def launch(args):
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
if args.proteins is not None:
align(pangenome=pangenome,
proteinFile=args.proteins,
output=args.output,
tmpdir=args.tmpdir,
identity=args.identity,
coverage=args.coverage,
defrag=args.defrag,
cpu=args.cpu,
getinfo=args.getinfo,
draw_related=args.draw_related)
if args.annotation is not None:
projectRGP(pangenome,
args.annotation,
args.output,
args.tmpdir,
args.identity,
args.coverage,
args.defrag,
args.cpu,
args.translation_table,
pseudo=args.use_pseudo)
def launch(args):
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
writeFlatFiles(pangenome,
args.output,
cpu=args.cpu,
soft_core=args.soft_core,
dup_margin=args.dup_margin,
csv=args.csv,
genePA=args.Rtab,
gexf=args.gexf,
light_gexf=args.light_gexf,
projection=args.projection,
stats=args.stats,
json=args.json,
partitions=args.partitions,
regions=args.regions,
families_tsv=args.families_tsv,
all_genes=args.all_genes,
all_prot_families=args.all_prot_families,
all_gene_families=args.all_gene_families,
spots=args.spots,
borders=args.borders,
compress=args.compress)
def launch(args):
"""
main code when launch partition from the command line.
"""
if args.draw_ICL or args.keep_tmp_files:
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
partition(pangenome,
args.tmpdir,
args.output,
args.force,
args.beta,
args.max_degree_smoothing,
args.free_dispersion,
args.chunk_size,
args.nb_of_partitions,
args.krange,
args.ICL_margin,
args.draw_ICL,
args.cpu,
args.seed,
args.keep_tmp_files,
show_bar=args.show_prog_bars)
writePangenome(pangenome,
pangenome.file,
args.force,
show_bar=args.show_prog_bars)
def launch(args):
""" launch the clustering step"""
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
if args.clusters is None:
clustering(pangenome,
args.tmpdir,
args.cpu,
defrag=not args.no_defrag,
code=args.translation_table,
coverage=args.coverage,
identity=args.identity,
mode=args.mode,
force=args.force,
disable_bar=args.disable_prog_bar)
logging.getLogger().info("Done with the clustering")
else:
readClustering(pangenome,
args.clusters,
args.infer_singletons,
args.force,
disable_bar=args.disable_prog_bar)
logging.getLogger().info("Done reading the cluster file")
writePangenome(pangenome,
pangenome.file,
args.force,
disable_bar=args.disable_prog_bar)
def launch(args):
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
if args.spot_graph or args.draw_hotspots:
mkOutdir(args.output, args.force)
predictHotspots(pangenome, args.output, force=args.force, cpu = args.cpu, spot_graph=args.spot_graph, overlapping_match=args.overlapping_match, set_size=args.set_size, exact_match=args.exact_match_size, draw_hotspot=args.draw_hotspots, interest=args.interest)
writePangenome(pangenome, pangenome.file, args.force)
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)
def launchSequences(args):
checkOptions(args)
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
writeSequenceFiles(pangenome, args.output, fasta=args.fasta, anno=args.anno, soft_core=args.soft_core,
regions=args.regions, genes=args.genes, gene_families=args.gene_families,
prot_families=args.prot_families, compress=args.compress, disable_bar=args.disable_prog_bar)
def launch(args):
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
if args.tile_plot:
drawTilePlot(pangenome, args.output, args.nocloud)
if args.ucurve:
drawUCurve(pangenome, args.output, soft_core = args.soft_core)
def launch(args):
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
writeFlatFiles(pangenome, args.output, args.cpu, args.soft_core,
args.dup_margin, args.csv, args.Rtab, args.gexf,
args.light_gexf, args.projection, args.stats, args.json,
args.partitions, args.families_tsv, args.all_genes,
args.all_prot_families, args.all_gene_families,
args.compress)
def launch(args):
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
predictRGP(pangenome,
force=args.force,
persistent_penalty=args.persistent_penalty,
variable_gain=args.variable_gain,
min_length=args.min_length,
min_score=args.min_score,
dup_margin=args.dup_margin,
cpu=args.cpu)
writePangenome(pangenome, pangenome.file, args.force)
def launchMSA(args):
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
writeMSAFiles(pangenome,
args.output,
cpu=args.cpu,
partition=args.partition,
tmpdir=args.tmpdir,
source=args.source,
force=args.force,
show_bar=args.show_prog_bars)
def launch(args):
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
if args.spot_graph:
mkOutdir(args.output, args.force)
if args.draw_hotspots or args.interest or args.fig_margin or args.priority:
logging.getLogger().warning(
"Options to draw the spots with the 'ppanggolin spot' subcommand have been deprecated, "
"and are now dealt with in a dedicated subcommand 'ppanggolin drawspot'.")
