finishm 0.0.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (554) hide show
  1. checksums.yaml +7 -0
  2. data/.document +5 -0
  3. data/.gitmodules +3 -0
  4. data/.rspec +1 -0
  5. data/Gemfile +31 -0
  6. data/LICENSE.txt +20 -0
  7. data/README.md +59 -0
  8. data/Rakefile +51 -0
  9. data/VERSION +1 -0
  10. data/bin/assembly_visualiser +106 -0
  11. data/bin/check_primer_combinations.rb +73 -0
  12. data/bin/contig_joiner.rb +244 -0
  13. data/bin/contigs_against_assembly.rb +153 -0
  14. data/bin/finishm +143 -0
  15. data/bin/finishm_assembler +55 -0
  16. data/bin/finishm_gap_closer.rb +241 -0
  17. data/bin/kmer_abundance_file_tool.rb +49 -0
  18. data/bin/kmer_pattern_to_assembly.rb +377 -0
  19. data/bin/kmer_profile_finder.rb +92 -0
  20. data/bin/kmers_count_parse.d +52 -0
  21. data/bin/kmers_count_tabulate.d +123 -0
  22. data/bin/kmers_count_tabulate.rb +84 -0
  23. data/bin/pcr_result_parser.rb +108 -0
  24. data/bin/primer_finder.rb +119 -0
  25. data/bin/read_selection_by_kmer.d +174 -0
  26. data/bin/scaffold_by_pattern.rb +119 -0
  27. data/bin/scaffold_connection_possibilities_to_knowns.rb +193 -0
  28. data/bin/scaffold_end_coverages.rb +69 -0
  29. data/bin/trail_validator.rb +84 -0
  30. data/ext/mkrf_conf.rb +56 -0
  31. data/ext/src/Makefile +140 -0
  32. data/ext/src/src/allocArray.c +305 -0
  33. data/ext/src/src/allocArray.h +86 -0
  34. data/ext/src/src/autoOpen.c +107 -0
  35. data/ext/src/src/autoOpen.h +18 -0
  36. data/ext/src/src/binarySequences.c +813 -0
  37. data/ext/src/src/binarySequences.h +125 -0
  38. data/ext/src/src/concatenatedGraph.c +233 -0
  39. data/ext/src/src/concatenatedGraph.h +30 -0
  40. data/ext/src/src/concatenatedPreGraph.c +262 -0
  41. data/ext/src/src/concatenatedPreGraph.h +29 -0
  42. data/ext/src/src/correctedGraph.c +2643 -0
  43. data/ext/src/src/correctedGraph.h +32 -0
  44. data/ext/src/src/dfib.c +509 -0
  45. data/ext/src/src/dfib.h +69 -0
  46. data/ext/src/src/dfibHeap.c +89 -0
  47. data/ext/src/src/dfibHeap.h +39 -0
  48. data/ext/src/src/dfibpriv.h +105 -0
  49. data/ext/src/src/fib.c +628 -0
  50. data/ext/src/src/fib.h +78 -0
  51. data/ext/src/src/fibHeap.c +79 -0
  52. data/ext/src/src/fibHeap.h +41 -0
  53. data/ext/src/src/fibpriv.h +110 -0
  54. data/ext/src/src/globals.h +154 -0
  55. data/ext/src/src/graph.c +3932 -0
  56. data/ext/src/src/graph.h +233 -0
  57. data/ext/src/src/graphReConstruction.c +1472 -0
  58. data/ext/src/src/graphReConstruction.h +30 -0
  59. data/ext/src/src/graphStats.c +2167 -0
  60. data/ext/src/src/graphStats.h +72 -0
  61. data/ext/src/src/graphStructures.h +52 -0
  62. data/ext/src/src/kmer.c +652 -0
  63. data/ext/src/src/kmer.h +73 -0
  64. data/ext/src/src/kmerOccurenceTable.c +236 -0
  65. data/ext/src/src/kmerOccurenceTable.h +44 -0
  66. data/ext/src/src/kseq.h +223 -0
  67. data/ext/src/src/locallyCorrectedGraph.c +557 -0
  68. data/ext/src/src/locallyCorrectedGraph.h +40 -0
  69. data/ext/src/src/passageMarker.c +677 -0
  70. data/ext/src/src/passageMarker.h +137 -0
  71. data/ext/src/src/preGraph.c +1717 -0
  72. data/ext/src/src/preGraph.h +106 -0
  73. data/ext/src/src/preGraphConstruction.c +990 -0
  74. data/ext/src/src/preGraphConstruction.h +26 -0
  75. data/ext/src/src/probe_node_finder.c +84 -0
  76. data/ext/src/src/probe_node_finder.h +6 -0
  77. data/ext/src/src/readCoherentGraph.c +557 -0
  78. data/ext/src/src/readCoherentGraph.h +30 -0
  79. data/ext/src/src/readSet.c +1734 -0
  80. data/ext/src/src/readSet.h +67 -0
  81. data/ext/src/src/readToNode.c +218 -0
  82. data/ext/src/src/readToNode.h +35 -0
  83. data/ext/src/src/recycleBin.c +199 -0
  84. data/ext/src/src/recycleBin.h +58 -0
  85. data/ext/src/src/roadMap.c +342 -0
  86. data/ext/src/src/roadMap.h +65 -0
  87. data/ext/src/src/run.c +318 -0
  88. data/ext/src/src/run.h +52 -0
  89. data/ext/src/src/run2.c +744 -0
  90. data/ext/src/src/runReadToNode.c +29 -0
  91. data/ext/src/src/scaffold.c +1876 -0
  92. data/ext/src/src/scaffold.h +64 -0
  93. data/ext/src/src/shortReadPairs.c +1243 -0
  94. data/ext/src/src/shortReadPairs.h +32 -0
  95. data/ext/src/src/splay.c +259 -0
  96. data/ext/src/src/splay.h +43 -0
  97. data/ext/src/src/splayTable.c +1315 -0
  98. data/ext/src/src/splayTable.h +31 -0
  99. data/ext/src/src/tightString.c +362 -0
  100. data/ext/src/src/tightString.h +82 -0
  101. data/ext/src/src/utility.c +199 -0
  102. data/ext/src/src/utility.h +98 -0
  103. data/ext/src/third-party/zlib-1.2.3/ChangeLog +855 -0
  104. data/ext/src/third-party/zlib-1.2.3/FAQ +339 -0
  105. data/ext/src/third-party/zlib-1.2.3/INDEX +51 -0
  106. data/ext/src/third-party/zlib-1.2.3/Makefile +154 -0
  107. data/ext/src/third-party/zlib-1.2.3/Makefile.in +154 -0
  108. data/ext/src/third-party/zlib-1.2.3/README +125 -0
  109. data/ext/src/third-party/zlib-1.2.3/adler32.c +149 -0
  110. data/ext/src/third-party/zlib-1.2.3/adler32.o +0 -0
  111. data/ext/src/third-party/zlib-1.2.3/algorithm.txt +209 -0
  112. data/ext/src/third-party/zlib-1.2.3/amiga/Makefile.pup +66 -0
  113. data/ext/src/third-party/zlib-1.2.3/amiga/Makefile.sas +65 -0
  114. data/ext/src/third-party/zlib-1.2.3/as400/bndsrc +132 -0
  115. data/ext/src/third-party/zlib-1.2.3/as400/compile.clp +123 -0
  116. data/ext/src/third-party/zlib-1.2.3/as400/readme.txt +111 -0
  117. data/ext/src/third-party/zlib-1.2.3/as400/zlib.inc +331 -0
  118. data/ext/src/third-party/zlib-1.2.3/compress.c +79 -0
  119. data/ext/src/third-party/zlib-1.2.3/compress.o +0 -0
  120. data/ext/src/third-party/zlib-1.2.3/configure +459 -0
  121. data/ext/src/third-party/zlib-1.2.3/contrib/README.contrib +71 -0
  122. data/ext/src/third-party/zlib-1.2.3/contrib/ada/buffer_demo.adb +106 -0
  123. data/ext/src/third-party/zlib-1.2.3/contrib/ada/mtest.adb +156 -0
  124. data/ext/src/third-party/zlib-1.2.3/contrib/ada/read.adb +156 -0
  125. data/ext/src/third-party/zlib-1.2.3/contrib/ada/readme.txt +65 -0
  126. data/ext/src/third-party/zlib-1.2.3/contrib/ada/test.adb +463 -0
  127. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib-streams.adb +225 -0
  128. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib-streams.ads +114 -0
  129. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib-thin.adb +141 -0
  130. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib-thin.ads +450 -0
  131. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib.adb +701 -0
  132. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib.ads +328 -0
  133. data/ext/src/third-party/zlib-1.2.3/contrib/ada/zlib.gpr +20 -0
  134. data/ext/src/third-party/zlib-1.2.3/contrib/asm586/README.586 +43 -0
  135. data/ext/src/third-party/zlib-1.2.3/contrib/asm586/match.S +364 -0
  136. data/ext/src/third-party/zlib-1.2.3/contrib/asm686/README.686 +34 -0
  137. data/ext/src/third-party/zlib-1.2.3/contrib/asm686/match.S +329 -0
  138. data/ext/src/third-party/zlib-1.2.3/contrib/blast/Makefile +8 -0
  139. data/ext/src/third-party/zlib-1.2.3/contrib/blast/README +4 -0
  140. data/ext/src/third-party/zlib-1.2.3/contrib/blast/blast.c +444 -0
  141. data/ext/src/third-party/zlib-1.2.3/contrib/blast/blast.h +71 -0
  142. data/ext/src/third-party/zlib-1.2.3/contrib/blast/test.pk +0 -0
  143. data/ext/src/third-party/zlib-1.2.3/contrib/blast/test.txt +1 -0
  144. data/ext/src/third-party/zlib-1.2.3/contrib/delphi/ZLib.pas +557 -0
  145. data/ext/src/third-party/zlib-1.2.3/contrib/delphi/ZLibConst.pas +11 -0
  146. data/ext/src/third-party/zlib-1.2.3/contrib/delphi/readme.txt +76 -0
  147. data/ext/src/third-party/zlib-1.2.3/contrib/delphi/zlibd32.mak +93 -0
  148. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib.build +33 -0
  149. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib.chm +0 -0
  150. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib.sln +21 -0
  151. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/AssemblyInfo.cs +58 -0
  152. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/ChecksumImpl.cs +202 -0
  153. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/CircularBuffer.cs +83 -0
  154. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/CodecBase.cs +198 -0
  155. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/Deflater.cs +106 -0
  156. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/DotZLib.cs +288 -0
  157. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/DotZLib.csproj +141 -0
  158. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/GZipStream.cs +301 -0
  159. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/Inflater.cs +105 -0
  160. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/DotZLib/UnitTests.cs +274 -0
  161. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/LICENSE_1_0.txt +23 -0
  162. data/ext/src/third-party/zlib-1.2.3/contrib/dotzlib/readme.txt +58 -0
  163. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/README +1 -0
  164. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/infback9.c +608 -0
  165. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/infback9.h +37 -0
  166. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/inffix9.h +107 -0
  167. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/inflate9.h +47 -0
  168. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/inftree9.c +323 -0
  169. data/ext/src/third-party/zlib-1.2.3/contrib/infback9/inftree9.h +55 -0
  170. data/ext/src/third-party/zlib-1.2.3/contrib/inflate86/inffas86.c +1157 -0
  171. data/ext/src/third-party/zlib-1.2.3/contrib/inflate86/inffast.S +1368 -0
  172. data/ext/src/third-party/zlib-1.2.3/contrib/iostream/test.cpp +24 -0
  173. data/ext/src/third-party/zlib-1.2.3/contrib/iostream/zfstream.cpp +329 -0
  174. data/ext/src/third-party/zlib-1.2.3/contrib/iostream/zfstream.h +128 -0
  175. data/ext/src/third-party/zlib-1.2.3/contrib/iostream2/zstream.h +307 -0
  176. data/ext/src/third-party/zlib-1.2.3/contrib/iostream2/zstream_test.cpp +25 -0
  177. data/ext/src/third-party/zlib-1.2.3/contrib/iostream3/README +35 -0
  178. data/ext/src/third-party/zlib-1.2.3/contrib/iostream3/TODO +17 -0
  179. data/ext/src/third-party/zlib-1.2.3/contrib/iostream3/test.cc +50 -0
  180. data/ext/src/third-party/zlib-1.2.3/contrib/iostream3/zfstream.cc +479 -0
  181. data/ext/src/third-party/zlib-1.2.3/contrib/iostream3/zfstream.h +466 -0
  182. data/ext/src/third-party/zlib-1.2.3/contrib/masm686/match.asm +413 -0
  183. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/bld_ml64.bat +2 -0
  184. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/gvmat64.asm +513 -0
  185. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/gvmat64.obj +0 -0
  186. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/inffas8664.c +186 -0
  187. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/inffasx64.asm +392 -0
  188. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/inffasx64.obj +0 -0
  189. data/ext/src/third-party/zlib-1.2.3/contrib/masmx64/readme.txt +28 -0
  190. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/bld_ml32.bat +2 -0
  191. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/gvmat32.asm +972 -0
  192. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/gvmat32.obj +0 -0
  193. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/gvmat32c.c +62 -0
  194. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/inffas32.asm +1083 -0
  195. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/inffas32.obj +0 -0
  196. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/mkasm.bat +3 -0
  197. data/ext/src/third-party/zlib-1.2.3/contrib/masmx86/readme.txt +21 -0
  198. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/ChangeLogUnzip +67 -0
  199. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/Makefile +25 -0
  200. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/crypt.h +132 -0
  201. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/ioapi.c +177 -0
  202. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/ioapi.h +75 -0
  203. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/iowin32.c +270 -0
  204. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/iowin32.h +21 -0
  205. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/miniunz.c +585 -0
  206. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/minizip.c +420 -0
  207. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/mztools.c +281 -0
  208. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/mztools.h +31 -0
  209. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/unzip.c +1598 -0
  210. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/unzip.h +354 -0
  211. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/zip.c +1219 -0
  212. data/ext/src/third-party/zlib-1.2.3/contrib/minizip/zip.h +235 -0
  213. data/ext/src/third-party/zlib-1.2.3/contrib/pascal/example.pas +599 -0
  214. data/ext/src/third-party/zlib-1.2.3/contrib/pascal/readme.txt +76 -0
  215. data/ext/src/third-party/zlib-1.2.3/contrib/pascal/zlibd32.mak +93 -0
  216. data/ext/src/third-party/zlib-1.2.3/contrib/pascal/zlibpas.pas +236 -0
  217. data/ext/src/third-party/zlib-1.2.3/contrib/puff/Makefile +8 -0
  218. data/ext/src/third-party/zlib-1.2.3/contrib/puff/README +63 -0
  219. data/ext/src/third-party/zlib-1.2.3/contrib/puff/puff.c +837 -0
  220. data/ext/src/third-party/zlib-1.2.3/contrib/puff/puff.h +31 -0
  221. data/ext/src/third-party/zlib-1.2.3/contrib/puff/zeros.raw +0 -0
  222. data/ext/src/third-party/zlib-1.2.3/contrib/testzlib/testzlib.c +275 -0
  223. data/ext/src/third-party/zlib-1.2.3/contrib/testzlib/testzlib.txt +10 -0
  224. data/ext/src/third-party/zlib-1.2.3/contrib/untgz/Makefile +14 -0
  225. data/ext/src/third-party/zlib-1.2.3/contrib/untgz/Makefile.msc +17 -0
