From 4575c8eba6ebd669b934c51ef91e9618cffa3936 Mon Sep 17 00:00:00 2001 From: gconcepcion Date: Fri, 1 Dec 2023 16:17:41 -0800 Subject: [PATCH 01/16] logo commit --- README.md | 16 ++++++++++++++-- images/logo_wdl_workflows.svg | 1 + {workflows => images}/main.graphviz.svg | 0 3 files changed, 15 insertions(+), 2 deletions(-) create mode 100644 images/logo_wdl_workflows.svg rename {workflows => images}/main.graphviz.svg (100%) diff --git a/README.md b/README.md index 89a557e..95fa25c 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,7 @@ +

+ +

PacBio Human Assembly pipeline

+ # DISCLAIMER TO THE GREATEST EXTENT PERMITTED BY APPLICABLE LAW, THIS WEBSITE AND ITS CONTENT, INCLUDING ALL SOFTWARE, SOFTWARE CODE, SITE-RELATED SERVICES, AND DATA, ARE PROVIDED "AS IS," WITH ALL FAULTS, WITH NO REPRESENTATIONS OR WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, ANY WARRANTIES OF MERCHANTABILITY, SATISFACTORY QUALITY, NON-INFRINGEMENT OR FITNESS FOR A PARTICULAR PURPOSE. ALL WARRANTIES ARE REJECTED AND DISCLAIMED. YOU ASSUME TOTAL RESPONSIBILITY AND RISK FOR YOUR USE OF THE FOREGOING. PACBIO IS NOT OBLIGATED TO PROVIDE ANY SUPPORT FOR ANY OF THE FOREGOING, AND ANY SUPPORT PACBIO DOES PROVIDE IS SIMILARLY PROVIDED WITHOUT REPRESENTATION OR WARRANTY OF ANY KIND. NO ORAL OR WRITTEN INFORMATION OR ADVICE SHALL CREATE A REPRESENTATION OR WARRANTY OF ANY KIND. ANY REFERENCES TO SPECIFIC PRODUCTS OR SERVICES ON THE WEBSITES DO NOT CONSTITUTE OR IMPLY A RECOMMENDATION OR ENDORSEMENT BY PACBIO. @@ -15,7 +19,7 @@ Workflow for running de novo assembly using human PacBio whole genome sequencing The assembly workflow performs _de novo_ assembly on samples and trios. -![De novo assembly workflow diagram](workflows/main.graphviz.svg "De novo assembly workflow diagram") +![De novo assembly workflow diagram](images/main.graphviz.svg "De novo assembly workflow diagram") ## Setup @@ -47,10 +51,12 @@ For backend-specific configuration, see the relevant documentation: - [GCP](backends/gcp) - [HPC](backends/hpc) -## Configuring a workflow engine +## Configuring a workflow engine and container runtime An execution engine is required to run workflows. Two popular engines for running WDL-based workflows are [`miniwdl`](https://miniwdl.readthedocs.io/en/latest/getting_started.html) and [`Cromwell`](https://cromwell.readthedocs.io/en/stable/tutorials/FiveMinuteIntro/). +Because workflow dependencies are containerized, a container runtime is required. This workflow has been tested with [Docker](https://docs.docker.com/get-docker/) and [Singularity](https://docs.sylabs.io/guides/3.10/user-guide/) container runtimes. + See [backend-specific documentation](backends) for details on setting up an engine. | Engine | Azure | AWS | GCP | HPC | @@ -200,3 +206,9 @@ The Docker image used by a particular step of the workflow can be identified by | parse-cohort | | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/parse-cohort) | | samtools | | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/samtools) | | yak | | [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/yak) | + +--- + +## DISCLAIMER + +TO THE GREATEST EXTENT PERMITTED BY APPLICABLE LAW, THIS WEBSITE AND ITS CONTENT, INCLUDING ALL SOFTWARE, SOFTWARE CODE, SITE-RELATED SERVICES, AND DATA, ARE PROVIDED "AS IS," WITH ALL FAULTS, WITH NO REPRESENTATIONS OR WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, ANY WARRANTIES OF MERCHANTABILITY, SATISFACTORY QUALITY, NON-INFRINGEMENT OR FITNESS FOR A PARTICULAR PURPOSE. ALL WARRANTIES ARE REJECTED AND DISCLAIMED. YOU ASSUME TOTAL RESPONSIBILITY AND RISK FOR YOUR USE OF THE FOREGOING. PACBIO IS NOT OBLIGATED TO PROVIDE ANY SUPPORT FOR ANY OF THE FOREGOING, AND ANY SUPPORT PACBIO DOES PROVIDE IS SIMILARLY PROVIDED WITHOUT REPRESENTATION OR WARRANTY OF ANY KIND. NO ORAL OR WRITTEN INFORMATION OR ADVICE SHALL CREATE A REPRESENTATION OR WARRANTY OF ANY KIND. ANY REFERENCES TO SPECIFIC PRODUCTS OR SERVICES ON THE WEBSITES DO NOT CONSTITUTE OR IMPLY A RECOMMENDATION OR ENDORSEMENT BY PACBIO. \ No newline at end of file diff --git a/images/logo_wdl_workflows.svg b/images/logo_wdl_workflows.svg new file mode 100644 