Update docs

.dockerignore

@@ -1,3 +1,29 @@
-/shiny/*
 /vignettes/*
 /docs/*
+
+# ignore file extensions
+*.DS_Store
+*.Rmd
+*.html
+*.md
+*.Rhistory
+*.gitignore
+*.Rbuildignore
+*.Rproj
+DESCRIPTION
+
+# ignore folders
+**.git
+**.github
+**.Rproj.user
+*docs
+*vignettes
+*man
+*inst
+*pkgdown
+
+# ignore specific files
+docker-compose.yml
+docker-compose-*.yml
+_pkgdown.yml
+NAMESPACE

.github/ISSUE_TEMPLATE/support-my-organism.md

@@ -0,0 +1,23 @@
+---
+name: Support my organism
+about: I want SeqSender to support my organism.
+title: "[ORGANISM : FEATURE / BUG]"
+labels: help wanted
+assignees: ''
+
+---
+
+**Have you attempted to upload your organism using SeqSender? If so, please list the organism affected. If not, please attempt using SeqSender with it first, as SeqSender currently supports a wide variety of organisms, databases, and submission options.**
+Be sure to check the Submission Wizard in the documentation for all the available customizations for submitting your samples to repositories.
+
+**Which databases are you uploading to? Are all of them affected? If not list which ones are affected:**
+BIOSAMPLE/SRA/GENBANK/GISAID
+
+**Is the problem related to a metadata field, an additional file, available submission options, or the submission process itself?**
+If the field is only an attribute, it can be added to any database even if not validated by SeqSender, by simply adding the correct column name with the database prefix.
+
+**If possible describe the solution you'd like to see along with any other additional details.**
+A clear and concise description of what you think needs to change/made available to resolve your issue.
+
+**Error Logs**
+Add any other context, logs, or screenshots related to the issue here.

.github/workflows/DH_GHCR_upload.yml

@@ -0,0 +1,52 @@
+name: Create and publish docker image to DockerHub and GitHub Container Repository
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  push_to_registry:
+    runs-on: ubuntu-latest
+    permissions:
+      packages: write
+      contents: read
+      attestations: write
+      id-token: write
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v4
+
+      - name: Log into GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            cdcgov/seqsender
+            ghcr.io/${{ github.repository }}
+
+      - name: Build and push Docker image
+        id: push
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: |
+            cdcgov/seqsender:${{ github.ref_name }}
+            cdcgov/seqsender:latest
+            ghcr.io/cdcgov/seqsender:${{ github.ref_name }}
+            ghcr.io/cdcgov/seqsender:latest
+          labels: "Genomic sequence pipeline to automate the process of generating necessary submission files and batch uploading them to public databases."

.gitignore

@@ -22,5 +22,4 @@ docker-compose-*.yaml
 **/.Rproj.user
 **/test_data/*
 **/gisaid_cli/*
-**/COV_TEST_DATA/*
-**/FLU_TEST_DATA/*
+**/*_TEST_DATA/*