  226. data/ext/src/third-party/zlib-1.2.3/contrib/untgz/untgz.c +674 -0
  227. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/readme.txt +73 -0
  228. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/miniunz.vcproj +126 -0
  229. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/minizip.vcproj +126 -0
  230. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/testzlib.vcproj +126 -0
  231. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/zlib.rc +32 -0
  232. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/zlibstat.vcproj +246 -0
  233. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/zlibvc.def +92 -0
  234. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/zlibvc.sln +78 -0
  235. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc7/zlibvc.vcproj +445 -0
  236. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/miniunz.vcproj +566 -0
  237. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/minizip.vcproj +563 -0
  238. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/testzlib.vcproj +948 -0
  239. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/testzlibdll.vcproj +567 -0
  240. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/zlib.rc +32 -0
  241. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/zlibstat.vcproj +870 -0
  242. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/zlibvc.def +92 -0
  243. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/zlibvc.sln +144 -0
  244. data/ext/src/third-party/zlib-1.2.3/contrib/vstudio/vc8/zlibvc.vcproj +1219 -0
  245. data/ext/src/third-party/zlib-1.2.3/crc32.c +423 -0
  246. data/ext/src/third-party/zlib-1.2.3/crc32.h +441 -0
  247. data/ext/src/third-party/zlib-1.2.3/crc32.o +0 -0
  248. data/ext/src/third-party/zlib-1.2.3/deflate.c +1736 -0
  249. data/ext/src/third-party/zlib-1.2.3/deflate.h +331 -0
  250. data/ext/src/third-party/zlib-1.2.3/deflate.o +0 -0
  251. data/ext/src/third-party/zlib-1.2.3/example +0 -0
  252. data/ext/src/third-party/zlib-1.2.3/example.c +565 -0
  253. data/ext/src/third-party/zlib-1.2.3/examples/README.examples +42 -0
  254. data/ext/src/third-party/zlib-1.2.3/examples/fitblk.c +233 -0
  255. data/ext/src/third-party/zlib-1.2.3/examples/gun.c +693 -0
  256. data/ext/src/third-party/zlib-1.2.3/examples/gzappend.c +500 -0
  257. data/ext/src/third-party/zlib-1.2.3/examples/gzjoin.c +448 -0
  258. data/ext/src/third-party/zlib-1.2.3/examples/gzlog.c +413 -0
  259. data/ext/src/third-party/zlib-1.2.3/examples/gzlog.h +58 -0
  260. data/ext/src/third-party/zlib-1.2.3/examples/zlib_how.html +523 -0
  261. data/ext/src/third-party/zlib-1.2.3/examples/zpipe.c +191 -0
  262. data/ext/src/third-party/zlib-1.2.3/examples/zran.c +404 -0
  263. data/ext/src/third-party/zlib-1.2.3/gzio.c +1026 -0
  264. data/ext/src/third-party/zlib-1.2.3/gzio.o +0 -0
  265. data/ext/src/third-party/zlib-1.2.3/infback.c +623 -0
  266. data/ext/src/third-party/zlib-1.2.3/infback.o +0 -0
  267. data/ext/src/third-party/zlib-1.2.3/inffast.c +318 -0
  268. data/ext/src/third-party/zlib-1.2.3/inffast.h +11 -0
  269. data/ext/src/third-party/zlib-1.2.3/inffast.o +0 -0
  270. data/ext/src/third-party/zlib-1.2.3/inffixed.h +94 -0
  271. data/ext/src/third-party/zlib-1.2.3/inflate.c +1368 -0
  272. data/ext/src/third-party/zlib-1.2.3/inflate.h +115 -0
  273. data/ext/src/third-party/zlib-1.2.3/inflate.o +0 -0
  274. data/ext/src/third-party/zlib-1.2.3/inftrees.c +329 -0
  275. data/ext/src/third-party/zlib-1.2.3/inftrees.h +55 -0
  276. data/ext/src/third-party/zlib-1.2.3/inftrees.o +0 -0
  277. data/ext/src/third-party/zlib-1.2.3/libz.a +0 -0
  278. data/ext/src/third-party/zlib-1.2.3/make_vms.com +461 -0
  279. data/ext/src/third-party/zlib-1.2.3/minigzip +0 -0
  280. data/ext/src/third-party/zlib-1.2.3/minigzip.c +322 -0
  281. data/ext/src/third-party/zlib-1.2.3/msdos/Makefile.bor +109 -0
  282. data/ext/src/third-party/zlib-1.2.3/msdos/Makefile.dj2 +104 -0
  283. data/ext/src/third-party/zlib-1.2.3/msdos/Makefile.emx +69 -0
  284. data/ext/src/third-party/zlib-1.2.3/msdos/Makefile.msc +106 -0
  285. data/ext/src/third-party/zlib-1.2.3/msdos/Makefile.tc +94 -0
  286. data/ext/src/third-party/zlib-1.2.3/old/Makefile.riscos +151 -0
  287. data/ext/src/third-party/zlib-1.2.3/old/README +3 -0
  288. data/ext/src/third-party/zlib-1.2.3/old/descrip.mms +48 -0
  289. data/ext/src/third-party/zlib-1.2.3/old/os2/Makefile.os2 +136 -0
  290. data/ext/src/third-party/zlib-1.2.3/old/os2/zlib.def +51 -0
  291. data/ext/src/third-party/zlib-1.2.3/old/visual-basic.txt +160 -0
  292. data/ext/src/third-party/zlib-1.2.3/old/zlib.html +971 -0
  293. data/ext/src/third-party/zlib-1.2.3/projects/README.projects +41 -0
  294. data/ext/src/third-party/zlib-1.2.3/projects/visualc6/README.txt +73 -0
  295. data/ext/src/third-party/zlib-1.2.3/projects/visualc6/example.dsp +278 -0
  296. data/ext/src/third-party/zlib-1.2.3/projects/visualc6/minigzip.dsp +278 -0
  297. data/ext/src/third-party/zlib-1.2.3/projects/visualc6/zlib.dsp +609 -0
  298. data/ext/src/third-party/zlib-1.2.3/projects/visualc6/zlib.dsw +59 -0
  299. data/ext/src/third-party/zlib-1.2.3/qnx/package.qpg +141 -0
  300. data/ext/src/third-party/zlib-1.2.3/trees.c +1219 -0
  301. data/ext/src/third-party/zlib-1.2.3/trees.h +128 -0
  302. data/ext/src/third-party/zlib-1.2.3/trees.o +0 -0
  303. data/ext/src/third-party/zlib-1.2.3/uncompr.c +61 -0
  304. data/ext/src/third-party/zlib-1.2.3/uncompr.o +0 -0
  305. data/ext/src/third-party/zlib-1.2.3/win32/DLL_FAQ.txt +397 -0
  306. data/ext/src/third-party/zlib-1.2.3/win32/Makefile.bor +107 -0
  307. data/ext/src/third-party/zlib-1.2.3/win32/Makefile.emx +69 -0
  308. data/ext/src/third-party/zlib-1.2.3/win32/Makefile.gcc +141 -0
  309. data/ext/src/third-party/zlib-1.2.3/win32/Makefile.msc +126 -0
  310. data/ext/src/third-party/zlib-1.2.3/win32/VisualC.txt +3 -0
  311. data/ext/src/third-party/zlib-1.2.3/win32/zlib.def +60 -0
  312. data/ext/src/third-party/zlib-1.2.3/win32/zlib1.rc +39 -0
  313. data/ext/src/third-party/zlib-1.2.3/zconf.h +332 -0
  314. data/ext/src/third-party/zlib-1.2.3/zconf.in.h +332 -0
  315. data/ext/src/third-party/zlib-1.2.3/zlib.3 +159 -0
  316. data/ext/src/third-party/zlib-1.2.3/zlib.h +1357 -0
  317. data/ext/src/third-party/zlib-1.2.3/zutil.c +318 -0
  318. data/ext/src/third-party/zlib-1.2.3/zutil.h +269 -0
  319. data/ext/src/third-party/zlib-1.2.3/zutil.o +0 -0
  320. data/lib/assembly/a_b_visualiser.rb +169 -0
  321. data/lib/assembly/acyclic_connection_finder.rb +81 -0
  322. data/lib/assembly/all_orfs.rb +615 -0
  323. data/lib/assembly/bad_format_writer.rb +46 -0
  324. data/lib/assembly/bam_probe_read_selector.rb +48 -0
  325. data/lib/assembly/bubbly_assembler.rb +842 -0
  326. data/lib/assembly/c_probe_node_finder.rb +38 -0
  327. data/lib/assembly/connection_interpreter.rb +350 -0
  328. data/lib/assembly/contig_printer.rb +400 -0
  329. data/lib/assembly/coverage_based_graph_filter.rb +68 -0
  330. data/lib/assembly/depth_first_search.rb +63 -0
  331. data/lib/assembly/dijkstra.rb +216 -0
  332. data/lib/assembly/fluffer.rb +253 -0
  333. data/lib/assembly/graph_explorer.rb +85 -0
  334. data/lib/assembly/graph_generator.rb +315 -0
  335. data/lib/assembly/height_finder.rb +355 -0
  336. data/lib/assembly/hybrid_velvet_graph.rb +70 -0
  337. data/lib/assembly/input_genome.rb +182 -0
  338. data/lib/assembly/kmer_coverage_based_path_filter.rb +65 -0
  339. data/lib/assembly/node_finder.rb +171 -0
  340. data/lib/assembly/oriented_node_trail.rb +507 -0
  341. data/lib/assembly/paired_end_assembler.rb +53 -0
  342. data/lib/assembly/paired_end_neighbour_finder.rb +176 -0
  343. data/lib/assembly/probed_graph.rb +105 -0
  344. data/lib/assembly/read_input.rb +79 -0
  345. data/lib/assembly/read_to_node.rb +37 -0
  346. data/lib/assembly/scaffold_breaker.rb +126 -0
  347. data/lib/assembly/sequence_hasher.rb +71 -0
  348. data/lib/assembly/single_coherent_paths_between_nodes.rb +533 -0
  349. data/lib/assembly/single_coherent_wanderer.rb +261 -0
  350. data/lib/assembly/single_ended_assembler.rb +441 -0
  351. data/lib/assembly/velvet_c_binding.rb +54 -0
  352. data/lib/assembly/velvet_graph_sequence_extractor.rb +123 -0
  353. data/lib/external/VERSION +1 -0
  354. data/lib/finishm/assemble.rb +224 -0
  355. data/lib/finishm/explore.rb +217 -0
  356. data/lib/finishm/finisher.rb +303 -0
  357. data/lib/finishm/fluff.rb +122 -0
  358. data/lib/finishm/gapfiller.rb +325 -0
  359. data/lib/finishm/orfs_finder.rb +88 -0
  360. data/lib/finishm/path_counter.rb +90 -0
  361. data/lib/finishm/primers.rb +425 -0
  362. data/lib/finishm/primers_check.rb +176 -0
  363. data/lib/finishm/roundup.rb +344 -0
  364. data/lib/finishm/sequence.rb +142 -0
  365. data/lib/finishm/visualise.rb +430 -0
  366. data/lib/finishm/wander.rb +270 -0
  367. data/lib/kmer_abundance_pattern.rb +79 -0
  368. data/lib/kmer_multi_abundance_file.rb +48 -0
  369. data/lib/oligo_designer.rb +88 -0
  370. data/lib/priner.rb +66 -0
  371. data/spec/acyclic_connection_finder_spec.rb +551 -0
  372. data/spec/all_orfs_spec.rb +443 -0
  373. data/spec/assemble_spec.rb +186 -0
  374. data/spec/bubbly_assembler_spec.rb +707 -0
  375. data/spec/c_node_finder_spec.rb +58 -0
  376. data/spec/connection_interpreter_spec.rb +284 -0
  377. data/spec/contig_printer_spec.rb +291 -0
  378. data/spec/coverage_based_graph_filter_spec.rb +102 -0
  379. data/spec/data/6_3e4e5e6e.1vANME.bam +0 -0
  380. data/spec/data/6_3e4e5e6e.1vANME.bam.bai +0 -0
  381. data/spec/data/acyclic_connection_finder/1/probes.fa +5 -0
  382. data/spec/data/acyclic_connection_finder/1/random1.fa +2 -0
  383. data/spec/data/acyclic_connection_finder/1/random1.sammy.fa.gz +0 -0
  384. data/spec/data/acyclic_connection_finder/1/random2.fa +2 -0
  385. data/spec/data/acyclic_connection_finder/1/random2.sammy.fa.gz +0 -0
  386. data/spec/data/assembly/1_simple_bubble_uneven_coverage/random3000.fa +39 -0
  387. data/spec/data/assembly/1_simple_bubble_uneven_coverage/random3000.slightly_changed.fa +39 -0
  388. data/spec/data/assembly/1_simple_bubble_uneven_coverage/reads_combined.fa.gz +0 -0
  389. data/spec/data/assembly_visualiser/Contig_6_1_to_250.fa.kmers31 +220 -0
  390. data/spec/data/assembly_visualiser/Contig_7_1_to_250.fa.kmers31 +220 -0
  391. data/spec/data/assembly_visualiser/Graph +46 -0
  392. data/spec/data/assembly_visualiser/start_kmers1 +2 -0
  393. data/spec/data/bands.csv +1 -0
  394. data/spec/data/c_probe_node_finder/1/CnyUnifiedSeq +0 -0
  395. data/spec/data/c_probe_node_finder/1/CnyUnifiedSeq.names +544 -0
  396. data/spec/data/c_probe_node_finder/1/Graph2 +668 -0
  397. data/spec/data/c_probe_node_finder/1/LastGraph +668 -0
  398. data/spec/data/c_probe_node_finder/1/Log +756 -0
  399. data/spec/data/c_probe_node_finder/1/PreGraph +11 -0
  400. data/spec/data/c_probe_node_finder/1/Roadmaps +2009 -0
  401. data/spec/data/c_probe_node_finder/1/contigs.fa +29 -0
  402. data/spec/data/c_probe_node_finder/1/stats.txt +6 -0
  403. data/spec/data/contig_printer/1/HOWTO_RECREATE +17 -0
  404. data/spec/data/contig_printer/1/contigs.fa +4 -0
  405. data/spec/data/contig_printer/1/seq.fa +2408 -0
  406. data/spec/data/contig_printer/1/seq.fa.svg +153 -0
  407. data/spec/data/contig_printer/1/seq.fa.velvet/Graph2 +2953 -0
  408. data/spec/data/contig_printer/1/seq.fa.velvet/LastGraph +2953 -0
  409. data/spec/data/contig_printer/1/seq.fa.velvet/Log +21 -0
  410. data/spec/data/contig_printer/1/seq.fa.velvet/PreGraph +27 -0
  411. data/spec/data/contig_printer/1/seq.fa.velvet/Roadmaps +5182 -0
  412. data/spec/data/contig_printer/1/seq.fa.velvet/Sequences +3612 -0
  413. data/spec/data/contig_printer/1/seq.fa.velvet/contigs.fa +36 -0
  414. data/spec/data/contig_printer/1/seq.fa.velvet/stats.txt +14 -0
  415. data/spec/data/contig_printer/1/seq.faVseq2_1to550.fa.bam +0 -0
  416. data/spec/data/contig_printer/1/seq.faVseq2_1to550.fa.bam.bai +0 -0
  417. data/spec/data/contig_printer/1/seq.node12.fa +4 -0
  418. data/spec/data/contig_printer/1/seq1_1to550.fa +2 -0
  419. data/spec/data/contig_printer/1/seq2_1to550.fa +2 -0
  420. data/spec/data/contig_printer/1/seq2_1to550.fa.fai +1 -0
  421. data/spec/data/explore/1/2seqs.sammy.fa +12004 -0
  422. data/spec/data/explore/1/HOWTO_RECREATE.txt +6 -0
  423. data/spec/data/explore/1/a.fa +2 -0
  424. data/spec/data/explore/1/seq1_and_a.fa +3 -0
  425. data/spec/data/explore/1/seq2.fa +2 -0
  426. data/spec/data/fluff/1/2seqs.sammy.fa +12004 -0
  427. data/spec/data/fluff/1/HOWTO_RECREATE.txt +5 -0
  428. data/spec/data/fluff/1/seq1.fa +2 -0
  429. data/spec/data/fluff/1/seq2.fa +2 -0
  430. data/spec/data/gapfilling/1/reads.fa +171 -0
  431. data/spec/data/gapfilling/1/trail_with_Ns.fa +5 -0
  432. data/spec/data/gapfilling/1/velvetAssembly/Graph2 +130 -0
  433. data/spec/data/gapfilling/1/velvetAssembly/LastGraph +130 -0
  434. data/spec/data/gapfilling/1/velvetAssembly/Log +199 -0
  435. data/spec/data/gapfilling/1/velvetAssembly/PreGraph +7 -0
  436. data/spec/data/gapfilling/1/velvetAssembly/Roadmaps +239 -0
  437. data/spec/data/gapfilling/1/velvetAssembly/Sequences +281 -0
  438. data/spec/data/gapfilling/1/velvetAssembly/contigs.fa +12 -0
  439. data/spec/data/gapfilling/1/velvetAssembly/stats.txt +4 -0
  440. data/spec/data/gapfilling/2/HOWTO_recreate +17 -0
  441. data/spec/data/gapfilling/2/reference.fa +2 -0
  442. data/spec/data/gapfilling/2/reference_part1.fa +4 -0
  443. data/spec/data/gapfilling/2/reference_part2.fa +4 -0
  444. data/spec/data/gapfilling/2/sammy_reads.fa.gz +0 -0
  445. data/spec/data/gapfilling/2/with_gaps.fa +4 -0
  446. data/spec/data/gapfilling/3/HOWTO_recreate +4 -0