predictHotspots(pangenome, args.output, force=args.force, cpu=args.cpu, spot_graph=args.spot_graph,
overlapping_match=args.overlapping_match, set_size=args.set_size, exact_match=args.exact_match_size,
disable_bar=args.disable_prog_bar)
writePangenome(pangenome, pangenome.file, args.force, disable_bar=args.disable_prog_bar)
def launch(args):
""" launch the clustering step"""
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
if args.clusters is None:
clustering(pangenome, args.tmpdir, args.cpu, args.defrag,
args.translation_table, args.coverage, args.identity,
args.force)
logging.getLogger().info("Done with the clustering")
else:
readClustering(pangenome, args.clusters, args.infer_singletons,
args.force)
logging.getLogger().info("Done reading the cluster file")
writePangenome(pangenome, pangenome.file, args.force)
def launchSequences(args):
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
checkOptions(args)
writeSequenceFiles(pangenome,
args.output,
fasta=args.fasta,
anno=args.anno,
cpu=args.cpu,
regions=args.regions,
genes=args.genes,
prot_families=args.prot_families,
gene_families=args.gene_families,
compress=args.compress,
show_bar=args.show_prog_bars)
def launch(args):
filename = mkFilename(args.basename, args.output, args.force)
pangenome = Pangenome()
if args.fasta is not None and args.anno is None:
annotatePangenome(pangenome,
args.fasta,
tmpdir=args.tmpdir,
cpu=args.cpu,
translation_table=args.translation_table,
kingdom=args.kingdom,
norna=args.norna,
overlap=args.overlap,
show_bar=args.show_prog_bars)
elif args.anno is not None:
readAnnotations(pangenome,
args.anno,
cpu=args.cpu,
pseudo=args.use_pseudo,
show_bar=args.show_prog_bars)
if pangenome.status["geneSequences"] == "No":
if args.fasta:
getGeneSequencesFromFastas(pangenome, args.fasta)
else:
logging.getLogger().warning(
"You provided gff files without sequences, and you did not provide fasta sequences. Thus it was not possible to get the gene sequences."
)
logging.getLogger().warning(
"You will be able to proceed with your analysis ONLY if you provide the clustering results in the next step."
)
writePangenome(pangenome,
filename,
args.force,
show_bar=args.show_prog_bars)
def launch(args):
if not any(x for x in [args.genome_fluidity, args.family_fluidity, args.info_modules, args.all]):
raise Exception("You did not indicate which metric you want to compute.")
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
logging.getLogger().debug("Check if one of the metrics was already compute")
check_metric(pangenome, all=args.all, genome_fluidity=args.genome_fluidity, family_fluidity=args.family_fluidity,
info_modules=args.info_modules, force=args.force)
logging.getLogger().info("Metrics computation begin")
metrics_dictionary = compute_metrics(pangenome, all=args.all, genome_fluidity=args.genome_fluidity,
family_fluidity=args.family_fluidity, info_modules=args.info_modules,
disable_bar=args.disable_prog_bar)
logging.getLogger().info("Metrics computation done")
write_metrics(pangenome, metrics_dictionary, no_print_info=args.no_print_info)
def launch(args):
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
if args.tile_plot:
drawTilePlot(pangenome,
args.output,
args.nocloud,
disable_bar=args.disable_prog_bar)
if args.ucurve:
drawUCurve(pangenome,
args.output,
soft_core=args.soft_core,
disable_bar=args.disable_prog_bar)
if args.spots != '':
drawSpots(pangenome=pangenome,
output=args.output,
spot_list=args.spots,
disable_bar=args.disable_prog_bar)
def launch(args):
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
if args.interest or args.fig_margin or args.label_priority:
logging.getLogger().warning(
"Options --interest, --fig_margin and --label_priority are deprecated, "
"and the actions they defined are now doable directly in the interactive figures "
"that are drawn")
align(pangenome=pangenome,
sequenceFile=args.sequences,
output=args.output,
tmpdir=args.tmpdir,
cpu=args.cpu,
identity=args.identity,
coverage=args.coverage,
no_defrag=args.no_defrag,
getinfo=args.getinfo,
draw_related=args.draw_related,
disable_bar=args.disable_prog_bar)
def launch(args):
"""
main code when launch partition from the command line.
