Merge branch 'main' into liftover

.github/workflows/manubot.yaml

@@ -3,11 +3,9 @@ on:
   push:
     branches:
       - main
-      - master
   pull_request:
     branches:
       - main
-      - master
   # NOTE: scheduled workflows aren't supported
   # https://git.luolix.topmunity/t/github-event-repository-fork-context-does-detect-forks-in-scheduled-jobs/185925
   workflow_dispatch:
@@ -19,7 +17,7 @@ on:
       BUILD_DOCX:
         type: boolean
         description: generate DOCX output
-        default: true
+        default: false
       BUILD_LATEX:
         type: boolean
         description: generate LaTeX output
@@ -33,13 +31,20 @@ on:
         description: Use Docker to generate PDF
         default: true
 
+concurrency:
+  # only one run per branch at a time
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   manubot:
     name: Manubot
     runs-on: ubuntu-latest
     permissions:
       contents: write
+      pull-requests: write
     env:
+      BUILD_DOCX: true
       GITHUB_PULL_REQUEST_SHA: ${{ github.event.pull_request.head.sha }}
       # Set SPELLCHECK to true/false for whether to check spelling in this action.
       # For workflow dispatch jobs, this SPELLCHECK setting will be overridden by the user input.
@@ -49,7 +54,7 @@ jobs:
         shell: bash --login {0}
     steps:
       - name: Checkout Repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           # fetch entire commit history to support get_rootstock_commit
           fetch-depth: 0
@@ -71,28 +76,29 @@ jobs:
           echo "DEFAULT_BRANCH_REF=refs/heads/$DEFAULT_BRANCH" >> $GITHUB_ENV
           echo "DEFAULT_BRANCH=$DEFAULT_BRANCH"
       - name: Cache
-        uses: actions/cache@v3
+        uses: actions/cache@v4
         with:
           path: ci/cache
           key: ci-cache-${{ github.ref }}
           restore-keys: |
             ci-cache-${{ env.DEFAULT_BRANCH_REF }}
       - name: Install Environment
-        uses: conda-incubator/setup-miniconda@v2
+        uses: conda-incubator/setup-miniconda@v3
         with:
           activate-environment: manubot
           environment-file: build/environment.yml
           auto-activate-base: false
           miniforge-variant: Mambaforge
-          miniforge-version: 'latest'
+          miniforge-version: "latest"
           use-mamba: true
       - name: Install Spellcheck
         if: env.SPELLCHECK == 'true'
         run: bash ci/install-spellcheck.sh
       - name: Build Manuscript
-        run: BUILD_DOCX=true bash build/build.sh
+        run: bash build/build.sh
       - name: Upload Artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
+        id: artifact-upload-step
         with:
           name: manuscript-${{ github.run_id }}-${{ env.TRIGGERING_SHA_7 }}
           path: output
@@ -104,3 +110,34 @@ jobs:
           CI_BUILD_WEB_URL: https://github.com/${{ github.repository }}/commit/${{ github.sha }}/checks
           CI_JOB_WEB_URL: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}
         run: bash ci/deploy.sh
+      - name: Count spelling errors
+        run: |
+          # count the number of spelling errors using the spelling-error-locations.txt file
+          # this file does not include preamble or author list spelling errors
+          if [ -s output/spelling-error-locations.txt ]; then
+            echo "SPELLING_ERRORS=$(wc -l < output/spelling-error-locations.txt)" >> $GITHUB_ENV
+          else
+            echo "SPELLING_ERRORS=0" >> $GITHUB_ENV
+          fi
+      - name: Post artifact comment to PR
+        if: github.event_name == 'pull_request'
+        uses: peter-evans/create-or-update-comment@v4
+        with:
+          issue-number: ${{ github.event.pull_request.number }}
+          body: |
+            **Click the link below to download the manuscript build as a ZIP file.**
+            This build is associated with commit ${{ env.TRIGGERING_SHA_7 }}.
+
+            [Manuscript build](${{ steps.artifact-upload-step.outputs.artifact-url }})
+
+            **There were ${{ env.SPELLING_ERRORS }} spelling errors.**
+            Check the build link above for details.
+
+      - name: Fail for spelling errors in manual builds
+        if: github.event_name == 'workflow_dispatch' && env.SPELLCHECK == 'true'
+        run: |
+          if [ $SPELLING_ERRORS ]; then
+            echo "Spelling errors (some may be in the author list):"
+            cat output/spelling-errors.txt
+            exit 1
+          fi