  447. data/spec/data/gapfilling/3/reads.fa.gz +0 -0
  448. data/spec/data/gapfilling/3/reference_part1.fa +4 -0
  449. data/spec/data/gapfilling/3/reference_part2.fa +4 -0
  450. data/spec/data/gapfilling/3/with_gaps.fa +4 -0
  451. data/spec/data/gapfilling/4/HOWTO_recreate +1 -0
  452. data/spec/data/gapfilling/4/reads.fa.gz +0 -0
  453. data/spec/data/gapfilling/5/HOWTO_RECREATE +7 -0
  454. data/spec/data/gapfilling/5/answer.fna +2 -0
  455. data/spec/data/gapfilling/5/gappy.fna +2 -0
  456. data/spec/data/gapfilling/5/reads.fa +17961 -0
  457. data/spec/data/gapfilling/5/velvet51_3.5/LastGraph +8337 -0
  458. data/spec/data/gapfilling/5/velvet51_3.5/Sequences +20921 -0
  459. data/spec/data/gapfilling/6/random1.fa +28 -0
  460. data/spec/data/gapfilling/6/random2.fa +28 -0
  461. data/spec/data/gapfilling/6/random_sequence_length_2000 +0 -0
  462. data/spec/data/gapfilling/6/reads.random1.fa.gz +0 -0
  463. data/spec/data/gapfilling/6/reads.random2.fa.gz +0 -0
  464. data/spec/data/gapfilling/6/to_gapfill.fa +22 -0
  465. data/spec/data/kmer_profile_to_assembly/multiple_abundance_file1.csv +2 -0
  466. data/spec/data/kmers_count1.csv +2 -0
  467. data/spec/data/kmers_count2.csv +3 -0
  468. data/spec/data/out +3 -0
  469. data/spec/data/positive_latching_pair.fa +2 -0
  470. data/spec/data/primers.csv +4 -0
  471. data/spec/data/read_selection_by_kmer/blacklist1.txt +1 -0
  472. data/spec/data/read_selection_by_kmer/input.fasta +6 -0
  473. data/spec/data/read_selection_by_kmer/whitelist1.txt +1 -0
  474. data/spec/data/read_selection_by_kmer/whitelist2.txt +2 -0
  475. data/spec/data/read_to_node/1_a_graph/HOWTO_RECREATE.txt +2 -0
  476. data/spec/data/read_to_node/1_a_graph/LastGraph +6695 -0
  477. data/spec/data/read_to_node/1_a_graph/ReadToNode.bin +0 -0
  478. data/spec/data/read_to_node/2_no_read256_or_259/HOWTO_RECREATE.txt +3 -0
  479. data/spec/data/read_to_node/2_no_read256_or_259/LastGraph +6693 -0
  480. data/spec/data/read_to_node/2_no_read256_or_259/ReadToNode.bin +0 -0
  481. data/spec/data/read_to_node/3_no_last_read/LastGraph +6694 -0
  482. data/spec/data/read_to_node/3_no_last_read/ReadToNode.bin +0 -0
  483. data/spec/data/t/details.txt +5 -0
  484. data/spec/data/t/details.txt.srt +5 -0
  485. data/spec/data/t/location.txt +3 -0
  486. data/spec/data/t/location.txt.srt +3 -0
  487. data/spec/data/tweak/1_gap_then_unscaffolded/answer.fa +2 -0
  488. data/spec/data/tweak/1_gap_then_unscaffolded/reads.fa.gz +0 -0
  489. data/spec/data/tweak/1_gap_then_unscaffolded/scaffolds.fa +6 -0
  490. data/spec/data/tweak/2_second_genome/answer2.fa +2 -0
  491. data/spec/data/tweak/2_second_genome/reads.fa.gz +0 -0
  492. data/spec/data/tweak/3_variant/answer.fa +2 -0
  493. data/spec/data/tweak/3_variant/lesser_answer.fa +2 -0
  494. data/spec/data/tweak/3_variant/reads.fa.gz +0 -0
  495. data/spec/data/tweak/3_variant/with_gaps.fa +2 -0
  496. data/spec/data/velvet_test_trails/Assem/Graph +17 -0
  497. data/spec/data/velvet_test_trails/Assem/Graph2 +40 -0
  498. data/spec/data/velvet_test_trails/Assem/LastGraph +40 -0
  499. data/spec/data/velvet_test_trails/Assem/Log +35 -0
  500. data/spec/data/velvet_test_trails/Assem/PreGraph +9 -0
  501. data/spec/data/velvet_test_trails/Assem/Roadmaps +89 -0
  502. data/spec/data/velvet_test_trails/Assem/Sequences +50 -0
  503. data/spec/data/velvet_test_trails/Assem/a.svg +53 -0
  504. data/spec/data/velvet_test_trails/Assem/contigs.fa +15 -0
  505. data/spec/data/velvet_test_trails/Assem/stats.txt +5 -0
  506. data/spec/data/velvet_test_trails/node_fwds.fa +8 -0
  507. data/spec/data/velvet_test_trails/node_seqs.fa +9 -0
  508. data/spec/data/velvet_test_trails/nodes_fwd_rev.fa +16 -0
  509. data/spec/data/velvet_test_trails/read1.fa +2 -0
  510. data/spec/data/velvet_test_trails/reads.fa +50 -0
  511. data/spec/data/velvet_test_trails_reverse/Assem/LastGraph +17 -0
  512. data/spec/data/velvet_test_trails_reverse/Assem/a.svg +53 -0
  513. data/spec/data/velvet_test_trails_reverse/reads_reversed.fa +10 -0
  514. data/spec/data/visualise/1/LastGraph +6695 -0
  515. data/spec/data/visualise/2_paired_end/HOWTO_RECREATE.txt +10 -0
  516. data/spec/data/visualise/2_paired_end/rand1.fa +2 -0
  517. data/spec/data/visualise/2_paired_end/rand2.fa +2 -0
  518. data/spec/data/visualise/2_paired_end/with_gaps.fa +8 -0
  519. data/spec/data/visualise/2_paired_end/with_gaps.read_pairs.fa.gz +0 -0
  520. data/spec/data/wander/1/random1.fa +2 -0
  521. data/spec/data/wander/1/random1.sammy.fa +804 -0
  522. data/spec/depth_first_search_spec.rb +190 -0
  523. data/spec/dijkstra_spec.rb +143 -0
  524. data/spec/explore_spec.rb +29 -0
  525. data/spec/fluffer_spec.rb +155 -0
  526. data/spec/gapfiller_spec.rb +107 -0
  527. data/spec/graph_explorer_spec.rb +475 -0
  528. data/spec/graph_generator_spec.rb +99 -0
  529. data/spec/height_finder_spec.rb +306 -0
  530. data/spec/kmer_abundance_pattern_spec.rb +56 -0
  531. data/spec/kmer_coverage_based_path_filter_spec.rb +73 -0
  532. data/spec/kmer_profile_finder_spec.rb +38 -0
  533. data/spec/kmers_count_tabulate_spec.rb +120 -0
  534. data/spec/oriented_node_trail_spec.rb +221 -0
  535. data/spec/paired_end_neighbours_spec.rb +126 -0
  536. data/spec/paths_between_nodes_spec.rb +349 -0
  537. data/spec/priner_spec.rb +7 -0
  538. data/spec/read_input_spec.rb +23 -0
  539. data/spec/read_selection_by_kmer_spec.rb +166 -0
  540. data/spec/read_to_node_spec.rb +35 -0
  541. data/spec/roundup_spec.rb +366 -0
  542. data/spec/scaffold_breaker_spec.rb +144 -0
  543. data/spec/sequence_spec.rb +43 -0
  544. data/spec/single_coherent_paths_between_nodes_spec.rb +492 -0
  545. data/spec/single_coherent_wanderer_spec.rb +120 -0
  546. data/spec/single_ended_assembler_spec.rb +398 -0
  547. data/spec/spec_helper.rb +310 -0
  548. data/spec/velvet_graph_sequence_extractor_spec.rb +80 -0
  549. data/spec/visualise_spec.rb +105 -0
  550. data/spec/wander_spec.rb +119 -0
  551. data/spec/watch_for_changes.sh +16 -0
  552. data/validation/fasta_compare.rb +72 -0
  553. data/validation/gapfill_simulate_perfect.rb +108 -0
  554. metadata +899 -0
@@ -0,0 +1,30 @@
1
+ /*
2
+ Copyright 2007, 2008 Daniel Zerbino (zerbino@ebi.ac.uk)
3
+
4
+ This file is part of Velvet.
5
+
6
+ Velvet is free software; you can redistribute it and/or modify
7
+ it under the terms of the GNU General Public License as published by
8
+ the Free Software Foundation; either version 2 of the License, or
9
+ (at your option) any later version.
10
+
11
+ Velvet is distributed in the hope that it will be useful,
12
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
13
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14
+ GNU General Public License for more details.
15
+
16
+ You should have received a copy of the GNU General Public License
17
+ along with Velvet; if not, write to the Free Software
18
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
19
+
20
+ */
21
+ #ifndef _GRAPHRECONSTRUCTION_H_
22
+ #define _GRAPHRECONSTRUCTION_H_
23
+
24
+ Graph *importPreGraph(char *preGraphFilename, ReadSet * reads, char * roadmapFilename,
25
+ boolean readTracking, short int accelerationBits);
26
+
27
+ Graph *importConnectedGraph(char *connectedGraphFilename, ReadSet * reads, char * roadmapFilename,
28
+ boolean readTracking, short int accelerationBits);
29
+
30
+ #endif
@@ -0,0 +1,2167 @@
1
+ /*
2
+ Copyright 2007, 2008 Daniel Zerbino (zerbino@ebi.ac.uk)
3
+
4
+ This file is part of Velvet.
5
+
6
+ Velvet is free software; you can redistribute it and/or modify
7
+ it under the terms of the GNU General Public License as published by
8
+ the Free Software Foundation; either version 2 of the License, or
9
+ (at your option) any later version.
10
+
11
+ Velvet is distributed in the hope that it will be useful,
12
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
13
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14
+ GNU General Public License for more details.
15
+
16
+ You should have received a copy of the GNU General Public License
17
+ along with Velvet; if not, write to the Free Software
18
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
19
+
20
+ */
21
+ #include <stdlib.h>
22
+ #include <stdio.h>
23
+ #include <math.h>
24
+ #include <string.h>
25
+ #include <ctype.h>
26
+
27
+ #include "globals.h"
28
+ #include "graph.h"
29
+ #include "graphStats.h"
30
+ #include "readSet.h"
31
+ #include "tightString.h"
32
+ #include "passageMarker.h"
33
+ #include "concatenatedGraph.h"
34
+ #include "readCoherentGraph.h"
35
+ #include "fibHeap.h"
36
+ #include "utility.h"
37
+ #include "recycleBin.h"
38
+ #include "passageMarker.h"
39
+ #include "binarySequences.h"
40
+
41
+ static PassageMarkerList *copyMarkers(Node * node)
42
+ {
43
+ PassageMarkerList *list = NULL;
44
+ PassageMarkerList *new;
45
+ PassageMarkerI currentMarker;
46
+
47
+ for (currentMarker = getMarker(node); currentMarker != NULL_IDX;
48
+ currentMarker = getNextInNode(currentMarker)) {
49
+ new = newPassageMarkerList(currentMarker, list);
50
+ list = new;
51
+ }
52
+
53
+ return list;
54
+ }
55
+
56
+ static boolean removeDead(PassageMarkerList ** list)
57
+ {
58
+ PassageMarkerList *current, *next;
59
+ boolean removed = false;
60
+
61
+ if (*list == NULL)
62
+ return false;
63
+
64
+ current = *list;
65
+
66
+ while (current->next != NULL) {
67
+ next = current->next;
68
+
69
+ if (isTerminal(next->marker)) {
70
+ removed = true;
71
+ current->next = next->next;
72
+ deallocatePassageMarkerList(next);
73
+ } else
74
+ current = current->next;
75
+ }
76
+
77
+ current = *list;
78
+ if (isTerminal(current->marker)) {
79
+ removed = true;
80
+ *list = current->next;
81
+ deallocatePassageMarkerList(current);
82
+ }
83
+
84
+ return removed;
85
+ }
86
+
87
+ static Node *chooseDestination(PassageMarkerList * list)
88
+ {
89
+ PassageMarkerList *current = list;
90
+ Node *destination;
91
+
92
+ destination = getNode(getNextInSequence(current->marker));
93
+ while (current != NULL) {
94
+ if (getNode(getNextInSequence(current->marker)) !=
95
+ destination)
96
+ return NULL;
97
+ current = current->next;
98
+ }
99
+
100
+ return destination;
101
+ }
102
+
103
+ static void destroyPassageMarkerList(PassageMarkerList ** list)
104
+ {
105
+ PassageMarkerList *ptr;
106
+
107
+ while (*list != NULL) {
108
+ ptr = *list;
109
+ *list = ptr->next;
110
+ deallocatePassageMarkerList(ptr);
111
+ }
112
+ }
113
+
114
+ static void updateMarkers(PassageMarkerList * list)
115
+ {
116
+ PassageMarkerList *current;
117
+
118
+ for (current = list; current != NULL; current = current->next)
119
+ current->marker = getNextInSequence(current->marker);
120
+ }
121
+
122
+ Coordinate computeSubsequentNodesLength(Node * node)
123
+ {
124
+ PassageMarkerList *list;
125
+ Node *nextNode;
126
+ Coordinate totalLength = 0;
127
+ boolean uncertain = false;
128
+
129
+ list = copyMarkers(node);
130
+
131
+ while (true) {
132
+ if (removeDead(&list))
133
+ uncertain = true;
134
+
135
+ if (uncertain && simpleArcCount(node) > 1) {
136
+ destroyPassageMarkerList(&list);
137
+ return totalLength;
138
+ }
139
+
140
+ if (list == NULL)
141
+ return totalLength;
142
+
143
+ nextNode = chooseDestination(list);
144
+ if (nextNode == NULL) {
145
+ destroyPassageMarkerList(&list);
146
+ return totalLength;
147
+ }
148
+
149
+ totalLength += getNodeLength(nextNode);
150
+
151
+ updateMarkers(list);
152
+ }
153
+
154
+ // Impossible instruction
155
+ return -1;
156
+ }
157
+
158
+ Coordinate computeVirtualNodeLength(Node * node)
159
+ {
160
+ Coordinate virtualLength;
161
+
162
+ if (node == NULL)
163
+ return 0;
164
+
165
+ virtualLength = getNodeLength(node);
166
+
167
+ virtualLength += computeSubsequentNodesLength(node);
168
+ virtualLength += computeSubsequentNodesLength(getTwinNode(node));
169
+
170
+ return virtualLength;
171
+ }
172
+
173
+ // Counts the number of markers for one node
174
+ int nodeGenomicMultiplicity(Node * node, IDnum firstStrain)
175
+ {
176
+ int counter = 0;
177
+ PassageMarkerI marker;
178
+
179
+ if (node == NULL)
180
+ return 0;
181
+
182
+ for (marker = getMarker(node); marker != NULL_IDX;
183
+ marker = getNextInNode(marker))
184
+ if (getAbsolutePassMarkerSeqID(marker) < firstStrain)
185
+ counter++;
186
+
187
+ return counter;
188
+ }
189
+
190
+ boolean isOnlyGenome(Node * node, IDnum firstStrain)
191
+ {
192
+ PassageMarkerI marker;
193
+
194
+ for (marker = getMarker(node); marker != NULL_IDX;
195
+ marker = getNextInNode(marker))
196
+ if (getAbsolutePassMarkerSeqID(marker) >= firstStrain)
197
+ return false;
198
+
199
+ return true;
200
+ }
201
+
202
+ boolean isOnlyStrain(Node * node, IDnum firstStrain)
203
+ {
204
+ PassageMarkerI marker;
205
+
206
+ for (marker = getMarker(node); marker != NULL_IDX;
207
+ marker = getNextInNode(marker))
208
+ if (getAbsolutePassMarkerSeqID(marker) < firstStrain)
209
+ return false;
210
+
211
+ return true;
212
+ }
213
+
214
+ boolean isSNP(Node * node, IDnum firstStrain, int WORDLENGTH)
215
+ {
216
+ IDnum sequence;
217
+ Coordinate position;
218
+
219
+ if (getNodeLength(node) != WORDLENGTH)
220
+ return false;
221
+
222
+ if (getMarker(node) == NULL_IDX)
223
+ return false;
224
+
225
+ if (getAbsolutePassMarkerSeqID(getMarker(node)) >= firstStrain)
226
+ return false;
227
+
228
+ if (getNextInNode(getMarker(node)) != NULL_IDX)
229
+ return false;
230
+
231
+ if (arcCount(node) != 1)
232
+ return false;
233
+
234
+ if (arcCount(getTwinNode(node)) != 1)
235
+ return false;
236
+
237
+ if (isOnlyGenome(getDestination(getArc(node)), firstStrain))
238
+ return false;
239
+
240
+ if (isOnlyGenome
241
+ (getDestination(getArc(getTwinNode(node))), firstStrain))
242
+ return false;
243
+
244
