@@ -260,17 +260,17 @@ task RunSVShell {
260260
261261# String final_vcf_filename = sample_id + ".vcf.gz"
262262# String final_vcf_idx_filename = final_vcf_filename + ".tbi"
263- String pre_cleanup_vcf_filename = batch + ".annotated.vcf.gz"
264- String pre_cleanup_vcf_idx_filename = pre_cleanup_vcf_filename + ".tbi"
265- String stripy_json_filename = sample_id + ".stripy.json"
266- String stripy_tsv_filename = sample_id + ".stripy.tsv"
267- String stripy_html_filename = sample_id + ".stripy.html"
268- String stripy_vcf_filename = sample_id + ".stripy.vcf"
269- String metrics_filename = "single_sample." + batch + ".metrics.tsv"
270- String qc_filename = "sv_qc." + batch + ".tsv"
271- String ploidy_matrix_filename = batch + "_ploidy_matrix.bed.gz"
272- String ploidy_plots_filename = batch + "_ploidy_plots.tar.gz"
273- String non_genotyped_unique_depth_calls_filename = batch + ".non_genotyped_unique_depth_calls.vcf.gz"
263+ # String pre_cleanup_vcf_filename = batch + ".annotated.vcf.gz"
264+ # String pre_cleanup_vcf_idx_filename = pre_cleanup_vcf_filename + ".tbi"
265+ # String stripy_json_filename = sample_id + ".stripy.json"
266+ # String stripy_tsv_filename = sample_id + ".stripy.tsv"
267+ # String stripy_html_filename = sample_id + ".stripy.html"
268+ # String stripy_vcf_filename = sample_id + ".stripy.vcf"
269+ # String metrics_filename = "single_sample." + batch + ".metrics.tsv"
270+ # String qc_filename = "sv_qc." + batch + ".tsv"
271+ # String ploidy_matrix_filename = batch + "_ploidy_matrix.bed.gz"
272+ # String ploidy_plots_filename = batch + "_ploidy_plots.tar.gz"
273+ # String non_genotyped_unique_depth_calls_filename = batch + ".non_genotyped_unique_depth_calls.vcf.gz"
274274
275275 command <<<
276276 set -Exeuo pipefail
@@ -281,163 +281,6 @@ task RunSVShell {
281281 mkdir -p "${PWD} /wd/tmp"
282282
283283 df -h
284-
285- # jq -n \
286- # --arg batch "~{batch}" \
287- # --arg sample_id "~{sample_id}" \
288- # --arg ref_samples_list "~{ref_samples_list}" \
289- # --arg ref_ped_file "~{ref_ped_file}" \
290- # --arg genome_file "~{genome_file}" \
291- # --arg primary_contigs_list "~{primary_contigs_list}" \
292- # --arg primary_contigs_fai "~{primary_contigs_fai}" \
293- # --arg reference_fasta "~{reference_fasta}" \
294- # --arg reference_index "~{reference_index}" \
295- # --arg reference_dict "~{reference_dict}" \
296- # --arg ref_panel_vcf "~{ref_panel_vcf}" \
297- # --arg autosome_file "~{autosome_file}" \
298- # --arg allosome_file "~{allosome_file}" \
299- # --arg bam_or_cram_file "~{bam_or_cram_file}" \
300- # --arg bam_or_cram_index "~{bam_or_cram_index}" \
301- # --arg preprocessed_intervals "~{preprocessed_intervals}" \
302- # --arg manta_region_bed "~{manta_region_bed}" \
303- # --arg sd_locs_vcf "~{sd_locs_vcf}" \
304- # --arg wham_include_list_bed_file "~{wham_include_list_bed_file}" \
305- # --arg reference_bwa_alt "~{reference_bwa_alt}" \
306- # --arg reference_bwa_amb "~{reference_bwa_amb}" \
307- # --arg reference_bwa_ann "~{reference_bwa_ann}" \
308- # --arg reference_bwa_bwt "~{reference_bwa_bwt}" \
309- # --arg reference_bwa_pac "~{reference_bwa_pac}" \
310- # --arg reference_bwa_sa "~{reference_bwa_sa}" \
311- # --argjson run_vcf_qc ~{run_vcf_qc} \
312- # --arg wgd_scoring_mask "~{wgd_scoring_mask}" \
313- # --argjson min_svsize ~{min_svsize} \
314- # --arg contig_ploidy_model_tar "~{contig_ploidy_model_tar}" \
315- # --arg gcnv_model_tars_list "~{write_lines(gcnv_model_tars)}" \
316- # --arg ref_panel_bincov_matrix "~{ref_panel_bincov_matrix}" \
317- # --arg ref_pesr_disc_files_list "~{write_lines(ref_pesr_disc_files)}" \
318- # --arg ref_pesr_split_files_list "~{write_lines(ref_pesr_split_files)}" \
319- # --arg ref_pesr_sd_files_list "~{write_lines(ref_pesr_sd_files)}" \
320- # --argjson ref_copy_number_autosomal_contigs ~{ref_copy_number_autosomal_contigs} \
321- # --argjson gcnv_qs_cutoff ~{gcnv_qs_cutoff} \
322- # --arg cnmops_exclude_list "~{cnmops_exclude_list}" \
323- # --argjson matrix_qc_distance ~{matrix_qc_distance} \
324- # --arg ref_std_manta_vcf_tar "~{ref_std_manta_vcf_tar}" \
325- # --arg ref_std_scramble_vcf_tar "~{ref_std_scramble_vcf_tar}" \
326- # --arg ref_std_wham_vcf_tar "~{ref_std_wham_vcf_tar}" \
327- # --arg ref_panel_del_bed "~{ref_panel_del_bed}" \
328- # --arg ref_panel_dup_bed "~{ref_panel_dup_bed}" \
329- # --arg depth_exclude_list "~{depth_exclude_list}" \
330- # --argjson depth_exclude_overlap_fraction ~{depth_exclude_overlap_fraction} \
331- # --argjson depth_interval_overlap ~{depth_interval_overlap} \
332- # --arg depth_clustering_algorithm "~{select_first([depth_clustering_algorithm, ""])}" \
333- # --arg pesr_exclude_intervals "~{pesr_exclude_intervals}" \
334- # --argjson pesr_interval_overlap ~{pesr_interval_overlap} \
335- # --arg pesr_clustering_algorithm "~{select_first([pesr_clustering_algorithm, ""])}" \
336- # --arg cutoffs "~{cutoffs}" \
337- # --arg genotyping_rd_table "~{genotyping_rd_table}" \
338- # --arg genotyping_pe_table "~{genotyping_pe_table}" \
339- # --arg genotyping_sr_table "~{genotyping_sr_table}" \
340- # --arg bin_exclude "~{bin_exclude}" \
341- # --argjson clean_vcf_min_sr_background_fail_batches ~{clean_vcf_min_sr_background_fail_batches} \
342- # --arg clustering_config_part1 "~{clustering_config_part1}" \
343- # --arg stratification_config_part1 "~{stratification_config_part1}" \
344- # --arg clustering_config_part2 "~{clustering_config_part2}" \
345- # --arg stratification_config_part2 "~{stratification_config_part2}" \
346- # --argjson clustering_track_names "$(jq -R . < ~{write_lines(clustering_track_names)} | jq -s .)" \
347- # --argjson clustering_track_bed_files "$(jq -R . < ~{write_lines(clustering_track_bed_files)} | jq -s .)" \
348- # --arg cytobands "~{cytobands}" \
349- # --arg mei_bed "~{mei_bed}" \
