diff --git a/.github/dependabot.yml b/.github/dependabot.yml
index 9a95c56552..246fafb79f 100644
--- a/.github/dependabot.yml
+++ b/.github/dependabot.yml
@@ -40,9 +40,9 @@ updates:
       interval: monthly
     groups:
       minorAndPatch:
-          update-types:
-            - "minor"
-            - "patch"
+        update-types:
+          - "minor"
+          - "patch"
   - package-ecosystem: docker
     directories:
       - website
@@ -58,6 +58,6 @@ updates:
       interval: weekly
     groups:
       minorAndPatch:
-          update-types:
-            - "minor"
-            - "patch"
+        update-types:
+          - "minor"
+          - "patch"
diff --git a/.github/workflows/actions-usage.yml b/.github/workflows/actions-usage.yml
index 0650635775..45ba379b85 100644
--- a/.github/workflows/actions-usage.yml
+++ b/.github/workflows/actions-usage.yml
@@ -1,10 +1,8 @@
 name: Github Actions Usage Stats
-
 on:
   workflow_dispatch:
   schedule:
     - cron: "0 3 * * *" # Runs at 03:00 AM (UTC) every day
-
 jobs:
   gha-usage-minutes-report:
     runs-on: ubuntu-latest
diff --git a/.github/workflows/backend-image.yml b/.github/workflows/backend-image.yml
index b88b878f2a..5f929d4353 100644
--- a/.github/workflows/backend-image.yml
+++ b/.github/workflows/backend-image.yml
@@ -1,5 +1,4 @@
 name: backend-image
-
 on:
   pull_request:
   push:
@@ -19,17 +18,14 @@ on:
         description: "Build for ARM as well"
         default: "false"
         required: true
-
 env:
   DOCKER_IMAGE_NAME: ghcr.io/loculus-project/backend
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
   BUILD_ARM: ${{ github.event.inputs.build_arm || inputs.build_arm || github.ref == 'refs/heads/main' }}
   sha: ${{ github.event.pull_request.head.sha || github.sha }}
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-backend
   cancel-in-progress: true
-
 jobs:
   backend-image:
     name: Build Backend Docker Image # Don't change: Referenced by .github/workflows/update-argocd-metadata.yml
@@ -45,13 +41,11 @@ jobs:
       - name: Shorten sha
         run: echo "sha=${sha::7}" >> $GITHUB_ENV
       - uses: actions/checkout@v4
-
       - name: Generate files hash
         id: files-hash
         run: |
           DIR_HASH=$(echo -n ${{ hashFiles('backend/**', '.github/workflows/backend-image.yml') }})
           echo "DIR_HASH=$DIR_HASH${{ env.BUILD_ARM == 'true' && '-arm' || '' }}" >> $GITHUB_ENV
-
       - name: Setup Docker metadata
         id: dockerMetadata
         uses: docker/metadata-action@v5
@@ -69,32 +63,26 @@ jobs:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
-
       - name: Check if image exists
         id: check-image
         run: |
           EXISTS=$(docker manifest inspect ${{ env.DOCKER_IMAGE_NAME }}:${{ env.DIR_HASH }} > /dev/null 2>&1 && echo "true" || echo "false")
           echo "CACHE_HIT=$EXISTS" >> $GITHUB_ENV
-
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
-
       - name: Set up JDK
         if: env.CACHE_HIT == 'false'
         uses: actions/setup-java@v4
         with:
           java-version: "21"
           distribution: "adopt"
-
       - name: Setup Gradle
         if: env.CACHE_HIT == 'false'
         uses: gradle/actions/setup-gradle@v3
-
       - name: Build Backend
         if: env.CACHE_HIT == 'false'
         working-directory: ./backend
         run: ./gradlew bootJar
-
       - name: Build and push image if input files changed
         if: env.CACHE_HIT == 'false'
         uses: docker/build-push-action@v5
@@ -105,7 +93,6 @@ jobs:
           cache-from: type=gha,scope=backend-${{ github.ref }}
           cache-to: type=gha,mode=max,scope=backend-${{ github.ref }}
           platforms: ${{ env.BUILD_ARM == 'true' && 'linux/amd64,linux/arm64' || 'linux/amd64' }}
-
       - name: Retag and push existing image if cache hit
         if: env.CACHE_HIT == 'true'
         run: |
diff --git a/.github/workflows/backend-tests.yml b/.github/workflows/backend-tests.yml
index 0d51ad5b81..f2480bf6f0 100644
--- a/.github/workflows/backend-tests.yml
+++ b/.github/workflows/backend-tests.yml
@@ -1,5 +1,4 @@
 name: backend-tests
-
 on:
   pull_request:
     paths:
@@ -9,11 +8,9 @@ on:
     branches:
       - main
   workflow_dispatch:
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-backend-tests
   cancel-in-progress: true
-
 jobs:
   Tests:
     runs-on: codebuild-loculus-ci-${{ github.run_id }}-${{ github.run_attempt }}
diff --git a/.github/workflows/build-arm-images.yaml b/.github/workflows/build-arm-images.yaml
index ee67e7e938..1d6d48f060 100644
--- a/.github/workflows/build-arm-images.yaml
+++ b/.github/workflows/build-arm-images.yaml
@@ -2,43 +2,35 @@
 
 on:
   workflow_dispatch:
-
 permissions:
   contents: read
   packages: write
   checks: read
-
 jobs:
   trigger-backend:
     uses: ./.github/workflows/backend-image.yml
     with:
       build_arm: true
-
   trigger-config-preprocessor:
     uses: ./.github/workflows/config-preprocessor-image.yml
     with:
       build_arm: true
-
   trigger-dummy-preprocessing:
     uses: ./.github/workflows/preprocessing-dummy-image.yml
     with:
       build_arm: true
-
   trigger-ingest:
     uses: ./.github/workflows/ingest-image.yml
     with:
       build_arm: true
-
   trigger-keycloakify:
     uses: ./.github/workflows/keycloakify-image.yml
     with:
       build_arm: true
-
   trigger-preprocessing-nextclade:
     uses: ./.github/workflows/preprocessing-nextclade-image.yml
     with:
       build_arm: true
-
   trigger-website:
     uses: ./.github/workflows/website-image.yml
     with:
diff --git a/.github/workflows/clean-cache-post-merge.yml b/.github/workflows/clean-cache-post-merge.yml
index 228ad67e68..29e0c5cbac 100644
--- a/.github/workflows/clean-cache-post-merge.yml
+++ b/.github/workflows/clean-cache-post-merge.yml
@@ -11,7 +11,6 @@ on:
         description: "Branch name"
         required: false
         default: ""
-
 jobs:
   cleanup:
     runs-on: ubuntu-latest
@@ -29,7 +28,6 @@ jobs:
           else
             echo "branch=${{ github.ref_name }}" >> $GITHUB_OUTPUT
           fi
-
       - name: Cleanup
         run: |
           gh extension install actions/gh-actions-cache
diff --git a/.github/workflows/config-preprocessor-image.yml b/.github/workflows/config-preprocessor-image.yml
index b786c39f3a..5b73b65496 100644
--- a/.github/workflows/config-preprocessor-image.yml
+++ b/.github/workflows/config-preprocessor-image.yml
@@ -1,5 +1,4 @@
 name: config-processor-image
-
 on:
   pull_request:
   push:
@@ -19,21 +18,17 @@ on:
         description: "Build for ARM as well"
         default: "false"
         required: true
-
 env:
   DOCKER_IMAGE_NAME: ghcr.io/loculus-project/config-processor
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
   BUILD_ARM: ${{ github.event.inputs.build_arm || inputs.build_arm || github.ref == 'refs/heads/main' }}
   sha: ${{ github.event.pull_request.head.sha || github.sha }}
-
 defaults:
   run:
     working-directory: ./kubernetes/config-processor
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-config-processor-${{github.event.inputs.build_arm}}
   cancel-in-progress: true
-
 jobs:
   config-processor-image:
     name: Build config-processor Docker Image # Don't change: Referenced by .github/workflows/update-argocd-metadata.yml
diff --git a/.github/workflows/dependabot-validate.yml b/.github/workflows/dependabot-validate.yml
index 7e4ed6ba7e..bfccdc6057 100644
--- a/.github/workflows/dependabot-validate.yml
+++ b/.github/workflows/dependabot-validate.yml
@@ -1,5 +1,4 @@
 name: dependabot validate
-
 on:
   pull_request:
     paths:
diff --git a/.github/workflows/docs-deploy.yml b/.github/workflows/docs-deploy.yml
index 0ac3eac8e1..07c717743a 100644
--- a/.github/workflows/docs-deploy.yml
+++ b/.github/workflows/docs-deploy.yml
@@ -1,38 +1,30 @@
 name: Builds and deploy documentation
-
 on:
   workflow_dispatch:
   push:
     branches:
       - main
-
 jobs:
   build-and-deploy:
     permissions:
       contents: write
     runs-on: ubuntu-latest
     timeout-minutes: 15
-
     steps:
       - name: Checkout Repository
         uses: actions/checkout@v4
-
       - name: Set up Node.js
         uses: actions/setup-node@v4
         with:
           node-version-file: ./docs/.nvmrc
-
       - name: Navigate to docs directory
         run: cd docs
-
       - name: Install Dependencies
         run: npm install
         working-directory: ./docs
-
       - name: Build Project
         run: npm run build
         working-directory: ./docs
-
       - name: Deploy to GitHub Pages
         uses: peaceiris/actions-gh-pages@v4
         with:
diff --git a/.github/workflows/docs-test.yml b/.github/workflows/docs-test.yml
index 37e935ef89..a1394bad9d 100644
--- a/.github/workflows/docs-test.yml
+++ b/.github/workflows/docs-test.yml
@@ -1,5 +1,4 @@
 name: Docs Build Check
-
 on:
   pull_request:
     paths:
@@ -8,31 +7,24 @@ on:
   push:
     branches:
       - main
-
   workflow_dispatch:
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-docs-build
   cancel-in-progress: true
-
 jobs:
   check-docs-build:
     runs-on: ubuntu-latest
     timeout-minutes: 15
-
     steps:
       - name: Checkout Repository
         uses: actions/checkout@v4
-
       - name: Set up Node.js
         uses: actions/setup-node@v4
         with:
           node-version-file: ./docs/.nvmrc
-
       - name: Install Dependencies
         run: npm install
         working-directory: ./docs
-
       - name: Check Build
         run: npm run build
         working-directory: ./docs
diff --git a/.github/workflows/e2e-k3d.yml b/.github/workflows/e2e-k3d.yml
index a9c7abaa39..43b042a447 100644
--- a/.github/workflows/e2e-k3d.yml
+++ b/.github/workflows/e2e-k3d.yml
@@ -1,5 +1,4 @@
 name: E2E test (on kubernetes)
-
 on:
   workflow_dispatch:
     inputs:
@@ -20,11 +19,9 @@ on:
   push:
     branches:
       - main
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-e2e-k3d
   cancel-in-progress: true
-
 jobs:
   k3d-e2e:
     permissions:
@@ -32,87 +29,68 @@ jobs:
       contents: read
       checks: read
       actions: read # Required by workflow-telemetry-action
-
     runs-on: ubuntu-latest-m
     timeout-minutes: 45
-
     env:
       ALL_BROWSERS: ${{ github.ref == 'refs/heads/main' || github.event.inputs.all_browsers && 'true' || 'false' }}
       sha: ${{ github.event.pull_request.head.sha || github.sha }}
       wait_timeout: ${{ github.ref == 'refs/heads/main' && 900 || 180 }}
-
     steps:
       - name: Shorten sha
         run: echo "sha=${sha::7}" >> $GITHUB_ENV
       - name: Collect Workflow Telemetry
         uses: catchpoint/workflow-telemetry-action@v2
-
       - name: Checkout repository
         uses: actions/checkout@v4
-
       - name: Install k3d
         run: |
           curl -s https://raw.githubusercontent.com/rancher/k3d/main/install.sh | bash
           k3d version
-
       - uses: azure/setup-helm@v4
-
       - name: Create k3d cluster
         run: |
           ./deploy.py --verbose cluster
-
       - name: Default template with helm
         uses: WyriHaximus/github-action-helm3@v4
         with:
           exec: helm template loculus kubernetes/loculus
-
       - name: E2E Template with helm
         uses: WyriHaximus/github-action-helm3@v4
         with:
           exec: ./deploy.py --verbose helm --branch ${{ github.ref_name }} --sha ${{ env.sha }} --for-e2e --template > /tmp/helm_template.yaml
-
       - name: Upload default helm template
         uses: actions/upload-artifact@v4
         with:
           name: helm-template
           path: /tmp/helm_template.yaml
-
       - name: Deploy with helm
         run: |
           ./deploy.py --verbose helm --branch ${{ github.ref_name }} --sha ${{ env.sha }} --for-e2e
-
       - uses: actions/setup-node@v4
         with:
           node-version-file: ./website/.nvmrc
-
       - name: Cache .npm
         uses: actions/cache@v4
         with:
           path: ~/.npm
           key: ${{ runner.os }}-node-${{ hashFiles('website/**/package-lock.json') }}
-
       - name: Install dependencies
         run: cd website && npm i
-
       - name: Get Installed Playwright Version
         id: playwright-version
         run: cd website && echo "PLAYWRIGHT_VERSION=$(node -e "console.log(require('./package-lock.json').packages['node_modules/@playwright/test'].version)")" >> $GITHUB_ENV
-
       - name: Cache Playwright Browsers
         uses: actions/cache@v4
         id: playwright-cache
         with:
           path: ~/.cache/ms-playwright
           key: ${{ runner.os }}-playwright-${{ env.PLAYWRIGHT_VERSION }}
-
       - name: Install Playwright Browsers and System Dependencies
         run: cd website && npx playwright install --with-deps
         if: steps.playwright-cache.outputs.cache-hit != 'true'
-
       - name: Install only System Dependencies
         run: cd website && npx playwright install-deps
         if: steps.playwright-cache.outputs.cache-hit == 'true'
-
       # Action misbehaved
       # # Waits are identical to the update-argocd-metadata.yml file
       # # Mirror changes to that file
@@ -148,7 +126,6 @@ jobs:
       #     repo-token: ${{ secrets.GITHUB_TOKEN }}
       #     wait-interval: 2
       # # End of wait block
-
       - name: Wait for the pods to be ready
         run: ./.github/scripts/wait_for_pods_to_be_ready.py --timeout ${{ env.wait_timeout }}
       - name: Sleep for 10 secs
@@ -172,7 +149,6 @@ jobs:
           name: test-results
           path: website/test-results/
           retention-days: 30
-
       - name: List running pods
         if: ${{ !cancelled() }}
         run: kubectl get pods --all-namespaces
@@ -182,7 +158,6 @@ jobs:
       - name: Show events
         if: ${{ !cancelled() }}
         run: kubectl get events
-
       - name: Save logs from all containers to file
         if: ${{ !cancelled() }}
         run: ./.github/scripts/collect_kubernetes_logs.sh
diff --git a/.github/workflows/format-website-on-dispatch.yml b/.github/workflows/format-website-on-dispatch.yml
index b5ec89dc32..3b065d145f 100644
--- a/.github/workflows/format-website-on-dispatch.yml
+++ b/.github/workflows/format-website-on-dispatch.yml
@@ -1,5 +1,4 @@
 name: Format website code
-
 on:
   workflow_dispatch:
   pull_request:
@@ -13,30 +12,25 @@ jobs:
       contents: write
     runs-on: ubuntu-latest
     timeout-minutes: 15
-
     steps:
       - name: Checkout Repository
         uses: actions/checkout@v4
         with:
           ref: ${{ github.head_ref }}
-
       - name: Set up Node.js
         uses: actions/setup-node@v2
         with:
           node-version-file: ./website/.nvmrc
-
       - name: Cache .npm
         uses: actions/cache@v4
         with:
           path: ~/.npm
           key: ${{ runner.os }}-node-${{ hashFiles('website/**/package-lock.json') }}
-
       - name: NPM install and format website
         working-directory: website
         run: |
           npm install
           npm run format
-
       - name: Commit and Push Changes
         run: |
           git config --global user.name 'Loculus bot'
diff --git a/.github/workflows/ingest-image.yml b/.github/workflows/ingest-image.yml
index 8a8cb83523..35a6d7df2d 100644
--- a/.github/workflows/ingest-image.yml
+++ b/.github/workflows/ingest-image.yml
@@ -18,17 +18,14 @@ on:
         description: "Build for ARM as well"
         default: false
         required: false
-
 env:
   DOCKER_IMAGE_NAME: ghcr.io/loculus-project/ingest
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
   BUILD_ARM: ${{ github.event.inputs.build_arm || inputs.build_arm || github.ref == 'refs/heads/main' }}
   sha: ${{ github.event.pull_request.head.sha || github.sha }}
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-ingest-${{github.event.inputs.build_arm}}
   cancel-in-progress: true
-
 jobs:
   ingest-image:
     name: Build ingest Docker Image # Don't change: Referenced by .github/workflows/update-argocd-metadata.yml
@@ -42,13 +39,11 @@ jobs:
       - name: Shorten sha
         run: echo "sha=${sha::7}" >> $GITHUB_ENV
       - uses: actions/checkout@v4
-
       - name: Generate files hash
         id: files-hash
         run: |
           DIR_HASH=$(echo -n ${{ hashFiles('ingest/**', '.github/workflows/ingest-image.yml') }})
           echo "DIR_HASH=$DIR_HASH${{ env.BUILD_ARM == 'true' && '-arm' || '' }}" >> $GITHUB_ENV
-
       - name: Setup Docker metadata
         id: dockerMetadata
         uses: docker/metadata-action@v5
@@ -60,23 +55,19 @@ jobs:
             type=raw,value=${{ env.BRANCH_NAME }}
             type=raw,value=commit-${{ env.sha }}
             type=raw,value=${{ env.BRANCH_NAME }}-arm,enable=${{ env.BUILD_ARM }}
-
       - name: Login to GitHub Container Registry
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
-
       - name: Check if image exists
         id: check-image
         run: |
           EXISTS=$(docker manifest inspect ${{ env.DOCKER_IMAGE_NAME }}:${{ env.DIR_HASH }} > /dev/null 2>&1 && echo "true" || echo "false")
           echo "CACHE_HIT=$EXISTS" >> $GITHUB_ENV
-
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
-
       - name: Build and push image if input files changed
         if: env.CACHE_HIT == 'false'
         uses: docker/build-push-action@v5
@@ -87,7 +78,6 @@ jobs:
           cache-from: type=gha,scope=ingest-${{ github.ref }}
           cache-to: type=gha,mode=max,scope=ingest-${{ github.ref }}
           platforms: ${{ env.BUILD_ARM == 'true' && 'linux/amd64,linux/arm64' || 'linux/amd64' }}
-
       - name: Retag and push existing image if cache hit
         if: env.CACHE_HIT == 'true'
         run: |
diff --git a/.github/workflows/keycloakify-image.yml b/.github/workflows/keycloakify-image.yml
index 150cd9200f..a7d3d0fe7c 100644
--- a/.github/workflows/keycloakify-image.yml
+++ b/.github/workflows/keycloakify-image.yml
@@ -1,5 +1,4 @@
 name: keycloakify-image
-
 on:
   pull_request:
   push:
@@ -24,11 +23,9 @@ env:
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
   BUILD_ARM: ${{ github.event.inputs.build_arm || inputs.build_arm || github.ref == 'refs/heads/main' }}
   sha: ${{ github.event.pull_request.head.sha || github.sha }}
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-keycloak-buil-${{github.event.inputs.build_arm}}d
   cancel-in-progress: true
-
 jobs:
   keycloakify-image:
     name: Build keycloakify Docker Image # Don't change: Referenced by .github/workflows/update-argocd-metadata.yml
diff --git a/.github/workflows/keycloakify-test.yml b/.github/workflows/keycloakify-test.yml
index 87775f3926..1a0da2cbf7 100644
--- a/.github/workflows/keycloakify-test.yml
+++ b/.github/workflows/keycloakify-test.yml
@@ -1,5 +1,4 @@
 name: keycloakify-test
-
 on:
   workflow_dispatch:
   pull_request:
@@ -9,11 +8,9 @@ on:
   push:
     branches:
       - main
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-keycloak-test
   cancel-in-progress: true
-
 jobs:
   keycloakify-test:
     name: Test keycloakify local builds
diff --git a/.github/workflows/preprocessing-dummy-image.yml b/.github/workflows/preprocessing-dummy-image.yml
index d56cb9ffc2..aca0eacc54 100644
--- a/.github/workflows/preprocessing-dummy-image.yml
+++ b/.github/workflows/preprocessing-dummy-image.yml
@@ -1,5 +1,4 @@
 name: preprocessing-dummy-image
-
 on:
   pull_request:
   push:
@@ -19,17 +18,14 @@ on:
         description: "Build for ARM as well"
         default: false
         required: false
-
 env:
   DOCKER_IMAGE_NAME: ghcr.io/loculus-project/preprocessing-dummy
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
   BUILD_ARM: ${{ github.event.inputs.build_arm || inputs.build_arm || github.ref == 'refs/heads/main' }}
   sha: ${{ github.event.pull_request.head.sha || github.sha }}
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-preprocessing-dumm-${{github.event.inputs.build_arm}}y
   cancel-in-progress: true
-
 jobs:
   preprocessing-dummy-image:
     name: Preprocessing dummy docker image build # Don't change: Referenced by .github/workflows/update-argocd-metadata.yml