+ sequence = getPassageMarkerSequenceID(getMarker(node));
245
+
246
+ if (sequence >= 0)
247
+ position = getPassageMarkerStart(getMarker(node));
248
+ else {
249
+ sequence = -sequence;
250
+ position = getPassageMarkerFinish(getMarker(node));
251
+ }
252
+
253
+ velvetLog("SNP\t%lld\t%ld\n", (long long) position, (long) sequence);
254
+
255
+ return true;
256
+ }
257
+
258
+ void removeStrainMarkers(Node * node, IDnum firstStrain)
259
+ {
260
+ PassageMarkerI marker;
261
+ PassageMarkerI tmp = NULL_IDX;
262
+
263
+ marker = getMarker(node);
264
+ while (marker != NULL_IDX) {
265
+ tmp = getNextInNode(marker);
266
+
267
+ if (getAbsolutePassMarkerSeqID(marker) >= firstStrain)
268
+ destroyPassageMarker(marker);
269
+ marker = tmp;
270
+ }
271
+
272
+ }
273
+
274
+ Coordinate commonLength(Node * node, IDnum firstStrain)
275
+ {
276
+ PassageMarkerI marker = getMarker(node);
277
+ int orig = 0;
278
+ int strain = 0;
279
+
280
+ while (marker != NULL_IDX) {
281
+ if (getAbsolutePassMarkerSeqID(marker) < firstStrain)
282
+ orig++;
283
+ else
284
+ strain++;
285
+ marker = getNextInNode(marker);
286
+ }
287
+
288
+ if (orig == 0 || strain == 0)
289
+ return 0;
290
+
291
+ return (Coordinate) orig *getNodeLength(node);
292
+ }
293
+
294
+ boolean isMixed(Node * node, IDnum firstStrain)
295
+ {
296
+ return !isOnlyStrain(node, firstStrain)
297
+ && !isOnlyGenome(node, firstStrain);
298
+ }
299
+
300
+ int countLocalBreakpoints(PassageMarkerI marker, IDnum firstStrain)
301
+ {
302
+ PassageMarkerI localMarker;
303
+ IDnum sequenceID = getAbsolutePassMarkerSeqID(marker);
304
+ IDnum localSeqID;
305
+ Coordinate start = getPassageMarkerStart(marker);
306
+ Node *localNode = getNode(marker);
307
+ Node *destination;
308
+ Arc *arc;
309
+ int arcCount = 0;
310
+ int arcIndex;
311
+ boolean *arcStatus;
312
+ int counter = 0;
313
+
314
+ if (!isMixed(localNode, firstStrain))
315
+ return 0;
316
+
317
+ // Count arcs
318
+ for (arc = getArc(localNode); arc != NULL; arc = getNextArc(arc))
319
+ arcCount++;
320
+ arcStatus = callocOrExit(arcCount, boolean);
321
+ // Check for other genomic markers in node
322
+ for (localMarker = getMarker(localNode); localMarker != NULL_IDX;
323
+ localMarker = getNextInNode(localMarker)) {
324
+ localSeqID = getAbsolutePassMarkerSeqID(localMarker);
325
+ if (localSeqID >= firstStrain)
326
+ continue;
327
+
328
+ if (localSeqID < sequenceID)
329
+ return 0;
330
+
331
+ if (localSeqID == sequenceID
332
+ && getPassageMarkerStart(localMarker) < start)
333
+ return 0;
334
+
335
+ destination = getNode(getNextInSequence(localMarker));
336
+
337
+ // Enter into table:
338
+ arcIndex = 0;
339
+ for (arc = getArc(localNode);
340
+ getDestination(arc) != destination;
341
+ arc = getNextArc(arc))
342
+ arcIndex++;
343
+ arcStatus[arcIndex] = true;
344
+ }
345
+
346
+ // Check other nodes
347
+ arcIndex = 0;
348
+ for (arc = getArc(localNode); arc != NULL; arc = getNextArc(arc)) {
349
+ if (!arcStatus[arcIndex]
350
+ && isMixed(getDestination(arc), firstStrain))
351
+ counter++;
352
+ arcIndex++;
353
+ }
354
+
355
+ free(arcStatus);
356
+ return counter;
357
+ }
358
+
359
+ IDnum genomeMarkerCount(Node * node, IDnum firstStrain)
360
+ {
361
+ PassageMarkerI marker;
362
+ IDnum counter = 0;
363
+
364
+ for (marker = getMarker(node); marker != NULL_IDX;
365
+ marker = getNextInNode(marker))
366
+ if (getAbsolutePassMarkerSeqID(marker) < firstStrain)
367
+ counter++;
368
+
369
+ return counter;
370
+ }
371
+
372
+ Coordinate readCoverage(Node * node)
373
+ {
374
+ PassageMarkerI marker;
375
+ Coordinate sum = 0;
376
+
377
+ for (marker = getMarker(node); marker != NULL_IDX;
378
+ marker = getNextInNode(marker)) {
379
+ if (getTwinMarker(marker) == NULL_IDX) {
380
+ velvetLog("Node %li screwed up\n", (long) getNodeID(node));
381
+ velvetLog("Sequence %li\n",
382
+ (long) getPassageMarkerSequenceID(marker));
383
+ abort();
384
+ }
385
+ sum += getPassageMarkerLength(marker);
386
+ }
387
+
388
+ return sum;
389
+ }
390
+
391
+ Coordinate refReadCoverage(Node * node, IDnum firstStrain)
392
+ {
393
+ PassageMarkerI marker;
394
+ Coordinate sum = 0;
395
+
396
+ for (marker = getMarker(node); marker != NULL_IDX;
397
+ marker = getNextInNode(marker))
398
+ if (getAbsolutePassMarkerSeqID(marker) < firstStrain)
399
+ sum += getPassageMarkerLength(marker);
400
+
401
+ return sum;
402
+ }
403
+
404
+ Coordinate newReadCoverage(Node * node, IDnum firstStrain)
405
+ {
406
+ PassageMarkerI marker;
407
+ Coordinate sum = 0;
408
+
409
+ for (marker = getMarker(node); marker != NULL_IDX;
410
+ marker = getNextInNode(marker))
411
+ if (getAbsolutePassMarkerSeqID(marker) >= firstStrain) {
412
+ sum += getPassageMarkerLength(marker);
413
+ if (getPassageMarkerLength(marker) < 0)
414
+ velvetLog("Bizarre marker %li at node %li\n",
415
+ (long) getPassageMarkerSequenceID(marker),
416
+ (long) getNodeID(node));
417
+ }
418
+
419
+ return sum;
420
+ }
421
+
422
+ static void printShortCounts(FILE * outfile, Node * node, Graph * graph, ReadSet * reads)
423
+ {
424
+ IDnum counts[CATEGORIES];
425
+ Category cat;
426
+ IDnum shortReadIndex;
427
+ IDnum readID;
428
+ IDnum shortReadCount;
429
+ ShortReadMarker *array;
430
+ ShortReadMarker *marker;
431
+
432
+ if (!readStartsAreActivated(graph)) {
433
+ for (cat = 0; cat < CATEGORIES; cat++)
434
+ velvetFprintf(outfile, "\tN/A");
435
+ return;
436
+ }
437
+
438
+ shortReadCount = getNodeReadCount(node, graph);
439
+ array = getNodeReads(node, graph);
440
+
441
+ for (cat = 0; cat < CATEGORIES; cat++)
442
+ counts[cat] = 0;
443
+
444
+ for (shortReadIndex = 0; shortReadIndex < shortReadCount; shortReadIndex++) {
445
+ marker = getShortReadMarkerAtIndex(array, shortReadIndex);
446
+ readID = getShortReadMarkerID(marker);
447
+ cat = reads->categories[readID - 1] / 2;
448
+ counts[cat]++;
449
+ }
450
+
451
+ for (cat = 0; cat < CATEGORIES; cat++)
452
+ velvetFprintf(outfile, "\t%li", (long) counts[cat]);
453
+ }
454
+
455
+ void displayGeneralStatistics(Graph * graph, char *filename, ReadSet * reads)
456
+ {
457
+ IDnum nodeIndex;
458
+ Node *node;
459
+ Category cat;
460
+ FILE *outfile;
461
+
462
+ outfile = fopen(filename, "w");
463
+ if (outfile == NULL) {
464
+ velvetLog("Couldn't open file %s, sorry\n", filename);
465
+ return;
466
+ } else
467
+ velvetLog("Writing into stats file %s...\n", filename);
468
+
469
+ velvetFprintf(outfile, "ID\tlgth\tout\tin\tlong_cov");
470
+
471
+ #ifndef SINGLE_COV_CAT
472
+ for (cat = 0; cat < CATEGORIES; cat++) {
473
+ velvetFprintf(outfile, "\tshort%i_cov", (int) (cat + 1));
474
+ velvetFprintf(outfile, "\tshort%i_Ocov", (int) (cat + 1));
475
+ }
476
+ #else
477
+ velvetFprintf(outfile, "\tshort_cov");
478
+ #endif
479
+
480
+ velvetFprintf(outfile, "\tlong_nb");
481
+ for (cat = 0; cat < CATEGORIES; cat++) {
482
+ velvetFprintf(outfile, "\tshort%i_nb", (int) (cat + 1));
483
+ }
484
+
485
+ velvetFprintf(outfile, "\n");
486
+
487
+ for (nodeIndex = 1; nodeIndex <= nodeCount(graph); nodeIndex++) {
488
+ node = getNodeInGraph(graph, nodeIndex);
489
+ if (node == NULL)
490
+ continue;
491
+ velvetFprintf
492
+ (outfile, "%ld\t%lld\t%i\t%i",
493
+ (long) getNodeID(node), (long long) getNodeLength(node), arcCount(node),
494
+ arcCount(getTwinNode(node)));
495
+
496
+ if (getNodeLength(node) > 0) {
497
+ velvetFprintf(outfile, "\t%f",
498
+ readCoverage(node) /
499
+ (double) getNodeLength(node));
500
+ #ifndef SINGLE_COV_CAT
501
+ for (cat = 0; cat < CATEGORIES; cat++) {
502
+ velvetFprintf(outfile, "\t%f",
503
+ getVirtualCoverage(node, cat) /
504
+ (double) getNodeLength(node));
505
+ velvetFprintf(outfile, "\t%f",
506
+ getOriginalVirtualCoverage(node, cat) /
507
+ (double) getNodeLength(node));
508
+ }
509
+ #else
510
+ velvetFprintf(outfile, "\t%f",
511
+ getVirtualCoverage(node) /
512
+ (double) getNodeLength(node));
513
+ #endif
514
+ } else {
515
+ velvetFprintf(outfile, "\tInf");
516
+ #ifndef SINGLE_COV_CAT
517
+ for (cat = 0; cat < CATEGORIES; cat++)
518
+ velvetFprintf(outfile, "\tInf\tInf");
519
+ #else
520
+ velvetFprintf(outfile, "\tInf");
521
+ #endif
522
+ }
523
+
524
+ velvetFprintf(outfile, "\t%li", (long) markerCount(node));
525
+ printShortCounts(outfile, node, graph, reads);
526
+
527
+ velvetFprintf(outfile, "\n");
528
+ }
529
+
530
+ fclose(outfile);
531
+ }
532
+
533
+ void displayLocalBreakpoint(PassageMarkerI strainMarker,
534
+ IDnum firstStrain,
535
+ PassageMarkerI genomeMarker,
536
+ Node ** genomeDestination,
537
+ Node ** strainDestination, IDnum * counter,
538
+ IDnum nodeCount)
539
+ {
540
+ boolean isTranslocation;
541
+ PassageMarkerI marker;
542
+ Node *destination, *destinationA;
543
+ Node *destination2, *destination2A;
544
+ Node *node1, *node2;
545
+ IDnum localID = getNodeID(getNode(strainMarker));
546
+
547
+ // Eliminate genomic markers
548
+ if (strainMarker == genomeMarker)
549
+ return;
550
+
551
+ destinationA = getNode(getNextInSequence(strainMarker));
552
+
553
+ if (destinationA == NULL)
554
+ return;
555
+
556
+ // Eliminate those that follow some local strain
557
+ if (isDestinationToMarker(genomeMarker, destinationA)) {
558
+ // velvetLog("Parallel paths\n");
559
+ return;
560
+ }
561
+
562
+ destination2A = getNode(getNextInSequence(genomeMarker));
563
+
564
+ if (destination2A == NULL)
565
+ return;
566
+
567
+ velvetLog("Lengths %lld %lld\n", (long long) getNodeLength(destinationA),
568
+ (long long) getNodeLength(destination2A));
569
+
570
+ // Hop to another genomic node
571
+ // if (getNodeLength(destinationA) > 24) {
572
+ //velvetLog("wrong length %d %d\n", getNodeLength(destination) , getNodeID(destination));
573
+ // return;
574
+ // }
575
+
576
+ destination =
577
+ getNode(getNextInSequence(getNextInSequence(strainMarker)));
578
+
579
+ if (destination == NULL)
580
+ return;
581
+
582
+ // Eliminate those that point to uniquely strain sequences
583
+ if (nodeGenomicMultiplicity(destination, firstStrain) != 1) {
584
+ // velvetLog("Multiple genome reads\n");
585
+ return;
586
+ }
587
+ // Hop to another genomic node
588
+ // if (getNodeLength(destination2A) != 24) {
589
+ //velvetLog("wrong length 2\n");
590
+ // return;
591
+ // }
592
+
593
+ destination2 =
594
+ getNode(getNextInSequence(getNextInSequence(genomeMarker)));
595
+
596
+ if (destination2 == NULL)
597
+ return;
598
+
599
+
600
+ if (destination == destination2)
601
+ return;
602
+
603
+ // Eliminate those that point to uniquely strain sequences
604
+ if (isOnlyGenome(destination2, firstStrain))
605
+ return;
606
+
607
+ setSingleNodeStatus(getNode(strainMarker), true);
608
+ strainDestination[localID + nodeCount] = destination;
609
+ genomeDestination[localID + nodeCount] = destination2;
610
+
611
+ // velvetLog("Assigning %p and %p to %d\n", destination, destination2, localID);
612
+ velvetLog("lengths %lld\t%lld\n", (long long) getNodeLength(destinationA),
613
+ (long long) getNodeLength(destination2A));
614
+
615
+ // Detect translocation
616
+ isTranslocation = true;
617
+ for (marker = getMarker(destination); marker != NULL_IDX;
618
+ marker = getNextInNode(marker))
619
+ if (getAbsolutePassMarkerSeqID(marker) ==
620
+ getAbsolutePassMarkerSeqID(genomeMarker)) {
621
+ isTranslocation = false;
622
+ break;
623
+ }
624
+
625
+ if (isTranslocation) {
626
+ velvetLog("BREAK TRANS\t%ld\t%lld\t%lld\t%lld\n",
627
+ (long) getAbsolutePassMarkerSeqID(genomeMarker),
628
+ (long long) getPassageMarkerStart(genomeMarker),
629
+ (long long) getNodeLength(destinationA),
630
+ (long long) getNodeLength(destination2A));
631
+ counter[2]++;
632
+ return;
633
+ }
634
+ // Detect breakpoint
635
+ velvetLog("BREAK INTRA\t%ld\t%lld\t%lld\t%lld\n",
636
+ (long) getAbsolutePassMarkerSeqID(genomeMarker),
637
+ (long long) getPassageMarkerStart(genomeMarker),
638
+ (long long) getNodeLength(destinationA), (long long) getNodeLength(destination2A));
639
+ counter[1]++;
640
+
641
+ // Check for inversion
642
+ if (getPassageMarkerSequenceID(marker) !=
643
+ -getPassageMarkerSequenceID(genomeMarker))
644
+ return;
645
+
646
+ // velvetLog("potential!!\n");
647
+
648
+ node1 = getTwinNode(destination);
649
+
650
+ if (getNodeStatus(node1)) {
651
+ node2 =
652
+ getTwinNode(genomeDestination
653
+ [getNodeID(node1) + nodeCount]);
654
+ if (getNodeStatus(node2))
655
+ if (strainDestination[getNodeID(node2) + nodeCount]
656
+ == destination2) {
657
+ // velvetLog("Safe\n");
658
+ counter[1] -= 4;
659
+ counter[0]++;
660
+ } else;
661
+ // velvetLog("stopped 3\n");
662
+ else;
663
+ // velvetLog("stopped 2\n");
664
+ } else;
665
+ // velvetLog("stopped 1\n");
666
+ }
667
+
668
+ PassageMarkerI genomeMarker(Node * node, IDnum firstStrain)
669
+ {
670
+ PassageMarkerI marker;
671
+
672
+ if (genomeMarkerCount(node, firstStrain) != 1)
673
+ return NULL_IDX;
674
+
675
+ for (marker = getMarker(node); marker != NULL_IDX;
676
+ marker = getNextInNode(marker))
677
+ if (getAbsolutePassMarkerSeqID(marker) < firstStrain)
678
+ return marker;
679
+
680
+ return NULL_IDX;
681
+ }
682
+
683
+ void exportArcSequence(Arc * arc, FILE * outfile, int WORDLENGTH,
684
+ TightString ** sequences)
685
+ {
686
+ char *str;
687
+ TightString *output =
688
+ newTightString(getNodeLength(getOrigin(arc)) +
689
+ getNodeLength(getDestination(arc)));
690
+ appendNodeSequence(getOrigin(arc), output, 0);
691
+ appendNodeSequence(getDestination(arc), output,
692
+ getNodeLength(getOrigin(arc)));
693
+ str = readTightString(output);
694
+ velvetFprintf(outfile, "> ARC from NODE %li", (long) getNodeID(getOrigin(arc)));
695
+ velvetFprintf(outfile, "%s\n", str);
696
+ destroyTightString(output);
697
+ free(str);
698
+ }
699
+
700
+ // Produce sequences necessary to recreate graph elsewhere...
