Merge pull request #270 from NBISweden/docker-changes

Changes to Docker material

tutorials/containers/Dockerfile

@@ -1,54 +1,41 @@
-FROM --platform=amd64 condaforge/miniforge3
+FROM condaforge/miniforge3:24.7.1-0
 
+LABEL authors="John Sundh, john.sundh@scilifelab.se; Erik Fasterius, erik.fasterius@nbis.se"
 LABEL description="Image for the NBIS reproducible research course."
-LABEL author="John Sundh"
-LABEL email="john.sundh@scilifelab.se"
-
-# Use bash as shell
-SHELL ["/bin/bash", "--login", "-c"]
 
 # Set workdir
 WORKDIR /course
 
-# Set timezone
-ENV TZ="Europe/Stockholm"
-ENV DEBIAN_FRONTEND=noninteractive
+# Use bash as shell
+SHELL ["/bin/bash", "-c"]
 
-# Install packages require for timezone and Quarto installation
-RUN apt-get update \
-    && apt-get install -y tzdata curl \
-    && apt-get clean
+# Install required packages
+RUN apt-get update && \
+    apt-get install -y curl && \
+    apt-get clean
 
 # Install Quarto
 ARG QUARTO_VERSION="1.3.450"
-RUN mkdir -p /opt/quarto/${QUARTO_VERSION} \
-    && curl -o quarto.tar.gz -L "https://github.com/quarto-dev/quarto-cli/releases/download/v${QUARTO_VERSION}/quarto-${QUARTO_VERSION}-linux-amd64.tar.gz" \
-    && tar -zxvf quarto.tar.gz -C "/opt/quarto/${QUARTO_VERSION}" --strip-components=1 \
-    && rm quarto.tar.gz
-ENV PATH /opt/quarto/${QUARTO_VERSION}/bin:${PATH}
+RUN mkdir -p /opt/quarto/${QUARTO_VERSION} && \
+    curl -o quarto.tar.gz -L "https://github.com/quarto-dev/quarto-cli/releases/download/v${QUARTO_VERSION}/quarto-${QUARTO_VERSION}-linux-amd64.tar.gz" && \
+    tar -zxvf quarto.tar.gz -C "/opt/quarto/${QUARTO_VERSION}" --strip-components=1 && \
+    rm quarto.tar.gz
+ENV PATH=/opt/quarto/${QUARTO_VERSION}/bin:${PATH}
 
 # Configure Conda
-RUN conda init bash && conda config --set channel_priority strict && \
-    conda config --append channels bioconda && \
-    conda config --append channels r && \
-    conda config --set subdir linux-64
+RUN conda config --set channel_priority strict && \
+    conda config --append channels bioconda
 
 # Install environment
 COPY environment.yml ./
 RUN conda env create -f environment.yml -n project_mrsa && \
     conda clean -a
 
-# Set mrsa-workflow environment as active at start-up
 RUN echo "source activate project_mrsa" >> ~/.bashrc
-
-# Add environment to PATH
-ENV PATH /opt/conda/envs/project_mrsa/bin:${PATH}
+ENV PATH=/opt/conda/envs/project_mrsa/bin:${PATH}
 
 # Add project files
 COPY Snakefile config.yml ./
 COPY code ./code/
 
-# Open up port 8888
-EXPOSE 8888
-
-CMD snakemake -p -c 1 --configfile config.yml
+CMD snakemake --configfile config.yml -p -c 1

tutorials/containers/code/supplementary_material.qmd

@@ -3,7 +3,7 @@ title: "Supplementary Material"
 format:
     html:
         echo: false
-        embed_resources: true
+        embed-resources: true
 engine: knitr
 params:
     counts_file: "results/tables/counts.tsv"
@@ -54,22 +54,29 @@ colnames(counts_summary) <- gsub(".*(SRR[0-9]+)\\..*", "\\1",
 meta <- data.frame()
 for (GSM in gsm_ids) {
     gsm <- Meta(getGEO(GSM))
-    current_meta <- as.data.frame(do.call(cbind, gsm))
+    current_meta <- as.data.frame(
+        list(
+            title=gsm$title, geo_accession=gsm$geo_accession, source_name_ch1=gsm$source_name_ch1, 
+            growth_phase=gsub("growth phase: ", "", gsm$characteristics_ch1[grep("growth phase", gsm$characteristics_ch1)]),
+            treatment=gsub("treatment: ", "", gsm$characteristics_ch1[grep("treatment", gsm$characteristics_ch1)])
+        )
+    )
     meta <- rbind(meta, current_meta)
 }
-meta <- meta[c("title", "geo_accession", "source_name_ch1", "characteristics_ch1")]
+meta <- meta[c("title", "geo_accession", "source_name_ch1", "growth_phase", "treatment")]
 gsm2srr <- data.frame(geo_accession = gsm_ids, SRR = srr_ids)
 meta <- merge(meta, gsm2srr, by = "geo_accession")
 
 # Read FastQC data and update column names
 qc <- read.delim(multiqc_file)
-patterns <- c(".+percent_duplicates.*",
-              ".+percent_gc.*",
-              ".+avg_sequence_length.*",
-              ".+percent_fails.*",
-              ".+total_sequences.*")
+patterns <- c("*.+percent_duplicates.*",
+              "*.+percent_gc.*",
+              "*.+avg_sequence_length.*",
+              "*.+median_sequence_length.*",
+              "*.+percent_fails.*",
+              "*.+total_sequences.*")
 subs <- c("Percent duplicates", "Percent GC", "Avg sequence length",
-          "Percent fails", "Total sequences")
+          "Median sequence length", "Percent fails", "Total sequences")
 for (i in 1:length(patterns)) {
     colnames(qc) <- gsub(patterns[i], subs[i], colnames(qc))
 }
@@ -85,10 +92,8 @@ was aligned and counted.
 # Supplementary Tables and Figures
 
 ```{r Sample info}
-columns <- c("SRR", "geo_accession", "source_name_ch1", "characteristics_ch1")
+columns <- c("SRR", "geo_accession", "source_name_ch1", "growth_phase", "treatment")
 sample_info <- meta[, columns]
-sample_info$characteristics_ch1 <- gsub("treatment: ", "", sample_info$characteristics_ch1)
-sample_info$characteristics_ch1 <- gsub("growth phase: ", "", sample_info$characteristics_ch1)
 sample_info
 ```
 

tutorials/containers/slim.Dockerfile

@@ -0,0 +1,20 @@
+FROM condaforge/miniforge3
+
+LABEL authors="John Sundh, john.sundh@scilifelab.se; Erik Fasterius, erik.fasterius@nbis.se"
+LABEL description="Minimal image for the NBIS reproducible research course."
+
+WORKDIR /course
+
+SHELL ["/bin/bash", "-c"]
+
+# Install `curl` for downloading of FASTQ data later in the tutorial
+RUN apt-get update && \
+    apt-get install -y curl && \
+    apt-get clean
+
+# Configure Conda
+RUN conda config --set channel_priority strict && \
+    conda config --append channels bioconda
+
+# Start Bash by default
+CMD /bin/bash

tutorials/git/Dockerfile

@@ -1,10 +1,11 @@
 FROM ubuntu:16.04
 
-LABEL description = "Image for the NBIS reproducible research course."
-MAINTAINER "John Sundh" john.sundh@scilifelab.se
+LABEL authors="John Sundh, john.sundh@scilifelab.se"
+LABEL description="Minimal image for the NBIS reproducible research course."
 
 # Use bash as shell
 SHELL ["/bin/bash", "-c"]
+
 # Set workdir
 WORKDIR /course