@@ -42,13 +38,11 @@ jobs:
       - name: Shorten sha
         run: echo "sha=${sha::7}" >> $GITHUB_ENV
       - uses: actions/checkout@v4
-
       - name: Generate files hash
         id: files-hash
         run: |
           DIR_HASH=$(echo -n ${{ hashFiles('preprocessing/dummy/**', '.github/workflows/preprocessing-dummy-image.yml') }})
           echo "DIR_HASH=$DIR_HASH${{ env.BUILD_ARM == 'true' && '-arm' || '' }}" >> $GITHUB_ENV
-
       - name: Setup Docker metadata
         id: dockerMetadata
         uses: docker/metadata-action@v5
@@ -60,23 +54,19 @@ jobs:
             type=raw,value=${{ env.BRANCH_NAME }}
             type=raw,value=commit-${{ env.sha }}
             type=raw,value=${{ env.BRANCH_NAME }}-arm,enable=${{ env.BUILD_ARM }}
-
       - name: Login to GitHub Container Registry
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
-
       - name: Check if image exists
         id: check-image
         run: |
           EXISTS=$(docker manifest inspect ${{ env.DOCKER_IMAGE_NAME }}:${{ env.DIR_HASH }} > /dev/null 2>&1 && echo "true" || echo "false")
           echo "CACHE_HIT=$EXISTS" >> $GITHUB_ENV
-
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
-
       - name: Build and push image
         if: env.CACHE_HIT == 'false'
         uses: docker/build-push-action@v5
@@ -87,7 +77,6 @@ jobs:
           cache-from: type=gha,scope=preprocessing-dummy-${{ github.ref }}
           cache-to: type=gha,mode=max,scope=preprocessing-dummy-${{ github.ref }}
           platforms: ${{ env.BUILD_ARM == 'true' && 'linux/amd64,linux/arm64' || 'linux/amd64' }}
-
       - name: Tag and push image if cache hit
         if: env.CACHE_HIT == 'true'
         run: |
diff --git a/.github/workflows/preprocessing-nextclade-image.yml b/.github/workflows/preprocessing-nextclade-image.yml
index f8c068a867..83223243b2 100644
--- a/.github/workflows/preprocessing-nextclade-image.yml
+++ b/.github/workflows/preprocessing-nextclade-image.yml
@@ -1,5 +1,4 @@
 name: preprocessing-nextclade-image
-
 on:
   pull_request:
   push:
@@ -19,17 +18,14 @@ on:
         description: "Build for ARM as well"
         default: false
         required: false
-
 env:
   DOCKER_IMAGE_NAME: ghcr.io/loculus-project/preprocessing-nextclade
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
   BUILD_ARM: ${{ github.event.inputs.build_arm || inputs.build_arm || github.ref == 'refs/heads/main' }}
   sha: ${{ github.event.pull_request.head.sha || github.sha }}
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-preprocessing-nextclade-${{github.event.inputs.build_arm}}
   cancel-in-progress: true
-
 jobs:
   preprocessing-nextclade-image:
     name: Build preprocessing-nextclade Docker Image # Don't change: Referenced by .github/workflows/update-argocd-metadata.yml
@@ -43,13 +39,11 @@ jobs:
       - name: Shorten sha
         run: echo "sha=${sha::7}" >> $GITHUB_ENV
       - uses: actions/checkout@v4
-
       - name: Generate files hash
         id: files-hash
         run: |
           DIR_HASH=$(echo -n ${{ hashFiles('preprocessing/nextclade/**', '.github/workflows/preprocessing-nextclade-image.yml') }})
           echo "DIR_HASH=$DIR_HASH${{ env.BUILD_ARM == 'true' && '-arm' || '' }}" >> $GITHUB_ENV
-
       - name: Setup Docker metadata
         id: dockerMetadata
         uses: docker/metadata-action@v5
@@ -61,23 +55,19 @@ jobs:
             type=raw,value=${{ env.BRANCH_NAME }}
             type=raw,value=commit-${{ env.sha }}
             type=raw,value=${{ env.BRANCH_NAME }}-arm,enable=${{ env.BUILD_ARM }}
-
       - name: Login to GitHub Container Registry
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
-
       - name: Check if image exists
         id: check-image
         run: |
           EXISTS=$(docker manifest inspect ${{ env.DOCKER_IMAGE_NAME }}:${{ env.DIR_HASH }} > /dev/null 2>&1 && echo "true" || echo "false")
           echo "CACHE_HIT=$EXISTS" >> $GITHUB_ENV
-
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
-
       - name: Build and push image if input files changed
         if: env.CACHE_HIT == 'false'
         uses: docker/build-push-action@v5
@@ -88,7 +78,6 @@ jobs:
           cache-from: type=gha,scope=nextclade-${{ github.ref }}
           cache-to: type=gha,mode=max,scope=nextclade-${{ github.ref }}
           platforms: ${{ env.BUILD_ARM == 'true' && 'linux/amd64,linux/arm64' || 'linux/amd64' }}
-
       - name: Retag and push existing image if cache hit
         if: env.CACHE_HIT == 'true'
         run: |
diff --git a/.github/workflows/update-argocd-metadata.yml b/.github/workflows/update-argocd-metadata.yml
index a78a779a10..8b17b91b0b 100644
--- a/.github/workflows/update-argocd-metadata.yml
+++ b/.github/workflows/update-argocd-metadata.yml
@@ -1,14 +1,11 @@
 name: Update argocd_metadata
-
 on:
   push:
     branches:
       - main
   workflow_dispatch:
-
 concurrency:
   group: ci-update-argocd-metadata
-
 jobs:
   update:
     permissions:
@@ -17,18 +14,15 @@ jobs:
       checks: read
     runs-on: ubuntu-latest
     timeout-minutes: 15
-
     steps:
       - name: Checkout Main Repository
         uses: actions/checkout@v4
         with:
           ref: ${{ github.ref }}
-
       - name: Get SHA - length 7
         id: get_sha
         run: |
           echo "sha=$(echo ${GITHUB_SHA} | cut -c1-7)" >> $GITHUB_OUTPUT
-
       # Waits are identical to the e2e-k3d.yml workflow file
       # Mirror changes to that file
       - name: Wait for Prepro Dummy Docker Image
@@ -38,7 +32,6 @@ jobs:
           check-name: Preprocessing dummy docker image build
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           wait-interval: 2
-
       - name: Wait for Config Processor Docker Image
         uses: lewagon/wait-on-check-action@v1.3.4
         with:
@@ -46,7 +39,6 @@ jobs:
           check-name: Build config-processor Docker Image
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           wait-interval: 2
-
       - name: Wait for Backend Docker Image
         uses: lewagon/wait-on-check-action@v1.3.4
         with:
@@ -54,7 +46,6 @@ jobs:
           check-name: Build Backend Docker Image
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           wait-interval: 2
-
       - name: Wait for Website Docker Image
         uses: lewagon/wait-on-check-action@v1.3.4
         with:
@@ -62,7 +53,6 @@ jobs:
           check-name: Build Website Docker Image
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           wait-interval: 2
-
       - name: Wait for Prepro Nextclade Docker Image
         uses: lewagon/wait-on-check-action@v1.3.4
         with:
@@ -70,7 +60,6 @@ jobs:
           check-name: Build preprocessing-nextclade Docker Image
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           wait-interval: 2
-
       - name: Wait for Ingest Docker Image
         uses: lewagon/wait-on-check-action@v1.3.4
         with:
@@ -78,7 +67,6 @@ jobs:
           check-name: Build ingest Docker Image
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           wait-interval: 2
-
       - name: Wait for Keycloakify Docker Image
         uses: lewagon/wait-on-check-action@v1.3.4
         with:
@@ -87,13 +75,11 @@ jobs:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           wait-interval: 2
       # End of wait block
-
       - name: Checkout External Repository
         uses: actions/checkout@v4
         with:
           repository: "loculus-project/argocd_metadata"
           token: ${{ secrets.ARGOCD_METADATA_PAT }}
-
       - name: Modify config.json
         run: |
           echo '{
@@ -101,7 +87,6 @@ jobs:
             "number" : 999,
             "head_short_sha_7": "${{ steps.get_sha.outputs.sha }}"
           }' > config.json
-
       - name: Commit and Push Changes
         run: |
           git config --global user.name 'Loculus bot'
diff --git a/.github/workflows/website-image.yml b/.github/workflows/website-image.yml
index 2c757a78fc..fd5322e95f 100644
--- a/.github/workflows/website-image.yml
+++ b/.github/workflows/website-image.yml
@@ -1,5 +1,4 @@
 name: website-image
-
 on:
   pull_request:
   push:
@@ -24,11 +23,9 @@ env:
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
   BUILD_ARM: ${{ github.event.inputs.build_arm || inputs.build_arm || github.ref == 'refs/heads/main' }}
   sha: ${{ github.event.pull_request.head.sha || github.sha }}
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-website-${{github.event.inputs.build_arm}}
   cancel-in-progress: true
-
 jobs:
   website-docker:
     name: Build Website Docker Image # Don't change: Referenced by .github/workflows/update-argocd-metadata.yml
@@ -41,15 +38,12 @@ jobs:
     steps:
       - name: Shorten sha
         run: echo "sha=${sha::7}" >> $GITHUB_ENV
-
       - uses: actions/checkout@v4
-
       - name: Generate files hash
         id: files-hash
         run: |
           DIR_HASH=$(echo -n ${{ hashFiles('website/**', '.github/workflows/website-image.yml') }})
           echo "DIR_HASH=$DIR_HASH${{ env.BUILD_ARM == 'true' && '-arm' || '' }}" >> $GITHUB_ENV
-
       - name: Setup Docker metadata
         id: dockerMetadata
         uses: docker/metadata-action@v5
@@ -61,29 +55,24 @@ jobs:
             type=raw,value=${{ env.BRANCH_NAME }}
             type=raw,value=commit-${{ env.sha }}
             type=raw,value=${{ env.BRANCH_NAME }}-arm,enable=${{ env.BUILD_ARM }}
-
       - name: Login to GitHub Container Registry
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
-
       - name: Check if image exists
         id: check-image
         run: |
           EXISTS=$(docker manifest inspect ${{ env.DOCKER_IMAGE_NAME }}:${{ env.DIR_HASH }} > /dev/null 2>&1 && echo "true" || echo "false")
           echo "CACHE_HIT=$EXISTS" >> $GITHUB_ENV
-
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
-
       - name: Get node version build arg
         if: env.CACHE_HIT == 'false'
         run: |
           NODE_VERSION=$(cat website/.nvmrc | tr -cd [:digit:].)
