Commit 5aef8353 authored by Sascha Steinbiss's avatar Sascha Steinbiss
Browse files

New upstream version 2.14.3+ds

parent d8ad6129

CHANGELOG.md

+8 −0
Original line number Diff line number Diff line 
# Change Log



[v2.14.3](https://github.com/sanger-pathogens/ariba/tree/v2.14.3) (2019-08-23)

[Full Changelog](https://github.com/sanger-pathogens/ariba/compare/v2.14.2...v2.14.3)



**Fixed bugs:**



- Version 3.0.3 of CARD breaks prepareref [\#278](https://github.com/sanger-pathogens/ariba/issues/278)

- RT 667288: Change docker file Ariba git clone to a copy



[v2.14.2](https://github.com/sanger-pathogens/ariba/tree/v2.14.2) (2019-06-18)

[Full Changelog](https://github.com/sanger-pathogens/ariba/compare/v2.14.1...v2.14.2)

Dockerfile

+20 −7
Original line number Diff line number Diff line
@@ -7,7 +7,10 @@ MAINTAINER ariba-help@sanger.ac.uk 
# Software version numbers

ARG BOWTIE2_VERSION=2.2.9

ARG SPADES_VERSION=3.13.1

ARG ARIBA_VERSION=2.14.2

ARG ARIBA_TAG=master

ARG ARIBA_BUILD_DIR=/ariba



ARG LOCALE_COUNTRY=en_GB



RUN apt-get -qq update && \

    apt-get install --no-install-recommends -y \
@@ -27,10 +30,18 @@ RUN apt-get -qq update && \ 
  wget \

  zlib1g-dev



# Install locales

RUN apt-get update && apt-get install -y locales-all && rm -rf /var/lib/apt/lists/* 

# Set a default locale.

ENV LANG=${LOCALE_COUNTRY}.UTF-8 \

    LANGUAGE=${LOCALE_COUNTRY}:en 



# Install bowtie

RUN wget -q http://downloads.sourceforge.net/project/bowtie-bio/bowtie2/${BOWTIE2_VERSION}/bowtie2-${BOWTIE2_VERSION}-linux-x86_64.zip \

  && unzip bowtie2-${BOWTIE2_VERSION}-linux-x86_64.zip \

  && rm -f bowtie2-${BOWTIE2_VERSION}-linux-x86_64.zip



# Install SPAdes

RUN wget -q https://github.com/ablab/spades/releases/download/v${SPADES_VERSION}/SPAdes-${SPADES_VERSION}-Linux.tar.gz \

  && tar -zxf SPAdes-${SPADES_VERSION}-Linux.tar.gz \

  && rm -f SPAdes-${SPADES_VERSION}-Linux.tar.gz
@@ -40,13 +51,15 @@ RUN wget -q https://github.com/ablab/spades/releases/download/v${SPADES_VERSION} 
ENV ARIBA_BOWTIE2=$PWD/bowtie2-${BOWTIE2_VERSION}/bowtie2 ARIBA_CDHIT=cdhit-est MPLBACKEND="agg"

ENV PATH=$PATH:$PWD/SPAdes-${SPADES_VERSION}-Linux/bin



RUN cd /usr/local/bin && ln -s /usr/bin/python3 python && cd

RUN ln -s -f /usr/bin/python3 /usr/local/bin/python



RUN git clone https://github.com/sanger-pathogens/ariba.git \

  && cd ariba \

  && git checkout v${ARIBA_VERSION} \

  && rm -rf .git \

# Install Ariba

RUN mkdir -p $ARIBA_BUILD_DIR

COPY . $ARIBA_BUILD_DIR

RUN cd $ARIBA_BUILD_DIR \

  && python3 setup.py clean --all \

  && python3 setup.py test \

  && python3 setup.py install

  && python3 setup.py install \

  && rm -rf $ARIBA_BUILD_DIR



CMD ariba

ariba/ref_preparer.py

+8 −1
Original line number Diff line number Diff line
@@ -16,6 +16,8 @@ class RefPreparer: 
        version_report_lines=None,

        min_gene_length=6,

        max_gene_length=10000,

        min_noncoding_length=6,

        max_noncoding_length=20000,

        genetic_code=11,

        cdhit_min_id=0.9,

        cdhit_min_length=0.0,
@@ -38,6 +40,8 @@ class RefPreparer: 
        self.all_coding = all_coding

        self.min_gene_length = min_gene_length

        self.max_gene_length = max_gene_length

        self.min_noncoding_length = min_noncoding_length

        self.max_noncoding_length = max_noncoding_length

        self.genetic_code = genetic_code

        self.cdhit_min_id = cdhit_min_id

        self.cdhit_min_length = cdhit_min_length
@@ -177,6 +181,8 @@ class RefPreparer: 
            self.metadata_tsv_files,

            min_gene_length=self.min_gene_length,

            max_gene_length=self.max_gene_length,

            min_noncoding_length = self.min_noncoding_length,

            max_noncoding_length = self.max_noncoding_length,

            genetic_code=self.genetic_code,

        )
@@ -213,8 +219,9 @@ class RefPreparer: 
            pickle.dump(clusters, f)



        if number_of_removed_seqs > 0:

            print('WARNING.', number_of_removed_seqs, 'sequence(s) excluded. Please see the log file 01.filter.check_genes.log for details. This will show them:', file=sys.stderr)

            print('WARNING.', number_of_removed_seqs, 'sequence(s) excluded. Please see the 01.filter.check_genes.log and 01.filter.check_noncoding.log for details. This will show them:', file=sys.stderr)

            print('    grep REMOVE', os.path.join(outdir, '01.filter.check_genes.log'), file=sys.stderr)

            print('    cat', os.path.join(outdir, '01.filter.check_noncoding.log'), file=sys.stderr)



        if number_of_bad_variants_logged > 0:

            print('WARNING. Problem with at least one variant. Problem variants are removed. Please see the file', os.path.join(outdir, '01.filter.check_metadata.log'), 'for details.', file=sys.stderr)

ariba/reference_data.py

+53 −4
Original line number Diff line number Diff line
@@ -19,6 +19,8 @@ class ReferenceData: 
        rename_file=None,

        min_gene_length=6,

        max_gene_length=10000,

        min_noncoding_length=6,

        max_noncoding_length=20000,

        genetic_code=11,

        parameters_file=None,

    ):
@@ -26,6 +28,8 @@ class ReferenceData: 
        self.seq_dicts = {}

        self.min_gene_length = min_gene_length

        self.max_gene_length = max_gene_length

        self.min_noncoding_length = min_noncoding_length

        self.max_noncoding_length = max_noncoding_length



        self.sequences, self.metadata = ReferenceData._load_input_files_and_check_seq_names(fasta_files, metadata_tsv_files)

        if len(self.sequences) == 0:
@@ -208,7 +212,7 @@ class ReferenceData: 


        for sequence_name, metadata_dict in sorted(all_metadata.items()):

            if sequence_name in removed_sequences:

                print(sequence_name, 'was removed because does not look like a gene, so removing its metadata', file=log_fh)

                print(sequence_name, 'was removed because it failed filtering checks, so removing its metadata', file=log_fh)

                log_lines += 1

                del all_metadata[sequence_name]

                continue
@@ -278,6 +282,16 @@ class ReferenceData: 
                return got[0], 'KEEP\tMade into gene. strand=' + got[1] + ', frame=' + str(got[2])





    @classmethod

    def _check_noncoding_seq(cls, seq, min_length, max_length):

        if len(seq) < min_length:

            return False, 'REMOVE\tToo short. Length: ' + str(len(seq))

        elif len(seq) > max_length:

            return False, 'REMOVE\tToo long. Length: ' + str(len(seq))

        else:

            return True, None





    @classmethod

    def _remove_bad_genes(cls, sequences, metadata, log_file, min_gene_length, max_gene_length):

        to_remove = set()
@@ -308,11 +322,46 @@ class ReferenceData: 
        return to_remove





    @classmethod

    def _remove_bad_noncoding_seqs(cls, sequences, metadata, log_file, min_noncoding_length, max_noncoding_length):

        to_remove = set()



        if len(sequences) == 0:

            return to_remove



        log_fh = pyfastaq.utils.open_file_write(log_file)



        for name in sorted(sequences):

            if metadata[name]['seq_type'] != 'n':

                continue



            valid, message = ReferenceData._check_noncoding_seq(sequences[name], min_noncoding_length, max_noncoding_length)

            if not valid:

                to_remove.add(name)



            if message is not None:

                print(name, message, sep='\t', file=log_fh)



        pyfastaq.utils.close(log_fh)



        for name in to_remove:

            sequences.pop(name)



        return to_remove



    def sanity_check(self, outprefix):

        removed_seqs = self._remove_bad_genes(self.sequences, self.metadata, outprefix + '.check_genes.log', self.min_gene_length, self.max_gene_length)

        log_lines = ReferenceData._filter_bad_variant_data(self.sequences, self.metadata, outprefix, removed_seqs)

        return len(removed_seqs), log_lines



        removed_gene_seqs = self._remove_bad_genes(self.sequences,

                                              self.metadata, outprefix + '.check_genes.log',

                                              self.min_gene_length, self.max_gene_length)



        removed_noncoding_seqs = self._remove_bad_noncoding_seqs(self.sequences, self.metadata,

                                                       outprefix + '.check_noncoding.log', self.min_noncoding_length,

                                                       self.max_noncoding_length)



        all_removed_seqs = removed_gene_seqs.union(removed_noncoding_seqs)

        log_lines = ReferenceData._filter_bad_variant_data(self.sequences, self.metadata, outprefix, all_removed_seqs)

        return len(all_removed_seqs), log_lines



    @classmethod

    def _new_seq_name(cls, name):

ariba/tasks/prepareref.py

+2 −0
Original line number Diff line number Diff line
@@ -18,6 +18,8 @@ def run(options): 
        version_report_lines=version_report_lines,

        min_gene_length=options.min_gene_length,

        max_gene_length=options.max_gene_length,

        min_noncoding_length=options.min_noncoding_length,

        max_noncoding_length=options.max_noncoding_length,

        genetic_code=options.genetic_code,

        cdhit_min_id=options.cdhit_min_id,

        cdhit_min_length=options.cdhit_min_length,