Skip to content

Commit

Permalink
change test dataset
Browse files Browse the repository at this point in the history
  • Loading branch information
emmarousseau committed Aug 20, 2024
1 parent aef65a1 commit 2918fb4
Show file tree
Hide file tree
Showing 13 changed files with 1,246,448 additions and 39 deletions.
2 changes: 1 addition & 1 deletion src/rsem/rsem_calculate_expression/config.vsh.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ argument_groups:
description: Sample strand-specificity. Must be one of unstranded, forward, reverse
choices: [forward, reverse, unstranded]
- name: "--paired"
type: boolean
type: boolean_true
description: Paired-end reads or not?
- name: "--input"
type: file
Expand Down
62 changes: 59 additions & 3 deletions src/rsem/rsem_calculate_expression/script.sh
100755 → 100644
Original file line number Diff line number Diff line change
Expand Up @@ -25,11 +25,67 @@ IFS=";" read -ra input <<< $par_input
INDEX=$(find -L $meta_resources_dir/$par_index -name "*.grp" | sed 's/\.grp$//')

rsem-calculate-expression \
${par_quiet:+-q} \
${par_no_bam_output:+--no-bam-output} \
${par_sampling_for_bam:+--sampling-for-bam} \
${par_no_qualities:+--no-qualities} \
${par_alignments:+--alignments} \
${par_bowtie2:+--bowtie2} \
${par_star:+--star} \
${par_hisat2_hca:+--hisat2-hca} \
${par_append_names:+--append-names} \
${par_single_cell_prior:+--single-cell-prior} \
${par_calc_pme:+--calc-pme} \
${par_calc_ci:+--calc-ci} \
${par_phred64_quals:+--phred64-quals} \
${par_solexa_quals:+--solexa-quals} \
${par_star_gzipped_read_file:+--star-gzipped-read-file} \
${par_star_bzipped_read_file:+--star-bzipped-read-file} \
${par_star_output_genome_bam:+--star-output-genome-bam} \
${par_estimate_rspd:+--estimate-rspd} \
${par_keep_intermediate_files:+--keep-intermediate-files} \
${par_time:+--time} \
${par_run_pRSEM:+--run-pRSEM} \
${par_cap_stacked_chipseq_reads:+--cap-stacked-chipseq-reads} \
${par_sort_bam_by_read_name:+--sort-bam-by-read-name} \
${par_counts_gene:+--counts-gene "$par_counts_gene"} \
${par_counts_transcripts:+--counts-transcripts "$par_counts_transcripts"} \
${par_stat:+--stat "$par_stat"} \
${par_bam_star:+--bam-star "\$par_bam_star"} \
${par_bam_genome:+--bam-genome "$par_bam_genome"} \
${par_bam_transcript:+--bam-transcript "$par_bam_transcript"} \
${par_fai:+--fai "$par_fai"} \
${par_seed:+--seed "$par_seed"} \
${par_seed_length:+--seed-length "$par_seed_length"} \
${par_bowtie_n:+--bowtie-n "$par_bowtie_n"} \
${par_bowtie_e:+--bowtie-e "$par_bowtie_e"} \
${par_bowtie_m:+--bowtie-m "$par_bowtie_m"} \
${par_bowtie_chunkmbs:+--bowtie-chunkmbs "$par_bowtie_chunkmbs"} \
${par_bowtie2_mismatch_rate:+--bowtie2-mismatch-rate "$par_bowtie2_mismatch_rate"} \
${par_bowtie2_k:+--bowtie2-k "$par_bowtie2_k"} \
${par_bowtie2_sensitivity_level:+--bowtie2-sensitivity-level "$par_bowtie2_sensitivity_level"} \
${par_tag:+--tag "$par_tag"} \
${par_fragment_length_min:+--fragment-length-min "$par_fragment_length_min"} \
${par_fragment_length_max:+--fragment-length-max "$par_fragment_length_max"} \
${par_fragment_length_mean:+--fragment-length-mean "$par_fragment_length_mean"} \
${par_fragment_length_sd:+--fragment-length-sd "$par_fragment_length_sd"} \
${par_num_rspd_bins:+--num-rspd-bins "$par_num_rspd_bins"} \
${par_gibbs_burnin:+--gibbs-burnin "$par_gibbs_burnin"} \
${par_gibbs_number_of_samples:+--gibbs-number-of-samples "$par_gibbs_number_of_samples"} \
${par_gibbs_sampling_gap:+--gibbs-sampling-gap "$par_gibbs_sampling_gap"} \
${par_ci_credibility_level:+--ci-credibility-level "$par_ci_credibility_level"} \
${par_ci_number_of_samples_per_count_vector:+--ci-number-of-samples-per-count-vector "$par_ci_number_of_samples_per_count_vector"} \
${par_temporary_folder:+--temporary-folder "$par_temporary_folder"} \
${par_chipseq_peak_file:+--chipseq-peak-file "$par_chipseq_peak_file"} \
${par_chipseq_target_read_files:+--chipseq-target-read-files "$par_chipseq_target_read_files"} \
${par_chipseq_control_read_files:+--chipseq-control-read-files "$par_chipseq_control_read_files"} \
${par_chipseq_read_files_multi_targets:+--chipseq-read-files-multi-targets "$par_chipseq_read_files_multi_targets"} \
${par_chipseq_bed_files_multi_targets:+--chipseq-bed-files-multi-targets "$par_chipseq_bed_files_multi_targets"} \
${par_n_max_stacked_chipseq_reads:+--n-max-stacked-chipseq-reads "$par_n_max_stacked_chipseq_reads"} \
${par_partition_model:+--partition-model "$par_partition_model"} \
$strandedness \
${par_paired:+--paired-end} \
$par_extra_args \
${input[*]} \
$INDEX \
$par_id \
--quiet
$par_id