           echo "NODE_VERSION=$NODE_VERSION" >> $GITHUB_ENV
-
       - name: Build and push image
         if: env.CACHE_HIT == 'false'
         uses: docker/build-push-action@v5
@@ -95,7 +84,6 @@ jobs:
           cache-to: type=gha,mode=max,scope=website-${{ github.ref }}
           platforms: ${{ env.BUILD_ARM == 'true' && 'linux/amd64,linux/arm64' || 'linux/amd64' }}
           build-args: NODE_VERSION=${{ env.NODE_VERSION }}
-
       - name: Retag and push existing image if cache hit
         if: env.CACHE_HIT == 'true'
         run: |
diff --git a/.github/workflows/website-playwright-dev-test.yml b/.github/workflows/website-playwright-dev-test.yml
index 59bd6bf275..1e5e463d1e 100644
--- a/.github/workflows/website-playwright-dev-test.yml
+++ b/.github/workflows/website-playwright-dev-test.yml
@@ -1,5 +1,4 @@
 name: Dev server test
-
 on:
   pull_request:
     paths:
@@ -10,13 +9,10 @@ on:
   push:
     branches:
       - main
-
   workflow_dispatch:
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-node-dev
   cancel-in-progress: true
-
 jobs:
   test:
     runs-on: ${{ matrix.os }}
@@ -29,23 +25,19 @@ jobs:
         #  - macos-latest
         exclude:
           - os: ${{ github.ref != 'refs/heads/main' && 'macos-latest' }}
-
     steps:
       - uses: azure/setup-helm@v4
       - name: Checkout repository
         uses: actions/checkout@v4
       - name: Install yaml package
         run: pip3 install PyYAML requests
-
       - name: Generate local test config
         run: ./generate_local_test_config.sh
-
       - name: Install dependencies
         working-directory: website
         run: |
           npm install
           npm install playwright --save-dev
-
       - name: Test dev node server
         working-directory: website
         run: |
diff --git a/.github/workflows/website-tests.yml b/.github/workflows/website-tests.yml
index b0d31fa459..5d2bd08ef7 100644
--- a/.github/workflows/website-tests.yml
+++ b/.github/workflows/website-tests.yml
@@ -1,5 +1,4 @@
 name: website-tests
-
 on:
   # test
   pull_request:
@@ -10,11 +9,9 @@ on:
     branches:
       - main
   workflow_dispatch:
-
 concurrency:
   group: ci-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-website-tests
   cancel-in-progress: true
-
 jobs:
   checks:
     name: Check format and types
diff --git a/.gitignore b/.gitignore
index e4d3694a2c..72da041b24 100644
--- a/.gitignore
+++ b/.gitignore
@@ -6,6 +6,7 @@
 !.idea/runConfigurations
 *.iml
 .vscode/*
+!.vscode/extensions.json
 .venv
 
 # build output
diff --git a/.vscode/extensions.json b/.vscode/extensions.json
new file mode 100644
index 0000000000..647466f3e5
--- /dev/null
+++ b/.vscode/extensions.json
@@ -0,0 +1,3 @@
+{
+  "recommendations": ["bluebrown.yamlfmt"]
+}
diff --git a/.yamlfmt.yaml b/.yamlfmt.yaml
new file mode 100644
index 0000000000..8369992be0
--- /dev/null
+++ b/.yamlfmt.yaml
@@ -0,0 +1,7 @@
+# See https://github.com/google/yamlfmt
+formatter:
+  type: basic
+  drop_merge_tag: true
+gitignore_excludes: true
+exclude:
+  - kubernetes/loculus/templates
diff --git a/ingest/config/defaults.yaml b/ingest/config/defaults.yaml
index 8cf173f816..f8d999f40c 100644
--- a/ingest/config/defaults.yaml
+++ b/ingest/config/defaults.yaml
@@ -39,7 +39,6 @@ keep:
   - sequence_md5
   - genbank_accession
   - joint_accession
-
 # Fields that that are not shared at sample level
 # But specific to each segment
 segment_specific_fields:
@@ -152,4 +151,4 @@ group_name: insdc_ingest_group
 username: insdc_ingest_user
 password: insdc_ingest_user
 keycloak_client_id: backend-client
-subsample_fraction: 1.0
\ No newline at end of file
+subsample_fraction: 1.0
diff --git a/ingest/profiles/default/config.yaml b/ingest/profiles/default/config.yaml
index 908e02dad9..c646b35345 100644
--- a/ingest/profiles/default/config.yaml
+++ b/ingest/profiles/default/config.yaml
@@ -2,4 +2,4 @@ rerun-incomplete: true
 printshellcmds: true
 cores: all
 configfile: config/config.yaml
-keep-going: true
\ No newline at end of file
+keep-going: true
diff --git a/keycloak/keycloakify/.yarnrc.yml b/keycloak/keycloakify/.yarnrc.yml
index 25b748b3e5..bdfbade9d2 100644
--- a/keycloak/keycloakify/.yarnrc.yml
+++ b/keycloak/keycloakify/.yarnrc.yml
@@ -1,3 +1,2 @@
 nodeLinker: node-modules
-
 yarnPath: .yarn/releases/yarn-4.2.2.cjs
diff --git a/kubernetes/appset.yaml b/kubernetes/appset.yaml
index 242b65bc57..211d093051 100644
--- a/kubernetes/appset.yaml
+++ b/kubernetes/appset.yaml
@@ -22,11 +22,10 @@ spec:
         repoURL: https://github.com/loculus-project/argocd_metadata.git
         revision: HEAD
         files:
-        - path: "config.json"
+          - path: "config.json"
   template:
     metadata:
       name: 'pp-{{ (printf "%.25s" .branch) | replace "_" "-" | replace "/" "-" | trimSuffix "-" | lower }}-{{.number}}'
-
     spec:
       destination:
         server: 'https://kubernetes.default.svc'
@@ -53,4 +52,4 @@ spec:
           - CreateNamespace=true
         automated:
           selfHeal: true
-          prune: true
\ No newline at end of file
+          prune: true
diff --git a/kubernetes/loculus/Chart.yaml b/kubernetes/loculus/Chart.yaml
index 5ef31ed10f..5b5d1cf408 100644
--- a/kubernetes/loculus/Chart.yaml
+++ b/kubernetes/loculus/Chart.yaml
@@ -1,4 +1,4 @@
 apiVersion: v2
 name: loculus
 description: A Helm chart for loculus
-version: 0.1.0
\ No newline at end of file
+version: 0.1.0
diff --git a/kubernetes/loculus/values.yaml b/kubernetes/loculus/values.yaml
index 2c4537eb51..59d4348147 100644
--- a/kubernetes/loculus/values.yaml
+++ b/kubernetes/loculus/values.yaml
@@ -107,10 +107,8 @@ defaultOrganismConfig: &defaultOrganismConfig
         header: Sample details
       - name: geo_loc_site
         ontology_id: GENEPIO:0100436
-        definition: The name of a specific geographical location e.g. Credit River (rather
-          than river).
-        guidance: Provide the name of the specific geographical site using a specific noun
-          (a word that names a certain place, thing).
+        definition: The name of a specific geographical location e.g. Credit River (rather than river).
+        guidance: Provide the name of the specific geographical site using a specific noun (a word that names a certain place, thing).
         example: Credit River
         displayName: Collection site
         header: Sample details
@@ -170,7 +168,7 @@ defaultOrganismConfig: &defaultOrganismConfig
         customDisplay:
           type: link
           url: "https://www.ncbi.nlm.nih.gov/biosample/__value__"
-        header: "INSDC" 
+        header: "INSDC"
         noInput: true
         perSegment: true
       - name: culture_id
@@ -179,13 +177,7 @@ defaultOrganismConfig: &defaultOrganismConfig
       - name: sample_received_date
         ontology_id: GENEPIO:0001177
         definition: The date on which the sample was received by the laboratory.
