renluyao
/
high_confidence_calls_manuscript
Watch 1
Star 0
Fork 0
Code Issues 0 Pull Requests 0 Releases 0 Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
8 Commits
1 Branch
Tree: 37783e9db9
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '37783e9db9'
${ noResults }
high_confidence_calls_manus.../workflow.wdl

421 lines
11KB
Raw Blame History 

  1. import "./tasks/variantsNorm.wdl" as variantsNorm

  2. import "./tasks/extract_info.wdl" as extract_info

  3. import "./tasks/mendelian.wdl" as mendelian

  4. import "./tasks/zipIndex.wdl" as zipIndex

  5. import "./tasks/VCFrename.wdl" as VCFrename

  6. import "./tasks/mergeSister.wdl" as mergeSister

  7. import "./tasks/reformVCF.wdl" as reformVCF

  8. import "./tasks/merge.wdl" as merge

  9. import "./tasks/votes.wdl" as votes

  10. import "./tasks/bed_annotation.wdl" as bed_annotation

  11. import "./tasks/mergeVCFInfo.wdl" as mergeVCFInfo

  12. import "./tasks/VCFinfo.wdl" as VCFinfo

  13. import "./tasks/final_result.wdl" as FinalResult

  14. 

  15. workflow {{ project_name }} {

  16. 	File inputSamplesFile

  17. 	Array[Array[File]] inputSamples = read_tsv(inputSamplesFile)

  18. 	File ref_dir

  19. 	File repeat_bed

  20. 	String fasta

  21. 	String cluster_config

  22. 	String disk_size

  23. 

  24. 	scatter (quartet in inputSamples){

  25. 		call variantsNorm.variantsNorm as LCL5variantsNorm{

  26. 			input:

  27. 			vcf=quartet[0],

  28. 			ref_dir=ref_dir,

  29. 			fasta=fasta,

  30. 			sampleName=quartet[4],

  31. 			cluster_config=cluster_config,

  32. 			disk_size=disk_size

  33. 		}

  34. 		call variantsNorm.variantsNorm as LCL6variantsNorm{

  35. 			input:

  36. 			vcf=quartet[1],

  37. 			ref_dir=ref_dir,

  38. 			fasta=fasta,

  39. 			sampleName=quartet[5],

  40. 			cluster_config=cluster_config,

  41. 			disk_size=disk_size

  42. 		}

  43. 		call variantsNorm.variantsNorm as LCL7variantsNorm{

  44. 			input:

  45. 			vcf=quartet[2],

  46. 			ref_dir=ref_dir,

  47. 			fasta=fasta,

  48. 			sampleName=quartet[6],

  49. 			cluster_config=cluster_config,

  50. 			disk_size=disk_size

  51. 		}

  52. 		call variantsNorm.variantsNorm as LCL8variantsNorm{

  53. 			input:

  54. 			vcf=quartet[3],

  55. 			ref_dir=ref_dir,

  56. 			fasta=fasta,

  57. 			sampleName=quartet[7],

  58. 			cluster_config=cluster_config,

  59. 			disk_size=disk_size

  60. 		}

  61. 		call extract_info.extract_info as LCL5extract_info {

  62. 			input:

  63. 			normed_vcf=LCL5variantsNorm.normed_vcf,

  64. 			sampleName=quartet[4],

  65. 			cluster_config=cluster_config,

  66. 			disk_size=disk_size

  67. 		}

  68. 		call extract_info.extract_info as LCL6extract_info {

  69. 			input:

  70. 			normed_vcf=LCL6variantsNorm.normed_vcf,

  71. 			sampleName=quartet[5],

  72. 			cluster_config=cluster_config,

  73. 			disk_size=disk_size

  74. 		}

  75. 		call extract_info.extract_info as LCL7extract_info {

  76. 			input:

  77. 			normed_vcf=LCL7variantsNorm.normed_vcf,

  78. 			sampleName=quartet[6],

  79. 			cluster_config=cluster_config,

  80. 			disk_size=disk_size

  81. 		}

  82. 		call extract_info.extract_info as LCL8extract_info {

  83. 			input:

  84. 			normed_vcf=LCL8variantsNorm.normed_vcf,

  85. 			sampleName=quartet[8],

  86. 			cluster_config=cluster_config,

  87. 			disk_size=disk_size

  88. 		}		

  89. 		call zipIndex.zipIndex as LCL5normZip{

  90. 			input:

  91. 			vcf=LCL5extract_info.vcf_info,

  92. 			cluster_config=cluster_config,

  93. 			disk_size=disk_size

  94. 		}

  95. 		call zipIndex.zipIndex as LCL6normZip{

  96. 			input:

  97. 			vcf=LCL6extract_info.vcf_info,

  98. 			cluster_config=cluster_config,

  99. 			disk_size=disk_size		

  100. 		}

  101. 		call zipIndex.zipIndex as LCL7normZip{

  102. 			input:

  103. 			vcf=LCL7extract_info.vcf_info,

  104. 			cluster_config=cluster_config,

  105. 			disk_size=disk_size		

  106. 		}

  107. 		call zipIndex.zipIndex as LCL8normZip{

  108. 			input:

  109. 			vcf=LCL8extract_info.vcf_info,

  110. 			cluster_config=cluster_config,

  111. 			disk_size=disk_size		

  112. 		}

  113. 		call mendelian.mendelian as LCL5mendelian {

  114. 			input:

  115. 			child_vcf=LCL5variantsNorm.normed_vcf,

  116. 			LCL7_vcf=LCL7variantsNorm.normed_vcf,

  117. 			LCL8_vcf=LCL8variantsNorm.normed_vcf,

  118. 			LCL7_name=quartet[6],

  119. 			LCL8_name=quartet[7],

  120. 			child_name=quartet[4],

  121. 			ref_dir=ref_dir,

  122. 			fasta=fasta,

  123. 			cluster_config=cluster_config,

  124. 			disk_size=disk_size

  125. 		}

  126. 		call mendelian.mendelian as LCL6mendelian {

  127. 			input:

  128. 			child_vcf=LCL6variantsNorm.normed_vcf,

  129. 			LCL7_vcf=LCL7variantsNorm.normed_vcf,

  130. 			LCL8_vcf=LCL8variantsNorm.normed_vcf,

  131. 			LCL7_name=quartet[6],

  132. 			LCL8_name=quartet[7],

  133. 			child_name=quartet[5],

  134. 			ref_dir=ref_dir,

  135. 			fasta=fasta,

  136. 			cluster_config=cluster_config,

  137. 			disk_size=disk_size

  138. 		}

  139. 		call zipIndex.zipIndex as LCL5zipIndex {

  140. 			input:

  141. 			vcf=LCL5mendelian.trio_vcf,

  142. 			cluster_config=cluster_config,

  143. 			disk_size=disk_size

  144. 		}

  145. 		call zipIndex.zipIndex as LCL6zipIndex {

  146. 			input:

  147. 			vcf=LCL6mendelian.trio_vcf,

  148. 			cluster_config=cluster_config,

  149. 			disk_size=disk_size

  150. 		}		

  151. 		call VCFrename.VCFrename as LCL5VCFrename {

  152. 			input:

  153. 			trio_vcf_gz=LCL5zipIndex.vcf_gz,

  154. 			trio_vcf_idx=LCL5zipIndex.vcf_idx,

  155. 			mother_name=quartet[7],

  156. 			father_name=quartet[6],

  157. 			child_name=quartet[4],

  158. 			family_name=quartet[8],

  159. 			child="LCL5",

  160. 			cluster_config=cluster_config,

  161. 			disk_size=disk_size

  162. 		}

  163. 		call VCFrename.VCFrename as LCL6VCFrename {

  164. 			input:

  165. 			trio_vcf_gz=LCL6zipIndex.vcf_gz,

  166. 			trio_vcf_idx=LCL6zipIndex.vcf_idx,

  167. 			mother_name=quartet[7],

  168. 			father_name=quartet[6],

  169. 			child_name=quartet[5],

  170. 			family_name=quartet[8],

  171. 			child="LCL6",

  172. 			cluster_config=cluster_config,

  173. 			disk_size=disk_size

  174. 		}

  175. 		call mergeSister.mergeSister as mergeSister {

  176. 			input:

  177. 			LCL5_trio_vcf_gz=LCL5VCFrename.rename_trio_vcf_gz,

  178. 			LCL5_trio_vcf_idx=LCL5VCFrename.rename_trio_vcf_idx,

  179. 			LCL6_trio_vcf_gz=LCL6VCFrename.rename_trio_vcf_gz,

  180. 			LCL6_trio_vcf_idx=LCL6VCFrename.rename_trio_vcf_idx,

  181. 			family_name=quartet[8],

  182. 			cluster_config=cluster_config,

  183. 			disk_size=disk_size

  184. 		}

  185. 		call reformVCF.reformVCF as reformVCF {

  186. 			input:

  187. 			family_mendelian_info=mergeSister.family_mendelian_info,

  188. 			family_name=quartet[8],

  189. 			cluster_config=cluster_config,

  190. 			disk_size=disk_size			

  191. 		}

  192. 		call zipIndex.zipIndex as LCL5familyzipIndex {

  193. 			input:

  194. 			vcf=reformVCF.LCL5_family_info,

  195. 			cluster_config=cluster_config,

  196. 			disk_size=disk_size

  197. 		}

  198. 		call zipIndex.zipIndex as LCL6familyzipIndex {

  199. 			input:

  200. 			vcf=reformVCF.LCL6_family_info,

  201. 			cluster_config=cluster_config,

  202. 			disk_size=disk_size

  203. 		}

  204. 		call zipIndex.zipIndex as LCL7familyzipIndex {

  205. 			input:

  206. 			vcf=reformVCF.LCL7_family_info,

  207. 			cluster_config=cluster_config,

  208. 			disk_size=disk_size

  209. 		}

  210. 		call zipIndex.zipIndex as LCL8familyzipIndex {

  211. 			input:

  212. 			vcf=reformVCF.LCL8_family_info,

  213. 			cluster_config=cluster_config,

  214. 			disk_size=disk_size

  215. 		}		

  216. 	}

  217. 	### family info merge

  218. 	call merge.merge as LCL5merge {

  219. 		input:

  220. 		family_vcf_gz=LCL5familyzipIndex.vcf_gz,

  221. 		family_vcf_idx=LCL5familyzipIndex.vcf_idx,

  222. 		sample="LCL5",

  223. 		cluster_config=cluster_config,

  224. 		disk_size=disk_size

  225. 	}

  226. 	call votes.votes as LCL5votes{

  227. 		input:

  228. 		merged_vcf=LCL5merge.merged_vcf,

  229. 		vcf_dup=LCL5merge.vcf_dup,

  230. 		sample='LCL5',

  231. 		prefix='LCL5_consensus',

  232. 		cluster_config=cluster_config,

  233. 		disk_size=disk_size

  234. 	}	

  235. 	call merge.merge as LCL6merge {

  236. 		input:

  237. 		family_vcf_gz=LCL6familyzipIndex.vcf_gz,

  238. 		family_vcf_idx=LCL6familyzipIndex.vcf_idx,

  239. 		sample="LCL6",

  240. 		cluster_config=cluster_config,

  241. 		disk_size=disk_size

  242. 	}

  243. 	call votes.votes as LCL6votes {

  244. 		input:

  245. 		merged_vcf=LCL6merge.merged_vcf,

  246. 		vcf_dup=LCL6merge.vcf_dup,

  247. 		sample='LCL6',

  248. 		prefix='LCL6_consensus',

  249. 		cluster_config=cluster_config,

  250. 		disk_size=disk_size

  251. 	}	

  252. 	call merge.merge as LCL7merge {

  253. 		input:

  254. 		family_vcf_gz=LCL7familyzipIndex.vcf_gz,

  255. 		family_vcf_idx=LCL7familyzipIndex.vcf_idx,

  256. 		sample="LCL7",

  257. 		cluster_config=cluster_config,

  258. 		disk_size=disk_size

  259. 	}

  260. 	call votes.votes as LCL7votes {

  261. 		input:

  262. 		merged_vcf=LCL7merge.merged_vcf,

  263. 		vcf_dup=LCL7merge.vcf_dup,

  264. 		sample='LCL7',

  265. 		prefix='LCL7_consensus',

  266. 		cluster_config=cluster_config,

  267. 		disk_size=disk_size

  268. 	}	

  269. 	call merge.merge as LCL8merge {

  270. 		input:

  271. 		family_vcf_gz=LCL8familyzipIndex.vcf_gz,

  272. 		family_vcf_idx=LCL8familyzipIndex.vcf_idx,

  273. 		sample="LCL8",

  274. 		cluster_config=cluster_config,

  275. 		disk_size=disk_size

  276. 	}

  277. 	call votes.votes as LCL8votes {

  278. 		input:

  279. 		merged_vcf=LCL8merge.merged_vcf,

  280. 		vcf_dup=LCL8merge.vcf_dup,

  281. 		sample='LCL8',

  282. 		prefix='LCL8_consensus',

  283. 		cluster_config=cluster_config,

  284. 		disk_size=disk_size

  285. 	}

  286. 	### vcf original information

  287. 	call mergeVCFInfo.mergeVCFInfo as LCL5mergeVCF {

  288. 		input:

  289. 		vcf_gz=LCL5normZip.vcf_gz,

  290. 		vcf_idx=LCL5normZip.vcf_idx,

  291. 		sample='LCL5',

  292. 		cluster_config=cluster_config,

  293. 		disk_size=disk_size

  294. 	}

  295. 	call bed_annotation.bed_annotation as LCL5bedAnnotation {

  296. 		input:

  297. 		merged_vcf=LCL5mergeVCF.merged_vcf,

  298. 		merged_vcf_idx=LCL5mergeVCF.merged_vcf_idx,

  299. 		repeat_bed=repeat_bed,

  300. 		sample='LCL5',

  301. 		cluster_config=cluster_config,

  302. 		disk_size=disk_size

  303. 	}

  304. 	call VCFinfo.VCFinfo as LCL5allSampleReform {

  305. 		input:

  306. 		repeat_annotated_vcf=LCL5bedAnnotation.repeat_annotated_vcf,

  307. 		sample='LCL5',

  308. 		cluster_config=cluster_config,

  309. 		disk_size=disk_size

  310. 	}

  311. 	call FinalResult.FinalResult as LCL5FinalResult {

  312. 		input:

  313. 		extracted_info=LCL5allSampleReform.extracted_info,

  314. 		annotated_txt=LCL5votes.annotated_txt,

  315. 		prefix='LCL5',

  316. 		sample='LCL5',

  317. 		cluster_config=cluster_config,

  318. 		disk_size=disk_size,

  319. 	}

  320. 	call mergeVCFInfo.mergeVCFInfo as LCL6mergeVCF {

  321. 		input:

  322. 		vcf_gz=LCL6normZip.vcf_gz,

  323. 		vcf_idx=LCL6normZip.vcf_idx,

  324. 		sample='LCL6',

  325. 		cluster_config=cluster_config,

  326. 		disk_size=disk_size

  327. 	}

  328. 	call bed_annotation.bed_annotation as LCL6bedAnnotation {

  329. 		input:

  330. 		merged_vcf=LCL6mergeVCF.merged_vcf,

  331. 		merged_vcf_idx=LCL6mergeVCF.merged_vcf_idx,

  332. 		repeat_bed=repeat_bed,

  333. 		sample='LCL6',

  334. 		cluster_config=cluster_config,

  335. 		disk_size=disk_size

  336. 	}

  337. 	call VCFinfo.VCFinfo as LCL6allSampleReform {

  338. 		input:

  339. 		repeat_annotated_vcf=LCL6bedAnnotation.repeat_annotated_vcf,

  340. 		sample='LCL6',

  341. 		cluster_config=cluster_config,

  342. 		disk_size=disk_size

  343. 	}

  344. 	call FinalResult.FinalResult as LCL6FinalResult {

  345. 		input:

  346. 		extracted_info=LCL6allSampleReform.extracted_info,

  347. 		annotated_txt=LCL6votes.annotated_txt,

  348. 		prefix='LCL6',

  349. 		sample='LCL6',

  350. 		cluster_config=cluster_config,

  351. 		disk_size=disk_size,

  352. 	}

  353. 	call mergeVCFInfo.mergeVCFInfo as LCL7mergeVCF {

  354. 		input:

  355. 		vcf_gz=LCL7normZip.vcf_gz,

  356. 		vcf_idx=LCL7normZip.vcf_idx,

  357. 		sample='LCL7',

  358. 		cluster_config=cluster_config,

  359. 		disk_size=disk_size

  360. 	}

  361. 	call bed_annotation.bed_annotation as LCL7bedAnnotation {

  362. 		input:

  363. 		merged_vcf=LCL7mergeVCF.merged_vcf,

  364. 		merged_vcf_idx=LCL7mergeVCF.merged_vcf_idx,

  365. 		repeat_bed=repeat_bed,

  366. 		sample='LCL7',

  367. 		cluster_config=cluster_config,

  368. 		disk_size=disk_size

  369. 	}

  370. 	call VCFinfo.VCFinfo as LCL7allSampleReform {

  371. 		input:

  372. 		repeat_annotated_vcf=LCL7bedAnnotation.repeat_annotated_vcf,

  373. 		sample='LCL7',

  374. 		cluster_config=cluster_config,

  375. 		disk_size=disk_size

  376. 	}

  377. 	call FinalResult.FinalResult as LCL7FinalResult {

  378. 		input:

  379. 		extracted_info=LCL7allSampleReform.extracted_info,

  380. 		annotated_txt=LCL7votes.annotated_txt,

  381. 		prefix='LCL7',

  382. 		sample='LCL7',

  383. 		cluster_config=cluster_config,

  384. 		disk_size=disk_size,

  385. 	}

  386. 	call mergeVCFInfo.mergeVCFInfo as LCL8mergeVCF {

  387. 		input:

  388. 		vcf_gz=LCL8normZip.vcf_gz,

  389. 		vcf_idx=LCL8normZip.vcf_idx,

  390. 		sample='LCL8',

  391. 		cluster_config=cluster_config,

  392. 		disk_size=disk_size

  393. 	}

  394. 	call bed_annotation.bed_annotation as LCL8bedAnnotation {

  395. 		input:

  396. 		merged_vcf=LCL8mergeVCF.merged_vcf,

  397. 		merged_vcf_idx=LCL8mergeVCF.merged_vcf_idx,

  398. 		repeat_bed=repeat_bed,

  399. 		sample='LCL8',

  400. 		cluster_config=cluster_config,

  401. 		disk_size=disk_size

  402. 	}

  403. 	call VCFinfo.VCFinfo as LCL8allSampleReform {

  404. 		input:

  405. 		repeat_annotated_vcf=LCL8bedAnnotation.repeat_annotated_vcf,

  406. 		sample='LCL8',

  407. 		cluster_config=cluster_config,

  408. 		disk_size=disk_size

  409. 	}

  410. 	call FinalResult.FinalResult as LCL8FinalResult {

  411. 		input:

  412. 		extracted_info=LCL8allSampleReform.extracted_info,

  413. 		annotated_txt=LCL8votes.annotated_txt,

  414. 		prefix='LCL8',

  415. 		sample='LCL8',

  416. 		cluster_config=cluster_config,

  417. 		disk_size=disk_size,

  418. 	}

  419. }