701
+ void projectGraphToFile(Graph * graph, char *filename, int WORDLENGTH,
702
+ TightString ** sequences)
703
+ {
704
+ FILE *outfile = fopen(filename, "w");
705
+ IDnum index;
706
+ Node *currentNode;
707
+ Arc *arc;
708
+
709
+ if (outfile == NULL) {
710
+ velvetLog("Could not open %s, sorry\n", filename);
711
+ return;
712
+ }
713
+
714
+ for (index = 1; index < nodeCount(graph); index++) {
715
+ currentNode = getNodeInGraph(graph, index);
716
+ for (arc = getArc(currentNode); arc != NULL;
717
+ arc = getNextArc(arc))
718
+ exportArcSequence(arc, outfile, WORDLENGTH,
719
+ sequences);
720
+
721
+ for (arc = getArc(getTwinNode(currentNode)); arc != NULL;
722
+ arc = getNextArc(arc))
723
+ exportArcSequence(arc, outfile, WORDLENGTH,
724
+ sequences);
725
+ }
726
+
727
+ fclose(outfile);
728
+ }
729
+
730
+ static RecycleBin * maskMemory = NULL;
731
+
732
+ static Mask *allocateMask()
733
+ {
734
+ if (maskMemory == NULL)
735
+ maskMemory = newRecycleBin(sizeof(Mask), 10000);
736
+
737
+ return (Mask *) allocatePointer(maskMemory);
738
+ }
739
+
740
+ static void deallocateMask(Mask * mask)
741
+ {
742
+ deallocatePointer(maskMemory, mask);
743
+ }
744
+
745
+
746
+ static Mask * newMask(Coordinate position)
747
+ {
748
+ Mask * mask = allocateMask();
749
+ mask->start = position;
750
+ mask->finish = position;
751
+ mask->next = NULL;
752
+ return mask;
753
+ }
754
+
755
+ static Mask * lowCoverageRegions(Coordinate * starts, Coordinate * stops, size_t length, IDnum cutoff, Coordinate nodeLength) {
756
+ size_t indexStart = 0;
757
+ size_t indexStop = 0;
758
+ int currentValue = 0;
759
+ Mask * regions = NULL;
760
+ Mask * lastRegion = NULL;
761
+ boolean openMask = false;
762
+
763
+ while (indexStart < length && indexStop < length) {
764
+ if (starts[indexStart] == stops[indexStop]) {
765
+ indexStart++;
766
+ indexStop++;
767
+ } else if (starts[indexStart] < stops[indexStop]) {
768
+ if (currentValue == cutoff - 1 && lastRegion) {
769
+ lastRegion->finish = starts[indexStart] - 1;
770
+ openMask = false;
771
+ }
772
+ currentValue++;
773
+ indexStart++;
774
+ } else {
775
+ if (currentValue == cutoff && stops[indexStop] != nodeLength) {
776
+ if (regions) {
777
+ lastRegion->next = newMask(stops[indexStop]);
778
+ lastRegion = lastRegion->next;
779
+ } else {
780
+ regions = newMask(stops[indexStop]);
781
+ lastRegion = regions;
782
+ }
783
+ openMask = true;
784
+ }
785
+ currentValue--;
786
+ indexStop++;
787
+ }
788
+ }
789
+
790
+ while (indexStart < length) {
791
+ if (currentValue == cutoff - 1 && lastRegion) {
792
+ lastRegion->finish = starts[indexStart] - 1;
793
+ openMask = false;
794
+ } else if (currentValue >= cutoff) {
795
+ break;
796
+ }
797
+ currentValue++;
798
+ indexStart++;
799
+ }
800
+
801
+ while (indexStop < length) {
802
+ if (currentValue == cutoff + 1) {
803
+ if (regions) {
804
+ lastRegion->next = newMask(stops[indexStop]);
805
+ lastRegion = lastRegion->next;
806
+ } else {
807
+ regions = newMask(stops[indexStop]);
808
+ lastRegion = regions;
809
+ }
810
+ openMask = true;
811
+ } else if (currentValue < cutoff)
812
+ break;
813
+ currentValue--;
814
+ indexStop++;
815
+ }
816
+
817
+ if (openMask)
818
+ lastRegion->finish = nodeLength;
819
+
820
+ free(starts);
821
+ free(stops);
822
+ return regions;
823
+ }
824
+
825
+ static int compareCoords(const void * A, const void * B) {
826
+ Coordinate * a_p = (Coordinate *) A;
827
+ Coordinate * b_p = (Coordinate *) B;
828
+ Coordinate a = * a_p;
829
+ Coordinate b = * b_p;
830
+ if (a < b)
831
+ return -1;
832
+ else if (a > b)
833
+ return 1;
834
+ else
835
+ return 0;
836
+ }
837
+
838
+ static void sortCoords(Coordinate * array, IDnum length) {
839
+ qsort(array, (size_t) length, sizeof(Coordinate), compareCoords);
840
+ }
841
+
842
+ static void getShortReadCoords(Coordinate * starts, Coordinate * stops, Node * node, Graph * graph, ShortLength * readLengths) {
843
+ ShortReadMarker * markers = getNodeReads(node, graph);
844
+ ShortReadMarker* marker;
845
+ IDnum index;
846
+ for (index = 0; index < getNodeReadCount(node, graph); index++) {
847
+ marker = getShortReadMarkerAtIndex(markers, index);
848
+ starts[index] = getShortReadMarkerPosition(marker);
849
+ stops[index] = starts[index] - getShortReadMarkerOffset(marker) + readLengths[getShortReadMarkerID(marker) - 1] - 1;
850
+ }
851
+ }
852
+
853
+ static void getShortReadTwinCoords(Coordinate * starts, Coordinate * stops, Node * node, Graph * graph, ShortLength * readLengths, IDnum offset) {
854
+ ShortReadMarker * markers = getNodeReads(getTwinNode(node), graph);
855
+ ShortReadMarker* marker;
856
+ IDnum index;
857
+ for (index = 0; index < getNodeReadCount(getTwinNode(node), graph); index++) {
858
+ marker = getShortReadMarkerAtIndex(markers, index);
859
+ stops[index + offset] = getNodeLength(node) - 1 - getShortReadMarkerPosition(marker);
860
+ starts[index + offset] = stops[index + offset] + getShortReadMarkerOffset(marker) - readLengths[getShortReadMarkerID(marker) - 1] + 1;
861
+ }
862
+ }
863
+
864
+ static void getLongReadCoords(Coordinate * starts, Coordinate * stops, Node * node, Graph * graph, ReadSet * reads, IDnum offset) {
865
+ PassageMarkerI marker;
866
+ IDnum index = offset;
867
+
868
+ for (marker = getMarker(node); marker; marker = getNextInNode(marker)) {
869
+ if (reads->categories[getAbsolutePassMarkerSeqID(marker) - 1] != REFERENCE) {
870
+ starts[index] = getStartOffset(marker);
871
+ stops[index++] = getNodeLength(node) - 1 - getFinishOffset(marker);
872
+ } else {
873
+ starts[index] = -5;
874
+ stops[index++] = -10;
875
+ }
876
+ }
877
+ }
878
+
879
+ static Mask * findLowCoverageRegions(Node * node, Graph * graph, IDnum cutoff, ReadSet * reads, ShortLength * readLengths) {
880
+ // Fill arrays
881
+ IDnum nodeReads = getNodeReadCount(node, graph);
882
+ IDnum twinReads = getNodeReadCount(getTwinNode(node), graph);
883
+ IDnum longReads = markerCount(node);
884
+ IDnum length = nodeReads + twinReads + longReads;
885
+ Coordinate * starts = callocOrExit(length, Coordinate);
886
+ Coordinate * stops = callocOrExit(length, Coordinate);
887
+ getShortReadCoords(starts, stops, node, graph, readLengths);
888
+ getShortReadTwinCoords(starts, stops, node, graph, readLengths, nodeReads);
889
+ getLongReadCoords(starts, stops, node, graph, reads, nodeReads + twinReads);
890
+
891
+ // Sort arrays
892
+ sortCoords(starts, length);
893
+ sortCoords(stops, length);
894
+
895
+ // Go through array
896
+ return lowCoverageRegions(starts, stops, length, cutoff, getNodeLength(node));
897
+ }
898
+
899
+ static void exportLongNodeSequence(FILE * outfile, Node * node, Graph * graph, ReadSet * reads, ShortLength * readLengths, IDnum cutoff) {
900
+ TightString *tString;
901
+ Coordinate position;
902
+ char nucleotide;
903
+ int WORDLENGTH = getWordLength(graph);
904
+ GapMarker *gap;
905
+ IDnum nodeIndex = getNodeID(node);
906
+ Mask * mask = NULL;
907
+ Mask * next;
908
+
909
+ if (readStartsAreActivated(graph) && cutoff > 0)
910
+ mask = findLowCoverageRegions(node, graph, cutoff, reads, readLengths);
911
+
912
+ tString = expandNode(node, WORDLENGTH);
913
+ velvetFprintf(outfile, ">NODE_%ld_length_%lld_cov_%f\n",
914
+ (long) nodeIndex, (long long) getNodeLength(node),
915
+ (getTotalCoverage(node) + readCoverage(node)) /
916
+ (float) getNodeLength(node));
917
+
918
+ gap = getGap(node, graph);
919
+ for (position = 0; position < WORDLENGTH; position++) {
920
+ if (position % 60 == 0 && position > 0)
921
+ velvetFprintf(outfile, "\n");
922
+ nucleotide = getNucleotideChar(position, tString);
923
+ velvetFprintf(outfile, "%c", nucleotide);
924
+ }
925
+
926
+ gap = getGap(node, graph);
927
+ for (; position < getLength(tString); position++) {
928
+ if (position % 60 == 0)
929
+ velvetFprintf(outfile, "\n");
930
+
931
+ while (gap
932
+ && position - WORDLENGTH + 1 >=
933
+ getGapFinish(gap))
934
+ gap = getNextGap(gap);
935
+
936
+ while (mask
937
+ && position - WORDLENGTH + 1 >=
938
+ mask->finish) {
939
+ next = mask->next;
940
+ deallocateMask(mask);
941
+ mask = next;
942
+ }
943
+
944
+ if (gap
945
+ && position - WORDLENGTH + 1 >=
946
+ getGapStart(gap)) {
947
+ velvetFprintf(outfile, "N");
948
+ } else if (mask &&
949
+ position - WORDLENGTH + 1 >=
950
+ mask->start) {
951
+ nucleotide =
952
+ getNucleotideChar(position, tString);
953
+ velvetFprintf(outfile, "%c", tolower(nucleotide));
954
+
955
+ } else {
956
+ nucleotide =
957
+ getNucleotideChar(position, tString);
958
+ velvetFprintf(outfile, "%c", nucleotide);
959
+ }
960
+ }
961
+ velvetFprintf(outfile, "\n");
962
+ destroyTightString (tString);
963
+ }
964
+
965
+ void exportLongNodeSequences(char *filename, Graph * graph,
966
+ Coordinate minLength, ReadSet * reads, ShortLength * readLengths, IDnum minCov)
967
+ {
968
+ FILE *outfile = fopen(filename, "w");
969
+ IDnum nodeIndex;
970
+ Node *node;
971
+ //double sensitivity, specificity;
972
+
973
+ if (outfile == NULL) {
974
+ velvetLog("Could not write into %s, sorry\n", filename);
975
+ return;
976
+ } else {
977
+ velvetLog("Writing contigs into %s...\n", filename);
978
+ }
979
+
980
+ for (nodeIndex = 1; nodeIndex <= nodeCount(graph); nodeIndex++) {
981
+ node = getNodeInGraph(graph, nodeIndex);
982
+
983
+ if (node == NULL || getNodeLength(node) < minLength)
984
+ continue;
985
+
986
+ exportLongNodeSequence(outfile, node, graph, reads, readLengths, minCov);
987
+ }
988
+
989
+ if (maskMemory)
990
+ destroyRecycleBin(maskMemory);
991
+ maskMemory = NULL;
992
+
993
+ fclose(outfile);
994
+ }
995
+
996
+ Coordinate maxLength(Graph * graph)
997
+ {
998
+ IDnum index;
999
+ Node *node;
1000
+ Coordinate max = 0;
1001
+
1002
+ for (index = 1; index <= nodeCount(graph); index++) {
1003
+ node = getNodeInGraph(graph, index);
1004
+ if (node != NULL && getNodeLength(node) > max)
1005
+ max = getNodeLength(node);
1006
+ }
1007
+
1008
+ return max;
1009
+ }
1010
+
1011
+ Coordinate n50(Graph * graph)
1012
+ {
1013
+ FibHeap *heap = newFibHeap();
1014
+ IDnum index;
1015
+ Coordinate totalLength = 0;
1016
+ Coordinate sumLength = 0;
1017
+ Node *node;
1018
+
1019
+ if (nodeCount(graph) == 0) {
1020
+ velvetLog("EMPTY GRAPH\n");
1021
+ return 0;
1022
+ }
1023
+
1024
+ for (index = 1; index <= nodeCount(graph); index++) {
1025
+ node = getNodeInGraph(graph, index);
1026
+ if (node == NULL)
1027
+ continue;
1028
+ insertNodeIntoHeap(heap, getNodeLength(node), node);
1029
+ totalLength += getNodeLength(node);
1030
+ }
1031
+ totalLength /= 2;
1032
+
1033
+ node = removeNextNodeFromHeap(heap);
1034
+ while (node != NULL) {
1035
+ sumLength += getNodeLength(node);
1036
+ if (sumLength >= totalLength)
1037
+ break;
1038
+ node = removeNextNodeFromHeap(heap);
1039
+ }
1040
+
1041
+ destroyHeap(heap);
1042
+ return getNodeLength(node);
1043
+ }
1044
+
1045
+ int compareNodeCovs(const void * A, const void * B) {
1046
+ Node * nodeA = *((Node **) A);
1047
+ Node * nodeB = *((Node **) B);
1048
+ double covA;
1049
+ double covB;
1050
+
1051
+ if (getNodeLength(nodeA) == 0)
1052
+ nodeA = NULL;
1053
+
1054
+ if (getNodeLength(nodeB) == 0)
1055
+ nodeB = NULL;
1056
+
1057
+ // Null nodes considered to have infinite coverage
1058
+ if (nodeA == NULL && nodeB == NULL)
1059
+ return 0;
1060
+ if (nodeA == NULL)
1061
+ return 1;
1062
+ if (nodeB == NULL)
1063
+ return -1;
1064
+
1065
+ // Deal with real coverage numbers:
1066
+ covA = getTotalCoverage(nodeA) / (double) getNodeLength(nodeA);
1067
+ covB = getTotalCoverage(nodeB) / (double) getNodeLength(nodeB);
1068
+
1069
+ if (covA > covB)
1070
+ return 1;
1071
+ if (covA == covB)
1072
+ return 0;
1073
+ return -1;
1074
+ }
1075
+
1076
+ double estimated_cov(Graph * graph, char * directory)
1077
+ {
1078
+ Node ** nodeArray = callocOrExit(nodeCount(graph), Node*);
1079
+ IDnum index;
1080
+ Coordinate halfTotalLength = 0;
1081
+ Coordinate sumLength = 0;
1082
+ Node *node;
1083
+ char *logFilename =
1084
+ mallocOrExit(strlen(directory) + 100, char);
1085
+ char *statsLine =
1086
+ mallocOrExit(5000, char);
1087
+ FILE *logFile;
1088
+
1089
+ strcpy(logFilename, directory);
1090
+ strcat(logFilename, "/Log");
1091
+ logFile = fopen(logFilename, "a");
1092
+
1093
+ if (logFile == NULL)
1094
+ exitErrorf(EXIT_FAILURE, true, "Could not write to %s",
1095
+ logFilename);
1096
+
1097
+ velvetLog("Measuring median coverage depth...\n");
1098
+
1099
+ if (nodeCount(graph) == 0) {
1100
+ velvetLog("EMPTY GRAPH\n");
1101
+ return 0;
1102
+ }
1103
+
1104
+ // Write nodes into array and compute total assembly length
1105
+ for (index = 1; index <= nodeCount(graph); index++) {
1106
+ node = getNodeInGraph(graph, index);
1107
+ nodeArray[index - 1] = node;
1108
+ if (node == NULL)
1109
+ continue;
1110
+ halfTotalLength += getNodeLength(node);
1111
+ }
1112
+ halfTotalLength /= 2;
1113
+
1114
+ // Sort nodes
1115
+ qsort(nodeArray, nodeCount(graph), sizeof(Node *), compareNodeCovs);
1116
+
1117
+ // Compute the length weighted median node coverage
1118
+ for (index = 0; index < nodeCount(graph); index++) {
1119
+ node = nodeArray[index];
1120
+ sumLength += getNodeLength(node);
1121
+ if (sumLength >= halfTotalLength) {
1122
+ velvetLog("Median coverage depth = %f\n", getTotalCoverage(node) / (double) getNodeLength(node));
1123
+ velvetFprintf(logFile, "Median coverage depth = %f\n", getTotalCoverage(node) / (double) getNodeLength(node));
1124
+ free(nodeArray);
1125
+ fclose(logFile);
1126
+ free(logFilename);
1127
+ free(statsLine);
1128
+ return getTotalCoverage(node) / (double) getNodeLength(node);
1129
+ }
1130
+ }
1131
+
1132
+ // In case something went wrong...
