From 867b707ce533015930fe14e84154becd385ee35d Mon Sep 17 00:00:00 2001
From: alisandra <alisandra.denton@hhu.de>
Date: Tue, 23 Aug 2022 19:50:34 +0200
Subject: [PATCH] slightly less broken isoseq
---
_reader/sections/04_section_longreads.tex | 35 ++++++------
workflows/maindocker/Dockerfile | 70 +++++++++++------------
2 files changed, 52 insertions(+), 53 deletions(-)
diff --git a/_reader/sections/04_section_longreads.tex b/_reader/sections/04_section_longreads.tex
index 7fd0c0a..0828439 100644
--- a/_reader/sections/04_section_longreads.tex
+++ b/_reader/sections/04_section_longreads.tex
@@ -216,10 +216,9 @@ multiplexed libraries, we could also perform demultiplexing with \il{lima}.
\begin{lstlisting}
mkdir -p runs/isoseq/trimmed/
lima runs/isoseq/ccs/m16.ccs.bam workflows/pacbiosciences_lima/clonetech_SMARTer.fa \
- runs/isoseq/trimmed/m16.ccs.bam --no-pbi --isoseq
+ runs/isoseq/trimmed/m16.ccs.bam --isoseq
# The first three arguments are obvious from the usage
# Usage: lima [options] INPUT BARCODES OUTPUT
-# --no-pbi since we won't need the .pbi output
# --isoseq is necessary to tell it what to expect for the primers
# let's check the output
@@ -236,7 +235,12 @@ less runs/isoseq/trimmed/head_trimmed.sam
# _most_ of the poly-A tails are at the end of the sequence now
\end{lstlisting}
-\subsubsection{Clustering}
+\subsubsection{Refining}
+
+\emph{This has changed a low, clustering and polising, are now called
+refining, and ran in one step / polising may be skipped.
+Please pardon if the description is off}
+
So at this point we have some reads that are \emph{in some ways} similar
to that which we had after running Trimmomatic on the Illumina data. But
not quite. We just saw the remaining poly-As and adapters that were in the
@@ -252,23 +256,22 @@ So if we were using more samples, we'd want to run \il{dataset create}
first, which would link files in a way that they could all be processed together.
\begin{lstlisting}
-mkdir -p runs/isoseq/unpolished/
+mkdir -p runs/isoseq/polished/
# from the help function:
-# isoseq3 cluster [options] input output
-isoseq3 cluster runs/isoseq/trimmed/m16.ccs.primer_5p--primer_3p.bam \
- runs/isoseq/unpolished/m16.unpolished.bam --verbose --require-polya
+# isoseq refine [options] <ccs.demux.bam|xml> <primer.fasta|xml> <flnc.bam|xml>
+isoseq3 refine runs/isoseq/trimmed/m16.ccs.primer_5p--primer_3p.bam \
+ workflows/pacbiosciences_lima/clonetech_SMARTer.fa \
+ runs/isoseq/polished/m16.polished.bam --verbose --require-polya
# again, we have a lot of output
-ls -sh runs/isoseq/unpolished/
+ls -sh runs/isoseq/polished/
# there's two files we really care about, and both are .bam
-# *.unpolished.flnc.bam contains the fully cleaned, AKA
+# *.polished.flnc.bam contains the fully cleaned, AKA
# "full-length non-chimeric" reads. Finally.
-# *.unpolished.bam has draft reconstructed transcripts
+# *.polished.bam has draft reconstructed transcripts
# we can also get a report on how many flnc reads were used
# for each draft transcript
-isoseq3 summarize runs/isoseq/unpolished/m16.unpolished.bam \
- runs/isoseq/unpolished/m16.summary.csv
-less runs/isoseq/unpolished/m16.summary.csv
+less runs/isoseq/polished/m16.polished.report.csv
\end{lstlisting}
After this, the pipelines we're looking at today start to diverge,
@@ -309,11 +312,7 @@ a ccs read with just a single subread.
%TODO : running into error: Missing .pbi
\begin{lstlisting}
-mkdir -p runs/isoseq/polished/
-# isoseq3 polish -h # uncomment for explanation
-isoseq3 polish runs/isoseq/unpolished/m16.unpolished.bam \
- runs/isoseq/subreads/m16*.subreads.bam \
- runs/isoseq/polished/m16.polished.bam
+# isoseq polish is no longer a thing...