Dockerfile

@@ -1,102 +1,92 @@
-# Create an argument to pull a particular version of micromamba image
-ARG micromamba_version
-ARG micromamba_version=${micromamba_version:-1.5.3}
-
-############# base image ##################
-FROM --platform=$BUILDPLATFORM ubuntu:focal as base
-
-# local apt mirror support
-# start every stage with updated apt sources
-ARG APT_MIRROR_NAME=
-RUN if [ -n "$APT_MIRROR_NAME" ]; then sed -i.bak -E '/security/! s^https?://.+?/(debian|ubuntu)^http://'"$APT_MIRROR_NAME"'/\1^' /etc/apt/sources.list && grep '^deb' /etc/apt/sources.list; fi
-RUN apt-get update --allow-releaseinfo-change --fix-missing
-
-############# micromamba image ##################
-
-FROM --platform=$BUILDPLATFORM mambaorg/micromamba:${micromamba_version} as micromamba
-RUN echo "Getting micromamba image"
-
-############# Build Stage: Final ##################
-
-# Build the final image 
-FROM base as final
-
-# if image defaults to a non-root user, then we may want to make the
-# next 3 ARG commands match the values in our image. 
-ENV MAMBA_USER=$MAMBA_USER
-ENV MAMBA_USER_ID=$MAMBA_USER_ID
-ENV MAMBA_USER_GID=$MAMBA_USER_GID
-ENV MAMBA_ROOT_PREFIX="/opt/conda"
-ENV MAMBA_EXE="/bin/micromamba"
-
-COPY --from=micromamba "$MAMBA_EXE" "$MAMBA_EXE"
-COPY --from=micromamba /usr/local/bin/_activate_current_env.sh /usr/local/bin/_activate_current_env.sh
-COPY --from=micromamba /usr/local/bin/_dockerfile_shell.sh /usr/local/bin/_dockerfile_shell.sh
-COPY --from=micromamba /usr/local/bin/_entrypoint.sh /usr/local/bin/_entrypoint.sh
-COPY --from=micromamba /usr/local/bin/_dockerfile_initialize_user_accounts.sh /usr/local/bin/_dockerfile_initialize_user_accounts.sh
-COPY --from=micromamba /usr/local/bin/_dockerfile_setup_root_prefix.sh /usr/local/bin/_dockerfile_setup_root_prefix.sh
-
-# Install system dependencies
-ARG DEBIAN_FRONTEND=noninteractive
-
-# Install system libraries of general use
-RUN apt-get update --allow-releaseinfo-change --fix-missing \
-  && apt-get install --no-install-recommends -y \
-  dos2unix \
-  ca-certificates \
-  && apt clean autoclean \
-  && apt autoremove --yes \
-  && rm -rf /var/lib/{apt,dpkg,cache,log}/
-
-# Create working directory 
-ENV WORKDIR=/data
-
-# Set up volume directory
-VOLUME ${WORKDIR}
-
-# Set up working directory
-WORKDIR ${WORKDIR}
-
-# Allow permission to read and write to working directory
-RUN chmod -R a+rwx ${WORKDIR}
-
-# Create a program variable
-ENV PROJECT_DIR=/seqsender
-
-# Set up a volume directory 
-VOLUME ${PROJECT_DIR}
-
-# Copy all files to project directory
-COPY . ${PROJECT_DIR}
-
-############ Set-up micromamba environment ##################
-
-# Copy requirement files to program directory
-COPY env.yaml "${PROJECT_DIR}/env.yaml"
-
-# Set up environments
-RUN micromamba install --yes --name base -f "${PROJECT_DIR}/env.yaml" \
-    && micromamba clean --all --yes
-
-############# Launch PROGRAM ##################
-
-# Copy bash script to run PROGRAM to docker image
-COPY seqsender-kickoff "${PROJECT_DIR}/seqsender-kickoff"
-
-# Convert bash script from Windows style line endings to Unix-like control characters
-RUN dos2unix "${PROJECT_DIR}/seqsender-kickoff"
-
-# Allow permission to excute the bash script
-RUN chmod a+x "${PROJECT_DIR}/seqsender-kickoff"
-
-# Allow permission to read and write to program directory
-RUN chmod a+rwx ${PROJECT_DIR}
-
-# Export bash script to path
-ENV PATH="$PATH:${PROJECT_DIR}"
-
-# Activate conda environment
-ENV PATH="$PATH:${MAMBA_ROOT_PREFIX}/bin"
-
-# Execute the pipeline 
-ENTRYPOINT ["tail", "-f", "/dev/null"]
+# Create an argument to pull a particular version of micromamba image
+ARG micromamba_version
+ARG micromamba_version=${micromamba_version:-1.5.3}
+
+############# micromamba image ##################
+
+FROM mambaorg/micromamba:${micromamba_version} as micromamba
+RUN echo "Getting micromamba image"
+
+############# base image ##################
+
+FROM ubuntu:focal as base
+
+# if image defaults to a non-root user, then we may want to make the
+# next 3 ARG commands match the values in our image. 
+ENV MAMBA_USER=$MAMBA_USER
+ENV MAMBA_USER_ID=$MAMBA_USER_ID
+ENV MAMBA_USER_GID=$MAMBA_USER_GID
+ENV MAMBA_ROOT_PREFIX="/opt/conda"
+ENV MAMBA_EXE="/bin/micromamba"
+
+COPY --from=micromamba "$MAMBA_EXE" "$MAMBA_EXE"
+COPY --from=micromamba /usr/local/bin/_activate_current_env.sh /usr/local/bin/_activate_current_env.sh
+COPY --from=micromamba /usr/local/bin/_dockerfile_shell.sh /usr/local/bin/_dockerfile_shell.sh
+COPY --from=micromamba /usr/local/bin/_entrypoint.sh /usr/local/bin/_entrypoint.sh
+COPY --from=micromamba /usr/local/bin/_dockerfile_initialize_user_accounts.sh /usr/local/bin/_dockerfile_initialize_user_accounts.sh
+COPY --from=micromamba /usr/local/bin/_dockerfile_setup_root_prefix.sh /usr/local/bin/_dockerfile_setup_root_prefix.sh
+
+# Install system dependencies
+ARG DEBIAN_FRONTEND=noninteractive
+
+# local apt mirror support
+# start every stage with updated apt sources
+ARG APT_MIRROR_NAME=
+RUN if [ -n "$APT_MIRROR_NAME" ]; then sed -i.bak -E '/security/! s^https?://.+?/(debian|ubuntu)^http://'"$APT_MIRROR_NAME"'/\1^' /etc/apt/sources.list && grep '^deb' /etc/apt/sources.list; fi
+RUN apt-get update --allow-releaseinfo-change --fix-missing \
+  && apt-get install --no-install-recommends -y \
+  dos2unix \
+  ca-certificates \
+  && apt clean autoclean \
+  && apt autoremove --yes \
+  && rm -rf /var/lib/{apt,dpkg,cache,log}/
+
+# Create working directory 
+ENV WORKDIR=/data
+
+# Set up volume directory
+VOLUME ${WORKDIR}
+
+# Set up working directory
+WORKDIR ${WORKDIR}
+
+# Allow permission to read and write to working directory
+RUN chmod -R a+rwx ${WORKDIR}
+
+# Create a program variable
+ENV PROJECT_DIR=/seqsender
+
+# Set up a volume directory 
+VOLUME ${PROJECT_DIR}
+
+# Copy all files to project directory
+COPY . ${PROJECT_DIR}
+
+############ Set-up micromamba environment ##################
+
+# Copy requirement files to program directory
+COPY env.yaml "${PROJECT_DIR}/env.yaml"
+
+# Set up environments
+RUN micromamba install --yes --name base -f "${PROJECT_DIR}/env.yaml" \
+    && micromamba clean --all --yes
+
+############# Launch PROGRAM ##################
+
+# Copy bash script to run PROGRAM to docker image
+COPY seqsender-kickoff "${PROJECT_DIR}/seqsender-kickoff"
+
+# Convert bash script from Windows style line endings to Unix-like control characters
+RUN dos2unix "${PROJECT_DIR}/seqsender-kickoff"
+
+# Allow permission to excute the bash script
+RUN chmod a+x "${PROJECT_DIR}/seqsender-kickoff"
+
+# Allow permission to read and write to program directory
+RUN chmod a+rwx ${PROJECT_DIR}
+
+# Export bash script to path
+ENV PATH="$PATH:${PROJECT_DIR}"
+
+# Activate conda environment
+ENV PATH="$PATH:${MAMBA_ROOT_PREFIX}/bin"

