYYYYYYYYW YWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGA AAGAGAAATG AGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYY WYYYYWWYYY WYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTT GATCATGATG ATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYY YYYYWYYWYY SYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAA GTTTTTCTCA ACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYY YYYYYYYYYW WWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTT AATGGCATAC ACTCAA
19
+ +SLXA-B3_649_FC8437_R1_1_1_183_714
20
+ YYYYYYYYY YWYYYYWYWW UWWWQQ
21
+
data/test/data/fastq/error_trunc_at_plus.fastq ADDED
@@ -0,0 +1,19 @@
1
+ @SLXA-B3_649_FC8437_R1_1_1_610_79
2
+ GATGTGCAATACCTTTGTAGAGGAA
3
+ +SLXA-B3_649_FC8437_R1_1_1_610_79
4
+ YYYYYYYYYYYYYYYYYYWYWYYSU
5
+ @SLXA-B3_649_FC8437_R1_1_1_397_389
6
+ GGTTTGAGAAAGAGAAATGAGATAA
7
+ +SLXA-B3_649_FC8437_R1_1_1_397_389
8
+ YYYYYYYYYWYYYYWWYYYWYWYWW
9
+ @SLXA-B3_649_FC8437_R1_1_1_850_123
10
+ GAGGGTGTTGATCATGATGATGGCG
11
+ +SLXA-B3_649_FC8437_R1_1_1_850_123
12
+ YYYYYYYYYYYYYWYYWYYSYYYSY
13
+ @SLXA-B3_649_FC8437_R1_1_1_362_549
14
+ GGAAACAAAGTTTTTCTCAACATAG
15
+ +SLXA-B3_649_FC8437_R1_1_1_362_549
16
+ YYYYYYYYYYYYYYYYYYWWWWYWY
17
+ @SLXA-B3_649_FC8437_R1_1_1_183_714
18
+ GTATTATTTAATGGCATACACTCAA
19
+