slurm-2557981.out 31 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562
  1. WARNING: While bind mounting '/mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25:/mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25': destination is already in the mount point list
  2. [COMMAND] /opt/bin/run_clairs --tumor_bam_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam --normal_bam_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/norm/CHAHA_norm_hs1.bam --ref_fn /home/t_steimle/ref/hs1/chm13v2.0.fa --threads 40 --platform ont_r10_dorado_sup_5khz_ssrs --output_dir /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25 --region chr22:1-51324926 --sample_name CHAHA_diag --include_all_ctgs --print_germline_calls --enable_indel_calling --enable_clair3_germline_output --use_longphase_for_intermediate_haplotagging True
  3. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs
  4. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp
  5. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/split_beds
  6. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/candidates
  7. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/pileup_tensor_can
  8. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/fa_tensor_can
  9. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/vcf_output
  10. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/tmp_vcf_output
  11. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/clair3_log
  12. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/phased_output
  13. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/vcf
  14. [INFO] --include_all_ctgs enabled
  15. [INFO] Call variants in contigs: chr22
  16. [INFO] Number of chunks for each contig: 11
  17. [INFO] CALLER VERSION: 0.4.4
  18. [INFO] NORMAL BAM FILE PATH: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/norm/CHAHA_norm_hs1.bam
  19. [INFO] TUMOR BAM FILE PATH: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam
  20. [INFO] REFERENCE FILE PATH: /home/t_steimle/ref/hs1/chm13v2.0.fa
  21. [INFO] PLATFORM: ont_r10_dorado_sup_5khz_ssrs
  22. [INFO] THREADS: 40
  23. [INFO] OUTPUT FOLDER: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25
  24. [INFO] OUTPUT VCF PATH: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/output.vcf.gz
  25. [INFO] PILEUP MODEL PATH: /opt/conda/envs/clairs/bin/clairs_models/ont_r10_dorado_sup_5khz_ssrs/pileup.pkl
  26. [INFO] FULL-ALIGNMENT MODEL PATH: /opt/conda/envs/clairs/bin/clairs_models/ont_r10_dorado_sup_5khz_ssrs/full_alignment.pkl
  27. [INFO] BED FILE PATH: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/region.bed
  28. [INFO] GENOTYPING MODE VCF FILE PATH: None
  29. [INFO] HYBRID MODE VCF FILE PATH: None
  30. [INFO] REGION FOR CALLING: chr22:1-51324926
  31. [INFO] CONTIGS FOR CALLING: None
  32. [INFO] CONDA BINARY PREFIX: /opt/conda/envs/clairs
  33. [INFO] SAMTOOLS BINARY PATH: samtools
  34. [INFO] PYTHON BINARY PATH: python3
  35. [INFO] PYPY BINARY PATH: pypy3
  36. [INFO] PARALLEL BINARY PATH: parallel
  37. [INFO] LONGPHASE BINARY PATH: /opt/conda/envs/clairs/bin/longphase
  38. [INFO] CHUNK SIZE: 5000000
  39. [INFO] SNV MINIMUM AF: 0.05
  40. [INFO] SNV MINIMUM QUAL: 8
  41. [INFO] INDEL MINIMUM AF: 0.1
  42. [INFO] INDEL PILEUP MODEL PATH: /opt/conda/envs/clairs/bin/clairs_models/ont_r10_dorado_sup_5khz_ssrs/indel/pileup.pkl
  43. [INFO] INDEL FULL-ALIGNMENT MODEL PATH: /opt/conda/envs/clairs/bin/clairs_models/ont_r10_dorado_sup_5khz_ssrs/indel/full_alignment.pkl
  44. [INFO] INDEL MINIMUM QUAL: 8
  45. [INFO] NORMAL VCF FILE PATH: None
  46. [INFO] DISABLE PHASING: False
  47. [INFO] ENABLE DRY RUN: False
  48. [INFO] ENABLE INDEL CALLING: True
  49. [INFO] ENABLE PRINTING REFERENCE CALLS: False
  50. [INFO] ENABLE PRINTING GERMLINE CALLS: True
  51. [INFO] ENABLE INCLUDING ALL CTGS FOR CALLING: True
  52. [INFO] ENABLE REMOVING INTERMEDIATE FILES: False
  53. [INFO] Call Germline Variants in Normal BAM using Clair3
  54. [INFO] RUN THE FOLLOWING COMMAND:
  55. ( /opt/conda/envs/clairs/bin/run_clair3.sh --bam_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/norm/CHAHA_norm_hs1.bam --ref_fn /home/t_steimle/ref/hs1/chm13v2.0.fa --model_path /opt/conda/envs/clairs/bin/clairs_models/clair3_models/r1041_e82_400bps_sup_v420 --platform ont --threads 40 --output /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output --ctg_name=chr22 --samtools=samtools --pypy=pypy3 --python=python3 --min_coverage=4 --snp_min_af=0.08 --indel_min_af=0.15 --longphase_for_phasing ) 2>&1 | tee /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/clair3_log/1_CLAIR3_NORMAL.log