README.Rmd

@@ -26,7 +26,7 @@ github_pages_url <- description$GITHUB_PAGES
 
 <p style="font-size: 16px;"><em>Public Database Submission Pipeline</em></p>
 
-**Beta Version**: v1.2.1. This pipeline is currently in Beta testing, and issues could appear during submission. Please use it at your own risk. Feedback and suggestions are welcome! 
+**Beta Version**: v1.2.5. This pipeline is currently in Beta testing, and issues could appear during submission. Please use it at your own risk. Feedback and suggestions are welcome! 
 
 **General Disclaimer**: This repository was created for use by CDC programs to collaborate on public health related projects in support of the [CDC mission](https://www.cdc.gov/about/organization/mission.htm).  GitHub is not hosted by the CDC, but is a third party website used by CDC and its partners to share information and collaborate on software. CDC use of GitHub does not imply an endorsement of any one particular service, product, or enterprise.
 

README.md

@@ -11,7 +11,7 @@
 
 </p>
 
-**Beta Version**: 1.2.1. This pipeline is currently in Beta testing, and
+**Beta Version**: 1.2.5. This pipeline is currently in Beta testing, and
 issues could appear during submission. Please use it at your own risk.
 Feedback and suggestions are welcome\!
 

biosample_sra_handler.py

@@ -244,7 +244,15 @@ def process_biosample_sra_report(report_file: str, database: str, submission_dir
 	if "Action" not in report_dict["SubmissionStatus"]:
 		return submission_status, submission_id
 	try:
-		for action_dict in report_dict["SubmissionStatus"]["Action"]:
+		# If only a single sample, convert into list for proper formatting
+		if isinstance(report_dict["SubmissionStatus"]["Action"], list):
+			action_list = report_dict["SubmissionStatus"]["Action"]
+		elif isinstance(report_dict["SubmissionStatus"]["Action"], dict):
+			action_list = [report_dict["SubmissionStatus"]["Action"]]
+		else:
+			print(f"Error: Unable to correctly process BioSample report at: {report_file}", file=sys.stderr)
+			return submission_status, submission_id
+		for action_dict in action_list:
 			# Skip if incorrect database
 			if "@target_db" not in action_dict or action_dict["@target_db"].lower() != database.lower():
 				continue
@@ -271,6 +279,8 @@ def process_biosample_sra_report(report_file: str, database: str, submission_dir
 					sample_info.append({sample_name_col:sample_name, f"{column_prefix}_status":action_dict["@status"], f"{column_prefix}_accession":accession, f"{column_prefix}_message":""})
 	except:
 		pass
+	if submission_status == "PROCESSED" and not sample_info:
+		print(f"Error: Unable to process {database} report.xml to retrieve accessions at: {report_file}", file=sys.stderr)
 	if sample_info:
 		update_df = pd.DataFrame(sample_info)
 		upload_log.update_submission_status_csv(submission_dir=submission_dir, update_database=database, update_df=update_df)