1133
+ free(nodeArray);
1134
+ fclose(logFile);
1135
+ free(logFilename);
1136
+ free(statsLine);
1137
+
1138
+ return -1;
1139
+ }
1140
+
1141
+ static boolean terminalReferenceMarker(Node * node, ReadSet * reads) {
1142
+ PassageMarkerI marker;
1143
+
1144
+ for (marker = getMarker(node); marker; marker = getNextInNode(marker))
1145
+ if (reads->categories[getAbsolutePassMarkerSeqID(marker) - 1] == REFERENCE
1146
+ && (!getNextInSequence(marker)
1147
+ || !getPreviousInSequence(marker)))
1148
+ return true;
1149
+
1150
+ return false;
1151
+ }
1152
+
1153
+ static boolean hasReferenceMarker(Node * node, ReadSet * reads) {
1154
+ PassageMarkerI marker;
1155
+
1156
+ for (marker = getMarker(node); marker != NULL_IDX; marker = getNextInNode(marker))
1157
+ if (reads->categories[getAbsolutePassMarkerSeqID(marker) - 1] == REFERENCE)
1158
+ return true;
1159
+
1160
+ return false;
1161
+ }
1162
+
1163
+ inline static void
1164
+ destroyNodePassageMarkers(Graph *graph,
1165
+ Node* node)
1166
+ {
1167
+ PassageMarkerI marker;
1168
+
1169
+ while ((marker = getMarker(node)) != NULL_IDX) {
1170
+ if (!isInitial(marker) && !isTerminal(marker))
1171
+ deleteNextPassageMarker(getPreviousInSequence(marker), graph);
1172
+ destroyPassageMarker(marker);
1173
+ }
1174
+ }
1175
+
1176
+ inline static void
1177
+ removeNodeAndDenounceDubiousReads(Graph *graph,
1178
+ Node *node,
1179
+ boolean denounceReads,
1180
+ boolean *res,
1181
+ Coordinate minLength,
1182
+ FILE *outfile)
1183
+ {
1184
+ if (denounceReads) {
1185
+ ShortReadMarker *nodeArray;
1186
+ ShortReadMarker *shortMarker;
1187
+ IDnum maxIndex;
1188
+ IDnum index;
1189
+ IDnum readID;
1190
+
1191
+ nodeArray = getNodeReads(node, graph);
1192
+ maxIndex = getNodeReadCount(node, graph);
1193
+ for (index = 0; index < maxIndex; index++) {
1194
+ shortMarker = getShortReadMarkerAtIndex(nodeArray, index);
1195
+ readID = getShortReadMarkerID(shortMarker);
1196
+ if (readID > 0)
1197
+ res[readID - 1] = true;
1198
+ else
1199
+ res[-readID - 1] = true;
1200
+ }
1201
+
1202
+ nodeArray = getNodeReads(getTwinNode(node), graph);
1203
+ maxIndex = getNodeReadCount(getTwinNode(node), graph);
1204
+ for (index = 0; index < maxIndex; index++) {
1205
+ shortMarker = getShortReadMarkerAtIndex(nodeArray, index);
1206
+ readID = getShortReadMarkerID(shortMarker);
1207
+ if (readID > 0)
1208
+ res[readID - 1] = true;
1209
+ else
1210
+ res[-readID - 1] = true;
1211
+ }
1212
+ }
1213
+
1214
+ destroyNodePassageMarkers(graph, node);
1215
+
1216
+ if (outfile != NULL && getNodeLength(node) > minLength)
1217
+ exportLongNodeSequence(outfile, node, graph, NULL, NULL, -1);
1218
+
1219
+ destroyNode(node, graph);
1220
+ }
1221
+
1222
+ boolean *removeLowCoverageNodesAndDenounceDubiousReads(Graph * graph,
1223
+ double minCov,
1224
+ ReadSet * reads,
1225
+ boolean export,
1226
+ Coordinate minLength,
1227
+ char *filename)
1228
+ {
1229
+ IDnum index;
1230
+ Node *node;
1231
+ boolean denounceReads = readStartsAreActivated(graph);
1232
+ boolean *res = NULL;
1233
+ FILE * outfile = NULL;
1234
+
1235
+ velvetLog("Removing contigs with coverage < %f...\n", minCov);
1236
+
1237
+ if (denounceReads)
1238
+ res = callocOrExit(sequenceCount(graph), boolean);
1239
+
1240
+ if (export) {
1241
+ outfile = fopen(filename, "w");
1242
+
1243
+ if (outfile == NULL) {
1244
+ velvetLog("Could not write into %s, sorry\n", filename);
1245
+ return res;
1246
+ } else {
1247
+ velvetLog("Writing contigs into %s...\n", filename);
1248
+ }
1249
+ }
1250
+
1251
+
1252
+ for (index = 1; index <= nodeCount(graph); index++) {
1253
+ node = getNodeInGraph(graph, index);
1254
+
1255
+ if (getNodeLength(node) == 0)
1256
+ continue;
1257
+
1258
+ if (getTotalCoverage(node) / getNodeLength(node) < minCov
1259
+ && !hasReferenceMarker(node, reads))
1260
+ removeNodeAndDenounceDubiousReads(graph,
1261
+ node,
1262
+ denounceReads,
1263
+ res,
1264
+ minLength,
1265
+ outfile);
1266
+ }
1267
+
1268
+ concatenateGraph(graph);
1269
+
1270
+ for (index = 1; index <= nodeCount(graph); index++) {
1271
+ node = getNodeInGraph(graph, index);
1272
+
1273
+ if (getNodeLength(node) == 0)
1274
+ continue;
1275
+
1276
+ if (getTotalCoverage(node) / getNodeLength(node) < minCov
1277
+ && !terminalReferenceMarker(node, reads))
1278
+ removeNodeAndDenounceDubiousReads(graph,
1279
+ node,
1280
+ denounceReads,
1281
+ res,
1282
+ minLength,
1283
+ outfile);
1284
+ }
1285
+
1286
+ if (export)
1287
+ fclose(outfile);
1288
+
1289
+ concatenateGraph(graph);
1290
+ return res;
1291
+ }
1292
+
1293
+ static Coordinate getLongCoverage(Node * node) {
1294
+ PassageMarkerI marker;
1295
+ Coordinate total = 0;
1296
+
1297
+ for (marker = getMarker(node); marker; marker = getNextInNode(marker))
1298
+ total += getPassageMarkerLength(marker);
1299
+
1300
+ return total;
1301
+ }
1302
+
1303
+ void removeLowCoverageReferenceNodes(Graph * graph, double minCov, double minLongCov, ReadSet * reads)
1304
+ {
1305
+ IDnum index;
1306
+ Node *node;
1307
+
1308
+ velvetLog("Removing reference contigs with coverage < %f...\n", minCov);
1309
+
1310
+ for (index = 1; index <= nodeCount(graph); index++) {
1311
+ node = getNodeInGraph(graph, index);
1312
+
1313
+ if (getNodeLength(node) == 0)
1314
+ continue;
1315
+
1316
+ if ((getTotalCoverage(node) / getNodeLength(node) < minCov
1317
+ || getLongCoverage(node) / getNodeLength(node) < minLongCov)
1318
+ && hasReferenceMarker(node, reads)) {
1319
+ destroyNodePassageMarkers(graph, node);
1320
+
1321
+ destroyNode(node, graph);
1322
+ }
1323
+ }
1324
+
1325
+ concatenateGraph(graph);
1326
+ }
1327
+
1328
+ void removeLowLongCoverageNodesAndDenounceDubiousReads(Graph * graph,
1329
+ double minCov,
1330
+ ReadSet * reads,
1331
+ boolean * res,
1332
+ boolean export,
1333
+ Coordinate minLength,
1334
+ char *filename)
1335
+ {
1336
+ IDnum index;
1337
+ Node *node;
1338
+ boolean denounceReads = readStartsAreActivated(graph);
1339
+ FILE * outfile = NULL;
1340
+
1341
+ if (minCov < 0)
1342
+ return;
1343
+
1344
+ velvetLog("Removing contigs with coverage < %f...\n", minCov);
1345
+
1346
+ if (export) {
1347
+ outfile = fopen(filename, "a");
1348
+
1349
+ if (outfile == NULL) {
1350
+ velvetLog("Could not write into %s, sorry\n", filename);
1351
+ return;
1352
+ } else {
1353
+ velvetLog("Writing contigs into %s...\n", filename);
1354
+ }
1355
+ }
1356
+
1357
+ for (index = 1; index <= nodeCount(graph); index++) {
1358
+ node = getNodeInGraph(graph, index);
1359
+
1360
+ if (getNodeLength(node) == 0)
1361
+ continue;
1362
+
1363
+ if (getLongCoverage(node) / getNodeLength(node) < minCov
1364
+ && !hasReferenceMarker(node, reads))
1365
+ removeNodeAndDenounceDubiousReads(graph,
1366
+ node,
1367
+ denounceReads,
1368
+ res,
1369
+ minLength,
1370
+ outfile);
1371
+ }
1372
+
1373
+ concatenateGraph(graph);
1374
+
1375
+ for (index = 1; index <= nodeCount(graph); index++) {
1376
+ node = getNodeInGraph(graph, index);
1377
+
1378
+ if (getNodeLength(node) == 0)
1379
+ continue;
1380
+
1381
+ if (getLongCoverage(node) / getNodeLength(node) < minCov
1382
+ && !terminalReferenceMarker(node, reads))
1383
+ removeNodeAndDenounceDubiousReads(graph,
1384
+ node,
1385
+ denounceReads,
1386
+ res,
1387
+ minLength,
1388
+ outfile);
1389
+ }
1390
+
1391
+ if (export)
1392
+ fclose(outfile);
1393
+
1394
+ concatenateGraph(graph);
1395
+ }
1396
+
1397
+ void removeHighCoverageNodes(Graph * graph, double maxCov, boolean export, Coordinate minLength, char *filename)
1398
+ {
1399
+ IDnum index;
1400
+ Node *node;
1401
+ FILE * outfile = NULL;
1402
+
1403
+ if (maxCov < 0)
1404
+ return;
1405
+
1406
+ velvetLog("Applying an upper coverage cutoff of %f...\n", maxCov);
1407
+
1408
+ if (export) {
1409
+ outfile = fopen(filename, "w");
1410
+
1411
+ if (outfile == NULL) {
1412
+ velvetLog("Could not write into %s, sorry\n", filename);
1413
+ return;
1414
+ } else {
1415
+ velvetLog("Writing contigs into %s...\n", filename);
1416
+ }
1417
+ }
1418
+
1419
+ for (index = 1; index <= nodeCount(graph); index++) {
1420
+ node = getNodeInGraph(graph, index);
1421
+
1422
+ if (getNodeLength(node) > 0
1423
+ && getTotalCoverage(node) / getNodeLength(node) > maxCov) {
1424
+ destroyNodePassageMarkers(graph, node);
1425
+
1426
+ if (export && getNodeLength(node) > minLength)
1427
+ exportLongNodeSequence(outfile, node, graph, NULL, NULL, -1);
1428
+
1429
+ destroyNode(node, graph);
1430
+ }
1431
+ }
1432
+
1433
+ if (export)
1434
+ fclose(outfile);
1435
+
1436
+ concatenateGraph(graph);
1437
+ }
1438
+
1439
+ static void exportAMOSLib(FILE * outfile, Graph * graph, Category cat)
1440
+ {
1441
+ Coordinate distance = getInsertLength(graph, cat * 2);
1442
+ double variance = getInsertLength_var(graph, cat * 2);
1443
+
1444
+ if (distance == -1)
1445
+ return;
1446
+
1447
+ velvetFprintf(outfile, "{LIB\n");
1448
+ velvetFprintf(outfile, "iid:%d\n", (int) (cat + 1));
1449
+ velvetFprintf(outfile, "{DST\n");
1450
+ velvetFprintf(outfile, "mea:%lld\n", (long long) distance);
1451
+ velvetFprintf(outfile, "std:%lld\n", (long long) sqrt(variance));
1452
+ velvetFprintf(outfile, "}\n");
1453
+ velvetFprintf(outfile, "}\n");
1454
+ }
1455
+
1456
+ static void exportAMOSMarker(FILE * outfile, PassageMarkerI marker,
1457
+ Coordinate nodeLength, Coordinate start,
1458
+ Coordinate finish, int wordShift)
1459
+ {
1460
+ Coordinate sequenceStart, sequenceFinish;
1461
+
1462
+ if (getStartOffset(marker) >= finish
1463
+ || getFinishOffset(marker) > nodeLength - start)
1464
+ return;
1465
+
1466
+ sequenceStart = getPassageMarkerStart(marker);
1467
+ if (start > getStartOffset(marker)) {
1468
+ if (getPassageMarkerSequenceID(marker) > 0)
1469
+ sequenceStart += start - getStartOffset(marker);
1470
+ else
1471
+ sequenceStart -= start - getStartOffset(marker);
1472
+ }
1473
+
1474
+ sequenceFinish = getPassageMarkerFinish(marker);
1475
+ if (nodeLength - finish > getFinishOffset(marker)) {
1476
+ if (getPassageMarkerSequenceID(marker) > 0)
1477
+ sequenceFinish -=
1478
+ nodeLength - finish - getFinishOffset(marker);
1479
+ else
1480
+ sequenceFinish +=
1481
+ nodeLength - finish - getFinishOffset(marker);
1482
+ }
1483
+
1484
+ if (getPassageMarkerSequenceID(marker) > 0)
1485
+ sequenceFinish += wordShift;
1486
+ else
1487
+ sequenceStart += wordShift;
1488
+
1489
+ velvetFprintf(outfile, "{TLE\n");
1490
+ velvetFprintf(outfile, "src:%li\n", (long) getAbsolutePassMarkerSeqID(marker));
1491
+ if (getStartOffset(marker) > start)
1492
+ velvetFprintf(outfile, "off:%lld\n",
1493
+ (long long) (getStartOffset(marker) - start));
1494
+ else
1495
+ velvetFprintf(outfile, "off:0\n");
1496
+ velvetFprintf(outfile, "clr:%lld,%lld\n", (long long) sequenceStart, (long long) sequenceFinish);
1497
+ velvetFprintf(outfile, "}\n");
1498
+ }
1499
+
1500
+ static void exportAMOSShortMarker(FILE * outfile, ShortReadMarker * marker,
1501
+ ReadSet * reads, Coordinate start,
1502
+ Coordinate finish)
1503
+ {
1504
+ Coordinate offset =
1505
+ getShortReadMarkerPosition(marker) -
1506
+ getShortReadMarkerOffset(marker);
1507
+ TightString *sequence =
1508
+ getTightStringInArray (reads->tSequences, getShortReadMarkerID(marker) - 1);
1509
+
1510
+ if (getShortReadMarkerPosition(marker) == -1)
1511
+ return;
1512
+
1513
+ if (offset >= finish || offset + getLength(sequence) < start)
1514
+ return;
1515
+
1516
+ velvetFprintf(outfile, "{TLE\n");
1517
+ velvetFprintf(outfile, "src:%li\n", (long) getShortReadMarkerID(marker));