  56. [INFO] CLAIR3 VERSION: v1.0.8
  57. [INFO] BAM FILE PATH: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/norm/CHAHA_norm_hs1.bam
  58. [INFO] REFERENCE FILE PATH: /home/t_steimle/ref/hs1/chm13v2.0.fa
  59. [INFO] MODEL PATH: /opt/conda/envs/clairs/bin/clairs_models/clair3_models/r1041_e82_400bps_sup_v420
  60. [INFO] OUTPUT FOLDER: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output
  61. [INFO] PLATFORM: ont
  62. [INFO] THREADS: 40
  63. [INFO] BED FILE PATH: EMPTY
  64. [INFO] VCF FILE PATH: EMPTY
  65. [INFO] CONTIGS: chr22
  66. [INFO] CONDA PREFIX:
  67. [INFO] SAMTOOLS PATH: samtools
  68. [INFO] PYTHON PATH: python3
  69. [INFO] PYPY PATH: pypy3
  70. [INFO] PARALLEL PATH: parallel
  71. [INFO] WHATSHAP PATH: whatshap
  72. [INFO] LONGPHASE PATH: /opt/conda/envs/clairs/bin/longphase
  73. [INFO] CHUNK SIZE: 5000000
  74. [INFO] FULL ALIGN PROPORTION: 0.7
  75. [INFO] FULL ALIGN REFERENCE PROPORTION: 0.1
  76. [INFO] PHASING PROPORTION: 0.7
  77. [INFO] MINIMUM MQ: 5
  78. [INFO] MINIMUM COVERAGE: 4
  79. [INFO] SNP AF THRESHOLD: 0.08
  80. [INFO] INDEL AF THRESHOLD: 0.15
  81. [INFO] BASE ERROR IN GVCF: 0.001
  82. [INFO] GQ BIN SIZE IN GVCF: 5
  83. [INFO] ENABLE FILEUP ONLY CALLING: False
  84. [INFO] ENABLE FAST MODE CALLING: False
  85. [INFO] ENABLE CALLING SNP CANDIDATES ONLY: False
  86. [INFO] ENABLE PRINTING REFERENCE CALLS: False
  87. [INFO] ENABLE OUTPUT GVCF: False
  88. [INFO] ENABLE HAPLOID PRECISE MODE: False
  89. [INFO] ENABLE HAPLOID SENSITIVE MODE: False
  90. [INFO] ENABLE INCLUDE ALL CTGS CALLING: False
  91. [INFO] ENABLE NO PHASING FOR FULL ALIGNMENT: False
  92. [INFO] ENABLE REMOVING INTERMEDIATE FILES: False
  93. [INFO] ENABLE LONGPHASE FOR INTERMEDIATE VCF PHASING: True
  94. [INFO] ENABLE PHASING FINAL VCF OUTPUT USING WHATSHAP: False
  95. [INFO] ENABLE PHASING FINAL VCF OUTPUT USING LONGPHASE: False
  96. [INFO] ENABLE HAPLOTAGGING FINAL BAM: False
  97. [INFO] ENABLE LONG INDEL CALLING: False
  98. [INFO] ENABLE C_IMPLEMENT: True
  99. + /opt/conda/envs/clairs/bin/scripts/clair3_c_impl.sh --bam_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/norm/CHAHA_norm_hs1.bam --ref_fn /home/t_steimle/ref/hs1/chm13v2.0.fa --threads 40 --model_path /opt/conda/envs/clairs/bin/clairs_models/clair3_models/r1041_e82_400bps_sup_v420 --platform ont --output /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output --bed_fn=EMPTY --vcf_fn=EMPTY --ctg_name=chr22 --sample_name=SAMPLE --chunk_num=0 --chunk_size=5000000 --samtools=samtools --python=python3 --pypy=pypy3 --parallel=parallel --whatshap=whatshap --qual=2 --var_pct_full=0.7 --ref_pct_full=0.1 --var_pct_phasing=0.7 --snp_min_af=0.08 --indel_min_af=0.15 --min_mq=5 --min_coverage=4 --min_contig_size=0 --pileup_only=False --gvcf=False --base_err=0.001 --gq_bin_size=5 --fast_mode=False --call_snp_only=False --print_ref_calls=False --haploid_precise=False --haploid_sensitive=False --include_all_ctgs=False --no_phasing_for_fa=False --pileup_model_prefix=pileup --fa_model_prefix=full_alignment --remove_intermediate_dir=False --enable_phasing=False --enable_long_indel=False --keep_iupac_bases=False --use_gpu=False --longphase_for_phasing=True --longphase=/opt/conda/envs/clairs/bin/longphase --use_whatshap_for_intermediate_phasing=True --use_longphase_for_intermediate_phasing=True --use_whatshap_for_final_output_phasing=False --use_longphase_for_final_output_phasing=False --use_whatshap_for_final_output_haplotagging=False
  100. [INFO] Check environment variables
  101. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/log
  102. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/tmp/pileup_output
  103. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/tmp/merge_output
  104. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/tmp/phase_output
  105. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/tmp/gvcf_tmp_output
  106. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/tmp/full_alignment_output
  107. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/tmp/phase_output/phase_vcf
  108. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/tmp/phase_output/phase_bam
  109. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/tmp/full_alignment_output/candidate_bed
  110. [INFO] Call variant in contigs: chr22
  111. [INFO] Chunk number for each contig: 11
  112. [INFO] 1/7 Call variants using pileup model
  113. Calling variants ...
  114. Total processed positions in chr22 (chunk 2/11) : 47403
  115. Total time elapsed: 76.59 s
  116. Calling variants ...
  117. Total processed positions in chr22 (chunk 3/11) : 53800
  118. Total time elapsed: 78.51 s
  119. Calling variants ...
  120. Total processed positions in chr22 (chunk 4/11) : 55146
  121. Total time elapsed: 84.17 s
  122. Calling variants ...
  123. Total processed positions in chr22 (chunk 1/11) : 54744
  124. Total time elapsed: 91.37 s
  125. Calling variants ...
  126. Total processed positions in chr22 (chunk 7/11) : 77013
  127. Total time elapsed: 103.88 s
  128. Calling variants ...
  129. Total processed positions in chr22 (chunk 9/11) : 78760
  130. Total time elapsed: 108.34 s
  131. Calling variants ...
  132. Total processed positions in chr22 (chunk 10/11) : 84773
  133. Total time elapsed: 110.66 s
  134. Calling variants ...
  135. Total processed positions in chr22 (chunk 11/11) : 85609
  136. Total time elapsed: 111.64 s
  137. Calling variants ...
  138. Total processed positions in chr22 (chunk 6/11) : 87769
  139. Total time elapsed: 114.11 s
  140. Calling variants ...
  141. Total processed positions in chr22 (chunk 5/11) : 86212
  142. Total time elapsed: 115.06 s
  143. Calling variants ...
  144. Total processed positions in chr22 (chunk 8/11) : 84558
  145. Total time elapsed: 117.46 s
  146. real 2m3.931s
  147. user 18m5.961s
  148. sys 0m48.172s
  149. [INFO] 2/7 Select heterozygous SNP variants for Whatshap phasing and haplotagging
  150. [INFO] Select heterozygous pileup variants exceeding phasing quality cutoff 13
  151. [INFO] Total heterozygous SNP positions selected: chr22: 46311
  152. real 0m2.154s
  153. user 0m2.043s
  154. sys 0m0.098s
  155. [INFO] 3/7 Phase VCF file using LongPhase
  156. LongPhase Ver 1.7
  157. --- File Parameter ---
  158. SNP File : /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/tmp/phase_output/phase_vcf/chr22.vcf
  159. SV File :
  160. MOD File :
  161. REF File : /home/t_steimle/ref/hs1/chm13v2.0.fa
  162. Output Prefix : /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/tmp/phase_output/phase_vcf/phased_chr22
  163. Generate Dot : False
  164. BAM File : /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/norm/CHAHA_norm_hs1.bam
  165. --- Phasing Parameter ---
  166. Seq Platform : ONT
  167. Phase Indel : False
  168. Distance Threshold : 300000
  169. Connect Adjacent : 20
  170. Edge Threshold : 0.7
  171. Mapping Quality : 1
  172. Variant Confidence : 0.75
  173. ReadTag Confidence : 0.65
  174. parsing VCF ... 0s
  175. parsing SV VCF ... 0s
  176. parsing Meth VCF ... 0s
  177. reading reference ... 1s
  178. (chr22,5s)