-        guidance: Alternative if "sample_collection_date" is not available. Record the date the sample was received by the laboratory. 
-          Required granularity includes year, month and day. Before sharing this data, ensure this date is not
-          considered identifiable information. If this date is considered identifiable,
-          it is acceptable to add "jitter" to the received date by adding or subtracting
-          calendar days. Do not change the received date in your original records. Alternatively,
-          collection_date may be used as a substitute in the data you share.
-          The date should be provided in ISO 8601 standard format "YYYY-MM-DD".
+        guidance: Alternative if "sample_collection_date" is not available. Record the date the sample was received by the laboratory. Required granularity includes year, month and day. Before sharing this data, ensure this date is not considered identifiable information. If this date is considered identifiable, it is acceptable to add "jitter" to the received date by adding or subtracting calendar days. Do not change the received date in your original records. Alternatively, collection_date may be used as a substitute in the data you share. The date should be provided in ISO 8601 standard format "YYYY-MM-DD".
         example: '2020-03-20'
         displayName: Sample Received Date
         type: date
@@ -205,139 +197,92 @@ defaultOrganismConfig: &defaultOrganismConfig
         header: Sampling
       - name: presampling_activity
         ontology_id: GENEPIO:0100433
-        definition: The activities or variables introduced upstream of sample collection
-          that may affect the sample collected.
-        guidance: If there was presampling activity that would affect the sample prior to
-          collection (this is different than sample processing which happens after the sample
-          is collected), provide the experimental activities by selecting one or more values
-          from the template pick list. If the information is unknown or cannot be provided,
-          leave blank or provide a null value.
+        definition: The activities or variables introduced upstream of sample collection that may affect the sample collected.
+        guidance: If there was presampling activity that would affect the sample prior to collection (this is different than sample processing which happens after the sample is collected), provide the experimental activities by selecting one or more values from the template pick list. If the information is unknown or cannot be provided, leave blank or provide a null value.
         example: Antimicrobial pre-treatment [GENEPIO:0100537]
         displayName: Presampling activity
         header: Sampling
       - name: anatomical_material
         ontology_id: GENEPIO:0001211
-        definition: A substance obtained from an anatomical part of an organism e.g. tissue,
-          blood.
-        guidance: 'Provide a descriptor if an anatomical material was sampled. Use the pick
-          list provided in the template. If a desired term is missing from the pick list,
-          use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/uberon.
-          If not applicable, leave blank.'
+        definition: A substance obtained from an anatomical part of an organism e.g. tissue, blood.
+        guidance: 'Provide a descriptor if an anatomical material was sampled. Use the pick list provided in the template. If a desired term is missing from the pick list, use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/uberon. If not applicable, leave blank.'
         example: Blood [UBERON:0000178]
         displayName: Anatomical material
         header: Sampling
       - name: anatomical_part
         ontology_id: GENEPIO:0001214
         definition: An anatomical part of an organism e.g. oropharynx.
-        guidance: 'Provide a descriptor if an anatomical part was sampled. Use the pick
-          list provided in the template. If a desired term is missing from the pick list,
-          use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/uberon.
-          If not applicable, leave blank.'
+        guidance: 'Provide a descriptor if an anatomical part was sampled. Use the pick list provided in the template. If a desired term is missing from the pick list, use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/uberon. If not applicable, leave blank.'
         example: Nasopharynx (NP) [UBERON:0001728]
         displayName: Anatomical part
         header: Sampling
       - name: body_product
         ontology_id: GENEPIO:0001216
         definition: A substance excreted/secreted from an organism e.g. feces, urine, sweat.
-        guidance: 'Provide a descriptor if a body product was sampled. Use the pick list
-          provided in the template. If a desired term is missing from the pick list, use
-          this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/uberon.
-          If not applicable, leave blank.'
+        guidance: 'Provide a descriptor if a body product was sampled. Use the pick list provided in the template. If a desired term is missing from the pick list, use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/uberon. If not applicable, leave blank.'
         example: Feces [UBERON:0001988]
         displayName: Body product
         header: Sampling
       - name: environmental_material
         ontology_id: GENEPIO:0001223
-        definition: A substance obtained from the natural or man-made environment e.g. soil,
-          water, sewage, door handle, bed handrail, face mask.
-        guidance: 'Provide a descriptor if an environmental material was sampled. Use the
-          pick list provided in the template. If a desired term is missing from the pick
-          list, use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/envo.
-          If not applicable, leave blank.'
+        definition: A substance obtained from the natural or man-made environment e.g. soil, water, sewage, door handle, bed handrail, face mask.
+        guidance: 'Provide a descriptor if an environmental material was sampled. Use the pick list provided in the template. If a desired term is missing from the pick list, use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/envo. If not applicable, leave blank.'
         example: Face mask [OBI:0002787]
         displayName: Environmental material
         header: Sampling
       - name: environmental_site
         ontology_id: GENEPIO:0001232
-        definition: An environmental location may describe a site in the natural or built
-          environment e.g. hospital, wet market, bat cave.
-        guidance: 'Provide a descriptor if an environmental site was sampled. Use the pick
-          list provided in the template. If a desired term is missing from the pick list,
-          use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/envo.
-          If not applicable, leave blank.'
+        definition: An environmental location may describe a site in the natural or built environment e.g. hospital, wet market, bat cave.
+        guidance: 'Provide a descriptor if an environmental site was sampled. Use the pick list provided in the template. If a desired term is missing from the pick list, use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/envo. If not applicable, leave blank.'
         example: Hospital [ENVO:00002173]
         displayName: Environmental site
         header: Sampling
       - name: collection_device
         ontology_id: GENEPIO:0001234
         definition: The instrument or container used to collect the sample e.g. swab.
-        guidance: 'Provide a descriptor if a collection device was used for sampling. Use
-          the pick list provided in the template. If a desired term is missing from the
-          pick list, use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/obi.
-          If not applicable, leave blank.'
+        guidance: 'Provide a descriptor if a collection device was used for sampling. Use the pick list provided in the template. If a desired term is missing from the pick list, use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/obi. If not applicable, leave blank.'
         example: Swab [GENEPIO:0100027]
         displayName: Collection device
         header: Sampling
       - name: collection_method
         ontology_id: GENEPIO:0001241
         definition: The process used to collect the sample e.g. phlebotomy, necropsy.
-        guidance: 'Provide a descriptor if a collection method was used for sampling. Use
-          the pick list provided in the template. If a desired term is missing from the
-          pick list, use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/obi.
-          If not applicable, leave blank.'
+        guidance: 'Provide a descriptor if a collection method was used for sampling. Use the pick list provided in the template. If a desired term is missing from the pick list, use this look-up service to identify a standardized term: https://www.ebi.ac.uk/ols/ontologies/obi. If not applicable, leave blank.'
         example: Bronchoalveolar lavage (BAL) [GENEPIO:0100032]
         displayName: Collection method
         header: Sampling
       - name: food_product
         ontology_id: GENEPIO:0100444
         definition: A material consumed and digested for nutritional value or enjoyment.
-        guidance: This field includes animal feed. If applicable, select the standardized
-          term and ontology ID for the anatomical material from the picklist provided. Multiple
-          values can be provided, separated by a semi-colon.
-        example: Feather meal [FOODON:00003927]; Bone meal [ENVO:02000054]; Chicken breast
-          [FOODON:00002703]
+        guidance: This field includes animal feed. If applicable, select the standardized term and ontology ID for the anatomical material from the picklist provided. Multiple values can be provided, separated by a semi-colon.
+        example: Feather meal [FOODON:00003927]; Bone meal [ENVO:02000054]; Chicken breast [FOODON:00002703]
         displayName: Food Product
         header: Sampling
       - name: food_product_properties
         ontology_id: GENEPIO:0100445
-        definition: Any characteristic of the food product pertaining to its state, processing,
-          a label claim, or implications for consumers.
-        guidance: Provide any characteristics of the food product including whether it has
-          been cooked, processed, preserved, any known information about its state (e.g.
-          raw, ready-to-eat), any known information about its containment (e.g. canned),
-          and any information about a label claim (e.g. organic, fat-free).
+        definition: Any characteristic of the food product pertaining to its state, processing, a label claim, or implications for consumers.
+        guidance: Provide any characteristics of the food product including whether it has been cooked, processed, preserved, any known information about its state (e.g. raw, ready-to-eat), any known information about its containment (e.g. canned), and any information about a label claim (e.g. organic, fat-free).
         example: Food (chopped) [FOODON:00002777]; Ready-to-eat (RTE) [FOODON:03316636]
         displayName: Food Product Properties
         header: Sampling
       - name: specimen_processing
         ontology_id: GENEPIO:0100435
-        definition: The processing applied to samples post-collection, prior to further
-          testing, characterization, or isolation procedures.
-        guidance: Provide the sample processing information by selecting a value from the
-          template pick list. If the information is unknown or cannot be provided, leave
-          blank or provide a null value.
+        definition: The processing applied to samples post-collection, prior to further testing, characterization, or isolation procedures.
+        guidance: Provide the sample processing information by selecting a value from the template pick list. If the information is unknown or cannot be provided, leave blank or provide a null value.
         example: Samples pooled [OBI:0600016]
         displayName: Specimen Processing
         header: Specimen processing
       - name: specimen_processing_details
         ontology_id: GENEPIO:0100311
-        definition: Detailed information regarding the processing applied to a sample during
-          or after receiving the sample.
-        guidance: Provide a free text description of any processing details applied to a
-          sample.
-        example: 25 swabs were pooled and further prepared as a single sample during library
-          prep.
+        definition: Detailed information regarding the processing applied to a sample during or after receiving the sample.
+        guidance: Provide a free text description of any processing details applied to a sample.
+        example: 25 swabs were pooled and further prepared as a single sample during library prep.
         displayName: Specimen Processing Details
         header: Specimen processing
       - name: experimental_specimen_role_type
         ontology_id: GENEPIO:0100921
         definition: The type of role that the sample represents in the experiment.
