Merge pull request #407 from lilab-bcb/yiming

Fix workflow issue with cellranger-arc

docker/cellranger-arc/2.0.2.strato/Dockerfile

@@ -0,0 +1,31 @@
+FROM debian:bullseye-slim
+SHELL ["/bin/bash", "-c"]
+
+RUN apt-get update && \
+    apt-get install --no-install-recommends -y unzip rsync build-essential dpkg-dev curl gnupg procps python3 python3-pip && \
+    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=392.0.0-0
+
+RUN curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64-2.7.11.zip" -o "awscliv2.zip" && \
+    unzip awscliv2.zip && \
+    ./aws/install && \
+    rm awscliv2.zip
+
+RUN pip3 install --upgrade pip && \
+    pip3 install pandas==1.4.3 && \
+    pip3 install packaging==21.3 && \
+    pip3 install stratocumulus==0.2.4
+
+RUN mkdir /software
+ADD https://raw.githubusercontent.com/lilab-bcb/cumulus/master/docker/monitor_script.sh /software
+ADD cellranger-arc-2.0.2.tar.gz /software
+
+RUN apt-get -qq -y autoremove && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/* /var/log/dpkg.log && \
+    rm -f /usr/bin/python && ln -s /usr/bin/python3 /usr/bin/python
+
+RUN chmod a+rx /software/monitor_script.sh
+ENV PATH=/software:/software/cellranger-arc-2.0.2:/usr/local/aws-cli/v2/current/bin:$PATH
+ENV TMPDIR=/tmp

docker/cellranger-arc/2.0.2/Dockerfile

@@ -15,7 +15,7 @@ RUN curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64-2.7.11.zip" -o "a
 RUN pip3 install --upgrade pip && \
     pip3 install pandas==1.4.3 && \
     pip3 install packaging==21.3 && \
-    pip3 install stratocumulus==0.2.4
+    pip3 install stratocumulus==0.1.7
 
 RUN mkdir /software
 ADD https://raw.githubusercontent.com/lilab-bcb/cumulus/master/docker/monitor_script.sh /software

docs/cellranger/sc_multiomics.rst

@@ -155,9 +155,9 @@ For single-cell multiomics data, ``cellranger_workflow`` takes Illumina outputs
 	  - "8.0.1"
 	  - "8.0.1"
 	* - cellranger_arc_version
-	  - cellranger-arc version, could be 2.0.2, 2.0.1, 2.0.0, 1.0.1, 1.0.0
-	  - "2.0.2"
-	  - "2.0.2"
+	  - cellranger-arc version, could be: ``2.0.2.strato`` (compatible with workflow v2.6.1+), ``2.0.2.custom-max-cell`` (with max_cell threshold set to 80,000), ``2.0.2`` (compatible with workflow v2.6.0 or earlier), ``2.0.1``, ``2.0.0``, ``1.0.1``, ``1.0.0``
+	  - "2.0.2.strato"
+	  - "2.0.2.strato"
 	* - docker_registry
 	  - Docker registry to use for cellranger_workflow. Options:
 

docs/conf.py

@@ -26,7 +26,7 @@
 # The short X.Y version
 version = '2.6'
 # The full version, including alpha/beta/rc tags
-release = '2.6.1'
+release = '2.6.2'
 
 
 # -- General configuration ---------------------------------------------------

docs/release_notes/version_2_6.rst

@@ -1,3 +1,8 @@
+2.6.2 :small:`June 19, 2024`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+* Solve the issue of Cellranger workflow with cellranger-arc. ``cellranger_arc_version`` default is now "2.0.2.strato" which is compatible with workflow v2.6.1 or later.
+
 2.6.1 :small:`May 8, 2024`
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
 

workflows/cellbender/frp_utils.py

@@ -0,0 +1,33 @@
+import pandas as pd
+import pegasusio as io
+
+from pegasusio import MultimodalData, UnimodalData
+from typing import Union, Optional
+
+
+def filter_included_genes(
+    data: Union[MultimodalData, UnimodalData],
+    filt_features_tsv: pd.DataFrame,
+    output_file: Optional[str] = None,
+) -> None:
+    df_var = pd.read_csv(filt_features_tsv, sep='\t', header=None)
+    assert df_var[0].nunique() == 18082, "Filtered genes inconsistent!"
+
+    data._inplace_subset_var(data.var['featureid'].isin(df_var[0].values))
+    correct_gene_names(data)
+    if output_file:
+        io.write_output(data, output_file)
+
+def correct_gene_names(data):
+    rename_dict = {
+        "ENSG00000285053": "GGPS1-TBCE",
+        "ENSG00000284770": "TBCE",
+        "ENSG00000187522": "HSPA14",
+        "ENSG00000284024": "MSANTD7",
+        "ENSG00000269226": "TMSB15C",
+        "ENSG00000158427": "TMSB15B",
+    }
+    df_var = data.var.reset_index()
+    for gene_id, gene_name in rename_dict.items():
+        df_var.loc[df_var['featureid']==gene_id, 'featurekey'] = gene_name    
+    data.var = df_var.set_index('featurekey')

workflows/cellranger/cellranger_workflow.wdl

@@ -104,8 +104,8 @@ workflow cellranger_workflow {
         String cumulus_feature_barcoding_version = "0.11.3"
         # 2.1.0, 2.0.0, 1.2.0, 1.1.0
         String cellranger_atac_version = "2.1.0"
-        # 2.0.2, 2.0.1, 2.0.0, 1.0.1, 1.0.0
-        String cellranger_arc_version = "2.0.2"
+        # 2.0.2.strato, 2.0.2.custom-max-cell, 2.0.2, 2.0.1, 2.0.0, 1.0.1, 1.0.0
+        String cellranger_arc_version = "2.0.2.strato"
         # config version
         String config_version = "0.3"