Exemple #1
0
def launch(args):
    pangenome = Pangenome()
    filename = mkFilename(args.basename, args.output, args.force)
    if args.anno:  #if the annotations are provided, we read from it
        getSeq = True
        if args.clusters is not None:
            getSeq = False
        readAnnotations(pangenome, args.anno, getSeq)
        writePangenome(pangenome, filename, args.force)
        if args.clusters is None and pangenome.status[
                "geneSequences"] == "No" and args.fasta is None:
            raise Exception(
                "The gff/gbff provided did not have any sequence informations, you did not provide clusters and you did not provide fasta file. Thus, we do not have the information we need to continue the analysis."
            )

        elif args.clusters is None and pangenome.status[
                "geneSequences"] == "No" and args.fasta is not None:
            getGeneSequencesFromFastas(pangenome, args.fasta)

        if args.clusters is not None:
            readClustering(pangenome, args.clusters)

        elif args.clusters is None:  #we should have the sequences here.
            clustering(pangenome, args.tmpdir, args.cpu)
    elif args.fasta is not None:
        pangenome = Pangenome()
        annotatePangenome(pangenome, args.fasta, args.tmpdir, args.cpu)
        writePangenome(pangenome, filename, args.force)
        clustering(pangenome, args.tmpdir, args.cpu)

    computeNeighborsGraph(pangenome)

    partition(pangenome,
              tmpdir=args.tmpdir,
              cpu=args.cpu,
              K=args.nb_of_partitions)
    writePangenome(pangenome, filename, args.force)

    if args.rarefaction:
        makeRarefactionCurve(pangenome, args.output, args.tmpdir, cpu=args.cpu)
    if len(pangenome.organisms) < 5000:
        drawTilePlot(pangenome,
                     args.output,
                     nocloud=False if len(pangenome.organisms) < 500 else True)
    drawUCurve(pangenome, args.output)

    writeFlatFiles(pangenome,
                   args.output,
                   args.cpu,
                   csv=True,
                   genePA=True,
                   gexf=True,
                   light_gexf=True,
                   projection=True,
                   json=True,
                   stats=True,
                   partitions=True)

    printInfo(filename, content=True)
Exemple #2
0
def launch(args):
    check_option_workflow(args)
    pangenome = Pangenome()
    filename = mkFilename(args.basename, args.output, args.force)
    writing_time, anno_time, clust_time, mod_time, desc_time = (None, None,
                                                                None, None,
                                                                None)
    if args.anno:  # if the annotations are provided, we read from it
        start_anno = time.time()
        readAnnotations(pangenome,
                        args.anno,
                        cpu=args.cpu,
                        disable_bar=args.disable_prog_bar)
        anno_time = time.time() - start_anno
        start_writing = time.time()
        writePangenome(pangenome,
                       filename,
                       args.force,
                       disable_bar=args.disable_prog_bar)
        writing_time = time.time() - start_writing
        if args.clusters is None and pangenome.status[
                "geneSequences"] == "No" and args.fasta is None:
            raise Exception(
                "The gff/gbff provided did not have any sequence informations, "
                "you did not provide clusters and you did not provide fasta file. "
                "Thus, we do not have the information we need to continue the analysis."
            )

        elif args.clusters is None and pangenome.status[
                "geneSequences"] == "No" and args.fasta is not None:
            getGeneSequencesFromFastas(pangenome, args.fasta)
        start_clust = time.time()
        if args.clusters is not None:
            readClustering(pangenome,
                           args.clusters,
                           disable_bar=args.disable_prog_bar)