-        guidance: Samples can play different types of roles in experiments. A sample under
-          study in one experiment may act as a control or be a replicate of another sample
-          in another experiment. This field is used to distinguish samples under study from
-          controls, replicates, etc.  If the sample acted as an experimental control or
-          a replicate, select a role type from the picklist. If the sample was not a control,
-          leave blank or select "Not Applicable".
+        guidance: Samples can play different types of roles in experiments. A sample under study in one experiment may act as a control or be a replicate of another sample in another experiment. This field is used to distinguish samples under study from controls, replicates, etc.  If the sample acted as an experimental control or a replicate, select a role type from the picklist. If the sample was not a control, leave blank or select "Not Applicable".
         example: Positive experimental control [GENEPIO:0101018]
         displayName: Experimental Specimen Role  Type
         header: Specimen processing
@@ -353,8 +298,7 @@ defaultOrganismConfig: &defaultOrganismConfig
       - name: host_age_bin
         ontology_id: GENEPIO:0001394
         definition: The age category of the host at the time of sampling.
-        guidance: Age bins in 10 year intervals have been provided. If a host's age cannot
-          be specified due to provacy concerns, an age bin can be used as an alternative.
+        guidance: Age bins in 10 year intervals have been provided. If a host's age cannot be specified due to provacy concerns, an age bin can be used as an alternative.
         example: 50 - 59 [GENEPIO:0100054]
         displayName: Host Age Bin
         header: Host
@@ -368,27 +312,20 @@ defaultOrganismConfig: &defaultOrganismConfig
       - name: host_origin_country
         ontology_id: GENEPIO:0100438
         definition: The country of origin of the host.
-        guidance: If a sample is from a human or animal host that originated from outside
-          of Canada, provide the the name of the country where the host originated by selecting
-          a value from the template pick list. If the information is unknown or cannot be
-          provided, leave blank or provide a null value.
+        guidance: If a sample is from a human or animal host that originated from outside of Canada, provide the the name of the country where the host originated by selecting a value from the template pick list. If the information is unknown or cannot be provided, leave blank or provide a null value.
         example: South Africa [GAZ:00001094]
         displayName: Host Origin Country
         header: Host
       - name: host_disease
         ontology_id: GENEPIO:0001391
         definition: The name of the disease experienced by the host.
-        guidance: "This field is only required if the Pathogen.cl package was selected.
-          If the host was sick, provide the name of the disease.The standardized term
-          can be sourced from this look-up service: https://www.ebi.ac.uk/ols/ontologies/doid
-          If the disease is not known, put \u201Cmissing\u201D."
+        guidance: "This field is only required if the Pathogen.cl package was selected. If the host was sick, provide the name of the disease.The standardized term can be sourced from this look-up service: https://www.ebi.ac.uk/ols/ontologies/doid If the disease is not known, put “missing”."
         example: mastitis, gastroenteritis
         displayName: Host disease
         header: Host
       - name: signs_and_symptoms
         ontology_id: GENEPIO:0001400
-        definition: A perceived change in function or sensation, (loss, disturbance or appearance)
-          indicative of a disease, reported by a patient.
+        definition: A perceived change in function or sensation, (loss, disturbance or appearance) indicative of a disease, reported by a patient.
         guidance: Select all of the symptoms experienced by the host from the pick list.
         example: Cough [HP:0012735], Fever [HP:0001945],  Rigors (fever shakes) [HP:0025145]
         displayName: Signs and symptoms
@@ -410,9 +347,7 @@ defaultOrganismConfig: &defaultOrganismConfig
       - name: travel_history
         ontology_id: GENEPIO:0001416
         definition: Travel history in last six months.
-        guidance: Specify the countries (and more granular locations if known) travelled
-          in the last six months; can include multiple travels. Separate multiple travel
-          events with a semicolon. Provide as free text.
+        guidance: Specify the countries (and more granular locations if known) travelled in the last six months; can include multiple travels. Separate multiple travel events with a semicolon. Provide as free text.
         example: Canada, Vancouver; USA, Seattle; Italy, Milan
         displayName: Travel History
         header: Host
@@ -426,16 +361,14 @@ defaultOrganismConfig: &defaultOrganismConfig
       - name: host_role
         ontology_id: GENEPIO:0001419
         definition: The role of the host in relation to the exposure setting.
-        guidance: Select the host's personal role(s) from the pick list provided in the
-          template. If the desired term is missing, contact the curation team.
+        guidance: Select the host's personal role(s) from the pick list provided in the template. If the desired term is missing, contact the curation team.
         example: Patient [OMRSE:00000030]
         displayName: Host role
         header: Host
       - name: exposure_setting
         ontology_id: GENEPIO:0001428
         definition: The setting leading to exposure.
-        guidance: Select the host exposure setting(s) from the pick list provided in the
-          template. If a desired term is missing, contact the curation team.
+        guidance: Select the host exposure setting(s) from the pick list provided in the template. If a desired term is missing, contact the curation team.
         example: Healthcare Setting [GENEPIO:0100201]
         displayName: Exposure setting
         header: Host
@@ -448,23 +381,19 @@ defaultOrganismConfig: &defaultOrganismConfig
         header: Host
       - name: previous_infection_disease
         definition: The name of the disease previously experienced by the host.
-        guidance: Provide the name(s) of the previous of ongoing disease(s). Multiple diseases
-          can be separated by a semi-colon.
+        guidance: Provide the name(s) of the previous of ongoing disease(s). Multiple diseases can be separated by a semi-colon.
         example: COVID-19
         displayName: Previous infection (disease)
         header: Host
       - name: previous_infection_organism
-        definition: The name of the pathogen causing the disease previously experienced
-          by the host.
-        guidance: Provide the name(s) of the pathogen(s) causing the previous or ongoing
-          infections. Multiple pathogen names can be separated using a semi-colon.
+        definition: The name of the pathogen causing the disease previously experienced by the host.
+        guidance: Provide the name(s) of the pathogen(s) causing the previous or ongoing infections. Multiple pathogen names can be separated using a semi-colon.
         example: Sudden Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2)
         displayName: Previous infection (organism)
         header: Host
       - name: host_vaccination_status
         ontology_id: GENEPIO:0001404
-        definition: The vaccination status of the host (fully vaccinated, partially vaccinated,
-          or not vaccinated).
+        definition: The vaccination status of the host (fully vaccinated, partially vaccinated, or not vaccinated).
         guidance: Select the vaccination status of the host from the pick list.
         example: Fully Vaccinated [GENEPIO:0100100]
         displayName: Host Vaccination Status
@@ -472,11 +401,7 @@ defaultOrganismConfig: &defaultOrganismConfig
       - name: purpose_of_sequencing
         ontology_id: GENEPIO:0001445
         definition: The reason that the sample was sequenced.
-        guidance: The reason why a sample was originally collected may differ from the reason
-          why it was selected for sequencing. The reason a sample was sequenced may provide
-          information about potential biases in sequencing strategy. Provide the purpose
-          of sequencing from the picklist in the template. The reason for sample collection
-          should be indicated in the "purpose of sampling" field.
+        guidance: The reason why a sample was originally collected may differ from the reason why it was selected for sequencing. The reason a sample was sequenced may provide information about potential biases in sequencing strategy. Provide the purpose of sequencing from the picklist in the template. The reason for sample collection should be indicated in the "purpose of sampling" field.
         example: Baseline surveillance (random sampling) [GENEPIO:0100005]
         displayName: Purpose Of Sequencing
         header: Sequencing
@@ -494,10 +419,8 @@ defaultOrganismConfig: &defaultOrganismConfig
         header: Sequencing
       - name: amplicon_pcr_primer_scheme
         ontology_id: GENEPIO:0001456
-        definition: The specifications of the primers (primer sequences, binding positions,
-          fragment size generated etc) used to generate the amplicons to be sequenced.
-        guidance: Provide the name and version of the primer scheme used to generate the
-          amplicons for sequencing.
+        definition: The specifications of the primers (primer sequences, binding positions, fragment size generated etc) used to generate the amplicons to be sequenced.
+        guidance: Provide the name and version of the primer scheme used to generate the amplicons for sequencing.
         example: https://github.com/joshquick/artic-ncov2019/blob/master/primer_schemes/nCoV-2019/V3/nCoV-2019.tsv
         displayName: Amplicon pcr primer scheme
         header: Sequencing
@@ -518,73 +441,49 @@ defaultOrganismConfig: &defaultOrganismConfig
       - name: sequencing_protocol
         ontology_id: GENEPIO:0001454
         definition: The protocol used to generate the sequence.
-        guidance: 'Provide a free text description of the methods and materials used to
-          generate the sequence. Suggested text, fill in information where indicated.: "Viral
-          sequencing was performed following a tiling amplicon strategy using the <fill
-          in> primer scheme. Sequencing was performed using a <fill in> sequencing instrument.
-          Libraries were prepared using <fill in> library kit. "'
-        example: Genomes were generated through amplicon sequencing of 1200 bp amplicons
-          with Freed schema primers. Libraries were created using Illumina DNA Prep kits,
-          and sequence data was produced using Miseq Micro v2 (500 cycles) sequencing kits.
+        guidance: 'Provide a free text description of the methods and materials used to generate the sequence. Suggested text, fill in information where indicated.: "Viral sequencing was performed following a tiling amplicon strategy using the <fill in> primer scheme. Sequencing was performed using a <fill in> sequencing instrument. Libraries were prepared using <fill in> library kit. "'
+        example: Genomes were generated through amplicon sequencing of 1200 bp amplicons with Freed schema primers. Libraries were created using Illumina DNA Prep kits, and sequence data was produced using Miseq Micro v2 (500 cycles) sequencing kits.
         displayName: Sequencing protocol
         header: Sequencing
       - name: sequencing_assay_type
         ontology_id: GENEPIO:0100997
-        definition: The overarching sequencing methodology that was used to determine the
-          sequence of a biomaterial.
-        guidance: 'Example Guidance: Provide the name of the DNA or RNA sequencing technology
-          used in your study. If unsure refer to the protocol documentation, or provide
-          a null value.'