index 0000000..4e78b8a --- /dev/null +++ b/images/logo_wdl_workflows.svg @@ -0,0 +1 @@ +{"payload":{"allShortcutsEnabled":false,"fileTree":{"images":{"items":[{"name":"logo_wdl_workflows.svg","path":"images/logo_wdl_workflows.svg","contentType":"file"},{"name":"main.graphviz.svg","path":"images/main.graphviz.svg","contentType":"file"}],"totalCount":2},"":{"items":[{"name":".github","path":".github","contentType":"directory"},{"name":"backends","path":"backends","contentType":"directory"},{"name":"images","path":"images","contentType":"directory"},{"name":"workflows","path":"workflows","contentType":"directory"},{"name":".dockstore.yml","path":".dockstore.yml","contentType":"file"},{"name":".gitignore","path":".gitignore","contentType":"file"},{"name":".gitmodules","path":".gitmodules","contentType":"file"},{"name":"LICENSE","path":"LICENSE","contentType":"file"},{"name":"README.md","path":"README.md","contentType":"file"},{"name":"wdl-ci.config.json","path":"wdl-ci.config.json","contentType":"file"}],"totalCount":10}},"fileTreeProcessingTime":9.498115,"foldersToFetch":[],"reducedMotionEnabled":null,"repo":{"id":561879270,"defaultBranch":"main","name":"HiFi-human-WGS-WDL","ownerLogin":"PacificBiosciences","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2022-11-04T17:43:44.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/999745?v=4","public":true,"private":false,"isOrgOwned":true},"symbolsExpanded":false,"treeExpanded":true,"refInfo":{"name":"develop","listCacheKey":"v0:1701474958.0","canEdit":false,"refType":"branch","currentOid":"64f6a6830b003e0871d3d5aea0ada44c68cf9133"},"path":"images/logo_wdl_workflows.svg","currentUser":null,"blob":{"rawLines":["",""," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," ",""],"stylingDirectives":null,"csv":null,"csvError":null,"dependabotInfo":{"showConfigurationBanner":false,"configFilePath":null,"networkDependabotPath":"/PacificBiosciences/HiFi-human-WGS-WDL/network/updates","dismissConfigurationNoticePath":"/settings/dismiss-notice/dependabot_configuration_notice","configurationNoticeDismissed":null,"repoAlertsPath":"/PacificBiosciences/HiFi-human-WGS-WDL/security/dependabot","repoSecurityAndAnalysisPath":"/PacificBiosciences/HiFi-human-WGS-WDL/settings/security_analysis","repoOwnerIsOrg":true,"currentUserCanAdminRepo":false},"displayName":"logo_wdl_workflows.svg","displayUrl":"https://viewscreen.githubusercontent.com/view/svg?browser=unknown_browser&bypass_fastly=true&color_mode=auto&commit=64f6a6830b003e0871d3d5aea0ada44c68cf9133&device=unknown_device&docs_host=https%3A%2F%2Fdocs.github.com&enc_url=68747470733a2f2f7261772e67697468756275736572636f6e74656e742e636f6d2f5061636966696342696f736369656e6365732f486946692d68756d616e2d5747532d57444c2f363466366136383330623030336530383731643364356165613061646134346336386366393133332f696d616765732f6c6f676f5f77646c5f776f726b666c6f77732e737667&logged_in=false&nwo=PacificBiosciences%2FHiFi-human-WGS-WDL&path=images%2Flogo_wdl_workflows.svg&platform=unknown_platform&repository_id=561879270&repository_type=Repository&version=0","headerInfo":{"blobSize":"3.41 KB","deleteInfo":{"deleteTooltip":"You must be signed in to make or propose changes"},"editInfo":{"editTooltip":"You must be signed in to make or propose changes"},"ghDesktopPath":"https://desktop.github.com","gitLfsPath":null,"onBranch":true,"shortPath":"4f065f0","siteNavLoginPath":"/login?return_to=https%3A%2F%2Fgithub.com%2FPacificBiosciences%2FHiFi-human-WGS-WDL%2Fblob%2Fdevelop%2Fimages%2Flogo_wdl_workflows.svg","isCSV":false,"isRichtext":false,"toc":null,"lineInfo":{"truncatedLoc":"83","truncatedSloc":"74"},"mode":"file"},"image":false,"isCodeownersFile":null,"isPlain":false,"isValidLegacyIssueTemplate":false,"issueTemplateHelpUrl":"https://docs.github.com/articles/about-issue-and-pull-request-templates","issueTemplate":null,"discussionTemplate":null,"language":"SVG","languageID":337,"large":false,"loggedIn":false,"newDiscussionPath":"/PacificBiosciences/HiFi-human-WGS-WDL/discussions/new","newIssuePath":"/PacificBiosciences/HiFi-human-WGS-WDL/issues/new","planSupportInfo":{"repoIsFork":null,"repoOwnedByCurrentUser":null,"requestFullPath":"/PacificBiosciences/HiFi-human-WGS-WDL/blob/develop/images/logo_wdl_workflows.svg","showFreeOrgGatedFeatureMessage":null,"showPlanSupportBanner":null,"upgradeDataAttributes":null,"upgradePath":null},"publishBannersInfo":{"dismissActionNoticePath":"/settings/dismiss-notice/publish_action_from_dockerfile","dismissStackNoticePath":"/settings/dismiss-notice/publish_stack_from_file","releasePath":"/PacificBiosciences/HiFi-human-WGS-WDL/releases/new?marketplace=true","showPublishActionBanner":false,"showPublishStackBanner":false},"rawBlobUrl":"https://github.com/PacificBiosciences/HiFi-human-WGS-WDL/raw/develop/images/logo_wdl_workflows.svg","renderImageOrRaw":false,"richText":null,"renderedFileInfo":{"identityUUID":"6b2159da-2a08-4c49-bbc9-5ded546a970b","renderFileType":"svg","size":3490},"shortPath":null,"tabSize":8,"topBannersInfo":{"overridingGlobalFundingFile":false,"globalPreferredFundingPath":null,"repoOwner":"PacificBiosciences","repoName":"HiFi-human-WGS-WDL","showInvalidCitationWarning":false,"citationHelpUrl":"https://docs.github.com/en/github/creating-cloning-and-archiving-repositories/creating-a-repository-on-github/about-citation-files","showDependabotConfigurationBanner":false,"actionsOnboardingTip":null},"truncated":false,"viewable":true,"workflowRedirectUrl":null,"symbols":{"timedOut":false,"notAnalyzed":true,"symbols":[]}},"copilotInfo":null,"copilotAccessAllowed":false,"csrf_tokens":{"/PacificBiosciences/HiFi-human-WGS-WDL/branches":{"post":"YZteKodRM_ApFZWh0x2uJ0reCnt40Y3tiUKH7eQEkeUMWCWg7KHtKzYC3ZEMmEoana_fNUkr3wWOzfdyxpmt6g"},"/repos/preferences":{"post":"5c1bwXMXRoHPg09Aa_TUeX2hq_lAzSEt3s5zXIp5cY6D-ko7xLNRfB9h1oZ4JOR16azvYWuPHmOBc4X7aXAGSA"}}},"title":"HiFi-human-WGS-WDL/images/logo_wdl_workflows.svg at develop · PacificBiosciences/HiFi-human-WGS-WDL"} \ No newline at end of file diff --git a/workflows/main.graphviz.svg b/images/main.graphviz.svg similarity index 100% rename from workflows/main.graphviz.svg rename to images/main.graphviz.svg From ed77b5b2a8e56398d2f6aa57e5a235f7886cce78 Mon Sep 17 00:00:00 2001 From: gconcepcion Date: Fri, 1 Dec 2023 16:23:28 -0800 Subject: [PATCH 02/16] fix logo --- images/logo_wdl_workflows.svg | 84 ++++++++++++++++++++++++++++++++++- 1 file changed, 83 insertions(+), 1 deletion(-) diff --git a/images/logo_wdl_workflows.svg b/images/logo_wdl_workflows.svg index 4e78b8a..4f065f0 100644 --- a/images/logo_wdl_workflows.svg +++ b/images/logo_wdl_workflows.svg @@ -1 +1,83 @@ -{"payload":{"allShortcutsEnabled":false,"fileTree":{"images":{"items":[{"name":"logo_wdl_workflows.svg","path":"images/logo_wdl_workflows.svg","contentType":"file"},{"name":"main.graphviz.svg","path":"images/main.graphviz.svg","contentType":"file"}],"totalCount":2},"":{"items":[{"name":".github","path":".github","contentType":"directory"},{"name":"backends","path":"backends","contentType":"directory"},{"name":"images","path":"images","contentType":"directory"},{"name":"workflows","path":"workflows","contentType":"directory"},{"name":".dockstore.yml","path":".dockstore.yml","contentType":"file"},{"name":".gitignore","path":".gitignore","contentType":"file"},{"name":".gitmodules","path":".gitmodules","contentType":"file"},{"name":"LICENSE","path":"LICENSE","contentType":"file"},{"name":"README.md","path":"README.md","contentType":"file"},{"name":"wdl-ci.config.json","path":"wdl-ci.config.json","contentType":"file"}],"totalCount":10}},"fileTreeProcessingTime":9.498115,"foldersToFetch":[],"reducedMotionEnabled":null,"repo":{"id":561879270,"defaultBranch":"main","name":"HiFi-human-WGS-WDL","ownerLogin":"PacificBiosciences","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2022-11-04T17:43:44.