1518
+ velvetFprintf(outfile, "off:%lld\n", (long long) (offset - start));
1519
+ velvetFprintf(outfile, "clr:0,%lld\n", (long long) getLength(sequence));
1520
+ velvetFprintf(outfile, "}\n");
1521
+ }
1522
+
1523
+ static void exportAMOSReverseShortMarker(FILE * outfile,
1524
+ ShortReadMarker * marker,
1525
+ Coordinate nodeLength,
1526
+ int wordShift, ReadSet * reads,
1527
+ Coordinate start,
1528
+ Coordinate finish)
1529
+ {
1530
+ TightString *sequence =
1531
+ getTightStringInArray (reads->tSequences, getShortReadMarkerID(marker) - 1);
1532
+
1533
+ Coordinate offset =
1534
+ nodeLength - getShortReadMarkerPosition(marker) +
1535
+ getShortReadMarkerOffset(marker) - getLength(sequence) +
1536
+ wordShift;
1537
+
1538
+ if (getShortReadMarkerPosition(marker) == -1)
1539
+ return;
1540
+
1541
+ if (offset >= finish || offset + getLength(sequence) < start)
1542
+ return;
1543
+
1544
+ velvetFprintf(outfile, "{TLE\n");
1545
+ velvetFprintf(outfile, "src:%li\n", (long) getShortReadMarkerID(marker));
1546
+ velvetFprintf(outfile, "off:%lld\n", (long long) (offset - start));
1547
+ velvetFprintf(outfile, "clr:%lld,0\n", (long long) getLength(sequence));
1548
+ velvetFprintf(outfile, "}\n");
1549
+ }
1550
+
1551
+ static void exportAMOSContig(FILE * outfile, ReadSet * reads, Node * node,
1552
+ Graph * graph, Coordinate contigStart,
1553
+ Coordinate contigFinish, IDnum iid,
1554
+ IDnum internalIndex)
1555
+ {
1556
+ Coordinate start;
1557
+ char str[100];
1558
+ PassageMarkerI marker;
1559
+ ShortReadMarker *shortMarkerArray, *shortMarker;
1560
+ Coordinate index, maxIndex;
1561
+ int wordShift = getWordLength(graph) - 1;
1562
+ char *string = expandNodeFragment(node, contigStart, contigFinish,
1563
+ getWordLength(graph));
1564
+ Coordinate length = contigFinish - contigStart + wordShift;
1565
+
1566
+ velvetFprintf(outfile, "{CTG\n");
1567
+ velvetFprintf(outfile, "iid:%li\n", (long) iid);
1568
+ velvetFprintf(outfile, "eid:%li-%li\n", (long) getNodeID(node), (long) internalIndex);
1569
+
1570
+ velvetFprintf(outfile, "seq:\n");
1571
+ for (start = 0; start <= length; start += 60) {
1572
+ strncpy(str, &(string[start]), 60);
1573
+ str[60] = '\0';
1574
+ velvetFprintf(outfile, "%s\n", str);
1575
+ }
1576
+ velvetFprintf(outfile, ".\n");
1577
+
1578
+ velvetFprintf(outfile, "qlt:\n");
1579
+ for (start = 0; start <= length; start += 60) {
1580
+ strncpy(str, &(string[start]), 60);
1581
+ str[60] = '\0';
1582
+ velvetFprintf(outfile, "%s\n", str);
1583
+ }
1584
+ velvetFprintf(outfile, ".\n");
1585
+
1586
+ free(string);
1587
+
1588
+ for (marker = getMarker(node); marker != NULL_IDX;
1589
+ marker = getNextInNode(marker))
1590
+ exportAMOSMarker(outfile, marker, getNodeLength(node),
1591
+ contigStart, contigFinish, wordShift);
1592
+
1593
+ if (readStartsAreActivated(graph)) {
1594
+ shortMarkerArray = getNodeReads(node, graph);
1595
+ maxIndex = getNodeReadCount(node, graph);
1596
+ for (index = 0; index < maxIndex; index++) {
1597
+ shortMarker =
1598
+ getShortReadMarkerAtIndex(shortMarkerArray,
1599
+ index);
1600
+ exportAMOSShortMarker(outfile, shortMarker, reads,
1601
+ contigStart, contigFinish);
1602
+ }
1603
+
1604
+ shortMarkerArray = getNodeReads(getTwinNode(node), graph);
1605
+ maxIndex = getNodeReadCount(getTwinNode(node), graph);
1606
+ for (index = 0; index < maxIndex; index++) {
1607
+ shortMarker =
1608
+ getShortReadMarkerAtIndex(shortMarkerArray,
1609
+ index);
1610
+ exportAMOSReverseShortMarker(outfile, shortMarker,
1611
+ getNodeLength(node),
1612
+ wordShift, reads,
1613
+ contigStart,
1614
+ contigFinish);
1615
+ }
1616
+ }
1617
+
1618
+ velvetFprintf(outfile, "}\n");
1619
+ }
1620
+
1621
+ static void exportAMOSNode(FILE * outfile, ReadSet * reads, Node * node,
1622
+ Graph * graph)
1623
+ {
1624
+ Coordinate start = 0;
1625
+ Coordinate finish;
1626
+ GapMarker *gap;
1627
+ IDnum smallIndex = 0;
1628
+ static IDnum iid = 1;
1629
+ IDnum contigIndex = iid;
1630
+ int wordShift = getWordLength(graph) - 1;
1631
+
1632
+ for (gap = getGap(node, graph); gap; gap = getNextGap(gap)) {
1633
+ finish = getGapStart(gap);
1634
+ exportAMOSContig(outfile, reads, node, graph, start,
1635
+ finish, iid++, smallIndex++);
1636
+ start = getGapFinish(gap);
1637
+ }
1638
+
1639
+ finish = getNodeLength(node);
1640
+ exportAMOSContig(outfile, reads, node, graph, start, finish, iid++,
1641
+ smallIndex);
1642
+
1643
+ if (!getGap(node, graph))
1644
+ return;
1645
+
1646
+ start = 0;
1647
+
1648
+ velvetFprintf(outfile, "{SCF\n");
1649
+ velvetFprintf(outfile, "eid:%li\n", (long) getNodeID(node));
1650
+ for (gap = getGap(node, graph); gap; gap = getNextGap(gap)) {
1651
+ finish = getGapStart(gap);
1652
+ velvetFprintf(outfile, "{TLE\n");
1653
+ velvetFprintf(outfile, "off:%lld\n", (long long) start);
1654
+ velvetFprintf(outfile, "clr:0,%lld\n",
1655
+ (long long) (finish - start + (long long) wordShift));
1656
+ velvetFprintf(outfile, "src:%li\n", (long) contigIndex++);
1657
+ velvetFprintf(outfile, "}\n");
1658
+ start = getGapFinish(gap);
1659
+ }
1660
+ finish = getNodeLength(node);
1661
+ velvetFprintf(outfile, "{TLE\n");
1662
+ velvetFprintf(outfile, "off:%lld\n", (long long) start);
1663
+ velvetFprintf(outfile, "clr:0,%lld\n", (long long) (finish - start));
1664
+ velvetFprintf(outfile, "src:%li\n", (long) contigIndex++);
1665
+ velvetFprintf(outfile, "}\n");
1666
+
1667
+ velvetFprintf(outfile, "}\n");
1668
+ }
1669
+
1670
+ static void exportAMOSRead(FILE * outfile, TightString * tString,
1671
+ IDnum index, IDnum frg_index)
1672
+ {
1673
+ Coordinate start, finish;
1674
+ char str[100];
1675
+
1676
+ velvetFprintf(outfile, "{RED\n");
1677
+ velvetFprintf(outfile, "iid:%li\n", (long) index);
1678
+ velvetFprintf(outfile, "eid:%li\n", (long) index);
1679
+ if (frg_index > 0)
1680
+ velvetFprintf(outfile, "frg:%li\n", (long) frg_index);
1681
+
1682
+ velvetFprintf(outfile, "seq:\n");
1683
+ start = 0;
1684
+ while (start <= getLength(tString)) {
1685
+ finish = start + 60;
1686
+ readTightStringFragment(tString, start, finish, str);
1687
+ velvetFprintf(outfile, "%s\n", str);
1688
+ start = finish;
1689
+ }
1690
+ velvetFprintf(outfile, ".\n");
1691
+
1692
+ velvetFprintf(outfile, "qlt:\n");
1693
+ start = 0;
1694
+ while (start <= getLength(tString)) {
1695
+ finish = start + 60;
1696
+ readTightStringFragment(tString, start, finish, str);
1697
+ velvetFprintf(outfile, "%s\n", str);
1698
+ start = finish;
1699
+ }
1700
+ velvetFprintf(outfile, ".\n");
1701
+
1702
+ velvetFprintf(outfile, "}\n");
1703
+ }
1704
+
1705
+ void exportAMOSContigs(char *filename, Graph * graph,
1706
+ Coordinate cutoff_length, ReadSet * reads)
1707
+ {
1708
+ IDnum index;
1709
+ Category cat;
1710
+ Node *node;
1711
+ FILE *outfile;
1712
+
1713
+ velvetLog("Writing into AMOS file %s...\n", filename);
1714
+ outfile = fopen(filename, "w");
1715
+
1716
+ if (outfile == NULL)
1717
+ exitErrorf(EXIT_FAILURE, true, "Could not write to AMOS file %s",
1718
+ filename);
1719
+
1720
+ for (cat = 0; cat <= CATEGORIES; cat++)
1721
+ exportAMOSLib(outfile, graph, cat);
1722
+
1723
+ for (index = 1; index <= reads->readCount; index++) {
1724
+ if (reads->categories[index - 1] % 2 != 0 &&
1725
+ getInsertLength(graph,
1726
+ reads->categories[index - 1]) >= 0) {
1727
+ velvetFprintf(outfile, "{FRG\n");
1728
+ velvetFprintf(outfile, "lib:%d\n",
1729
+ (int) ((reads->categories[index - 1] / 2) + 1));
1730
+ velvetFprintf(outfile, "rds:%li,%li\n", (long) index,
1731
+ (long) index + 1);
1732
+ velvetFprintf(outfile, "eid:%li\n", (long) index);
1733
+ velvetFprintf(outfile, "iid:%li\n", (long) index);
1734
+ velvetFprintf(outfile, "typ:I\n");
1735
+ velvetFprintf(outfile, "}\n");
1736
+ index++;
1737
+ }
1738
+ }
1739
+
1740
+ for (index = 1; index <= reads->readCount; index++) {
1741
+ if (reads->categories[index - 1] % 2 != 0 &&
1742
+ getInsertLength(graph,
1743
+ reads->categories[index - 1]) >= 0) {
1744
+ exportAMOSRead(outfile,
1745
+ getTightStringInArray(reads->tSequences, index - 1), index,
1746
+ index);
1747
+ index++;
1748
+ exportAMOSRead(outfile,
1749
+ getTightStringInArray(reads->tSequences, index - 1), index,
1750
+ index - 1);
1751
+ } else {
1752
+ exportAMOSRead(outfile,
1753
+ getTightStringInArray(reads->tSequences, index - 1), index,
1754
+ -1);
1755
+ }
1756
+ }
1757
+
1758
+ for (index = 1; index <= nodeCount(graph); index++) {
1759
+ node = getNodeInGraph(graph, index);
1760
+
1761
+ if (node == NULL)
1762
+ continue;
1763
+
1764
+ if (getNodeLength(node) >= cutoff_length)
1765
+ exportAMOSNode(outfile, reads, node, graph);
1766
+ }
1767
+
1768
+ fclose(outfile);
1769
+
1770
+ }
1771
+
1772
+ Coordinate totalAssemblyLength(Graph * graph)
1773
+ {
1774
+ IDnum index;
1775
+ Node *node;
1776
+ Coordinate total = 0;
1777
+
1778
+ for (index = 1; index <= nodeCount(graph); index++) {
1779
+ node = getNodeInGraph(graph, index);
1780
+ if (node)
1781
+ total += getNodeLength(node);
1782
+ }
1783
+
1784
+ return total;
1785
+ }
1786
+
1787
+ IDnum usedReads(Graph * graph, Coordinate minContigLength)
1788
+ {
1789
+ IDnum res = 0;
1790
+ boolean * used = callocOrExit(sequenceCount(graph) + 1, boolean);
1791
+ IDnum nodeID, readID;
1792
+ Node * node;
1793
+ PassageMarkerI marker;
1794
+ ShortReadMarker * shortReadArray, * shortReadMarker;
1795
+ IDnum shortReadCount, shortReadIndex;
1796
+
1797
+ for(nodeID = 1; nodeID <= nodeCount(graph); nodeID++) {
1798
+ node = getNodeInGraph(graph, nodeID);
1799
+ if (node == NULL || getNodeLength(node) < minContigLength)
1800
+ continue;
1801
+
1802
+ // Long reads
1803
+ for(marker = getMarker(node); marker != NULL_IDX; marker = getNextInNode(marker)) {
1804
+ readID = getPassageMarkerSequenceID(marker);
1805
+ if (readID < 0)
1806
+ readID = -readID;
1807
+ used[readID] = true;
1808
+ }
1809
+
1810
+ // Short reads
1811
+ if (!readStartsAreActivated(graph))
1812
+ continue;
1813
+
1814
+ shortReadArray = getNodeReads(node, graph);
1815
+ shortReadCount = getNodeReadCount(node, graph);
1816
+ for (shortReadIndex = 0; shortReadIndex < shortReadCount; shortReadIndex++) {
1817
+ shortReadMarker = getShortReadMarkerAtIndex(shortReadArray, shortReadIndex);
1818
+ readID = getShortReadMarkerID(shortReadMarker);
1819
+ used[readID] = true;
1820
+ }
1821
+
1822
+ shortReadArray = getNodeReads(getTwinNode(node), graph);
1823
+ shortReadCount = getNodeReadCount(getTwinNode(node), graph);
1824
+ for (shortReadIndex = 0; shortReadIndex < shortReadCount; shortReadIndex++) {
1825
+ shortReadMarker = getShortReadMarkerAtIndex(shortReadArray, shortReadIndex);
1826
+ readID = getShortReadMarkerID(shortReadMarker);
1827
+ used[readID] = true;
1828
+ }
1829
+ }
1830
+
1831
+ for (readID = 1; readID <= sequenceCount(graph); readID++)
1832
+ if (used[readID])
1833
+ res++;
1834
+
1835
+ free(used);
1836
+
1837
+ return res;
1838
+ }
1839
+
1840
+ void logFinalStats(Graph * graph, Coordinate minContigKmerLength, char *directory)
1841
+ {
1842
+ char *logFilename =
1843
+ mallocOrExit(strlen(directory) + 100, char);
1844
+ char *statsLine =
1845
+ mallocOrExit(5000, char);
1846
+ FILE *logFile;
1847
+
1848
+ strcpy(logFilename, directory);
1849
+ strcat(logFilename, "/Log");
1850
+ logFile = fopen(logFilename, "a");
1851
+
1852
+ if (logFile == NULL)
1853
+ exitErrorf(EXIT_FAILURE, true, "Could not write to %s",
1854
+ logFilename);
1855
+
1856
+ sprintf
1857