        elif args.clusters is None:  # we should have the sequences here.
            clustering(pangenome,
                       args.tmpdir,
                       args.cpu,
                       identity=args.identity,
                       coverage=args.coverage,
                       mode=args.mode,
                       defrag=not args.no_defrag,
                       disable_bar=args.disable_prog_bar)
        clust_time = time.time() - start_clust
    elif args.fasta is not None:
        start_anno = time.time()
        annotatePangenome(pangenome,
                          args.fasta,
                          args.tmpdir,
                          args.cpu,
                          contig_filter=args.contig_filter,
                          disable_bar=args.disable_prog_bar)
        anno_time = time.time() - start_anno
        start_writing = time.time()
        writePangenome(pangenome,
                       filename,
                       args.force,
                       disable_bar=args.disable_prog_bar)
        writing_time = time.time() - start_writing
        start_clust = time.time()
        clustering(pangenome,
                   args.tmpdir,
                   args.cpu,
                   identity=args.identity,
                   coverage=args.coverage,
                   mode=args.mode,
                   defrag=not args.no_defrag,
                   disable_bar=args.disable_prog_bar)
        clust_time = time.time() - start_clust

    writePangenome(pangenome,
                   filename,
                   args.force,
                   disable_bar=args.disable_prog_bar)
    start_graph = time.time()
    computeNeighborsGraph(pangenome, disable_bar=args.disable_prog_bar)
    graph_time = time.time() - start_graph

    start_part = time.time()
    partition(pangenome,
              tmpdir=args.tmpdir,
              cpu=args.cpu,
              K=args.nb_of_partitions,
              disable_bar=args.disable_prog_bar)
    part_time = time.time() - start_part

    start_writing = time.time()
    writePangenome(pangenome,
                   filename,
                   args.force,
                   disable_bar=args.disable_prog_bar)
    writing_time = writing_time + time.time() - start_writing

    start_regions = time.time()
    predictRGP(pangenome, disable_bar=args.disable_prog_bar)
    regions_time = time.time() - start_regions

    start_spots = time.time()
    predictHotspots(pangenome, args.output, disable_bar=args.disable_prog_bar)
    spot_time = time.time() - start_spots

    start_mods = time.time()
    predictModules(pangenome=pangenome,
                   cpu=args.cpu,
                   tmpdir=args.tmpdir,
                   disable_bar=args.disable_prog_bar)
    mod_time = time.time() - start_mods

    start_writing = time.time()
    writePangenome(pangenome,
                   filename,
                   args.force,
                   disable_bar=args.disable_prog_bar)
    writing_time = writing_time + time.time() - start_writing

    if not args.only_pangenome:
        start_spot_drawing = time.time()
        mkOutdir(args.output + '/spot_figures', force=True)
        drawSpots(pangenome=pangenome,
                  output=args.output + '/spot_figures',
                  spot_list='all',
                  disable_bar=args.disable_prog_bar)
        spot_time = spot_time + time.time() - start_spot_drawing

        if args.rarefaction:
            makeRarefactionCurve(pangenome,
                                 args.output,
                                 args.tmpdir,
                                 cpu=args.cpu,
                                 disable_bar=args.disable_prog_bar)
        if 1 < len(pangenome.organisms) < 5000:
            drawTilePlot(
                pangenome,
                args.output,
                nocloud=False if len(pangenome.organisms) < 500 else True)
        drawUCurve(pangenome, args.output)

        start_desc = time.time()
        writeFlatFiles(pangenome,
                       args.output,
                       args.cpu,
                       csv=True,
                       genePA=True,
                       gexf=True,
                       light_gexf=True,
                       projection=True,
                       json=True,
                       stats=True,
                       partitions=True,
                       regions=True,
                       spots=True,
                       borders=True,
                       spot_modules=True,
                       modules=True)
        desc_time = time.time() - start_desc