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/999745?v=4","public":true,"private":false,"isOrgOwned":true},"symbolsExpanded":false,"treeExpanded":true,"refInfo":{"name":"develop","listCacheKey":"v0:1701474958.0","canEdit":false,"refType":"branch","currentOid":"64f6a6830b003e0871d3d5aea0ada44c68cf9133"},"path":"images/logo_wdl_workflows.svg","currentUser":null,"blob":{"rawLines":["",""," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," "," ",""],"stylingDirectives":null,"csv":null,"csvError":null,"dependabotInfo":{"showConfigurationBanner":false,"configFilePath":null,"networkDependabotPath":"/PacificBiosciences/HiFi-human-WGS-WDL/network/updates","dismissConfigurationNoticePath":"/settings/dismiss-notice/dependabot_configuration_notice","configurationNoticeDismissed":null,"repoAlertsPath":"/PacificBiosciences/HiFi-human-WGS-WDL/security/dependabot","repoSecurityAndAnalysisPath":"/PacificBiosciences/HiFi-human-WGS-WDL/settings/security_analysis","repoOwnerIsOrg":true,"currentUserCanAdminRepo":false},"displayName":"logo_wdl_workflows.svg","displayUrl":"https://viewscreen.githubusercontent.com/view/svg?browser=unknown_browser&bypass_fastly=true&color_mode=auto&commit=64f6a6830b003e0871d3d5aea0ada44c68cf9133&device=unknown_device&docs_host=https%3A%2F%2Fdocs.github.com&enc_url=68747470733a2f2f7261772e67697468756275736572636f6e74656e742e636f6d2f5061636966696342696f736369656e6365732f486946692d68756d616e2d5747532d57444c2f363466366136383330623030336530383731643364356165613061646134346336386366393133332f696d616765732f6c6f676f5f77646c5f776f726b666c6f77732e737667&logged_in=false&nwo=PacificBiosciences%2FHiFi-human-WGS-WDL&path=images%2Flogo_wdl_workflows.svg&platform=unknown_platform&repository_id=561879270&repository_type=Repository&version=0","headerInfo":{"blobSize":"3.41 KB","deleteInfo":{"deleteTooltip":"You must be signed in to make or propose changes"},"editInfo":{"editTooltip":"You must be signed in to make or propose changes"},"ghDesktopPath":"https://desktop.github.com","gitLfsPath":null,"onBranch":true,"shortPath":"4f065f0","siteNavLoginPath":"/login?return_to=https%3A%2F%2Fgithub.com%2FPacificBiosciences%2FHiFi-human-WGS-WDL%2Fblob%2Fdevelop%2Fimages%2Flogo_wdl_workflows.svg","isCSV":false,"isRichtext":false,"toc":null,"lineInfo":{"truncatedLoc":"83","truncatedSloc":"74"},"mode":"file"},"image":false,"isCodeownersFile":null,"isPlain":false,"isValidLegacyIssueTemplate":false,"issueTemplateHelpUrl":"https://docs.github.com/articles/about-issue-and-pull-request-templates","issueTemplate":null,"discussionTemplate":null,"language":"SVG","languageID":337,"large":false,"loggedIn":false,"newDiscussionPath":"/PacificBiosciences/HiFi-human-WGS-WDL/discussions/new","newIssuePath":"/PacificBiosciences/HiFi-human-WGS-WDL/issues/new","planSupportInfo":{"repoIsFork":null,"repoOwnedByCurrentUser":null,"requestFullPath":"/PacificBiosciences/HiFi-human-WGS-WDL/blob/develop/images/logo_wdl_workflows.svg","showFreeOrgGatedFeatureMessage":null,"showPlanSupportBanner":null,"upgradeDataAttributes":null,"upgradePath":null},"publishBannersInfo":{"dismissActionNoticePath":"/settings/dismiss-notice/publish_action_from_dockerfile","dismissStackNoticePath":"/settings/dismiss-notice/publish_stack_from_file","releasePath":"/PacificBiosciences/HiFi-human-WGS-WDL/releases/new?marketplace=true","showPublishActionBanner":false,"showPublishStackBanner":false},"rawBlobUrl":"https://github.com/PacificBiosciences/HiFi-human-WGS-WDL/raw/develop/images/logo_wdl_workflows.svg","renderImageOrRaw":false,"richText":null,"renderedFileInfo":{"identityUUID":"6b2159da-2a08-4c49-bbc9-5ded546a970b","renderFileType":"svg","size":3490},"shortPath":null,"tabSize":8,"topBannersInfo":{"overridingGlobalFundingFile":false,"globalPreferredFundingPath":null,"repoOwner":"PacificBiosciences","repoName":"HiFi-human-WGS-WDL","showInvalidCitationWarning":false,"citationHelpUrl":"https://docs.github.com/en/github/creating-cloning-and-archiving-repositories/creating-a-repository-on-github/about-citation-files","showDependabotConfigurationBanner":false,"actionsOnboardingTip":null},"truncated":false,"viewable":true,"workflowRedirectUrl":null,"symbols":{"timedOut":false,"notAnalyzed":true,"symbols":[]}},"copilotInfo":null,"copilotAccessAllowed":false,"csrf_tokens":{"/PacificBiosciences/HiFi-human-WGS-WDL/branches":{"post":"YZteKodRM_ApFZWh0x2uJ0reCnt40Y3tiUKH7eQEkeUMWCWg7KHtKzYC3ZEMmEoana_fNUkr3wWOzfdyxpmt6g"},"/repos/preferences":{"post":"5c1bwXMXRoHPg09Aa_TUeX2hq_lAzSEt3s5zXIp5cY6D-ko7xLNRfB9h1oZ4JOR16azvYWuPHmOBc4X7aXAGSA"}}},"title":"HiFi-human-WGS-WDL/images/logo_wdl_workflows.svg at develop · PacificBiosciences/HiFi-human-WGS-WDL"} \ No newline at end of file + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + \ No newline at end of file From 6775678a1e6180024e1d3f69ff3971a47ab95319 Mon Sep 17 00:00:00 2001 From: gconcepcion Date: Fri, 1 Dec 2023 16:25:13 -0800 Subject: [PATCH 03/16] remove upper disclaimer --- README.md | 4 ---- 1 file changed, 4 deletions(-) diff --git a/README.md b/README.md index 95fa25c..3f663d1 100644 --- a/README.md +++ b/README.md @@ -2,10 +2,6 @@