350- # --argjson max_shard_size_resolve ~{max_shard_size_resolve} \
351- # --arg chr_x "~{chr_x}" \
352- # --arg chr_y "~{chr_y}" \
353- # --arg protein_coding_gtf "~{protein_coding_gtf}" \
354- # --arg noncoding_bed "~{noncoding_bed}" \
355- # --argjson annotation_sv_per_shard ~{annotation_sv_per_shard} \
356- # --arg external_af_ref_bed "~{select_first([external_af_ref_bed, ""])}" \
357- # --arg external_af_ref_bed_prefix "~{select_first([external_af_ref_bed_prefix, ""])}" \
358- # --argjson external_af_population "$(jq -R . < ~{write_lines(select_first([external_af_population, []]))} | jq -s .)" \
359- # --argjson min_pe_cpx ~{min_pe_cpx} \
360- # --argjson min_pe_ctx ~{min_pe_ctx} \
361- # --arg gq_recalibrator_model_file "~{gq_recalibrator_model_file}" \
362- # --argjson recalibrate_gq_args "$(jq -R . < ~{write_lines(recalibrate_gq_args)} | jq -s .)" \
363- # --argjson genome_tracks "$(jq -R . < ~{write_lines(genome_tracks)} | jq -s .)" \
364- # --argjson no_call_rate_cutoff ~{no_call_rate_cutoff} \
365- # --arg sl_cutoff_table "~{sl_cutoff_table}" \
366- # --arg sl_filter_args "~{select_first([sl_filter_args, ""])}" \
367- # --arg qc_definitions "~{qc_definitions}" \
368- # --arg ref_panel_median_cov "~{ref_panel_median_cov}" \
369- # --arg manta_region_bed_index "~{manta_region_bed_index}" \
370- # --arg HERVK_reference "~{HERVK_reference}" \
371- # --arg LINE1_reference "~{LINE1_reference}" \
372- # --arg intron_reference "~{intron_reference}" \
373- # --arg outlier_samples_list "~{outlier_samples_list}" \
374- # --arg par_bed "~{par_bed}" \
375- # --argjson run_sampleevidence_metrics ~{run_sampleevidence_metrics} \
376- # --arg sample_bincov_matrix "~{sample_bincov_matrix}" \
377- # --arg sample_bincov_matrix_idx "~{sample_bincov_matrix_idx}" \
378- # --arg PE_metrics "~{PE_metrics}" \
379- # --arg SR_metrics "~{SR_metrics}" \
380- # --arg rmsk "~{rmsk}" \
381- # --arg segdups "~{segdups}" \
382- # --arg genotype_pesr_depth_sepcutoff "~{genotype_pesr_depth_sepcutoff}" \
383- # --arg genotype_pesr_pesr_sepcutoff "~{genotype_pesr_pesr_sepcutoff}" \
384- # --arg genotype_depth_depth_sepcutoff "~{genotype_depth_depth_sepcutoff}" \
385- # --arg genotype_depth_pesr_sepcutoff "~{genotype_depth_pesr_sepcutoff}" \
386- # --argjson genotyping_n_per_split ~{genotyping_n_per_split} \
387- # --argjson n_RD_genotype_bins ~{n_RD_genotype_bins} \
388- # --argjson clean_vcf1b_records_per_shard ~{clean_vcf1b_records_per_shard} \
389- # --argjson clean_vcf5_records_per_shard ~{clean_vcf5_records_per_shard} \
390- # --argjson clean_vcf_max_shards_per_chrom_clean_vcf_step1 ~{clean_vcf_max_shards_per_chrom_clean_vcf_step1} \
391- # --argjson clean_vcf_min_records_per_shard_clean_vcf_step1 ~{clean_vcf_min_records_per_shard_clean_vcf_step1} \
392- # --argjson clean_vcf_random_seed ~{clean_vcf_random_seed} \