    logging.getLogger().info(
        f"Annotation took : {round(anno_time, 2)} seconds")
    logging.getLogger().info(
        f"Clustering took : {round(clust_time, 2)} seconds")
    logging.getLogger().info(
        f"Building the graph took : {round(graph_time, 2)} seconds")
    logging.getLogger().info(
        f"Partitioning the pangenome took : {round(part_time, 2)} seconds")
    logging.getLogger().info(
        f"Predicting RGP took : {round(regions_time, 2)} seconds")
    logging.getLogger().info(
        f"Gathering RGP into spots took : {round(spot_time, 2)} seconds")
    logging.getLogger().info(
        f"Predicting modules took : {round(mod_time, 2)} seconds")
    logging.getLogger().info(
        f"Writing the pangenome data in HDF5 took : {round(writing_time, 2)} seconds"
    )
    if not args.only_pangenome:
        logging.getLogger().info(
            f"Writing descriptive files for the pangenome took : {round(desc_time, 2)} seconds"
        )
    printInfo(filename, content=True)
Exemple #3
0
def launch(args):
    check_option_workflow(args)
    pangenome = Pangenome()
    filename = mkFilename(args.basename, args.output, args.force)
    if args.anno:  # if the annotations are provided, we read from it
        readAnnotations(pangenome,
                        args.anno,
                        cpu=args.cpu,
                        disable_bar=args.disable_prog_bar)
        writePangenome(pangenome,
                       filename,
                       args.force,
                       disable_bar=args.disable_prog_bar)
        if args.clusters is None and pangenome.status[
                "geneSequences"] == "No" and args.fasta is None:
            raise Exception(
                "The gff/gbff provided did not have any sequence informations, "
                "you did not provide clusters and you did not provide fasta file. "
                "Thus, we do not have the information we need to continue the analysis."
            )

        elif args.clusters is None and pangenome.status[
                "geneSequences"] == "No" and args.fasta is not None:
            getGeneSequencesFromFastas(pangenome, args.fasta)

        if args.clusters is not None:
            readClustering(pangenome,
                           args.clusters,
                           disable_bar=args.disable_prog_bar)

        elif args.clusters is None:  # we should have the sequences here.
            clustering(pangenome,
                       tmpdir=args.tmpdir,
                       cpu=args.cpu,
                       identity=args.identity,
                       coverage=args.coverage,
                       mode=args.mode,
                       defrag=not args.no_defrag,
                       disable_bar=args.disable_prog_bar)
    elif args.fasta is not None:
        pangenome = Pangenome()
        annotatePangenome(pangenome,
                          args.fasta,
                          args.tmpdir,
                          args.cpu,
                          contig_filter=args.contig_filter,
                          disable_bar=args.disable_prog_bar)
        writePangenome(pangenome,
                       filename,
                       args.force,
                       disable_bar=args.disable_prog_bar)
        clustering(pangenome,
                   tmpdir=args.tmpdir,
                   cpu=args.cpu,
                   identity=args.identity,
                   coverage=args.coverage,
                   mode=args.mode,
                   defrag=not args.no_defrag,
                   disable_bar=args.disable_prog_bar)

    computeNeighborsGraph(pangenome, disable_bar=args.disable_prog_bar)

    partition(pangenome,
              tmpdir=args.tmpdir,
              cpu=args.cpu,
              K=args.nb_of_partitions,
              disable_bar=args.disable_prog_bar)
    writePangenome(pangenome,
                   filename,
                   args.force,
                   disable_bar=args.disable_prog_bar)

    if args.rarefaction:
        makeRarefactionCurve(pangenome,
                             args.output,
                             args.tmpdir,
                             cpu=args.cpu,
                             disable_bar=args.disable_prog_bar)
    if 1 < len(pangenome.organisms) < 5000:
        drawTilePlot(pangenome,
                     args.output,
                     nocloud=False if len(pangenome.organisms) < 500 else True)
    drawUCurve(pangenome, args.output)

    writeFlatFiles(pangenome,
                   args.output,
                   args.cpu,
                   csv=True,
                   genePA=True,
                   gexf=True,
                   light_gexf=True,
                   projection=True,
                   json=True,
                   stats=True,
                   partitions=True)

    printInfo(filename, content=True)
Exemple #4
0
def launch(args):
    pangenome = Pangenome()
    filename = mkFilename(args.basename, args.output, args.force)
    if args.anno:#if the annotations are provided, we read from it
        getSeq = True
        if args.clusters is not None:
            getSeq = False
        start_anno = time.time()
        readAnnotations(pangenome, args.anno, cpu = args.cpu, getSeq = getSeq, show_bar=args.show_prog_bars)
        annotime = time.time() - start_anno
        start_writing = time.time()
        writePangenome(pangenome, filename, args.force, show_bar=args.show_prog_bars)
        writing_time = time.time() - start_writing
        if args.clusters is None and pangenome.status["geneSequences"] == "No" and args.fasta is None:
            raise Exception("The gff/gbff provided did not have any sequence informations, you did not provide clusters and you did not provide fasta file. Thus, we do not have the information we need to continue the analysis.")