PacBio Human Assembly pipeline

-# DISCLAIMER - -TO THE GREATEST EXTENT PERMITTED BY APPLICABLE LAW, THIS WEBSITE AND ITS CONTENT, INCLUDING ALL SOFTWARE, SOFTWARE CODE, SITE-RELATED SERVICES, AND DATA, ARE PROVIDED "AS IS," WITH ALL FAULTS, WITH NO REPRESENTATIONS OR WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, ANY WARRANTIES OF MERCHANTABILITY, SATISFACTORY QUALITY, NON-INFRINGEMENT OR FITNESS FOR A PARTICULAR PURPOSE. ALL WARRANTIES ARE REJECTED AND DISCLAIMED. YOU ASSUME TOTAL RESPONSIBILITY AND RISK FOR YOUR USE OF THE FOREGOING. PACBIO IS NOT OBLIGATED TO PROVIDE ANY SUPPORT FOR ANY OF THE FOREGOING, AND ANY SUPPORT PACBIO DOES PROVIDE IS SIMILARLY PROVIDED WITHOUT REPRESENTATION OR WARRANTY OF ANY KIND. NO ORAL OR WRITTEN INFORMATION OR ADVICE SHALL CREATE A REPRESENTATION OR WARRANTY OF ANY KIND. ANY REFERENCES TO SPECIFIC PRODUCTS OR SERVICES ON THE WEBSITES DO NOT CONSTITUTE OR IMPLY A RECOMMENDATION OR ENDORSEMENT BY PACBIO. - # wdl-humanassembly Workflow for running de novo assembly using human PacBio whole genome sequencing (WGS) data. Written using [Workflow Description Language (WDL)](https://openwdl.org/). From 60db0f1a2a643de8f97cf78b8798a6e0b7c29d17 Mon Sep 17 00:00:00 2001 From: gconcepcion Date: Thu, 8 Feb 2024 15:59:31 -0800 Subject: [PATCH 04/16] minor readme updates --- README.md | 2 -- 1 file changed, 2 deletions(-) diff --git a/README.md b/README.md index 3f663d1..1bbfe32 100644 --- a/README.md +++ b/README.md @@ -2,8 +2,6 @@

PacBio Human Assembly pipeline

-# wdl-humanassembly - Workflow for running de novo assembly using human PacBio whole genome sequencing (WGS) data. Written using [Workflow Description Language (WDL)](https://openwdl.org/). - Docker images used by these workflows are defined [here](https://github.com/PacificBiosciences/wdl-dockerfiles). From f5e1b4c4c23ba1e0a54e87c36bd246d204f25487 Mon Sep 17 00:00:00 2001 From: gconcepcion Date: Tue, 13 Feb 2024 13:43:18 -0800 Subject: [PATCH 05/16] update README --- README.md | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 1bbfe32..52c6b97 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,14 @@ The assembly workflow performs _de novo_ assembly on samples and trios. ## Setup -Some tasks and workflows are pulled in from other repositories. Ensure you have initialized submodules following cloning by running `git submodule update --init --recursive`. +We recommend cloning the repo rather than downloading the release package. + +```git clone \ + --depth 1 --branch v1.1.0 \ # for reproducibility + --recursive \ # to clone submodule + https://github.com/PacificBiosciences/HiFi-human-assembly-WDL.git +``` + ## Resource requirements @@ -115,7 +122,7 @@ A cohort can include one or more samples. Samples need not be related. | Type | Name | Description | Notes | | :- | :- | :- | :- | -| String | cohort_id | A unique name for the cohort; used to name outputs | | +| String | cohort_id | A unique name for the cohort; used to name outputs. Alphanumeric characters, underscore (_), and dash (-) are allowed. | | | Array[[Sample](#sample)] | samples | The set of samples for the cohort. At least one sample must be defined. | | | Boolean | run_de_novo_assembly_trio | Run trio binned _de novo_ assembly. | Cohort must contain at least one valid trio (child and both parents present in the cohort) | @@ -125,10 +132,10 @@ Sample information for each sample in the workflow run. | Type | Name | Description | Notes | | :- | :- | :- | :- | -| String | sample_id | A unique name for the sample; used to name outputs | | +| String | sample_id | A unique name for the sample; used to name outputs. Alphanumeric characters, underscore (_), and dash (-) are allowed | | | Array[[IndexData](https://github.com/PacificBiosciences/wdl-common/blob/main/wdl/structs.wdl)] | movie_bams | The set of unaligned movie BAMs associated with this sample | | -| String? | father_id | Paternal `sample_id` | | -| String? | mother_id | Maternal `sample_id` | | +| String? | father_id | Paternal `sample_id`. Alphanumeric characters, underscore (_), and dash (-) are allowed. | | +| String? | mother_id | Maternal `sample_id`. Alphanumeric characters, underscore (_), and dash (-) are allowed. | | | Boolean | run_de_novo_assembly | If true, run single-sample _de novo_ assembly for this sample | \[true, false\] | ## [ReferenceData](workflows/humanwgs_structs.wdl) From b76af786ab7cc2d4749583989a0e6834a0325889 Mon Sep 17 00:00:00 2001 From: William Rowell Date: Tue, 13 Feb 2024 15:40:21 -0800 Subject: [PATCH 06/16] The parse-cohort image is deprecated, and the script from this container has been added to the pyyaml container. Updated parse_families task to use pyyaml@sha256:af6f0689a7412b1edf76bd4bf6434e7fa6a86192eebf19573e8618880d9c1dbb --- workflows/de_novo_assembly_trio/de_novo_assembly_trio.wdl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/workflows/de_novo_assembly_trio/de_novo_assembly_trio.wdl b/workflows/de_novo_assembly_trio/de_novo_assembly_trio.wdl index b11e5a0..230ad9a 100644 --- a/workflows/de_novo_assembly_trio/de_novo_assembly_trio.wdl +++ b/workflows/de_novo_assembly_trio/de_novo_assembly_trio.wdl @@ -191,7 +191,7 @@ task parse_families { } runtime { - docker: "~{runtime_attributes.container_registry}/parse-cohort@sha256:e6a8ac24ada706644e62878178790a0006db9a6abec7a312232052bb0666fe8f" + docker: "~{runtime_attributes.container_registry}/pyyaml@sha256:af6f0689a7412b1edf76bd4bf6434e7fa6a86192eebf19573e8618880d9c1dbb" cpu: 2 memory: "4 GB" disk: "20 GB" From 5ae02e64cb39343bd028b76ac59581c2253f3b93 Mon Sep 17 00:00:00 2001 From: github-actions <41898282+github-actions[bot]@users.noreply.github.com> Date: Wed, 14 Feb 2024 19:13:52 +0000 Subject: [PATCH 07/16] update wdl-ci config file after successful tests --- wdl-ci.config.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/wdl-ci.config.json b/wdl-ci.config.json index 4315946..01e1183 100644 --- a/wdl-ci.config.json +++ b/wdl-ci.config.json @@ -79,7 +79,7 @@ "tasks": { "parse_families": { "key": "parse_families", - "digest": "rprxafsnidgno35awynatngwbnuw6suo", + "digest": "rbuiru23pdiayrbc4zmrqcjyqay4c2aa", "tests": [ { "inputs": { From a4d57e00e4f267552f2bc22eb01c5660a478899d Mon Sep 17 00:00:00 2001 From: Greg Date: Wed, 14 Feb 2024 11:39:16 -0800 Subject: [PATCH 08/16] Update README.md Co-authored-by: Billy Rowell --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 52c6b97..084b8dc 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ The assembly workflow performs _de novo_ assembly on samples and trios. ## Setup -We recommend cloning the repo rather than downloading the release package. +Clone a tagged version of the git repository. Use the `--branch` flag to pull the desired version, and the `--recursive` flag to pull code from any submodules. ```git clone \ --depth 1 --branch v1.1.0 \ # for reproducibility From b558dc95c10cf3f390bbcfaee18485446736ea48 Mon Sep 17 00:00:00 2001 From: Greg Date: Wed, 14 Feb 2024 11:39:29 -0800 Subject: [PATCH 09/16] Update README.md Co-authored-by: Billy Rowell --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 084b8dc..9af1845 100644 --- a/README.md +++ b/README.md @@ -122,7 +122,7 @@ A cohort can include one or more samples. Samples need not be related. | Type | Name | Description | Notes | | :- | :- | :- | :- | -| String | cohort_id | A unique name for the cohort; used to name outputs. Alphanumeric characters, underscore (_), and dash (-) are allowed. | | +| String | cohort_id | A unique name for the cohort; used to name outputs. Alphanumeric characters, underscore (`_`), and dash (`-`) are allowed. | | | Array[[Sample](#sample)] | samples | The set of samples for the cohort. At least one sample must be defined. | | | Boolean | run_de_novo_assembly_trio | Run trio binned _de novo_ assembly. | Cohort must contain at least one valid trio (child and both parents present