  179. parsing total: 5s
  180. merge results ... 0s
  181. writeResult SNP ... 0s
  182. total process: 6s
  183. real 0m6.434s
  184. user 0m13.166s
  185. sys 0m0.864s
  186. [INFO] 5/7 Select candidates for full-alignment calling
  187. [INFO] Set variants quality cutoff 19.0
  188. [INFO] Set reference calls quality cutoff 12.0
  189. [INFO] Low quality reference calls to be processed in chr22: 67750
  190. [INFO] Low quality variants to be processed in chr22: 82189
  191. real 0m2.278s
  192. user 0m2.071s
  193. sys 0m0.173s
  194. [INFO] 6/7 Call low-quality variants using full-alignment model
  195. Calling variants ...
  196. Total processed positions in chr22 (chunk 12/15) : 10000
  197. Total time elapsed: 72.79 s
  198. Calling variants ...
  199. Total processed positions in chr22 (chunk 4/15) : 10000
  200. Total time elapsed: 73.40 s
  201. Calling variants ...
  202. Total processed positions in chr22 (chunk 13/15) : 10000
  203. Total time elapsed: 73.92 s
  204. Calling variants ...
  205. Total processed positions in chr22 (chunk 5/15) : 10000
  206. Total time elapsed: 74.41 s
  207. Calling variants ...
  208. Total processed positions in chr22 (chunk 8/15) : 10000
  209. Total time elapsed: 74.48 s
  210. Calling variants ...
  211. Total processed positions in chr22 (chunk 9/15) : 10000
  212. Total time elapsed: 74.94 s
  213. Calling variants ...
  214. Total processed positions in chr22 (chunk 10/15) : 10000
  215. Total time elapsed: 75.68 s
  216. Calling variants ...
  217. Total processed positions in chr22 (chunk 11/15) : 10000
  218. Total time elapsed: 76.15 s
  219. Calling variants ...
  220. Total processed positions in chr22 (chunk 14/15) : 10000
  221. Total time elapsed: 76.72 s
  222. Calling variants ...
  223. Total processed positions in chr22 (chunk 1/15) : 10000
  224. Total time elapsed: 77.61 s
  225. Calling variants ...
  226. Total processed positions in chr22 (chunk 2/15) : 10000
  227. Total time elapsed: 78.09 s
  228. Calling variants ...
  229. Total processed positions in chr22 (chunk 6/15) : 10000
  230. Total time elapsed: 78.83 s
  231. Calling variants ...
  232. Total processed positions in chr22 (chunk 3/15) : 10000
  233. Total time elapsed: 79.62 s
  234. Calling variants ...
  235. Total processed positions in chr22 (chunk 15/15) : 9939
  236. Total time elapsed: 81.12 s
  237. Calling variants ...
  238. Total processed positions in chr22 (chunk 7/15) : 10000
  239. Total time elapsed: 88.00 s
  240. real 1m31.215s
  241. user 18m41.810s
  242. sys 1m11.725s
  243. [INFO] 7/7 Merge pileup VCF and full-alignment VCF
  244. [INFO] Pileup variants processed in chr22: 35275
  245. [INFO] Full-alignment variants processed in chr22: 85432
  246. real 0m2.993s
  247. user 0m3.163s
  248. sys 0m0.172s
  249. [INFO] Finish calling, output file: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/merge_output.vcf.gz
  250. real 4m0.719s
  251. user 37m18.840s
  252. sys 2m2.204s
  253. [INFO] Call Germline Variant in Tumor BAM using Clair3
  254. [INFO] RUN THE FOLLOWING COMMAND:
  255. ( /opt/conda/envs/clairs/bin/run_clair3.sh --bam_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam --ref_fn /home/t_steimle/ref/hs1/chm13v2.0.fa --model_path /opt/conda/envs/clairs/bin/clairs_models/clair3_models/r1041_e82_400bps_sup_v420 --platform ont --threads 40 --output /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output --ctg_name=chr22 --samtools=samtools --pypy=pypy3 --python=python3 --min_coverage=4 --snp_min_af=0.08 --indel_min_af=0.15 --longphase_for_phasing ) 2>&1 | tee /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/clair3_log/2_CLAIR3_TUMOR.log
