Merge pull request #398 from lilab-bcb/upgrade-cellbender

Upgrade cellbender to 0.3.0

docker/cellbender/0.3.0/Dockerfile

@@ -0,0 +1,50 @@
+# Start from nvidia-docker image with drivers pre-installed to use a GPU
+FROM nvcr.io/nvidia/cuda:11.7.1-base-ubuntu22.04
+
+LABEL description="This docker is modified from the official BSD-3-Clause licensed CellBender dockerfile (https://github.com/broadinstitute/CellBender/blob/master/docker/Dockerfile)."
+
+# Install curl and sudo and git and miniconda and pytorch, cudatoolkit, pytables, and cellbender
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+        curl \
+        wget \
+        rsync \
+        ca-certificates \
+        unzip
+
+RUN curl -so miniconda.sh https://repo.anaconda.com/miniconda/Miniconda3-py37_23.1.0-1-Linux-x86_64.sh && \
+    bash miniconda.sh -b -p /opt/miniconda3 && \
+    rm miniconda.sh
+
+ENV PATH=/opt/miniconda3/bin:$PATH \
+    DOCKER=true \
+    CONDA_AUTO_UPDATE_CONDA=false
+
+RUN echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] http://packages.cloud.google.com/apt cloud-sdk main" | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list && \
+    curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key --keyring /usr/share/keyrings/cloud.google.gpg add - && \
+    apt-get update -y && apt-get install -y google-cloud-cli
+
+RUN curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64-2.15.10.zip" -o "awscliv2.zip" && \
+    unzip awscliv2.zip && \
+    ./aws/install && \
+    rm awscliv2.zip
+
+RUN pip install stratocumulus==0.2.1
+
+RUN wget https://github.com/broadinstitute/CellBender/archive/refs/tags/v0.3.0.tar.gz && \
+    tar -xzf v0.3.0.tar.gz && \
+    rm v0.3.0.tar.gz && \
+    mkdir /software && \
+    mv CellBender-0.3.0 /software/CellBender && \
+    cd /software/CellBender && \
+    pip install -e .
+
+RUN apt-get -qq -y autoremove && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/* /var/log/dpkg.log
+
+ADD https://raw.githubusercontent.com/lilab-bcb/cumulus/master/docker/monitor_script.sh /software
+RUN chmod a+rx /software/monitor_script.sh
+
+# Add cellbender command to PATH
+ENV PATH=/software:$PATH

docs/cellbender.rst

@@ -63,13 +63,15 @@ Below are inputs for *CellBender* workflow. Notice that required inputs are **in
       - "gs://fc-e0000000-0000-0000-0000-000000000000/my-project/cellbender_output"
       -
     * - expected_cells
-      - Number of cells expected in the dataset (a rough estimate within a factor of 2 is sufficient).
+      - | Number of cells expected in the dataset (a rough estimate within a factor of 2 is sufficient).
+        | **Notice:** If *cellbender_version* is ``0.3.0``, no need to specify this parameter.
       - 2048
-      - ``None``
+      - Automatically inferred from data
     * - total_droplets_included
-      - The number of droplets from the rank-ordered UMI plot that will be analyzed. The largest *total_droplets_included* droplets will have their cell probabilities inferred as an output.
-      - 25000
+      - | The number of droplets from the rank-ordered UMI plot that will be analyzed. The largest *total_droplets_included* droplets will have their cell probabilities inferred as an output.
+        | **Notice:** If *cellbender_version* is ``0.3.0``, no need to specify this parameter.
       - 25000
+      - Automatically inferred from data
     * - model
       - Which model is being used for count data:
 
@@ -127,9 +129,9 @@ Below are inputs for *CellBender* workflow. Notice that required inputs are **in
       - "quay.io/cumulus"
       - "quay.io/cumulus"
     * - cellbender_version
-      - CellBender version to use. Currently available: ``0.2.0``.
-      - "0.2.0"
-      - "0.2.0"
+      - CellBender version to use. Currently available: ``0.3.0``, ``0.2.0``.
+      - "0.3.0"
+      - "0.3.0"
     * - zones
       - Google cloud zones to consider for execution. Only works if *backend* is ``gcp``.
       - "us-east1-d us-west1-a us-west1-b"

workflows/cellbender/cellbender.wdl

@@ -12,8 +12,8 @@ workflow cellbender {
         String output_directory
         # Docker image for cellbender remove-background version
         String docker_registry = "quay.io/cumulus"
-        # Cellbender version to use. Currently support: 0.2.0
-        String cellbender_version = "0.2.0"
+        # Cellbender version to use. Currently support: 0.3.0, 0.2.0
+        String cellbender_version = "0.3.0"
 
         # Expected cells
         Int? expected_cells
@@ -156,7 +156,7 @@ task run_cellbender_remove_background_gpu {
            ~{"--learning-rate " + learning_rate} \
            ~{true="--exclude-antibody-capture" false=" " exclude_antibody_capture}
 
-        strato cp --backend ~{backend} ~{sample_name}_out* ~{output_directory}/~{sample_name}/
+        strato cp ~{sample_name}_out* ~{output_directory}/~{sample_name}/
     }
 
     output {