\end{lstlisting}
OK, this step is going to take a long time (maybe an hour?). It's working with 5GB of reads after all
diff --git a/workflows/maindocker/Dockerfile b/workflows/maindocker/Dockerfile
index d48e6cd..79e8ee8 100644
--- a/workflows/maindocker/Dockerfile
+++ b/workflows/maindocker/Dockerfile
@@ -48,48 +48,46 @@ RUN apt install hisat2 \
samtools \
minimap2 \
mash \
- cd-hit -y
+ cd-hit tar bzip2 \
+ libhdf5-dev m4 -y
+# last ones are for kallisto
# --- used to be conda, now binaries... --- #
-RUN pip install HTSeq
-RUN apt install wget tar bzip2 -y
-RUN wget https://anaconda.org/bioconda/isoseq3/3.7.0/download/linux-64/isoseq3-3.7.0-h9ee0642_0.tar.bz2
-RUN tar xvf isoseq3-3.7.0-h9ee0642_0.tar.bz2
-RUN wget https://anaconda.org/bioconda/lima/2.6.0/download/linux-64/lima-2.6.0-h9ee0642_0.tar.bz2
-RUN tar xvf lima-2.6.0-h9ee0642_0.tar.bz2
-RUN wget https://anaconda.org/bioconda/pbccs/6.4.0/download/linux-64/pbccs-6.4.0-h9ee0642_0.tar.bz2
-RUN tar xvf pbccs-6.4.0-h9ee0642_0.tar.bz2
-RUN wget https://anaconda.org/bioconda/bax2bam/0.0.11/download/linux-64/bax2bam-0.0.11-0.tar.bz2
-RUN tar xvf bax2bam-0.0.11-0.tar.bz2
+# for virtualenv intro
+ENV PATH="/home/$DOCKER_USER/.local/bin:${PATH}"
+RUN pip install HTSeq virtualenv
+RUN wget https://anaconda.org/bioconda/isoseq3/3.7.0/download/linux-64/isoseq3-3.7.0-h9ee0642_0.tar.bz2 && \
+ tar xvf isoseq3-3.7.0-h9ee0642_0.tar.bz2 && \
+ wget https://anaconda.org/bioconda/lima/2.6.0/download/linux-64/lima-2.6.0-h9ee0642_0.tar.bz2 && \
+ tar xvf lima-2.6.0-h9ee0642_0.tar.bz2 && \
+ wget https://anaconda.org/bioconda/pbccs/6.4.0/download/linux-64/pbccs-6.4.0-h9ee0642_0.tar.bz2 && \
+ tar xvf pbccs-6.4.0-h9ee0642_0.tar.bz2 && \
+ wget https://anaconda.org/bioconda/bax2bam/0.0.11/download/linux-64/bax2bam-0.0.11-0.tar.bz2 && \
+ tar xvf bax2bam-0.0.11-0.tar.bz2
# kallisto
-RUN apt install libhdf5-dev m4 -y
-WORKDIR /home/$DOCKER_USER/repos
-RUN curl -O -L http://ftpmirror.gnu.org/autoconf/autoconf-2.69.tar.gz
-RUN tar -xzf autoconf-2.69.tar.gz
-WORKDIR /home/$DOCKER_USER/repos/autoconf-2.69
-RUN ./configure && make && make install
-WORKDIR /home/$DOCKER_USER/repos
-RUN git clone https://github.com/pachterlab/kallisto.git && mkdir kallisto/build
-WORKDIR /home/$DOCKER_USER/repos/kallisto/build
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/x86_64-linux-gnu/hdf5/serial/lib
-RUN cmake -DCMAKE_INSTALL_PREFIX=/home/$DOCKER_USER/ -DUSE_HDF5=ON .. && make && make install
+RUN cd /home/$DOCKER_USER/repos && \
+ curl -O -L http://ftpmirror.gnu.org/autoconf/autoconf-2.69.tar.gz && \
+ tar -xzf autoconf-2.69.tar.gz && cd /home/$DOCKER_USER/repos/autoconf-2.69 && \
+ ./configure && make && make install && cd /home/$DOCKER_USER/repos && \
+ git clone https://github.com/pachterlab/kallisto.git && \
+ mkdir kallisto/build && \
+ cd /home/$DOCKER_USER/repos/kallisto/build && \
+ cmake -DCMAKE_INSTALL_PREFIX=/home/$DOCKER_USER/ -DUSE_HDF5=ON .. && make && make install
# python
COPY python_installs.sh ./
RUN ./python_installs.sh && rm python_installs.sh
-# for virtualenv intro
-RUN pip install virtualenv
-ENV PATH="/home/$DOCKER_USER/.local/bin:${PATH}"
# jars
-RUN mkdir /home/$DOCKER_USER/sw
-WORKDIR /home/$DOCKER_USER/sw
-RUN wget http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/Trimmomatic-0.39.zip && \
- apt install unzip -y && \
- unzip Trimmomatic-0.39.zip && \
- rm Trimmomatic-0.39.zip
+RUN mkdir /home/$DOCKER_USER/sw && \
+ cd /home/$DOCKER_USER/sw && \
+ wget http://www.usadellab.org/cms/uploads/supplementary/Trimmomatic/Trimmomatic-0.39.zip && \
+ apt install unzip -y && \
+ unzip Trimmomatic-0.39.zip && \
+ rm Trimmomatic-0.39.zip
# cleanup
WORKDIR /home/$DOCKER_USER/
@@ -99,11 +97,11 @@ RUN rm *.bz2 && rm -r info
# shared folder
# rnaseq-workshop folder
RUN wget https://github.com/git-lfs/git-lfs/releases/download/v3.2.0/git-lfs-linux-amd64-v3.2.0.tar.gz && \
- mv git-lfs-linux-amd64-v3.2.0.tar.gz sw/
-WORKDIR /home/$DOCKER_USER/sw/
-RUN tar xvf git-lfs-linux-amd64-v3.2.0.tar.gz
-WORKDIR /home/$DOCKER_USER/sw/git-lfs-3.2.0/
-RUN ./install.sh && \
+ mv git-lfs-linux-amd64-v3.2.0.tar.gz sw/ && \
+ cd /home/$DOCKER_USER/sw/ && \
+ tar xvf git-lfs-linux-amd64-v3.2.0.tar.gz && \
+ cd /home/$DOCKER_USER/sw/git-lfs-3.2.0/ && \
+ ./install.sh && \
rm ../git-lfs-linux-amd64-v3.2.0.tar.gz
WORKDIR /home/$DOCKER_USER/
@@ -118,6 +116,8 @@ EXPOSE 8889
COPY ./first.sh /home/$DOCKER_USER/
RUN chown $DOCKER_USER:$DOCKER_USER /home/$DOCKER_USER/first.sh
+
+ENV PATH="/home/$DOCKER_USER/bin:${PATH}"
USER $DOCKER_USER
RUN git lfs install
--
GitLab