  256. [INFO] CLAIR3 VERSION: v1.0.8
  257. [INFO] BAM FILE PATH: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam
  258. [INFO] REFERENCE FILE PATH: /home/t_steimle/ref/hs1/chm13v2.0.fa
  259. [INFO] MODEL PATH: /opt/conda/envs/clairs/bin/clairs_models/clair3_models/r1041_e82_400bps_sup_v420
  260. [INFO] OUTPUT FOLDER: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output
  261. [INFO] PLATFORM: ont
  262. [INFO] THREADS: 40
  263. [INFO] BED FILE PATH: EMPTY
  264. [INFO] VCF FILE PATH: EMPTY
  265. [INFO] CONTIGS: chr22
  266. [INFO] CONDA PREFIX:
  267. [INFO] SAMTOOLS PATH: samtools
  268. [INFO] PYTHON PATH: python3
  269. [INFO] PYPY PATH: pypy3
  270. [INFO] PARALLEL PATH: parallel
  271. [INFO] WHATSHAP PATH: whatshap
  272. [INFO] LONGPHASE PATH: /opt/conda/envs/clairs/bin/longphase
  273. [INFO] CHUNK SIZE: 5000000
  274. [INFO] FULL ALIGN PROPORTION: 0.7
  275. [INFO] FULL ALIGN REFERENCE PROPORTION: 0.1
  276. [INFO] PHASING PROPORTION: 0.7
  277. [INFO] MINIMUM MQ: 5
  278. [INFO] MINIMUM COVERAGE: 4
  279. [INFO] SNP AF THRESHOLD: 0.08
  280. [INFO] INDEL AF THRESHOLD: 0.15
  281. [INFO] BASE ERROR IN GVCF: 0.001
  282. [INFO] GQ BIN SIZE IN GVCF: 5
  283. [INFO] ENABLE FILEUP ONLY CALLING: False
  284. [INFO] ENABLE FAST MODE CALLING: False
  285. [INFO] ENABLE CALLING SNP CANDIDATES ONLY: False
  286. [INFO] ENABLE PRINTING REFERENCE CALLS: False
  287. [INFO] ENABLE OUTPUT GVCF: False
  288. [INFO] ENABLE HAPLOID PRECISE MODE: False
  289. [INFO] ENABLE HAPLOID SENSITIVE MODE: False
  290. [INFO] ENABLE INCLUDE ALL CTGS CALLING: False
  291. [INFO] ENABLE NO PHASING FOR FULL ALIGNMENT: False
  292. [INFO] ENABLE REMOVING INTERMEDIATE FILES: False
  293. [INFO] ENABLE LONGPHASE FOR INTERMEDIATE VCF PHASING: True
  294. [INFO] ENABLE PHASING FINAL VCF OUTPUT USING WHATSHAP: False
  295. [INFO] ENABLE PHASING FINAL VCF OUTPUT USING LONGPHASE: False
  296. [INFO] ENABLE HAPLOTAGGING FINAL BAM: False
  297. [INFO] ENABLE LONG INDEL CALLING: False
  298. [INFO] ENABLE C_IMPLEMENT: True
  299. + /opt/conda/envs/clairs/bin/scripts/clair3_c_impl.sh --bam_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam --ref_fn /home/t_steimle/ref/hs1/chm13v2.0.fa --threads 40 --model_path /opt/conda/envs/clairs/bin/clairs_models/clair3_models/r1041_e82_400bps_sup_v420 --platform ont --output /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output --bed_fn=EMPTY --vcf_fn=EMPTY --ctg_name=chr22 --sample_name=SAMPLE --chunk_num=0 --chunk_size=5000000 --samtools=samtools --python=python3 --pypy=pypy3 --parallel=parallel --whatshap=whatshap --qual=2 --var_pct_full=0.7 --ref_pct_full=0.1 --var_pct_phasing=0.7 --snp_min_af=0.08 --indel_min_af=0.15 --min_mq=5 --min_coverage=4 --min_contig_size=0 --pileup_only=False --gvcf=False --base_err=0.001 --gq_bin_size=5 --fast_mode=False --call_snp_only=False --print_ref_calls=False --haploid_precise=False --haploid_sensitive=False --include_all_ctgs=False --no_phasing_for_fa=False --pileup_model_prefix=pileup --fa_model_prefix=full_alignment --remove_intermediate_dir=False --enable_phasing=False --enable_long_indel=False --keep_iupac_bases=False --use_gpu=False --longphase_for_phasing=True --longphase=/opt/conda/envs/clairs/bin/longphase --use_whatshap_for_intermediate_phasing=True --use_longphase_for_intermediate_phasing=True --use_whatshap_for_final_output_phasing=False --use_longphase_for_final_output_phasing=False --use_whatshap_for_final_output_haplotagging=False
  300. [INFO] Check environment variables