+ (statsLine, "Final graph has %ld nodes and n50 of %lld, max %lld, total %lld, using %ld/%ld reads\n",
1858
+ (long) nodeCount(graph), (long long) n50(graph), (long long) maxLength(graph),
1859
+ (long long) totalAssemblyLength(graph), (long) usedReads(graph, minContigKmerLength),
1860
+ (long) sequenceCount(graph));
1861
+
1862
+ velvetFprintf(logFile, "%s", statsLine);
1863
+ velvetFprintf(stdout, "%s", statsLine);
1864
+
1865
+ fclose(logFile);
1866
+ free(logFilename);
1867
+ free(statsLine);
1868
+ }
1869
+
1870
+ void exportUnusedReads(Graph* graph, ReadSet * reads, Coordinate minContigKmerLength, char* directory) {
1871
+ char *outFilename =
1872
+ mallocOrExit(strlen(directory) + 100, char);
1873
+ FILE * outfile;
1874
+ boolean * used = callocOrExit(sequenceCount(graph) + 1, boolean);
1875
+ IDnum nodeID, readID;
1876
+ Node * node;
1877
+ PassageMarkerI marker;
1878
+ ShortReadMarker * shortReadArray, * shortReadMarker;
1879
+ IDnum shortReadCount, shortReadIndex;
1880
+
1881
+ strcpy(outFilename, directory);
1882
+ strcat(outFilename, "/UnusedReads.fa");
1883
+ outfile = fopen(outFilename, "w");
1884
+
1885
+ velvetLog("Printing unused reads into %s\n", outFilename);
1886
+
1887
+ for(nodeID = 1; nodeID <= nodeCount(graph); nodeID++) {
1888
+ node = getNodeInGraph(graph, nodeID);
1889
+ if (node == NULL || getNodeLength(node) < minContigKmerLength)
1890
+ continue;
1891
+
1892
+ // Long reads
1893
+ for(marker = getMarker(node); marker != NULL_IDX; marker = getNextInNode(marker)) {
1894
+ readID = getPassageMarkerSequenceID(marker);
1895
+ if (readID < 0)
1896
+ readID = -readID;
1897
+ used[readID] = true;
1898
+ }
1899
+
1900
+ // Short reads
1901
+ if (!readStartsAreActivated(graph))
1902
+ continue;
1903
+
1904
+ shortReadArray = getNodeReads(node, graph);
1905
+ shortReadCount = getNodeReadCount(node, graph);
1906
+ for (shortReadIndex = 0; shortReadIndex < shortReadCount; shortReadIndex++) {
1907
+ shortReadMarker = getShortReadMarkerAtIndex(shortReadArray, shortReadIndex);
1908
+ readID = getShortReadMarkerID(shortReadMarker);
1909
+ used[readID] = true;
1910
+ }
1911
+
1912
+ shortReadArray = getNodeReads(getTwinNode(node), graph);
1913
+ shortReadCount = getNodeReadCount(getTwinNode(node), graph);
1914
+ for (shortReadIndex = 0; shortReadIndex < shortReadCount; shortReadIndex++) {
1915
+ shortReadMarker = getShortReadMarkerAtIndex(shortReadArray, shortReadIndex);
1916
+ readID = getShortReadMarkerID(shortReadMarker);
1917
+ used[readID] = true;
1918
+ }
1919
+ }
1920
+
1921
+ for (readID = 1; readID <= sequenceCount(graph); readID++)
1922
+ if (!used[readID])
1923
+ exportTightString(outfile, getTightStringInArray(reads->tSequences, readID - 1), readID);
1924
+
1925
+ free(outFilename);
1926
+ free(used);
1927
+ fclose(outfile);
1928
+ }
1929
+
1930
+ static IDnum getReferenceCount(ReadSet * reads) {
1931
+ IDnum index;
1932
+
1933
+ for (index = 0; index < reads->readCount; index++)
1934
+ if (reads->categories[index] != REFERENCE)
1935
+ break;
1936
+
1937
+ return index;
1938
+ }
1939
+
1940
+ //////////////////////////////////////////////////////////////////////////
1941
+ // Reference identifiers
1942
+ //////////////////////////////////////////////////////////////////////////
1943
+
1944
+ typedef struct referenceCoord_st ReferenceCoord;
1945
+
1946
+ struct referenceCoord_st {
1947
+ IDnum start;
1948
+ IDnum finish;
1949
+ char * name;
1950
+ boolean positive_strand;
1951
+ } ATTRIBUTE_PACKED;
1952
+
1953
+ static ReferenceCoord * collectReferenceCoords(SequencesReader *seqReadInfo, IDnum referenceCount) {
1954
+ ReferenceCoord * refCoords = callocOrExit(referenceCount, ReferenceCoord);
1955
+ IDnum refIndex = 0;
1956
+ if (seqReadInfo->m_bIsBinary) {
1957
+ velvetLog("Creating placeholder reference headers\n");
1958
+ // binary seqs does not have reference header so a placeholder is created
1959
+ do {
1960
+ refCoords[refIndex].name = callocOrExit(sizeof("PLACEHLDR.%ld PLACEHOLDER000") + 20, char);
1961
+ sprintf(refCoords[refIndex].name, "PLACEHLDR.%ld PLACEHOLDER000", (int64_t) refIndex + 1);
1962
+ refCoords[refIndex].start = 1;
1963
+ refCoords[refIndex].finish = -1;
1964
+ refCoords[refIndex].positive_strand = true;
1965
+ } while (++refIndex < referenceCount);
1966
+ } else {
1967
+ FILE * file = fopen(seqReadInfo->m_seqFilename, "r");
1968
+ char line[MAXLINE];
1969
+ char name[5000];
1970
+ Coordinate start, finish;
1971
+ long long longlongvar;
1972
+ int i;
1973
+
1974
+ while (fgets(line, MAXLINE, file)) {
1975
+ if (line[0] == '>') {
1976
+ if (strchr(line, ':')) {
1977
+ sscanf(strtok(line, ":-\r\n"), ">%s", name);
1978
+ sscanf(strtok(NULL, ":-\r\n"), "%lli", &longlongvar);
1979
+ start = longlongvar;
1980
+ sscanf(strtok(NULL, ":-\r\n"), "%lli", &longlongvar);
1981
+ finish = longlongvar;
1982
+ refCoords[refIndex].name = callocOrExit(strlen(name) + 1, char);
1983
+ if (start <= finish) {
1984
+ strcpy(refCoords[refIndex].name, name);
1985
+ refCoords[refIndex].start = start;
1986
+ refCoords[refIndex].finish = finish;
1987
+ refCoords[refIndex].positive_strand = true;
1988
+ } else {
1989
+ strcpy(refCoords[refIndex].name, name);
1990
+ refCoords[refIndex].start = finish;
1991
+ refCoords[refIndex].finish = start;
1992
+ refCoords[refIndex].positive_strand = false;
1993
+ }
1994
+ } else {
1995
+ for (i = strlen(line) - 1;
1996
+ i >= 0 && (line[i] == '\n' || line[i] == '\r'); i--) {
1997
+ line[i] = '\0';
1998
+ }
1999
+
2000
+ strcpy(name, line + 1);
2001
+ refCoords[refIndex].name = callocOrExit(strlen(name) + 1, char);
2002
+ strcpy(refCoords[refIndex].name, name);
2003
+ refCoords[refIndex].start = 1;
2004
+ refCoords[refIndex].finish = -1;
2005
+ refCoords[refIndex].positive_strand = true;
2006
+ }
2007
+ if (++refIndex == referenceCount)
2008
+ break;
2009
+ }
2010
+ }
2011
+
2012
+ fclose(file);
2013
+ }
2014
+ return refCoords;
2015
+ }
2016
+
2017
+ typedef struct refMap_st {
2018
+ IDnum start;
2019
+ IDnum finish;
2020
+ IDnum refID;
2021
+ IDnum refStart;
2022
+ IDnum refFinish;
2023
+ } ATTRIBUTE_PACKED ReferenceMapping;
2024
+
2025
+ static int compareReferenceMappings(const void * A, const void * B) {
2026
+ ReferenceMapping * refMapA = (ReferenceMapping *) A;
2027
+ ReferenceMapping * refMapB = (ReferenceMapping *) B;
2028
+
2029
+ if (refMapA->start < refMapB->start)
2030
+ return -1;
2031
+ else if (refMapA->start == refMapB->start)
2032
+ return 0;
2033
+ else
2034
+ return 1;
2035
+ }
2036
+
2037
+ static void initializeReferenceMapping(ReferenceMapping * refMap, PassageMarkerI marker, Node * node) {
2038
+ refMap->start = getStartOffset(marker);
2039
+ refMap->finish = getNodeLength(node) - getFinishOffset(marker);
2040
+ refMap->refID = getPassageMarkerSequenceID(marker);
2041
+ refMap->refStart = getPassageMarkerStart(marker);
2042
+ refMap->refFinish = getPassageMarkerFinish(marker);
2043
+ }
2044
+
2045
+ static void velvetFprintfReferenceMapping(FILE * file, ReferenceMapping * mapping, ReferenceCoord * refCoords, int wordLength) {
2046
+ ReferenceCoord * refCoord;
2047
+ Coordinate start, finish;
2048
+
2049
+ if (mapping->refID > 0)
2050
+ refCoord = &refCoords[mapping->refID - 1];
2051
+ else
2052
+ refCoord = &refCoords[-mapping->refID - 1];
2053
+
2054
+ if (mapping->refID > 0) {
2055
+ if (refCoord->positive_strand) {
2056
+ start = refCoord->start + mapping->refStart;
2057
+ finish = refCoord->start + mapping->refFinish + wordLength - 2;
2058
+ } else {
2059
+ start = refCoord->finish - mapping->refStart + wordLength - 1;
2060
+ finish = refCoord->finish - mapping->refFinish + 1;
2061
+ }
2062
+ } else {
2063
+ if (refCoord->positive_strand) {
2064
+ start = refCoord->start + mapping->refStart + wordLength - 1;
2065
+ finish = refCoord->start + mapping->refFinish + 1;
2066
+ } else {
2067
+ start = refCoord->finish - mapping->refStart;
2068
+ finish = refCoord->finish - mapping->refFinish + wordLength;
2069
+ }
2070
+ }
2071
+
2072
+ velvetFprintf(file, "%lli\t%lli\t%s\t%lli\t%lli\n",
2073
+ (long long) mapping->start + 1, (long long) mapping->finish + wordLength - 1,
2074
+ refCoord->name, (long long) start, (long long) finish);
2075
+ }
2076
+
2077
+ static void exportLongNodeMapping(FILE * outfile, Node * node, ReadSet * reads, ReferenceCoord * refCoords, int wordLength) {
2078
+ PassageMarkerI marker;
2079
+ ReferenceMapping * referenceMappings;
2080
+ IDnum index;
2081
+ IDnum referenceCount = 0;
2082
+
2083
+ // Count reference sequences
2084
+ for (marker = getMarker(node); marker != NULL_IDX; marker = getNextInNode(marker))
2085
+ if (reads->categories[getAbsolutePassMarkerSeqID(marker) - 1] == REFERENCE)
2086
+ referenceCount++;
2087
+
2088
+ // Header
2089
+ velvetFprintf(outfile, ">contig_%li\n", (long) getNodeID(node));
2090
+
2091
+ // Create table
2092
+ referenceMappings = callocOrExit(referenceCount, ReferenceMapping);
2093
+
2094
+ // Initialize table
2095
+ referenceCount = 0;
2096
+ for (marker = getMarker(node); marker != NULL_IDX; marker = getNextInNode(marker))
2097
+ if (reads->categories[getAbsolutePassMarkerSeqID(marker) - 1] == REFERENCE)
2098
+ initializeReferenceMapping(&referenceMappings[referenceCount++], marker, node);
2099
+
2100
+ // Sort table
2101
+ qsort(referenceMappings, referenceCount, sizeof(ReferenceMapping), compareReferenceMappings);
2102
+
2103
+ // Print table
2104
+ for (index = 0; index < referenceCount; index++)
2105
+ velvetFprintfReferenceMapping(outfile, &referenceMappings[index], refCoords, wordLength);
2106
+
2107
+ // Clean table
2108
+ free(referenceMappings);
2109
+ }
2110
+
2111
+ void exportLongNodeMappings(char *filename, Graph * graph, ReadSet * reads,
2112
+ Coordinate minLength, SequencesReader *seqReadInfo)
2113
+ {
2114
+ FILE * outfile;
2115
+ IDnum nodeIndex, refIndex;
2116
+ Node *node;
2117
+ ReferenceCoord * refCoords;
2118
+ IDnum referenceCount = getReferenceCount(reads);
2119
+
2120
+ if (referenceCount == 0)
2121
+ return;
2122
+
2123
+ refCoords = collectReferenceCoords(seqReadInfo, referenceCount);
2124
+
2125
+ outfile = fopen(filename, "w");
2126
+ if (outfile == NULL) {
2127
+ velvetLog("Could not write into %s, sorry\n", filename);
2128
+ return;
2129
+ } else {
2130
+ velvetLog("Writing contigs into %s...\n", filename);
2131
+ }
2132
+
2133
+ for (nodeIndex = 1; nodeIndex <= nodeCount(graph); nodeIndex++) {
2134
+ node = getNodeInGraph(graph, nodeIndex);
2135
+
2136
+ if (node == NULL || getNodeLength(node) < minLength)
2137
+ continue;
2138
+
2139
+ exportLongNodeMapping(outfile, node, reads, refCoords, getWordLength(graph));
2140
+ }
2141
+
2142
+ for (refIndex = 0; refIndex < referenceCount; refIndex++)
2143
+ free(refCoords[refIndex].name);
2144
+ free(refCoords);
2145
+ fclose(outfile);
2146
+ }
2147
+
2148
+ static void removeLowArcsFromNode(Node* node, Graph * graph, double cutoff) {
2149
+ Arc * arc, * next;
2150
+ if (node == NULL)
2151
+ return;
2152
+
2153
+ for (arc = getArc(node); arc; arc = next) {
2154
+ next = getNextArc(arc);
2155
+ if (getMultiplicity(arc) <= cutoff)
2156
+ destroyArc(arc, graph);
2157
+ }
2158
+ }
2159
+
2160
+ void removeLowArcs(Graph * graph, double cutoff) {
2161
+ velvetLog("Removing single arcs\n");
2162
+ IDnum index;
2163
+ for (index = -nodeCount(graph); index <= nodeCount(graph); index++)
2164
+ removeLowArcsFromNode(getNodeInGraph(graph, index), graph, cutoff);
2165
+
2166
+ concatenateGraph(graph);
2167
+ }