Merge pull request #25 from daichengxin/main

add pyonsite

Author: daichengxin

.github/workflows/quantms-containers.yml

@@ -10,6 +10,7 @@ on:
       - "diann-*/**"
       - "relink-*/Dockerfile"
       - "wiffconverter-*/**"
+      - "pyonsite-*/**"
       - ".github/workflows/**"
   release:
     types: [published]
@@ -37,9 +38,11 @@ jobs:
       diann_matrix: ${{ steps.set-matrix.outputs.diann_matrix }}
       relink_matrix: ${{ steps.set-matrix.outputs.relink_matrix }}
       wiffconverter_matrix: ${{ steps.set-matrix.outputs.wiffconverter_matrix }}
+      pyonsite_matrix: ${{ steps.set-matrix.outputs.pyonsite_matrix }}
       has_diann: ${{ steps.set-matrix.outputs.has_diann }}
       has_relink: ${{ steps.set-matrix.outputs.has_relink }}
       has_wiffconverter: ${{ steps.set-matrix.outputs.has_wiffconverter }}
+      has_pyonsite: ${{ steps.set-matrix.outputs.has_pyonsite }}
     steps:
       - uses: actions/checkout@v4
 
@@ -58,6 +61,7 @@ jobs:
             diann_1_8_1:  [ 'diann-1.8.1/**', '.github/workflows/**' ]
             relink_1_1_0: [ 'relink-1.1.0/**', '.github/workflows/**' ]
             wiffconverter_0_10: [ 'wiffconverter-0.10/**', '.github/workflows/**' ]
+            pyonsite_0_0_3: [ 'pyonsite-0.0.3/**', '.github/workflows/**' ]
 
       - name: Build matrices
         id: set-matrix
@@ -73,6 +77,7 @@ jobs:
           CHG_181: ${{ steps.filter.outputs.diann_1_8_1 }}
           CHG_RLK: ${{ steps.filter.outputs.relink_1_1_0 }}
           CHG_WC010: ${{ steps.filter.outputs.wiffconverter_0_10 }}
+          CHG_OS003: ${{ steps.filter.outputs.pyonsite_0_0_3 }}
         run: |
           DIANN_ALL='[
             {"context":"diann-2.5.1","tag":"ghcr.io/${{ github.repository_owner }}/diann:2.5.1","sif":"diann-sif:2.5.1","extra_tags":"ghcr.io/${{ github.repository_owner }}/diann:latest","chg":"CHG_251"},
@@ -90,11 +95,15 @@ jobs:
           WIFFCONV_ALL='[
             {"context":"wiffconverter-0.10","tag":"ghcr.io/${{ github.repository_owner }}/wiffconverter:0.10","sif":"wiffconverter-sif:0.10","extra_tags":"ghcr.io/${{ github.repository_owner }}/wiffconverter:latest","chg":"CHG_WC010"}
           ]'
+          PYONSITE_ALL='[
+            {"context":"pyonsite-0.0.3","tag":"ghcr.io/${{ github.repository_owner }}/pyonsite:0.0.3","sif":"pyonsite-sif:0.0.3","extra_tags":"ghcr.io/${{ github.repository_owner }}/pyonsite:latest","chg":"CHG_OS003"}
+          ]'
 
           if [[ "$EVENT" == "release" || "$EVENT" == "workflow_dispatch" ]]; then
             DIANN=$(echo "$DIANN_ALL" | jq -c '[.[] | del(.chg)]')
             RELINK=$(echo "$RELINK_ALL" | jq -c '[.[] | del(.chg)]')
             WIFFCONV=$(echo "$WIFFCONV_ALL" | jq -c '[.[] | del(.chg)]')
+            PYONSITE=$(echo "$PYONSITE_ALL" | jq -c '[.[] | del(.chg)]')
           else
             DIANN=$(echo "$DIANN_ALL" | jq -c --arg c251 "${CHG_251:-false}" --arg c250 "${CHG_250:-false}" --arg c232 "${CHG_232:-false}" --arg c220 "${CHG_220:-false}" --arg c210 "${CHG_210:-false}" \
               --arg c20 "${CHG_20:-false}" --arg c192 "${CHG_192:-false}" --arg c181 "${CHG_181:-false}" \
@@ -112,17 +121,22 @@ jobs:
               '[.[] | select(.chg == "CHG_RLK" and $crlk == "true") | del(.chg)]')
             WIFFCONV=$(echo "$WIFFCONV_ALL" | jq -c --arg cwc010 "${CHG_WC010:-false}" \
               '[.[] | select(.chg == "CHG_WC010" and $cwc010 == "true") | del(.chg)]')
+            PYONSITE=$(echo "$PYONSITE_ALL" | jq -c --arg cos003 "${CHG_OS003:-false}" \
+              '[.[] | select(.chg == "CHG_OS003" and $cos003 == "true") | del(.chg)]')
           fi
 
           echo "diann_matrix={\"include\":$DIANN}" >> $GITHUB_OUTPUT
           echo "relink_matrix={\"include\":$RELINK}" >> $GITHUB_OUTPUT
           echo "wiffconverter_matrix={\"include\":$WIFFCONV}" >> $GITHUB_OUTPUT
+          echo "pyonsite_matrix={\"include\":$PYONSITE}" >> $GITHUB_OUTPUT
           echo "has_diann=$([ "$DIANN" != "[]" ] && echo true || echo false)" >> $GITHUB_OUTPUT
           echo "has_relink=$([ "$RELINK" != "[]" ] && echo true || echo false)" >> $GITHUB_OUTPUT
           echo "has_wiffconverter=$([ "$WIFFCONV" != "[]" ] && echo true || echo false)" >> $GITHUB_OUTPUT
+          echo "has_pyonsite=$([ "$PYONSITE" != "[]" ] && echo true || echo false)" >> $GITHUB_OUTPUT
           echo "DIA-NN: $DIANN"
           echo "Relink: $RELINK"
           echo "WiffConverter: $WIFFCONV"
+          echo "Pyonsite: $PYONSITE"
 
   # ── Build DIA-NN containers (sequential) ───────────────────────────────
   build-diann:
@@ -323,10 +337,68 @@ jobs:
             singularity push image.sif oras://ghcr.io/${{ github.repository_owner }}/$SIF_LATEST
           fi
 
+  # ── Build pyonsite container (after WiffConverter) ──────────────────────────
+  build-pyonsite:
+    name: "pyonsite ${{ matrix.context }}"
+    needs: [detect-changes, build-diann, build-relink, build-wiffconverter]
+    if: always() && needs.detect-changes.outputs.has_pyonsite == 'true' && github.repository_owner == 'bigbio'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    strategy:
+      fail-fast: false
+      max-parallel: 1
+      matrix: ${{ fromJSON(needs.detect-changes.outputs.pyonsite_matrix) }}
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GitHub Container Registry (GHCR)
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: ./${{ matrix.context }}
+          push: ${{ github.event_name != 'pull_request' }}
+          load: true
+          tags: |
+            ${{ matrix.tag }}
+            ${{ matrix.extra_tags }}
+          cache-from: type=gha,scope=${{ matrix.context }}
+          cache-to: type=gha,scope=${{ matrix.context }},mode=max
+          provenance: false
+
+      - name: Set up Singularity
+        if: github.event_name != 'pull_request'
+        uses: eWaterCycle/setup-singularity@v7
+        with:
+          singularity-version: 3.8.7
+
+      - name: Convert to Singularity and push
+        if: github.event_name != 'pull_request'
+        run: |
+          docker save ${{ matrix.tag }} -o image.tar
+          singularity build image.sif docker-archive://image.tar
+
+          echo ${{ secrets.GITHUB_TOKEN }} | singularity remote login -u ${{ github.actor }} --password-stdin oras://ghcr.io
+
+          singularity push image.sif oras://ghcr.io/${{ github.repository_owner }}/${{ matrix.sif }}
+          if [[ "${{ github.event_name }}" == "release" && -n "${{ matrix.extra_tags }}" ]]; then
+            SIF_LATEST=$(echo "${{ matrix.sif }}" | sed 's/:[^:]*$/:latest/')
+            singularity push image.sif oras://ghcr.io/${{ github.repository_owner }}/$SIF_LATEST
+          fi
+
   # ── Sync OpenMS containers (after everything else) ─────────────────────
   sync-openms:
     name: Sync OpenMS Containers
-    needs: [build-diann, build-relink, build-wiffconverter]
+    needs: [build-diann, build-relink, build-wiffconverter, build-pyonsite]
     if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch') && github.repository_owner == 'bigbio'
     runs-on: ubuntu-latest
     permissions:

README.md

@@ -1,13 +1,14 @@
 # QuantMS Docker Containers
 
-A repository of production-ready Docker and Singularity containers for proteomics tools used in quantms pipelines, including **DIA-NN**, **Relink**, and **OpenMS**.
+A repository of production-ready Docker and Singularity containers for proteomics tools used in quantms pipelines, including **DIA-NN**, **Relink**, **pyonsite**, and **OpenMS**.
 
 ## Overview
 
 This repository provides containerized versions of popular proteomics tools:
 
 - [DIA-NN](https://github.com/vdemichev/DiaNN): A powerful software solution for analyzing DIA proteomics data
 - [Relink](https://github.com/bigbio/relink): Crosslinking mass spectrometry analysis pipeline (xiSEARCH, xiFDR, Scout)
+- [pyonsite](https://github.com/bigbio/onsite): Mass spectrometry post-translational modification localization tool (AScore, PhosphoRS, LucXor) — published on PyPI as `pyonsite`
 - [OpenMS](https://www.openms.de/): A versatile open-source software for mass spectrometry data analysis
 - [WiffConverter](https://hub.docker.com/r/sciex/wiffconverter): SCIEX `.wiff` / `.wiff.scan` to indexed `.mzML` conversion via the bundled `OneOmics.WiffConverter` .NET assembly
 
@@ -181,6 +182,43 @@ On failure the wrapper prints a banner with the input/output/mode and the last
 `.wiff.scan`, locked output, unsupported acquisition) are diagnosable from the
 console without re-running.
 
+### pyonsite Container
+
+The pyonsite container provides a complete mass spectrometry PTM localization environment for phosphorylation site assignment and scoring. The PyPI package name is `pyonsite`; the CLI tool is invoked as `onsite`.
+
+| Algorithm  | Description                                                  |
+| ---------- | ------------------------------------------------------------ |
+| AScore     | Probability-based approach using binomial statistics         |
+| PhosphoRS  | Site-specific probabilities with isomer analysis             |
+| LucXor     | Two-stage processing with false localization rate estimation |
+
+| Container Type | Tag   | URL                                           |
+| -------------- | ----- | --------------------------------------------- |
+| Docker         | 0.0.3 | `ghcr.io/bigbio/pyonsite:0.0.3`              |
+| Docker         | latest | `ghcr.io/bigbio/pyonsite:latest`             |
+| Singularity    | 0.0.3 | `oras://ghcr.io/bigbio/pyonsite-sif:0.0.3`   |
+
+```bash
+# Pull the image
+docker pull ghcr.io/bigbio/pyonsite:latest
+
+# AScore algorithm
+docker run --rm -v /path/to/data:/data ghcr.io/bigbio/pyonsite:latest \
+  onsite ascore -in /data/spectra.mzML -id /data/identifications.idparquet -out /data/results.idparquet
+
+# PhosphoRS algorithm
+docker run --rm -v /path/to/data:/data ghcr.io/bigbio/pyonsite:latest \
+  onsite phosphors -in /data/spectra.mzML -id /data/identifications.idparquet -out /data/results.idparquet
+
+# LucXor algorithm with FLR
+docker run --rm -v /path/to/data:/data ghcr.io/bigbio/pyonsite:latest \
+  onsite lucxor -in /data/spectra.mzML -id /data/identifications.idparquet -out /data/results.idparquet
+
+# Compute all three algorithms at once
+docker run --rm -v /path/to/data:/data ghcr.io/bigbio/pyonsite:latest \
+  onsite ascore --compute-all-scores -in /data/spectra.mzML -id /data/identifications.idparquet -out /data/results.idparquet
+```
+
 ### OpenMS Containers
 
 OpenMS containers are publicly available and can be pulled directly:
@@ -200,6 +238,7 @@ Please note the following license restrictions:
 
 - **DIA-NN**: Custom academic license with restrictions. Please review the [DIA-NN license](diann-2.1.0/LICENSE.txt) before using. No commercial use or cloud deployment without collaboration agreement.
 - **DIA-NN Enterprise**: Separate per-user license issued by the DIA-NN authors. The key and the Enterprise binary are **not redistributable** — never commit them or publish the Enterprise image. Build locally only.
+- **pyonsite**: Available under the [MIT License](https://github.com/bigbio/onsite/blob/main/LICENSE) (the underlying `onsite` software)
 - **Relink/xiSEARCH/xiFDR/Scout**: Please review the individual tool licenses
 - **OpenMS**: Available under the [BSD 3-Clause License](https://github.com/OpenMS/OpenMS/blob/develop/LICENSE)
 - **WiffConverter**: Proprietary SCIEX redistributable (via the public `sciex/wiffconverter` Docker Hub image). Users are responsible for complying with SCIEX's terms of use.
@@ -221,6 +260,13 @@ Please note the following license restrictions:
 - Architecture: `amd64`/`x86_64`
 - Includes: Java 21, .NET 9.0, Python 3.12, pyOpenMS, polars, pandas
 
+### pyonsite Container
+
+- Base Image: `python:3.12-slim`
+- Version: 0.0.3
+- Architecture: `amd64`/`x86_64`
+- Includes: Python 3.12, pyOpenMS, NumPy, SciPy, pyarrow, click
+
 ### OpenMS Containers
 
 - Sourced from: `ghcr.io/openms/openms-tools-thirdparty`
@@ -323,6 +369,29 @@ docker run -v /path/to/data:/data ghcr.io/bigbio/relink:latest \
   process_dataset [options]
 ```
 
+#### pyonsite
+
+The CLI tool inside the container is invoked as `onsite` (the PyPI package is `pyonsite`). It provides three PTM localization algorithms (AScore, PhosphoRS, LucXor) and accepts mzML spectra files with identifications in idparquet format:
+
+```bash
+# AScore algorithm
+docker run -v /path/to/data:/data ghcr.io/bigbio/pyonsite:latest \
+  onsite ascore -in /data/spectra.mzML -id /data/identifications.idparquet -out /data/results.idparquet
+
+# PhosphoRS algorithm
+docker run -v /path/to/data:/data ghcr.io/bigbio/pyonsite:latest \
+  onsite phosphors -in /data/spectra.mzML -id /data/identifications.idparquet -out /data/results.idparquet
+
+# LucXor algorithm with FLR
+docker run -v /path/to/data:/data ghcr.io/bigbio/pyonsite:latest \
+  onsite lucxor -in /data/spectra.mzML -id /data/identifications.idparquet -out /data/results.idparquet
+
+# Compute all three algorithms with decoy-based FLR
+docker run -v /path/to/data:/data ghcr.io/bigbio/pyonsite:latest \
+  onsite ascore --compute-all-scores --add-decoys \
+  -in /data/spectra.mzML -id /data/identifications.idparquet -out /data/results.idparquet
+```
+
 #### OpenMS
 
 ```bash
@@ -347,7 +416,8 @@ This repository includes a GitHub Actions workflow that builds and syncs all con
 1. Builds and pushes DIA-NN Docker and Singularity containers (all versions)
 2. Builds and pushes Relink Docker and Singularity containers
 3. Builds and pushes WiffConverter Docker and Singularity containers
-4. Syncs OpenMS containers from the official repository to BigBio
+4. Builds and pushes pyonsite Docker and Singularity containers
+5. Syncs OpenMS containers from the official repository to BigBio
 
 The workflow is triggered by:
 

pyonsite-0.0.3/Dockerfile

@@ -0,0 +1,47 @@
+FROM python:3.12-slim
+
+# Metadata
+LABEL base_image="python:3.12-slim"
+LABEL version="1"
+LABEL software="pyonsite"
+LABEL software.version="0.0.3"
+LABEL about.summary="onsite: mass spectrometry post-translational modification localization tool (AScore, PhosphoRS, LucXor)"
+LABEL about.home="https://github.com/bigbio/onsite"
+LABEL about.documentation="https://github.com/bigbio/onsite"
+LABEL about.license="MIT"
+LABEL about.tags="Proteomics,PTM,Phosphorylation,MassSpectrometry"
+LABEL maintainer="Yasset Perez-Riverol <ypriverol@gmail.com>"
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1
+
+# Install system dependencies required by pyopenms (libglib-2.0)
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        libglib2.0-0 && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install pyonsite and its dependencies (pyopenms, numpy, scipy, pyarrow, click)
+RUN pip install --no-cache-dir pyonsite==0.0.3
+
+# Verify installation
+RUN set -e; \
+    echo "=== Version checks ===" && \
+    python -c "from importlib.metadata import version; print(f'pyonsite {version(\"pyonsite\")}')" && \
+    python -c "import pyopenms; print(f'pyopenms {pyopenms.__version__}')" && \
+    python -c "import numpy; print(f'numpy {numpy.__version__}')" && \
+    python -c "import scipy; print(f'scipy {scipy.__version__}')" && \
+    python -c "import pyarrow; print(f'pyarrow {pyarrow.__version__}')" && \
+    echo "=== CLI smoke test ===" && \
+    onsite --help && \
+    echo "=== Subcommand help ===" && \
+    onsite ascore --help && \
+    onsite phosphors --help && \
+    onsite lucxor --help && \
+    echo "=== All checks passed ==="
+
+WORKDIR /data/
+
+# Reset ENTRYPOINT/CMD so the container behaves like the other images in this repo
+ENTRYPOINT []
+CMD ["/bin/bash"]