  301. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/log
  302. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/tmp/pileup_output
  303. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/tmp/merge_output
  304. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/tmp/phase_output
  305. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/tmp/gvcf_tmp_output
  306. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/tmp/full_alignment_output
  307. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/tmp/phase_output/phase_vcf
  308. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/tmp/phase_output/phase_bam
  309. [INFO] Create folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/tmp/full_alignment_output/candidate_bed
  310. [INFO] Call variant in contigs: chr22
  311. [INFO] Chunk number for each contig: 11
  312. [INFO] 1/7 Call variants using pileup model
  313. Calling variants ...
  314. Total processed positions in chr22 (chunk 7/11) : 10394
  315. Total time elapsed: 45.47 s
  316. Calling variants ...
  317. Total processed positions in chr22 (chunk 9/11) : 10976
  318. Total time elapsed: 45.59 s
  319. Calling variants ...
  320. Total processed positions in chr22 (chunk 8/11) : 11033
  321. Total time elapsed: 45.89 s
  322. Calling variants ...
  323. Total processed positions in chr22 (chunk 6/11) : 11739
  324. Total time elapsed: 47.16 s
  325. Calling variants ...
  326. Total processed positions in chr22 (chunk 10/11) : 13612
  327. Total time elapsed: 49.61 s
  328. Calling variants ...
  329. Total processed positions in chr22 (chunk 11/11) : 13812
  330. Total time elapsed: 50.55 s
  331. Calling variants ...
  332. Total processed positions in chr22 (chunk 5/11) : 18299
  333. Total time elapsed: 54.44 s
  334. Calling variants ...
  335. Total processed positions in chr22 (chunk 3/11) : 33075
  336. Total time elapsed: 71.24 s
  337. Calling variants ...
  338. Total processed positions in chr22 (chunk 4/11) : 28574
  339. Total time elapsed: 73.72 s
  340. Calling variants ...
  341. Total processed positions in chr22 (chunk 2/11) : 26998
  342. Total time elapsed: 76.03 s
  343. Calling variants ...
  344. Total processed positions in chr22 (chunk 1/11) : 70814
  345. Total time elapsed: 137.65 s
  346. real 2m20.973s
  347. user 9m31.820s
  348. sys 0m35.384s
  349. [INFO] 2/7 Select heterozygous SNP variants for Whatshap phasing and haplotagging
  350. [INFO] Select heterozygous pileup variants exceeding phasing quality cutoff 15
  351. [INFO] Total heterozygous SNP positions selected: chr22: 44110
  352. real 0m1.090s
  353. user 0m0.991s
  354. sys 0m0.091s
  355. [INFO] 3/7 Phase VCF file using LongPhase
  356. LongPhase Ver 1.7
  357. --- File Parameter ---
  358. SNP File : /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/tmp/phase_output/phase_vcf/chr22.vcf
  359. SV File :
  360. MOD File :
  361. REF File : /home/t_steimle/ref/hs1/chm13v2.0.fa
  362. Output Prefix : /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/tmp/phase_output/phase_vcf/phased_chr22
  363. Generate Dot : False
  364. BAM File : /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam
  365. --- Phasing Parameter ---
  366. Seq Platform : ONT
  367. Phase Indel : False
  368. Distance Threshold : 300000
  369. Connect Adjacent : 20
  370. Edge Threshold : 0.7
  371. Mapping Quality : 1
  372. Variant Confidence : 0.75
  373. ReadTag Confidence : 0.65
  374. parsing VCF ... 0s
  375. parsing SV VCF ... 0s
  376. parsing Meth VCF ... 0s
  377. reading reference ... 1s
  378. (chr22,18s)