build/assets/custom-dictionary.txt

@@ -1,23 +1,226 @@
-personal_ws-1.1 en 22
-al
+personal_ws-1.1 en 225
+adenylated
+Aditya
+aliquot
+ALK
+Ambion
+AML
+AMPure
+Arriba
+Asif
+ATRT
+BAF
+barcode
+Barcoded
+barcoding
+BaseSpace
+bcps
+Bioinformatics
+Biomedicine
+biospecimen
+biospecimens
+Biosystem
+Biosystems
+Blackden
+CAVATICA
+CBTN
+CCDI
+cDNA
+centromeric
+Chinwalla
+chordoma
+Chuwei
+cn
+cnv
+CNVKit
+CNVs
+Corbett
+CpG
+CPUs
+CRANIO
+Curation
+cytobands
+dataset
+datasets
+dbSNP
+deconv
+DESeq
+DGD
+DIPG
+Diskin
+DKFZ
 doi
-eq
-et
-github
-isbn
-latex
-manubot
-orcid
+DRC
+EdgeSeq
+efo
+embryonal
+Ennis
+Ensembl
+ENSG
+EPN
+ERCC
+EWS
+exome
+Farrel
+FASTQ
+Flowcell
+FPKM
+FREEC
+Gabriella
+ganglioneuroblastoma
+ganglioneuroma
+Gaonkar
+GATK
+GENCODE
+Geng
+genomic
+genomically
+Genotype
+germline
+GFF
+gistic
+glioma
+gliomas
+GMKF
+gnomAD
+gtex
+gtf
+HGG
+histological
+HL
+hotspot
+HotSpotAllele
+HPC
+HTG
+IDAT
+IHG
+IHGs
+Illumina
+INDEL
+Infinium
+isoform
+Jin
+Kapa
+KK
+Komal
+Kraya
+Krutika
+Kuren
+Lahiri
+LGAT
+Lueder
+Lymphoblastic
+lysis
+MAF
+MantaSV
+mappability
+Mariarita
+methylation
+MGMT
+minfi
+miRNA
+miRNAs
+Missense
+MNP
+MNPs
+MNV
+MNVs
+molecularly
+mondo
+MTP
+multinucleotide
+Mutect
+MYC
+MYCN
+Myeloid
+NaOH
+NBL
+NCI
+NCI's
+Neuro
+Neuroblastoma
+neurocytoma
+Nextseq
+nonsynonymous
+normals
+NovaSeq
+NTRK
+oncogenic
+ONCOSEQ
+OPC
+OpenPBTA
+OpenPedCan
+ORCID
+Osteosarcoma
+pathogenesis
+PBTA
+PCR
+pedcbio
+PedcBioPortal
+pedot
 permalink
-pmc
-pmcid
-pmid
-pubmed
-rootstock
-s
-strikethrough
-svg
-svgs
-tbl
-unicode
-wikidata
+Phul
+Picard
+PicoGreen
+PNOC
+polymorphisms
+pre
+preprocessed
+preprocessing
+proteomic
+qPCR
+Quant
+Rathi
+README
+reproducibility
+Resnick
+Rhabdoid
+RiboGreen
+rMATS
+rnaseq
+Rokita
+ROS
+RTK
+Saksham
+Sangeeta
+Santi
+Shukla
+Sickler
+Slurm
+SNP
+snps
+SNV
+SNVs
+Strelka
+subtype
+subtyped
+subtypes
+subtyping
+Takara
+TCGA
+telomeric
+teratoid
+TMB
+TP
+TPM
+transcriptome
+TruSeq
+TYR
+tyrosine
+utils
+VarDict
+VCF
+VEP
+Wafula
+WGS
+Wilm's
+WTA
+WXS
+Xiaoyan
+XP
+Yuanchao
+Yuankun
+Zhang
+Zhong
+Zhu
+Zhuangzhuang

content/02.introduction.md

@@ -28,7 +28,7 @@ OpenPedCan analyses include Neuroblastoma data from the Kids First project.
 
 **The Genotype-Tissue Expression [(GTEx)](https://gtexportal.org/home/)**
 GTEx project is an ongoing effort to build a comprehensive public data resource and tissue bank to study tissue-specific gene expression, regulation and their relationship with genetic variants.
-Samples were collected from 54 non-diseased tissue sites across nearly 1000 individuals, primarily for molecular assays including WGS, WES, and RNA-Seq.
+Samples were collected from 54 non-diseased tissue sites across nearly 1000 individuals, primarily for molecular assays including WGS, WXS, and RNA-Seq.
 OpenPedCan project includes 17,382 GTEx RNA-Seq samples from GTEx v8 release, which span across 31 GTEx groups in the v12 release.
 
 **The Cancer Genome Atlas Program [(TCGA)](https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga)**