From 3e3692cd2cef15dc659cccd91edf9a6373f226c4 Mon Sep 17 00:00:00 2001 From: Matteo Date: Mon, 6 May 2019 16:44:23 +0200 Subject: [PATCH 1/5] included recursive clone of git repo --- solida/cache_manager.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/solida/cache_manager.py b/solida/cache_manager.py index dca5801..07d571c 100644 --- a/solida/cache_manager.py +++ b/solida/cache_manager.py @@ -36,7 +36,7 @@ def clone(self, label): ensure_dir(repo_dir) if path_is_empty(repo_dir): print("Cloning {}".format(pipeline.url)) - Repo.clone_from(pipeline.url, repo_dir) + Repo.clone_from(pipeline.url, repo_dir, recursive=True) repo = Repo(repo_dir) heads = repo.heads master = heads.master From 05b8a6ce9edb1ec41790aa7316b72cf0e41679eb Mon Sep 17 00:00:00 2001 From: Matteo Date: Mon, 6 May 2019 17:17:17 +0200 Subject: [PATCH 2/5] included diva pipeline --- solida/config/config.yaml | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/solida/config/config.yaml b/solida/config/config.yaml index 565d596..263266d 100644 --- a/solida/config/config.yaml +++ b/solida/config/config.yaml @@ -141,3 +141,26 @@ pipelines: datasets_dir: /path/to/datasets # optional gatk_dir: path/to/software/gatk-3.7 # optional + diva: + label: 'diva' + description: 'Snakemake pipeline to identify genomic variants from exome data, +using GATK4 variant calling following the best practices guide from BroadInstitute.' + url: "https://github.com/solida-core/diva.git" + type: "git" + playbook: 'install_pipeline.yaml' + playbook_vars_template: + # Pipeline dependencies + project_environment_file: environment.yaml + # References + references_dir: /path/to/references + _provider_: reference_genome_provider (es. ucsc) + _release_: reference_genome_release (es. hg19) + _genome_fasta: reference_genome_fasta_filename (*.fasta) + _enrichment_kit_: enrichment_kit + _db_suffix_: folder name for genomicsDBImport folder + # Paths + kggseq_path: "path/to/software/kggseq.jar" + ped_file: ../resources/project.ped + blocks_file: ../resources/annot.blocks + reheader_file: ../resources/reheader.txt + recalibrated_vcf_dir: path/to/recalibrated_vcf_dir \ No newline at end of file From 99325d58104eae234b9c00faf1f0c864ebcd0615 Mon Sep 17 00:00:00 2001 From: Matteo Date: Tue, 18 Jun 2019 14:23:33 +0200 Subject: [PATCH 3/5] included pipelines from solida-core hub --- solida/config/config.yaml | 122 +++++++------------------------------- 1 file changed, 21 insertions(+), 101 deletions(-) diff --git a/solida/config/config.yaml b/solida/config/config.yaml index 263266d..34ed61a 100644 --- a/solida/config/config.yaml +++ b/solida/config/config.yaml @@ -23,31 +23,6 @@ default_vars: snakefile: Snakefile # required jobs: 2 pipelines: - annotation: - label: 'annotation' - description: 'Snakemake pipeline to annotate genomic data.' - url: "https://bitbucket.org/biopipelines/annotation.git" - type: "git" - playbook: 'install_pipeline.yaml' - playbook_vars_template: - # Pipeline dependencies - project_environment_file: environment.yml - # Project vars - project_name: 'noname_project' - project_email_address: 'example@example' - project_config_file: 'config.yaml' - # References - references_dir: /path/to/references - references_provider: provider - references_release: release - reference_genome_fasta: genome_fasta_file - # Paths - kggseq_path: "path/to/software/kggseq.jar" - ped_file: ../resources/project.ped - blocks_file: ../resources/annot.blocks - reheader_file: ../resources/reheader.txt - recalibrated_vcf_dir: path/to/recalibrated_vcf_dir - dima: label: 'dima' description: 'Pipeline to map DNA datasets to a given reference @@ -64,22 +39,34 @@ pipelines: # Paths datasets_dir: /path/to/datasets # optional - viper: - label: 'viper' - description: 'Visualization Pipeline for RNA-Seq data' - url: "https://bitbucket.org/cfce/viper.git" + diva: + label: 'diva' + description: 'DiVA (DNA Variant Analysis) is a pipeline for Next-Generation Sequencing Exome data analysis' + url: "https://github.com/solida-core/diva.git" type: "git" playbook: 'install_pipeline.yaml' playbook_vars_template: + # Pipeline dependencies + project_environment_file: environment.yaml + # References + references_dir: /path/to/references + _provider_: reference_genome_provider (es. ucsc) + _release_: reference_genome_release (es. hg19) + _genome_fasta: reference_genome_fasta_filename (*.fasta) + _enrichment_kit_: enrichment_kit + _db_suffix_: folder name for genomicsDBImport folder # Paths - references_dir: /path/to/references # optional - datasets_dir: /path/to/datasets # optional + kggseq_path: "path/to/software/kggseq.jar" + ped_file: ../resources/project.ped + blocks_file: ../resources/annot.blocks + reheader_file: ../resources/reheader.txt + recalibrated_vcf_dir: path/to/recalibrated_vcf_dir ride: label: 'ride' description: 'Pipeline to quantify abundances of transcripts from RNA-Seq data' - url: "https://bitbucket.org/biopipelines/ride.git" + url: "https://github.com/solida-core/ride.git" type: "git" playbook: 'install_pipeline.yaml' playbook_vars_template: @@ -90,77 +77,10 @@ pipelines: sride: label: 'sride' description: 'Snakemake enabled pipeline for smallRNA-Seq identification' - url: "https://bitbucket.org/biopipelines/sride.git" - type: "git" - playbook: 'install_pipeline.yaml' - playbook_vars_template: - sm_wrappers_repo: https://bitbucket.org/snakemake/snakemake-wrappers.git - sm_wrappers_release: 0.27.0 - # flags to activate specific tasks - local_git_4_wrappers: True - # Paths - references_dir: /path/to/references # optional - datasets_dir: /path/to/datasets # optional - - sride_data: - label: 'sride_data' - description: 'Snakemake workflow to produce reference and test data - for smallRNA-Seq identification pipeline' - url: "https://bitbucket.org/biopipelines/sride_data.git" - type: "git" - playbook: 'install_pipeline.yaml' - playbook_vars_template: - # Paths - references_dir: /path/to/references # optional - datasets_dir: /path/to/datasets # optional - - rna-seq-star-deseq2: - label: 'rna-seq-star-deseq2' - description: 'RNA-seq workflow using STAR and DESeq2' - url: "https://github.com/snakemake-workflows/rna-seq-star-deseq2" + url: "https://github.com/solida-core/sride.git" type: "git" playbook: 'install_pipeline.yaml' playbook_vars_template: # Paths references_dir: /path/to/references # optional - datasets_dir: /path/to/datasets # optional - - coverest: - label: 'coverest' - description: 'Snakemake enabled pipeline for coverage estimation' - url: "https://bitbucket.org/massiddaMT/coverest.git" - type: "git" - playbook: 'install_pipeline.yaml' - playbook_vars_template: - project_environment_file: environment.yaml - # Paths - references_dir: /path/to/references # optional - _provider_: reference_genome_provider (es. ncbi) - _release_: reference_genome_release (es. hg19) - _genome_fasta: reference_genome_fasta_filename (*.fasta) - datasets_dir: /path/to/datasets # optional - gatk_dir: path/to/software/gatk-3.7 # optional - - diva: - label: 'diva' - description: 'Snakemake pipeline to identify genomic variants from exome data, -using GATK4 variant calling following the best practices guide from BroadInstitute.' - url: "https://github.com/solida-core/diva.git" - type: "git" - playbook: 'install_pipeline.yaml' - playbook_vars_template: - # Pipeline dependencies - project_environment_file: environment.yaml - # References - references_dir: /path/to/references - _provider_: reference_genome_provider (es. ucsc) - _release_: reference_genome_release (es. hg19) - _genome_fasta: reference_genome_fasta_filename (*.fasta) - _enrichment_kit_: enrichment_kit - _db_suffix_: folder name for genomicsDBImport folder - # Paths - kggseq_path: "path/to/software/kggseq.jar" - ped_file: ../resources/project.ped - blocks_file: ../resources/annot.blocks - reheader_file: ../resources/reheader.txt - recalibrated_vcf_dir: path/to/recalibrated_vcf_dir \ No newline at end of file + datasets_dir: /path/to/datasets # optional \ No newline at end of file From d51ebb1a97e8834366243d2d841fbc623645adaf Mon Sep 17 00:00:00 2001 From: Matteo Date: Tue, 18 Jun 2019 14:24:09 +0200 Subject: [PATCH 4/5] patients.tsv replacement was present twice: removed one --- solida/playbooks/replace_paths.yaml | 7 ------- 1 file changed, 7 deletions(-) diff --git a/solida/playbooks/replace_paths.yaml b/solida/playbooks/replace_paths.yaml index d975dbf..c1a9289 100644 --- a/solida/playbooks/replace_paths.yaml +++ b/solida/playbooks/replace_paths.yaml @@ -35,13 +35,6 @@ replace: "{{ pipeline_dir }}/patients.tsv" ignore_errors: yes -- name: Replace path to patients.tsv into the project configuration file - replace: - dest: "{{ pipeline_dir }}/{{ project_config_file }}" - regexp: "patients.tsv" - replace: "{{ pipeline_dir }}/patients.tsv" - ignore_errors: yes - - name: Replace path_to_references_data into the project configuration file replace: dest: "{{ pipeline_dir }}/{{ project_config_file }}" From 7f4dfc717a72bbd1fa8b18e673d09a2d07fb5ca5 Mon Sep 17 00:00:00 2001 From: massiddaMT Date: Fri, 19 Jun 2020 11:32:05 +0200 Subject: [PATCH 5/5] fix dependencies issues --- requirements.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index a284404..3e119ef 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,4 +1,5 @@ -ansible>=2.4.0 +ansible==2.4.0 appdirs==1.4.3 comoda==0.3.7 gitpython==2.1.10 +gitdb2==2.0.6 \ No newline at end of file