plachta11b/emd repository overview

FROM plachta11b/emd:0.1-build AS builder

FROM plachta11b/bioprospector:0.1 AS bioprospector
FROM plachta11b/motifsampler:0.1 AS motifsampler

# perl 5.30-slim 125MB
FROM perl:5.30-slim

# File::Copy module | libfile-copy-recursive-perl
# --no-install-recommends saves 2MB
ENV DEBIAN_FRONTEND "noninteractive"
RUN dpkg --add-architecture i386 \
	&& apt-get update && apt-get install -y --no-install-recommends \
	libc6:i386 \
	libfile-copy-recursive-perl \
	&& rm -rf /var/lib/apt/lists/*

COPY --from=builder /source/EMD/ /packages/EMD
COPY --from=builder /lib/i386-linux-gnu/libstdc++.so.5 /lib/i386-linux-gnu/libstdc++.so.5
COPY --from=builder /lib/i386-linux-gnu/libm.so.6 /lib/i386-linux-gnu/libm.so.6
COPY --from=builder /lib/i386-linux-gnu/libgcc_s.so.1 /lib/i386-linux-gnu/libgcc_s.so.1

# mock qsub with bash script
ADD ./qsub /packages/EMD/qsub
RUN ls /packages/EMD/
RUN chmod +x /packages/EMD/qsub

RUN sed -i 's/.*echo Working directory is \/bio$PBS_O_WORKDIR.*//' /packages/EMD/runmotif.sh \
	&& sed -i 's/.*cd $PBS_O_WORKDIR.*//' /packages/EMD/runmotif.sh

WORKDIR /packages/EMD
ENV PATH $PATH:/packages/EMD
ENV PERL5LIB $PERL5LIB:/packages/EMD

# emdrunPX.pl runs all the component algorithms on the input data sets(./step5regulon). The number of component algorithms, the number of runs of each algorithm, and their command line options are all specified in a configuration file, e.g., emd.cfg
# emdMotif.pl combines the results from multiple component algorithms and output the consensus result.

# In the EMD directory:
# 1) $mkdir test
# 2) $cd test
# 3) $mkdir step5regulon
# 4) create input files in step5regulon/, ( e.g. cp ../input/Ada.txt step5regulon/)
# 5) $cp ../runmotif.sh . #template PBS job file
# 6) $cp ../emd.cfg . #configuration file of EMD algorithm
# 6) $cp ../bg_seq/*.bg . #background files of component algorithms
# 7) $emdrunPX.pl -f emd.cfg -w 15 -n 5
# 8) $emdMotif.pl -f step5regulon/Ada.txt -c emd.cfg -n 5

RUN chmod 774 /packages/EMD/emdrunP.pl
RUN chmod 774 /packages/EMD/emdrunPX.pl
RUN chmod 774 /packages/EMD/emdMotif.pl
RUN chmod 774 /packages/EMD/runmotif.sh

RUN sed -i 's#emdrunP.pl -r $i -a#perl /packages/EMD/emdrunP.pl -r $i -a#' /packages/EMD/emdrunPX.pl

RUN mkdir test \
	&& cd test \
	&& mkdir step5regulon \
	&& cp ../input/Ada.txt step5regulon/ \
	&& cp ../runmotif.sh . \
	&& cp ../emd.cfg . \
	&& cp ../bg_seq/*.bg . \
	&& emdrunPX.pl -f emd.cfg -w 15 -n 5 \
	&& emdMotif.pl -f step5regulon/Ada.txt -c emd.cfg -n 5 \
	rm -r .

COPY --from=bioprospector /usr/local/bin/genomebg /packages/EMD/
COPY --from=motifsampler /packages/CreateBackgroundModel /packages/EMD/

CMD [ "echo", "run: AlignACE, MEME, BioProspector, MDScan, MotifSampler" ]

FROM ubuntu:20.04

ENV DEBIAN_FRONTEND "noninteractive"
RUN dpkg --add-architecture i386 \
	&& apt-get update && apt-get install -y \
	libc6:i386 libncurses5:i386 libstdc++6:i386 \
	libstdc++5 libstdc++5:i386 \
	g++ \
	&& rm -rf /var/lib/apt/lists/*

# wget http://dragon.bio.purdue.edu/EMD/EMD.tar.gz
ADD ./EMD.tar.gz /source

WORKDIR /source/EMD

RUN ldd AlignACE MEME BioProspector MDScan MotifSampler

RUN find / -name libstdc++.so.5

FROM plachta11b/emd:0.1-build as builder

# i386/busybox 1.31.1-glibc 4.8MB
FROM i386/busybox:1.31.1-glibc as emd_noperl

COPY --from=builder /source/EMD/ /packages/EMD
COPY --from=builder /lib/i386-linux-gnu/libstdc++.so.5 /lib/i386-linux-gnu/libstdc++.so.5
COPY --from=builder /lib/i386-linux-gnu/libm.so.6 /lib/i386-linux-gnu/libm.so.6
COPY --from=builder /lib/i386-linux-gnu/libgcc_s.so.1 /lib/i386-linux-gnu/libgcc_s.so.1

WORKDIR /packages/EMD
ENV PATH $PATH:/packages/EMD
CMD [ "echo", "run: AlignACE, MEME, BioProspector, MDScan, MotifSampler" ]