+        definition: The overarching sequencing methodology that was used to determine the sequence of a biomaterial.
+        guidance: 'Example Guidance: Provide the name of the DNA or RNA sequencing technology used in your study. If unsure refer to the protocol documentation, or provide a null value.'
         example: whole genome sequencing assay [OBI:0002117]
         displayName: Sequencing Assay Type
         header: Sequencing
       - name: sequenced_by_organization
         ontology_id: GENEPIO:0100416
-        definition: The name of the agency, organization or institution responsible for
-          sequencing the isolate's genome.
-        guidance: Provide the name of the agency, organization or institution that performed
-          the sequencing in full (avoid abbreviations). If the information is unknown or
-          cannot be provided, leave blank or provide a null value.
+        definition: The name of the agency, organization or institution responsible for sequencing the isolate's genome.
+        guidance: Provide the name of the agency, organization or institution that performed the sequencing in full (avoid abbreviations). If the information is unknown or cannot be provided, leave blank or provide a null value.
         example: Public Health Agency of Canada (PHAC) [GENEPIO:0100551]
         displayName: Sequenced By
         header: Sequencing
       - name: sequenced_by_contact_name
         ontology_id: GENEPIO:0100471
-        definition: The name or title of the contact responsible for follow-up regarding
-          the sequence.
-        guidance: Provide the name of an individual or their job title. As personnel turnover
-          may render the contact's name obsolete, it is more prefereable to provide a job
-          title for ensuring accuracy of information and institutional memory. If the information
-          is unknown or cannot be provided, leave blank or provide a null value.
+        definition: The name or title of the contact responsible for follow-up regarding the sequence.
+        guidance: Provide the name of an individual or their job title. As personnel turnover may render the contact's name obsolete, it is more prefereable to provide a job title for ensuring accuracy of information and institutional memory. If the information is unknown or cannot be provided, leave blank or provide a null value.
         example: Enterics Lab Manager
         displayName: Sequenced By Contact Name
         header: Sequencing
       - name: sequenced_by_contact_email
         ontology_id: GENEPIO:0100422
-        definition: The email address of the contact responsible for follow-up regarding
-          the sequence.
-        guidance: Provide the email associated with the listed contact. As personnel turnover
-          may render an individual's email obsolete, it is more prefereable to provide an
-          address for a position or lab, to ensure accuracy of information and institutional
-          memory. If the information is unknown or cannot be provided, leave blank or provide
-          a null value.
+        definition: The email address of the contact responsible for follow-up regarding the sequence.
+        guidance: Provide the email associated with the listed contact. As personnel turnover may render an individual's email obsolete, it is more prefereable to provide an address for a position or lab, to ensure accuracy of information and institutional memory. If the information is unknown or cannot be provided, leave blank or provide a null value.
         example: enterics@lab.ca
         displayName: Sequenced By Contact Email
         header: Sequencing
       - name: raw_sequence_data_processing_method
         ontology_id: GENEPIO:0001458
-        definition: The method used for raw data processing such as removing barcodes, adapter
-          trimming, filtering etc.
-        guidance: Provide the name and version numbers of the software used to process the
-          raw data.
+        definition: The method used for raw data processing such as removing barcodes, adapter trimming, filtering etc.
+        guidance: Provide the name and version numbers of the software used to process the raw data.
         example: Porechop 0.2.3
         displayName: Raw sequence data processing method
         header: Sequencing
       - name: dehosting_method
         ontology_id: GENEPIO:0001459
         definition: The method used to remove host reads from the pathogen sequence.
-        guidance: Provide the name and version number of the software used to remove host
-          reads.
+        guidance: Provide the name and version number of the software used to remove host reads.
         example: Nanostripper 1.2.3
         displayName: Dehosting method
         header: Sequencing
@@ -611,8 +510,7 @@ defaultOrganismConfig: &defaultOrganismConfig
         header: Sequencing
       - name: depth_of_coverage
         ontology_id: GENEPIO:0001474
-        definition: The average number of reads representing a given nucleotide in the reconstructed
-          sequence.
+        definition: The average number of reads representing a given nucleotide in the reconstructed sequence.
         guidance: Provide value as a fold of coverage (as a number).
         example: 400
         displayName: Depth of coverage
@@ -628,51 +526,35 @@ defaultOrganismConfig: &defaultOrganismConfig
         header: Sequencing
       - name: quality_control_method_name
         ontology_id: GENEPIO:0100557
-        definition: The name of the method used to assess whether a sequence passed a predetermined
-          quality control threshold.
-        guidance: Providing the name of the method used for quality control is very important
-          for interpreting the rest of the QC information. Method names can be provided
-          as the name of a pipeline or a link to a GitHub repository. Multiple methods should
-          be listed and separated by a semi-colon. Do not include QC tags in other fields
-          if no method name is provided.
+        definition: The name of the method used to assess whether a sequence passed a predetermined quality control threshold.
+        guidance: Providing the name of the method used for quality control is very important for interpreting the rest of the QC information. Method names can be provided as the name of a pipeline or a link to a GitHub repository. Multiple methods should be listed and separated by a semi-colon. Do not include QC tags in other fields if no method name is provided.
         example: ncov-tools
         displayName: Quality control method name
         header: Sequencing
       - name: quality_control_method_version
         ontology_id: GENEPIO:0100558
-        definition: The version number of the method used to assess whether a sequence passed
-          a predetermined quality control threshold.
-        guidance: Methods updates can make big differences to their outputs. Provide the
-          version of the method used for quality control. The version can be expressed using
-          whatever convention the developer implements (e.g. date, semantic versioning).
-          If multiple methods were used, record the version numbers in the same order as
-          the method names. Separate the version numbers using a semi-colon.
+        definition: The version number of the method used to assess whether a sequence passed a predetermined quality control threshold.
+        guidance: Methods updates can make big differences to their outputs. Provide the version of the method used for quality control. The version can be expressed using whatever convention the developer implements (e.g. date, semantic versioning). If multiple methods were used, record the version numbers in the same order as the method names. Separate the version numbers using a semi-colon.
         example: "1.2.3"
         displayName: Quality control method version
         header: Sequencing
       - name: quality_control_determination
         ontology_id: GENEPIO:0100559
         definition: The determination of a quality control assessment.
-        guidance: Select a value from the pick list provided. If a desired value is missing,
-          submit a new term request to the PHA4GE QC Tag GitHub issuetracker using the New
-          Term Request form.
+        guidance: Select a value from the pick list provided. If a desired value is missing, submit a new term request to the PHA4GE QC Tag GitHub issuetracker using the New Term Request form.
         example: sequence failed quality control
         displayName: Quality control determination
         header: Sequencing
       - name: quality_control_issues
         ontology_id: GENEPIO:0100560
-        definition: The reason contributing to, or causing, a low quality determination
-          in a quality control assessment.
-        guidance: Select a value from the pick list provided. If a desired value is missing,
-          submit a new term request to the PHA4GE QC Tag GitHub issuetracker using the New
-          Term Request form.
+        definition: The reason contributing to, or causing, a low quality determination in a quality control assessment.
+        guidance: Select a value from the pick list provided. If a desired value is missing, submit a new term request to the PHA4GE QC Tag GitHub issuetracker using the New Term Request form.
         example: low average genome coverage
         displayName: Quality control issues
         header: Sequencing
       - name: quality_control_details
         ontology_id: GENEPIO:0100561
-        definition: The details surrounding a low quality determination in a quality control
-          assessment.
+        definition: The details surrounding a low quality determination in a quality control assessment.
         guidance: Provide notes or details regarding QC results using free text.
         example: CT value of 39. Low viral load. Low DNA concentration after amplification.
         displayName: Quality control details
@@ -777,7 +659,7 @@ defaultOrganismConfig: &defaultOrganismConfig
         rangeSearch: true
         perSegment: true
         preprocessing:
-          inputs: { input: nextclade.totalSubstitutions }
+          inputs: {input: nextclade.totalSubstitutions}
       - name: total_inserted_nucs
         type: int
         header: "Alignment states and QC metrics"
@@ -785,7 +667,7 @@ defaultOrganismConfig: &defaultOrganismConfig
         rangeSearch: true
         perSegment: true
         preprocessing:
-          inputs: { input: nextclade.totalInsertions }
+          inputs: {input: nextclade.totalInsertions}
       - name: total_deleted_nucs
         type: int
         header: "Alignment states and QC metrics"
@@ -793,7 +675,7 @@ defaultOrganismConfig: &defaultOrganismConfig
         rangeSearch: true
         perSegment: true
         preprocessing:
-          inputs: { input: nextclade.totalDeletions }
+          inputs: {input: nextclade.totalDeletions}
       - name: total_ambiguous_nucs
         type: int
         header: "Alignment states and QC metrics"
@@ -801,7 +683,7 @@ defaultOrganismConfig: &defaultOrganismConfig
         rangeSearch: true
         perSegment: true
         preprocessing:
-          inputs: { input: "nextclade.totalNonACGTNs" }
+          inputs: {input: "nextclade.totalNonACGTNs"}
       - name: total_unknown_nucs
         type: int
         header: "Alignment states and QC metrics"
@@ -809,7 +691,7 @@ defaultOrganismConfig: &defaultOrganismConfig
         rangeSearch: true
         perSegment: true
         preprocessing:
-          inputs: { input: nextclade.totalMissing }
+          inputs: {input: nextclade.totalMissing}
       - name: total_frame_shifts
         type: int
         rangeSearch: true
@@ -817,20 +699,20 @@ defaultOrganismConfig: &defaultOrganismConfig
         noInput: true
         perSegment: true
         preprocessing:
-          inputs: { input: nextclade.totalFrameShifts }
+          inputs: {input: nextclade.totalFrameShifts}
       - name: frame_shifts
         header: "Alignment states and QC metrics"
         noInput: true
         perSegment: true
         preprocessing:
-          inputs: { input: nextclade.frameShifts }
+          inputs: {input: nextclade.frameShifts}
       - name: completeness
         type: float
         header: "Alignment states and QC metrics"
         noInput: true
         perSegment: true
         preprocessing:
-          inputs: { input: nextclade.coverage }
+          inputs: {input: nextclade.coverage}
     website: &website
       tableColumns:
         - sample_collection_date
@@ -860,7 +742,7 @@ defaultOrganismConfig: &defaultOrganismConfig
       configFile: &preprocessingConfigFile
         log_level: DEBUG
         nextclade_dataset_name: nextstrain/ebola/zaire
-        genes: [ NP, VP35, VP40, GP, sGP, ssGP, VP30, VP24, L ]
+        genes: [NP, VP35, VP40, GP, sGP, ssGP, VP30, VP24, L]
         batch_size: 100
   ingest: &ingest
     image: ghcr.io/loculus-project/ingest
@@ -893,11 +775,11 @@ defaultOrganisms:
   ebola-zaire:
     <<: *defaultOrganismConfig
     preprocessing:
-    - <<: *preprocessing
-      configFile:
-        <<: *preprocessingConfigFile
-        nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/ebola/data_output
-        nextclade_dataset_name: nextstrain/ebola/zaire
+      - <<: *preprocessing
+        configFile:
+          <<: *preprocessingConfigFile
+          nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/ebola/data_output
+          nextclade_dataset_name: nextstrain/ebola/zaire
   ebola-sudan:
     <<: *defaultOrganismConfig
     schema:
@@ -910,18 +792,18 @@ defaultOrganisms:
           header: "Alignment states and QC metrics"
           noInput: true
           preprocessing:
-            inputs: { input: nextclade.qc.stopCodons.totalStopCodons }
+            inputs: {input: nextclade.qc.stopCodons.totalStopCodons}
         - name: stop_codons
           header: "Alignment states and QC metrics"
           noInput: true
           preprocessing:
-            inputs: { input: nextclade.qc.stopCodons.stopCodons }
+            inputs: {input: nextclade.qc.stopCodons.stopCodons}
     preprocessing:
-    - <<: *preprocessing
-      configFile:
-        <<: *preprocessingConfigFile
-        nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/ebola/data_output
-        nextclade_dataset_name: nextstrain/ebola/sudan
+      - <<: *preprocessing
+        configFile:
+          <<: *preprocessingConfigFile
+          nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/ebola/data_output
+          nextclade_dataset_name: nextstrain/ebola/sudan
     ingest:
       <<: *ingest
       configFile:
@@ -963,14 +845,14 @@ defaultOrganisms:
           autocomplete: true
           initiallyVisible: true
           preprocessing:
-            inputs: { input: nextclade.clade }
+            inputs: {input: nextclade.clade}
         - name: outbreak
           header: "Clade & Lineage"
           noInput: true
           generateIndex: true
           autocomplete: true
           preprocessing:
-            inputs: { input: nextclade.customNodeAttributes.outbreak }
+            inputs: {input: nextclade.customNodeAttributes.outbreak}
         - name: lineage
           header: "Clade & Lineage"
           noInput: true
@@ -978,18 +860,18 @@ defaultOrganisms:
           autocomplete: true
           initiallyVisible: true
           preprocessing:
-            inputs: { input: nextclade.customNodeAttributes.lineage }
+            inputs: {input: nextclade.customNodeAttributes.lineage}
         - name: total_stop_codons
           type: int
           header: "Alignment states and QC metrics"
           noInput: true
           preprocessing:
-            inputs: { input: nextclade.qc.stopCodons.totalStopCodons }
+            inputs: {input: nextclade.qc.stopCodons.totalStopCodons}
         - name: stop_codons
           header: "Alignment states and QC metrics"
           noInput: true
           preprocessing:
-            inputs: { input: nextclade.qc.stopCodons.stopCodons }
+            inputs: {input: nextclade.qc.stopCodons.stopCodons}
       website:
         <<: *website
         tableColumns:
@@ -998,19 +880,19 @@ defaultOrganisms:
           - authors
           - author_affiliations
           - geo_loc_country
-          - length 
+          - length
           - clade
           - lineage
         defaultOrderBy: sample_collection_date
         defaultOrder: descending
     preprocessing:
-    - <<: *preprocessing
-      configFile:
-        <<: *preprocessingConfigFile
-        nextclade_dataset_name: nextstrain/mpox/all-clades
-        batch_size: 5
-        genes:
-          - OPG001
+      - <<: *preprocessing
+        configFile:
+          <<: *preprocessingConfigFile
+          nextclade_dataset_name: nextstrain/mpox/all-clades
+          batch_size: 5
+          genes:
+            - OPG001
     ingest:
       <<: *ingest
       configFile:
@@ -1038,18 +920,18 @@ defaultOrganisms:
           autocomplete: true
           initiallyVisible: true
           preprocessing:
-            inputs: { input: nextclade.clade }
+            inputs: {input: nextclade.clade}
         - name: total_stop_codons
           type: int
           header: "Alignment states and QC metrics"
           noInput: true
           preprocessing:
-            inputs: { input: nextclade.qc.stopCodons.totalStopCodons }
+            inputs: {input: nextclade.qc.stopCodons.totalStopCodons}
         - name: stop_codons
           header: "Alignment states and QC metrics"
           noInput: true
           preprocessing:
-            inputs: { input: nextclade.qc.stopCodons.stopCodons }
+            inputs: {input: nextclade.qc.stopCodons.stopCodons}
       website:
         <<: *website
         tableColumns:
@@ -1064,16 +946,16 @@ defaultOrganisms:
         defaultOrderBy: sample_collection_date
         defaultOrder: descending
     preprocessing:
-    - <<: *preprocessing
-      configFile:
-        <<: *preprocessingConfigFile
-        nextclade_dataset_name: nextstrain/wnv/all-lineages
-        nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/wnv/data_output
-        genes: [ capsid, prM, env, NS1, NS2A, NS2B, NS3, NS4A, 2K, NS4B, NS5 ]
+      - <<: *preprocessing
+        configFile:
+          <<: *preprocessingConfigFile
+          nextclade_dataset_name: nextstrain/wnv/all-lineages
+          nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/wnv/data_output
+          genes: [capsid, prM, env, NS1, NS2A, NS2B, NS3, NS4A, 2K, NS4B, NS5]
     ingest:
       <<: *ingest
       configFile:
-         taxon_id: 3048448
+        taxon_id: 3048448
     referenceGenomes:
       nucleotideSequences:
         - name: main
@@ -1191,7 +1073,7 @@ defaultOrganisms:
     schema:
       <<: *schema
       organismName: "Crimean-Congo Hemorrhagic Fever Virus"
-      nucleotideSequences: [ L, M, S ]
+      nucleotideSequences: [L, M, S]
       image: "https://upload.wikimedia.org/wikipedia/commons/thumb/5/5e/Crimean-Congo_Hemorrhagic_Fever_%28CCHF%29_Virus_%2840689899455%29.jpg/1920px-Crimean-Congo_Hemorrhagic_Fever_%28CCHF%29_Virus_%2840689899455%29.jpg"
       website:
         <<: *website
@@ -1209,14 +1091,14 @@ defaultOrganisms:
         defaultOrderBy: sample_collection_date
         defaultOrder: descending
     preprocessing:
-    - <<: *preprocessing
-      configFile:
-        <<: *preprocessingConfigFile
-        log_level: DEBUG
-        nextclade_dataset_name: nextstrain/cchfv/linked
-        nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/cornelius-cchfv/data_output
-        nucleotideSequences: [ L, M, S ]
-        genes: [ RdRp, GPC, NP ]
+      - <<: *preprocessing
+        configFile:
+          <<: *preprocessingConfigFile
+          log_level: DEBUG
+          nextclade_dataset_name: nextstrain/cchfv/linked
+          nextclade_dataset_server: https://raw.githubusercontent.com/nextstrain/nextclade_data/cornelius-cchfv/data_output
+          nucleotideSequences: [L, M, S]
+          genes: [RdRp, GPC, NP]
     ingest:
       <<: *ingest
       configFile:
diff --git a/kubernetes/loculus/values_e2e_and_dev.yaml b/kubernetes/loculus/values_e2e_and_dev.yaml
index f815ca4642..4981c3d8e4 100644
--- a/kubernetes/loculus/values_e2e_and_dev.yaml
+++ b/kubernetes/loculus/values_e2e_and_dev.yaml
@@ -1,12 +1,12 @@
 secrets:
-    service-accounts:
-      type: raw
-      data:
-        insdcIngestUserPassword: "insdc_ingest_user"
-        dummyPreprocessingPipelinePassword: "preprocessing_pipeline"
-        siloImportJobPassword: "silo_import_job"
-        backendUserPassword: "backend"
+  service-accounts:
+    type: raw
+    data:
+      insdcIngestUserPassword: "insdc_ingest_user"
+      dummyPreprocessingPipelinePassword: "preprocessing_pipeline"
+      siloImportJobPassword: "silo_import_job"
+      backendUserPassword: "backend"
 createTestAccounts: true
 backendExtraArgs:
   - "--loculus.debug-mode=true"
-reduceResourceRequest: true
\ No newline at end of file
+reduceResourceRequest: true
diff --git a/kubernetes/loculus/values_preview_server.yaml b/kubernetes/loculus/values_preview_server.yaml
index 4391d3e94e..671c8959bb 100644
--- a/kubernetes/loculus/values_preview_server.yaml
+++ b/kubernetes/loculus/values_preview_server.yaml
@@ -10,4 +10,4 @@ secrets:
     clusterWide: "true"
     data:
       orcidSecret: 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
-reduceResourceRequest: true
\ No newline at end of file
+reduceResourceRequest: true
diff --git a/preprocessing/nextclade/environment.yml b/preprocessing/nextclade/environment.yml
index e0d058f98b..131ac14465 100644
--- a/preprocessing/nextclade/environment.yml
+++ b/preprocessing/nextclade/environment.yml
@@ -12,4 +12,4 @@ dependencies:
   - pyjwt=2.8
   - python-dateutil=2.9
   - pytz=2024.1
-  - requests=2.32
\ No newline at end of file
+  - requests=2.32