        elif args.clusters is None and pangenome.status["geneSequences"] == "No" and args.fasta is not None:
            getGeneSequencesFromFastas(pangenome, args.fasta)
        start_clust = time.time()
        if args.clusters is not None:
            readClustering(pangenome, args.clusters, show_bar=args.show_prog_bars)

        elif args.clusters is None:#we should have the sequences here.
            clustering(pangenome, args.tmpdir, args.cpu, defrag=not args.no_defrag, show_bar=args.show_prog_bars)
        clust_time = time.time() - start_clust
    elif args.fasta is not None:
        start_anno = time.time()
        annotatePangenome(pangenome, args.fasta, args.tmpdir, args.cpu, show_bar=args.show_prog_bars)
        annotime = time.time() - start_anno
        start_writing = time.time()
        writePangenome(pangenome, filename, args.force, show_bar=args.show_prog_bars)
        writing_time = time.time() - start_writing
        start_clust = time.time()
        clustering(pangenome, args.tmpdir, args.cpu, defrag=not args.no_defrag, show_bar=args.show_prog_bars)
        clust_time = time.time() - start_clust

    writePangenome(pangenome, filename, args.force, show_bar=args.show_prog_bars)
    start_graph = time.time()
    computeNeighborsGraph(pangenome, show_bar=args.show_prog_bars)
    graph_time = time.time() - start_graph

    start_part = time.time()
    partition(pangenome, tmpdir = args.tmpdir, cpu = args.cpu, K=args.nb_of_partitions, show_bar=args.show_prog_bars)
    part_time = time.time() - start_part

    start_writing = time.time()
    writePangenome(pangenome, filename, args.force, show_bar=args.show_prog_bars)
    writing_time = writing_time + time.time() - start_writing

    start_regions = time.time()
    predictRGP(pangenome, show_bar=args.show_prog_bars)
    regions_time = time.time() - start_regions

    start_spots = time.time()
    predictHotspots(pangenome, args.output, interest=args.interest, show_bar=args.show_prog_bars)
    spot_time = time.time() - start_spots

    start_writing = time.time()
    writePangenome(pangenome, filename, args.force, show_bar=args.show_prog_bars)
    writing_time = writing_time + time.time() - start_writing

    if args.rarefaction:
        makeRarefactionCurve(pangenome,args.output, args.tmpdir, cpu=args.cpu, show_bar=args.show_prog_bars)
    if len(pangenome.organisms) > 1 and len(pangenome.organisms) < 5000:
        drawTilePlot(pangenome, args.output, nocloud = False if len(pangenome.organisms) < 500 else True)
    drawUCurve(pangenome, args.output)

    start_desc = time.time()
    writeFlatFiles(pangenome, args.output, args.cpu, csv = True, genePA=True, gexf=True, light_gexf = True, projection=True, json = True, stats = True, partitions = True, regions = True, spots=True)
    desc_time = time.time() - start_desc

    logging.getLogger().info(f"Annotation took : {round(annotime,2)} seconds")
    logging.getLogger().info(f"Clustering took : {round(clust_time,2)} seconds")
    logging.getLogger().info(f"Building the graph took : {round(graph_time,2)} seconds")
    logging.getLogger().info(f"Partitionning the pangenome took : {round(part_time,2)} seconds")
    logging.getLogger().info(f"Predicting RGP took : {round(regions_time,2)} seconds")
    logging.getLogger().info(f"Gathering RGP into spots took : {round(spot_time,2)} seconds")
    logging.getLogger().info(f"Writing the pangenome data in HDF5 took : {round(writing_time,2)} seconds")
    logging.getLogger().info(f"Writing descriptive files for the pangenome took : {round(desc_time,2)} seconds")
    printInfo(filename, content = True)