in the cohort) | From 9ccd7e888544f1c16a7d3544e01a02bb983b8628 Mon Sep 17 00:00:00 2001 From: Greg Date: Wed, 14 Feb 2024 11:39:35 -0800 Subject: [PATCH 10/16] Update README.md Co-authored-by: Billy Rowell --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 9af1845..e93e021 100644 --- a/README.md +++ b/README.md @@ -134,8 +134,8 @@ Sample information for each sample in the workflow run. | :- | :- | :- | :- | | String | sample_id | A unique name for the sample; used to name outputs. Alphanumeric characters, underscore (_), and dash (-) are allowed | | | Array[[IndexData](https://github.com/PacificBiosciences/wdl-common/blob/main/wdl/structs.wdl)] | movie_bams | The set of unaligned movie BAMs associated with this sample | | -| String? | father_id | Paternal `sample_id`. Alphanumeric characters, underscore (_), and dash (-) are allowed. | | -| String? | mother_id | Maternal `sample_id`. Alphanumeric characters, underscore (_), and dash (-) are allowed. | | +| String? | father_id | Paternal `sample_id`. Alphanumeric characters, underscore (`_`), and dash (`-`) are allowed. | | +| String? | mother_id | Maternal `sample_id`. Alphanumeric characters, underscore (`_`), and dash (`-`) are allowed. | | | Boolean | run_de_novo_assembly | If true, run single-sample _de novo_ assembly for this sample | \[true, false\] | ## [ReferenceData](workflows/humanwgs_structs.wdl) From 6252d83dcb47bcf853fa455487691c04afa733d1 Mon Sep 17 00:00:00 2001 From: Greg Date: Wed, 14 Feb 2024 11:39:47 -0800 Subject: [PATCH 11/16] Update README.md Co-authored-by: Billy Rowell --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index e93e021..e73bfac 100644 --- a/README.md +++ b/README.md @@ -204,7 +204,7 @@ The Docker image used by a particular step of the workflow can be identified by | hifiasm |
  • [hifiasm 0.19.4](https://github.com/chhylp123/hifiasm/releases/tag/0.19.4)
| [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/hifiasm) | | htslib |
  • [htslib 1.14](https://github.com/samtools/htslib/releases/tag/1.14)
| [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/htslib) | | paftools |
  • [paftools 2.26-r1182-dirty](https://github.com/lh3/minimap2/blob/bc588c0eeb26426d0d90a93fb0877358a389c515/misc/paftools.js)
| [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/align_hifiasm) | -| parse-cohort |
  • python 3.8.10; custom scripts
| [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/parse-cohort) | +| pyyaml |
  • python 3.8.10; custom scripts
| [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/f72e862bca2f209b9909e6043ef0197975762f27/docker/pyyaml) | | samtools |
  • [samtools 1.14](https://github.com/samtools/samtools/releases/tag/1.14)
| [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/samtools) | | yak |
  • [yak 0.1](https://github.com/lh3/yak/releases/tag/v0.1)
| [Dockerfile](https://github.com/PacificBiosciences/wdl-dockerfiles/tree/3560fcc5a84e044067cea9c9a7669cfc2659178e/docker/yak) | From 49c2d4ccd2a041494ea6e9c8ca3f1501ec4e4719 Mon Sep 17 00:00:00 2001 From: Greg Date: Wed, 14 Feb 2024 11:39:59 -0800 Subject: [PATCH 12/16] Update README.md Co-authored-by: Billy Rowell --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index e73bfac..d8390b7 100644 --- a/README.md +++ b/README.md @@ -132,7 +132,7 @@ Sample information for each sample in the workflow run. | Type | Name | Description | Notes | | :- | :- | :- | :- | -| String | sample_id | A unique name for the sample; used to name outputs. Alphanumeric characters, underscore (_), and dash (-) are allowed | | +| String | sample_id | A unique name for the sample; used to name outputs. Alphanumeric characters, underscore (`_`), and dash (`-`) are allowed | | | Array[[IndexData](https://github.com/PacificBiosciences/wdl-common/blob/main/wdl/structs.wdl)] | movie_bams | The set of unaligned movie BAMs associated with this sample | | | String? | father_id | Paternal `sample_id`. Alphanumeric characters, underscore (`_`), and dash (`-`) are allowed. | | | String? | mother_id | Maternal `sample_id`. Alphanumeric characters, underscore (`_`), and dash (`-`) are allowed. | | From 4574ebdfe0156323b3cce82d379595e5dae00d01 Mon Sep 