From 8b7731c276cb8d51affc15c252625235bb29ec18 Mon Sep 17 00:00:00 2001 From: Chris Tomkins-Tinch Date: Tue, 5 Nov 2024 15:12:37 -0500 Subject: [PATCH 1/2] add deduplication of sequences by ID in augur_from_assemblies (#564) add deduplication of sequences by ID in augur_from_assemblies, after filtering by length, prior to MSA via MAFFT. --- pipes/WDL/workflows/augur_from_assemblies.wdl | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/pipes/WDL/workflows/augur_from_assemblies.wdl b/pipes/WDL/workflows/augur_from_assemblies.wdl index 08c3ab87e..0eb30b244 100644 --- a/pipes/WDL/workflows/augur_from_assemblies.wdl +++ b/pipes/WDL/workflows/augur_from_assemblies.wdl @@ -67,9 +67,13 @@ workflow augur_from_assemblies { sequences_fasta = zcat.combined, min_non_N = min_unambig_genome } + call nextstrain.nextstrain_deduplicate_sequences as dedup_seqs { + input: + sequences_fasta = filter_sequences_by_length.filtered_fasta + } call nextstrain.mafft_one_chr as mafft { input: - sequences = filter_sequences_by_length.filtered_fasta, + sequences = dedup_seqs.sequences_deduplicated_fasta, ref_fasta = ref_fasta, basename = "all_samples_aligned.fasta" } From c26935720a5fb248dd1625750271c5501bdeff87 Mon Sep 17 00:00:00 2001 From: Chris Tomkins-Tinch Date: Wed, 6 Nov 2024 12:55:46 -0500 Subject: [PATCH 2/2] limit GH build concurrency (#549) * formatting of megablast wdl for consistency; add memory reporting to kraken2 and krakenuniq tasks * (re)formatting of blastoff.wdl * change in scope of blast_hits_output in ChunkBlastHits * trigger dnanexus deployment on PRs targeting master * cancel earlier actions, if a commit is added to a branch or a PR * apply GH Actions concurrency limit only to deploy_dnanexus job * allow the user to pass an email address as an input to fetch_sra_to_bam (for NCBI API access) * limit GH Actions build concurrency for all jobs to one per group for a given branch or PR (and one per branch or per PR, but not both) --- .github/workflows/build.yml | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 6619c4add..e7e50df8d 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -10,6 +10,12 @@ on: types: - created +concurrency: + # Group jobs by the branch or tag ref to ensure only one job runs for a ref at a time + group: ${{ github.ref }} + # Cancel any in-progress jobs for the same group + cancel-in-progress: true + env: PYTHONIOENCODING: UTF8 DOCKER_REGISTRY: "quay.io" @@ -32,6 +38,8 @@ env: jobs: validate_wdl_miniwdl: + # Run if not a push event or if there's no pull request for the branch + if: github.event_name != 'push' || github.event.pull_request == null runs-on: ubuntu-20.04 steps: - name: checkout repository @@ -85,6 +93,8 @@ jobs: miniwdl check pipes/WDL/workflows/*.wdl validate_wdl_womtool: + # Run if not a push event or if there's no pull request for the branch + if: github.event_name != 'push' || github.event.pull_request == null runs-on: ubuntu-20.04 steps: - name: checkout repository @@ -135,6 +145,8 @@ jobs: ## readthedocs does its own build trigger. this job exists simply to ## attempt a build and alert us of documentation build failures because otherwise we would never know. test_docs: + # Run if not a push event or if there's no pull request for the branch + if: github.event_name != 'push' || github.event.pull_request == null runs-on: ubuntu-20.04 steps: - name: checkout repository @@ -179,6 +191,8 @@ jobs: github_actions_ci/build-docs.sh test_cromwell: + # Run if not a push event or if there's no pull request for the branch + if: github.event_name != 'push' || github.event.pull_request == null needs: validate_wdl_womtool runs-on: ubuntu-20.04 steps: @@ -234,6 +248,8 @@ jobs: github_actions_ci/tests-cromwell.sh test_miniwdl: + # Run if not a push event or if there's no pull request for the branch + if: github.event_name != 'push' || github.event.pull_request == null needs: validate_wdl_miniwdl runs-on: ubuntu-20.04 steps: