I/O operations

.github/workflows/crates.yml

@@ -0,0 +1,28 @@
+name: crates
+# This builds the docker image and pushes it to DockerHub
+# Runs on nf-core repo releases and push event to 'dev' branch (PR merges)
+on:
+  release:
+    types: [published]
+
+jobs:
+  push_cratesio:
+    name: Push repository to crates.io
+    runs-on: ubuntu-latest
+    # Only run for the nf-core repo, for releases and merged PRs
+    if: ${{ github.repository == 'RenzoTale88/xpclrs' }}
+    steps:
+      - name: Check out pipeline code
+        uses: actions/checkout@v4
+
+      - name: Linux deps
+        run: sudo apt-get update && sudo apt-get install libopenblas-dev
+
+      - name: Build
+        run: cargo login --token ${{ secrets.CARGO_REGISTRY_TOKEN }}
+
+      - name: Build
+        run: cargo publish --dry-run
+
+      - name: Publish xpclrs to crates.io
+        run: cargo publish

.github/workflows/docker.yml

@@ -0,0 +1,56 @@
+name: Docker
+# This builds the docker image and pushes it to DockerHub
+# Runs on nf-core repo releases and push event to 'dev' branch (PR merges)
+on:
+  push:
+    branches:
+      - main
+  release:
+    types: [published]
+
+jobs:
+  push_dockerhub:
+    name: Push new Docker image to Docker Hub
+    runs-on: ubuntu-latest
+    # Only run for the nf-core repo, for releases and merged PRs
+    if: ${{ github.repository == 'RenzoTale88/xpclrs' }}
+    env:
+      DOCKERHUB_USERNAME: ${{ secrets.DOCKER_HUB_USERNAME }}
+      DOCKERHUB_PASS: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
+    steps:
+      - name: Check out pipeline code
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_HUB_USERNAME }}
+          password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
+
+      - name: Build and push Docker image (push event)
+        if: ${{ github.event_name == 'push' }}
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ secrets.DOCKER_HUB_USERNAME }}/xpclrs:latest
+          no-cache: true
+
+      - name: Build and push Docker image (release event)
+        if: ${{ github.event_name == 'release' }}
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            ${{ secrets.DOCKER_HUB_USERNAME }}/xpclrs:latest
+            ${{ secrets.DOCKER_HUB_USERNAME }}/xpclrs:${{ github.event.release.tag_name }}
+          no-cache: true

.github/workflows/rust.yml

@@ -16,8 +16,8 @@ jobs:
       fail-fast: false
       matrix:
         build: [
-          ubuntu,
-          ubuntu-arm,
+          linux_x86,
+          linux_arm,
           macos_arm64,
           macos_x86_64
         ]
@@ -26,9 +26,9 @@ jobs:
             os: macos-latest
           - build: macos_x86_64
             os: macos-15-intel
-          - build: ubuntu
+          - build: linux_x86
             os: ubuntu-latest
-          - build: ubuntu-arm
+          - build: linux_arm
             os: ubuntu-24.04-arm
     steps:
     - uses: actions/checkout@v4
@@ -53,14 +53,13 @@ jobs:
     - name: Release
       run: cargo build --release
 
-    # Upload the binaries from the ubuntu analysis
+    # Upload the binaries from each build
     - name: Upload artifacts
-      if: matrix.os == 'ubuntu-latest'
       uses: actions/upload-artifact@v4
       with:
-        name: binaries
-        path: target/release
-        retention-days: 0.5
+        name: xpclrs_${{ matrix.build }}
+        path: target/release/xpclrs
+        retention-days: 1
 
   # Test the binaries
   exe:
@@ -72,18 +71,40 @@ jobs:
       - name: Download Binaries
         uses: actions/download-artifact@v4
         with:
-          name: binaries
+          name: xpclrs_linux_x86
           path: ./bin/  # This will store the downloaded artifacts in ./bin
       - name: Run help
         run: |
+          ls ./bin/
           chmod +x ./bin/xpclrs
           ./bin/xpclrs --help
-      - name: Run test
+      - name: Run test (VCF, unphased)
+        run: |
+          chmod +x ./bin/xpclrs
+          ./bin/xpclrs --input test/test.vcf.gz --out test --samplesA test/samplesA.txt --samplesB test/samplesB.txt --chr chr1 -t 1
+          head test.chr1.xpclr
+      - name: Run test (VCF, phased)
+        run: |
+          chmod +x ./bin/xpclrs
+          ./bin/xpclrs --input test/test.vcf.gz --out test --samplesA test/samplesA.txt --samplesB test/samplesB.txt --chr chr1 -t 1 --phased
+          head test.chr1.xpclr
+      - name: Run test (VCF, unphased, fast)
+        run: |
+          chmod +x ./bin/xpclrs
+          ./bin/xpclrs --input test/test.vcf.gz --out test --samplesA test/samplesA.txt --samplesB test/samplesB.txt --chr chr1 -t 1 --fast
+          head test.chr1.xpclr
+      - name: Run test (VCF, phased, fast)
+        run: |
+          chmod +x ./bin/xpclrs
+          ./bin/xpclrs --input test/test.vcf.gz --out test --samplesA test/samplesA.txt --samplesB test/samplesB.txt --chr chr1 -t 1 --phased --fast
+          head test.chr1.xpclr
+      - name: Run test (plink)
+        run: |
+          chmod +x ./bin/xpclrs
+          ./bin/xpclrs --input test/plink --plink --out test --samplesA test/samplesA_plink.txt --samplesB test/samplesB_plink.txt --chr 1 -t 1
+          head test.chr1.xpclr
+      - name: Run test (plink, fast)
         run: |
           chmod +x ./bin/xpclrs
-          wget https://raw.githubusercontent.com/hardingnj/xpclr/refs/heads/master/fixture/samplesA.txt
-          wget https://raw.githubusercontent.com/hardingnj/xpclr/refs/heads/master/fixture/samplesB.txt
-          wget https://raw.githubusercontent.com/hardingnj/xpclr/refs/heads/master/fixture/small.vcf.gz
-          wget https://raw.githubusercontent.com/hardingnj/xpclr/refs/heads/master/fixture/small.vcf.gz.tbi
-          ./bin/xpclrs --input small.vcf.gz --out test --samplesA samplesA.txt --samplesB samplesB.txt --chr 3L -t 1
-          cat test.3L.xpclr
+          ./bin/xpclrs --input test/plink --plink --out test --samplesA test/samplesA_plink.txt --samplesB test/samplesB_plink.txt --chr 1 -t 1 --fast
+          head test.chr1.xpclr

Cargo.toml

@@ -1,13 +1,14 @@
 [package]
 name = "xpclrs"
-version = "0.1.0"
+version = "1.0.0"
 authors = ["Andrea Talenti"]
 edition = "2021"
 license = "MIT"
 repository = "https://github.com/RenzoTale88/xpclrs"
 readme = "README.md"
-keywords = ["genome", "bioinformatics", "sequencing"]
-categories = ["bioinformatics"]
+keywords = ["genome", "bioinformatics", "sequencing", "selection"]
+categories = ["science::bioinformatics"]
+description = "A high-performance rust implementation of the XP-CLR method."
 
 [dependencies]
 anyhow           = "1.0.98"

Dockerfile

@@ -1,5 +1,9 @@
-# Use the official NVIDIA CUDA image as the base image
-FROM ubuntu:18.04
+# Use an old ubuntu image to maximize compatibility with older systems relying on
+# older libc versions
+FROM ubuntu:18.04 AS build
+
+# Copy source code
+COPY . /xpclrs
 
 # Set up the environment
 ENV DEBIAN_FRONTEND=noninteractive
@@ -17,3 +21,10 @@ RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
 
 # Add Cargo to PATH
 ENV PATH="/root/.cargo/bin:${PATH}"
+
+# Compile the tool, then declutter the image
+WORKDIR /xpclrs
+RUN /root/.cargo/bin/cargo build --release
+
+FROM ubuntu:18.04 AS runtime
+COPY --from=build /xpclrs/target/release/xpclrs /usr/local/bin/xpclrs

README.md

@@ -30,10 +30,13 @@ xpclrs --help
 ## Input
 The software requires the following mandatory options:
 1. Input genotypes in VCF(.GZ)/BCF format with `-I-`/`--input`.
+    * PLINK binary files (BED/BIM/FAM) are also supported by providing the root of the file name with the same `-I`/`--input` option and adding the `--plink` flag..
+    * Loading in plink file is substantially faster than using the VCF format, but worth noticing that it can lead to different results due to the variants being coded as major/minor rather than REF/ALT (XP-CLR relies on allele frequencies).
 2. The lists of individuals in each group (one individual per line) with `-A`/`--samplesA` and `-B`/`--samplesB`.
+    * PLINK samples are loaded as `FID_IID`. So if your sample in the FAM file is `POP1 SAMP1 0 0 0 -9`, the sample will be listed as `POP1_SAMP1` in the group of individuals.
 3. The sequence to analyse with `-C`/`--chr`.
 
-The VCF can optionally include a genetic distance key, that can be specified with the `--gdistkey [NAME]`. Alternatively, users can provide the recombination rate with the `-R`/`--rrate` option.
+The VCF can optionally include a genetic distance key, that can be specified with the `--gdistkey [NAME]`. Alternatively, users can provide the recombination rate with the `-R`/`--rrate` option. For PLINK inputs, the software will automatically detect the presence of a genetic position in the dataset and use that; if the value is equal to 0, the script will compute the genetic position based on the physical position and the recombination rate. Ensure that there are not gaps in the genetic position (i.e. a 0 following a known genetic position).
 
 The analysis can be further sped up using multithreading with the `--threads`/`-t` option, followed by the number of threads to use. If set to 0, the software will try to use all the threads available.