  379. parsing total: 18s
  380. merge results ... 0s
  381. writeResult SNP ... 0s
  382. total process: 19s
  383. real 0m19.006s
  384. user 0m47.392s
  385. sys 0m2.952s
  386. [INFO] 5/7 Select candidates for full-alignment calling
  387. [INFO] Set variants quality cutoff 21.0
  388. [INFO] Set reference calls quality cutoff 8.0
  389. [INFO] Low quality reference calls to be processed in chr22: 12609
  390. [INFO] Low quality variants to be processed in chr22: 85928
  391. real 0m1.085s
  392. user 0m0.932s
  393. sys 0m0.136s
  394. [INFO] 6/7 Call low-quality variants using full-alignment model
  395. Calling variants ...
  396. Total processed positions in chr22 (chunk 2/10) : 10000
  397. Total time elapsed: 81.37 s
  398. Calling variants ...
  399. Total processed positions in chr22 (chunk 1/10) : 10000
  400. Total time elapsed: 87.73 s
  401. Calling variants ...
  402. Total processed positions in chr22 (chunk 10/10) : 8537
  403. Total time elapsed: 91.82 s
  404. Calling variants ...
  405. Total processed positions in chr22 (chunk 4/10) : 10000
  406. Total time elapsed: 95.70 s
  407. Calling variants ...
  408. Total processed positions in chr22 (chunk 3/10) : 10000
  409. Total time elapsed: 97.11 s
  410. Calling variants ...
  411. Total processed positions in chr22 (chunk 5/10) : 10000
  412. Total time elapsed: 98.39 s
  413. Calling variants ...
  414. Total processed positions in chr22 (chunk 9/10) : 10000
  415. Total time elapsed: 98.82 s
  416. Calling variants ...
  417. Total processed positions in chr22 (chunk 8/10) : 10000
  418. Total time elapsed: 100.34 s
  419. Calling variants ...
  420. Total processed positions in chr22 (chunk 7/10) : 10000
  421. Total time elapsed: 103.07 s
  422. Calling variants ...
  423. Total processed positions in chr22 (chunk 6/10) : 10000
  424. Total time elapsed: 115.45 s
  425. real 1m58.631s
  426. user 15m21.575s
  427. sys 0m51.191s
  428. [INFO] 7/7 Merge pileup VCF and full-alignment VCF
  429. [INFO] Pileup variants processed in chr22: 37132
  430. [INFO] Full-alignment variants processed in chr22: 80741
  431. real 0m1.719s
  432. user 0m1.719s
  433. sys 0m0.142s
  434. [INFO] Finish calling, output file: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/merge_output.vcf.gz
  435. real 4m48.800s
  436. user 25m49.863s
  437. sys 1m30.517s
  438. [INFO] Select Heterozygous SNP for Phasing
  439. [INFO] RUN THE FOLLOWING COMMAND:
  440. ( parallel --joblog /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/clair3_log/parallel_1_select_hetero_snp_for_phasing.log -j 40 pypy3 /opt/bin/clairs.py select_hetero_snp_for_phasing --tumor_vcf_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_tumor_output/merge_output.vcf.gz --normal_vcf_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/clair3_normal_output/merge_output.vcf.gz --output_folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/vcf --ctg_name {1} --use_heterozygous_snp_in_normal_sample_for_intermediate_phasing True :::: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/CONTIGS ) 2>&1 | tee /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/clair3_log/1_select_hetero_snp_for_phasing.log
  441. [INFO] Total HET SNP calls selected: chr22: 61121, not found:919, not match:76, low_qual_count:0. Total normal:66656 Total tumor:62116, pro: 0.984
  442. [INFO] Phase the Tumor BAM
  443. [INFO] RUN THE FOLLOWING COMMAND:
  444. ( parallel --joblog /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/clair3_log/parallel_4_phase_tumor.log -j 40 /opt/conda/envs/clairs/bin/longphase phase -s /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/vcf/{1}.vcf -b /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam -r /home/t_steimle/ref/hs1/chm13v2.0.fa -t 40 -o /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/phased_output/tumor_phased_{1} --ont :::: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/CONTIGS && parallel -j 40 bgzip -f /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/phased_output/tumor_phased_{1}.vcf :::: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/CONTIGS ) 2>&1 | tee /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/clair3_log/4_phase_tumor.log && parallel -j 40 tabix -f -p vcf /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/phased_output/tumor_phased_{1}.vcf.gz :::: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/CONTIGS
  445. LongPhase Ver 1.7
  446. --- File Parameter ---
  447. SNP File : /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/vcf/chr22.vcf
  448. SV File :
  449. MOD File :
  450. REF File : /home/t_steimle/ref/hs1/chm13v2.0.fa
  451. Output Prefix : /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/phased_output/tumor_phased_chr22
  452. Generate Dot : False
  453. BAM File : /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam
  454. --- Phasing Parameter ---
  455. Seq Platform : ONT
  456. Phase Indel : False
  457. Distance Threshold : 300000
  458. Connect Adjacent : 20
  459. Edge Threshold : 0.7
  460. Mapping Quality : 1
  461. Variant Confidence : 0.75
  462. ReadTag Confidence : 0.65
  463. parsing VCF ... 1s
  464. parsing SV VCF ... 0s
  465. parsing Meth VCF ... 0s
  466. reading reference ... 0s
  467. (chr22,39s)
  468. parsing total: 40s
  469. merge results ... 0s
  470. writeResult SNP ... 0s
  471. total process: 41s
  472. [INFO] Haplotag the Tumor BAM
  473. [INFO] RUN THE FOLLOWING COMMAND:
  474. ( parallel --joblog /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/clair3_log/parallel_5_haplotag_tumor.log -j 40 /opt/conda/envs/clairs/bin/longphase haplotag -o /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/phased_output/tumor_{1} --reference /home/t_steimle/ref/hs1/chm13v2.0.fa --region {1} -s /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/phased_output/tumor_phased_{1}.vcf.gz -b /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam :::: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/CONTIGS ) 2>&1 | tee /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/clair3_log/5_tumor_haplotag.log && parallel -j 40 samtools index -@40 /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/phased_output/tumor_{1}.bam :::: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/CONTIGS
  475. phased SNP file: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/phased_output/tumor_phased_chr22.vcf.gz
  476. phased SV file:
  477. phased MOD file:
  478. input bam file: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam
  479. input ref file: /home/t_steimle/ref/hs1/chm13v2.0.fa
  480. output bam file: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/clair3_output/phased_output/tumor_chr22.bam
  481. number of threads: 1
  482. write log file: false
  483. log file:
  484. -------------------------------------------
  485. tag region: chr22
  486. filter mapping quality below: 1
  487. percentage threshold: 0.6
  488. tag supplementary: false
  489. -------------------------------------------
  490. parsing SNP VCF ... 1s
  491. tag read start ...
  492. chr: chr22 ... 691s
  493. tag read 692s
  494. -------------------------------------------
  495. total process time: 693s
  496. total alignment: 1020895
  497. total supplementary: 24756
  498. total secondary: 0
  499. total unmapped: 0
  500. total tag alignment: 315339
  501. total untagged: 705556
  502. [INFO] STEP 1: Extract Variant Candidates from Tumor and Normal BAMs
  503. [INFO] RUN THE FOLLOWING COMMAND:
  504. ( parallel --joblog /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/parallel_1_extract_tumor_candidates.log -C " " -j 40 pypy3 /opt/bin/clairs.py extract_pair_candidates --tumor_bam_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/CHAHA_diag_hs1.bam --normal_bam_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/norm/CHAHA_norm_hs1.bam --ref_fn /home/t_steimle/ref/hs1/chm13v2.0.fa --samtools samtools --snv_min_af 0.05 --indel_min_af 0.1 --chunk_id {2} --chunk_num {3} --ctg_name {1} --platform ont --min_coverage 4 --bed_fn /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/split_beds/{1} --candidates_folder /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/candidates --output_depth True --select_indel_candidates True --hybrid_mode_vcf_fn None --genotyping_mode_vcf_fn None :::: /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/CHUNK_LIST ) 2>&1 | tee /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/logs/1_EC.log && pypy3 /opt/bin/clairs.py concat_files --input_dir /mnt/beegfs02/scratch/t_steimle/data/wgs/CHAHA/diag/ClairS/part25/tmp/candidates --input_prefix CANDIDATES_FILE_ --output_fn CANDIDATES_FILES
  505. [INFO] chr22 chunk 0/11: Total snv candidates found: 14326, total indel candidates found: 1131