17 00:00:00 2001 From: gconcepcion Date: Wed, 14 Feb 2024 11:48:44 -0800 Subject: [PATCH 13/16] add example inputs --- backends/example/single.json | 19 ++++++++++++++++++ backends/example/trio.json | 38 ++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 backends/example/single.json create mode 100644 backends/example/trio.json diff --git a/backends/example/single.json b/backends/example/single.json new file mode 100644 index 0000000..f351659 --- /dev/null +++ b/backends/example/single.json @@ -0,0 +1,19 @@ +{ + "de_novo_assembly.cohort": { + "cohort_id": "HG002", + "samples": [ + { + "father_id": "HG003", + "mother_id": "HG004", + "movie_bams": [ + "/path/to/input1.bam", + "/path/to/input2.bam", + "/path/to/input3.bam" + ], + "run_de_novo_assembly": true, + "sample_id": "HG002" + } + ], + "run_de_novo_assembly_trio": false + } +} diff --git a/backends/example/trio.json b/backends/example/trio.json new file mode 100644 index 0000000..af839e1 --- /dev/null +++ b/backends/example/trio.json @@ -0,0 +1,38 @@ +{ + "de_novo_assembly.cohort": { + "cohort_id": "HG002", + "samples": [ + { + "father_id": "HG003", + "mother_id": "HG004", + "movie_bams": [ + "/path/to/sampleA_1.bam", + "/path/to/sampleA_2.bam" + ], + "run_de_novo_assembly": false, + "sample_id": "HG002" + }, + { + "father_id": "", + "mother_id": "", + "movie_bams": [ + "/path/to/sampleB_1.bam", + "/path/to/sampleB_2.bam" + ], + "run_de_novo_assembly": true, + "sample_id": "HG003" + }, + { + "father_id": "", + "mother_id": "", + "movie_bams": [ + "/path/to/sampleC_1.bam", + "/path/to/sampleC_2.bam" + ], + "run_de_novo_assembly": true, + "sample_id": "HG004" + } + ], + "run_de_novo_assembly_trio": true + } +} From 714aef0275651ab204e6707ddc08e9953b868816 Mon Sep 17 00:00:00 2001 From: gconcepcion Date: Wed, 14 Feb 2024 11:50:03 -0800 Subject: [PATCH 14/16] update readme --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 52c6b97..fa28717 100644 --- a/README.md +++ b/README.md @@ -20,7 +20,7 @@ The assembly workflow performs _de novo_ assembly on samples and trios. We recommend cloning the repo rather than downloading the release package. ```git clone \ - --depth 1 --branch v1.1.0 \ # for reproducibility + --depth 1 --branch v1.0.0 \ # for reproducibility --recursive \ # to clone submodule https://github.com/PacificBiosciences/HiFi-human-assembly-WDL.git ``` From 4852a95f7a9284ab0356e86af9a752a628167e3c Mon Sep 17 00:00:00 2001 From: gconcepcion Date: Wed, 14 Feb 2024 11:53:50 -0800 Subject: [PATCH 15/16] fix git command in README --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 7dcbb94..001cf56 100644 --- a/README.md +++ b/README.md @@ -19,7 +19,8 @@ The assembly workflow performs _de novo_ assembly on samples and trios. Clone a tagged version of the git repository. Use the `--branch` flag to pull the desired version, and the `--recursive` flag to pull code from any submodules. -```git clone \ +``` +git clone \ --depth 1 --branch v1.0.0 \ # for reproducibility --recursive \ # to clone submodule https://github.com/PacificBiosciences/HiFi-human-assembly-WDL.git From 2ab2d8e7efc273c926a6fd84a05d82581dbe15f6 Mon Sep 17 00:00:00 2001 From: gconcepcion Date: Wed, 14 Feb 2024 11:55:58 -0800 Subject: [PATCH 16/16] remove unnecessary lines --- backends/example/single.json | 2 -- backends/example/trio.json | 4 ---- 2 files changed, 6 deletions(-) diff --git a/backends/example/single.json b/backends/example/single.json index f351659..734d169 100644 --- a/backends/example/single.json +++ b/backends/example/single.json @@ -3,8 +3,6 @@ "cohort_id": "HG002", "samples": [ { - "father_id": "HG003", - "mother_id": "HG004", "movie_bams": [ "/path/to/input1.bam", "/path/to/input2.bam", diff --git a/backends/example/trio.json b/backends/example/trio.json index af839e1..b09f10e 100644 --- a/backends/example/trio.json +++ b/backends/example/trio.json @@ -13,8 +13,6 @@ "sample_id": "HG002" }, { - "father_id": "", - "mother_id": "", "movie_bams": [ "/path/to/sampleB_1.bam", "/path/to/sampleB_2.bam" @@ -23,8 +21,6 @@ "sample_id": "HG003" }, { - "father_id": "", - "mother_id": "", "movie_bams": [ "/path/to/sampleC_1.bam", "/path/to/sampleC_2.bam"