57 changes: 30 additions & 27 deletions src/rsem/rsem_calculate_expression/test.sh
Original file line number Diff line number Diff line change
Expand Up @@ -3,19 +3,18 @@
echo ">>> Testing $meta_executable"

test_dir="${meta_resources_dir}/test_data"
gunzip -k $test_dir/index.tar.gz
tar -xf $test_dir/index.tar

gunzip "${test_dir}/rsem.tar.gz"
tar -xf "${test_dir}/rsem.tar"

echo ">>> Calculating expression"
echo ">>> Test 1: Paired-end reads using STAR to align reads"
"$meta_executable" \
--id WT_REP1 \
--id mmliver \
--strandedness reverse \
--paired true \
--input "${test_dir}/SRR6357070_1.fastq.gz;${test_dir}/SRR6357070_2.fastq.gz" \
--index rsem \
--extra_args "--star --star-output-genome-bam --star-gzipped-read-file --estimate-rspd --seed 1" \
--logs WT_REP1.log \
--paired \
--input "${test_dir}/mmliver_1.fq.gz;${test_dir}/mmliver_2.fq.gz" \
--index index \
--star --star_output_genome_bam --star_gzipped_read_file --estimate_rspd --seed 1 \
--quiet

echo ">>> Checking whether output exists"
[ ! -f "WT_REP1.genes.results" ] && echo "Gene level expression counts file does not exist!" && exit 1
Expand All @@ -30,23 +29,27 @@ echo ">>> Checking whether output exists"

####################################################################################################

echo ">>> Test 2: Single-end reads without quality scores"
"$meta_executable" \
--no-qualities \
--input "${test_dir}/SRR6357070_1.fastq.gz" \
--index rsem \
--id WT_REP1_no_qual

####################################################################################################

echo ">>> Test 3: Paired-end reads with quality scores, using STAR to align reads"
"$meta_executable" \
--star \
--star-gzipped-read-file \
--paired-end \
--input "${test_dir}/SRR6357070_1.fastq.gz;${test_dir}/SRR6357070_2.fastq.gz" \
--index rsem \
WT_REP1_star
# echo ">>> Test 2: Single-end reads without quality scores"
# "$meta_executable" \
# --phred64-quals \
# --append-names \
# --output-genome-bam \
# --input /$test_dir/mmliver_1.fq \
# --index index \
# --id mmliver_single_quals

# ####################################################################################################

# echo ">>> Test 3: Paired-end reads with quality scores, using STAR to align reads"
# "$meta_executable" \
# --phred64-quals \
# --fragment-length-mean 150.0 \
# --fragment-length-sd 35.0 \
# --output-genome-bam \
# --calc-ci \
# --input /$test_dir/mmliver.fq \
# --index index \
# --id mmliver_single_quals

echo "All tests succeeded!"
exit 0
Loading

0 comments on commit 2918fb4

Please sign in to comment.