393- # --argjson clean_vcf_samples_per_clean_vcf_step2_shard ~{clean_vcf_samples_per_clean_vcf_step2_shard} \
394- # --argjson "RefineComplexVariants.n_per_split" ~{refine_complex_variants_n_per_split} \
395- # '$ARGS.named | with_entries(select(.value != "" and .value != null))' > "${SV_SHELL_BASE_DIR}/single_sample_pipeline_inputs.json"
396- #
397- # bash /opt/sv_shell/single_sample_pipeline.sh \
398- # "${SV_SHELL_BASE_DIR}/single_sample_pipeline_inputs.json" \
399- # "${SV_SHELL_BASE_DIR}/single_sample_pipeline_outputs.json"
400-
401- # echo "----------------------"
402- # echo "${PWD}"
403- # cp "${SV_SHELL_BASE_DIR}/single_sample_pipeline_inputs.json" "${BASE_DIR}/"
404- # cp "${SV_SHELL_BASE_DIR}/single_sample_pipeline_outputs.json" "${BASE_DIR}/"
405- # ls
406- #
407- # final_vcf_path=$(jq -r '.final_vcf' "${BASE_DIR}/single_sample_pipeline_outputs.json")
408- # mv "${final_vcf_path}" "${BASE_DIR}/~{final_vcf_filename}"
409- # mv "${final_vcf_path}.tbi" "${BASE_DIR}/~{final_vcf_idx_filename}"
410- #
411- # pre_cleanup_vcf_path=$(jq -r '.pre_cleanup_vcf' "${BASE_DIR}/single_sample_pipeline_outputs.json")
412- # mv "${pre_cleanup_vcf_path}" "${BASE_DIR}/~{pre_cleanup_vcf_filename}"
413- # mv "${pre_cleanup_vcf_path}.tbi" "${BASE_DIR}/~{pre_cleanup_vcf_idx_filename}"
414- #
415- # stripy_json_path=$(jq -r '.stripy_json_output' "${BASE_DIR}/single_sample_pipeline_outputs.json")
416- # mv "${stripy_json_path}" "${BASE_DIR}/~{stripy_json_filename}"
417- #
418- # stripy_tsv_path=$(jq -r '.stripy_tsv_output' "${BASE_DIR}/single_sample_pipeline_outputs.json")
419- # mv "${stripy_tsv_path}" "${BASE_DIR}/~{stripy_tsv_filename}"
420- #
421- # stripy_html_path=$(jq -r '.stripy_html_output' "${BASE_DIR}/single_sample_pipeline_outputs.json")
422- # mv "${stripy_html_path}" "${BASE_DIR}/~{stripy_html_filename}"
423- #
424- # stripy_vcf_path=$(jq -r '.stripy_vcf_output' "${BASE_DIR}/single_sample_pipeline_outputs.json")
425- # mv "${stripy_vcf_path}" "${BASE_DIR}/~{stripy_vcf_filename}"
426- #
427- # metrics_path=$(jq -r '.metrics_file' "${BASE_DIR}/single_sample_pipeline_outputs.json")
428- # mv "${metrics_path}" "${BASE_DIR}/~{metrics_filename}"
429- #
430- # qc_path=$(jq -r '.qc_file' "${BASE_DIR}/single_sample_pipeline_outputs.json")
431- # mv "${qc_path}" "${BASE_DIR}/~{qc_filename}"
432- #
433- # ploidy_matrix_path=$(jq -r '.ploidy_matrix' "${BASE_DIR}/single_sample_pipeline_outputs.json")
434- # mv "${ploidy_matrix_path}" "${BASE_DIR}/~{ploidy_matrix_filename}"
435- #
436- # ploidy_plots_path=$(jq -r '.ploidy_plots' "${BASE_DIR}/single_sample_pipeline_outputs.json")
437- # mv "${ploidy_plots_path}" "${BASE_DIR}/~{ploidy_plots_filename}"
438- #
439- # non_genotyped_path=$(jq -r '.non_genotyped_unique_depth_calls' "${BASE_DIR}/single_sample_pipeline_outputs.json")
440- # mv "${non_genotyped_path}" "${BASE_DIR}/~{non_genotyped_unique_depth_calls_filename}"
441284 >>>
442285
443286 output {
0 commit comments