"""
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
makeRarefactionCurve( pangenome = pangenome,
output = args.output,
tmpdir = args.tmpdir,
beta =args.beta,
depth = args.depth,
minSampling=args.min,
maxSampling=args.max,
sm_degree=args.max_degree_smoothing,
free_dispersion=args.free_dispersion,
chunk_size=args.chunk_size,
K=args.nb_of_partitions,
cpu = args.cpu,
seed = args.seed,
kestimate=args.reestimate_K,
krange = args.krange,
soft_core = args.soft_core)
def test_cstr():
o_pang = Pangenome()
assert isinstance(o_pang, Pangenome)
for attr in "max_fam_id", "parameters", "status":
assert hasattr(o_pang, attr)
assert o_pang.max_fam_id == 0
assert o_pang.parameters == {}
assert o_pang.status == {
'genomesAnnotated': "No",
'geneSequences': "No",
'genesClustered': "No",
'defragmented': "No",
'geneFamilySequences': "No",
'neighborsGraph': "No",
'partitionned': "No"
}
def launch(args):
if not any([args.fasta, args.anno]):
raise Exception("At least one of --fasta or --anno must be given")
filename = mkFilename(args.basename, args.output, args.force)
pangenome = Pangenome()
if args.fasta is not None and args.anno is None:
annotatePangenome(pangenome, args.fasta, tmpdir=args.tmpdir, cpu=args.cpu,
translation_table=args.translation_table, kingdom=args.kingdom, norna=args.norna,
overlap=args.overlap, contig_filter=args.contig_filter, disable_bar=args.disable_prog_bar)
elif args.anno is not None:
readAnnotations(pangenome, args.anno, cpu=args.cpu, pseudo=args.use_pseudo, disable_bar=args.disable_prog_bar)
if pangenome.status["geneSequences"] == "No":
if args.fasta:
getGeneSequencesFromFastas(pangenome, args.fasta)
else:
logging.getLogger().warning("You provided gff files without sequences, and you did not provide "
"fasta sequences. Thus it was not possible to get the gene sequences.")
logging.getLogger().warning("You will be able to proceed with your analysis ONLY if you provide "
"the clustering results in the next step.")
writePangenome(pangenome, filename, args.force, disable_bar=args.disable_prog_bar)
def projectRGP(pangenome,
annotation,
output,
tmpdir,
identity=0.8,
coverage=0.8,
defrag=False,
cpu=1,
translation_table=11):
if pangenome.status["geneFamilySequences"] not in [
"inFile", "Loaded", "Computed"
]:
raise Exception(
"Cannot use this function as your pangenome does not have gene families representatives associated to it. For now this works only if the clustering is realised by PPanGGOLiN."
)
#read given file
logging.getLogger().info("Retrieving the annotations from the given file")
singleOrgPang = Pangenome(
) #need to create a new 'pangenome' as the annotation reading functions take a pangenome as input.
filetype = detect_filetype(annotation)
if filetype == "gff":
singleOrgPang.status[
"geneSequences"] = "Computed" #if there are no sequences in the gff, this value will change to 'No'
read_org_gff(singleOrgPang, 'myGenome', annotation, [], True)
if singleOrgPang.status["geneSequences"] == "No":
raise Exception(
f"The given annotation file did not have a FASTA sequence included (expected '##FASTA' pragma followed by a fasta-like file format). This is required for computing the Regions of Genomic Plasticity of your organism"
)
elif filetype == "gbff":
read_org_gbff(singleOrgPang, 'myGenome', annotation, [], True)
#check and read given pangenome
checkPangenomeInfo(pangenome,
needFamilies=True,
needPartitions=True,
needAnnotations=True)
newtmpdir = tempfile.TemporaryDirectory(dir=tmpdir)
tmpPangFile = tempfile.NamedTemporaryFile(mode="w", dir=newtmpdir.name)
tmpGeneFile = tempfile.NamedTemporaryFile(mode="w", dir=newtmpdir.name)
writeGeneSequencesFromAnnotations(singleOrgPang, tmpGeneFile)
writeGeneFamSequences(pangenome, tmpPangFile)
blastout = alignSeqToPang(tmpPangFile, tmpGeneFile, output, newtmpdir, cpu,
defrag, identity, coverage, True,
translation_table)
tmpPangFile.close()
tmpGeneFile.close()
newtmpdir.cleanup()
#artificially reconstruct the gene families and their partitions
linkNewGenomeFamilies(singleOrgPang, pangenome, blastout)
multigenics = pangenome.get_multigenics(
pangenome.parameters["RGP"]["dup_margin"])
genomeMultigenics = linkMultigenicFamilies(singleOrgPang, multigenics)
logging.getLogger().info("Predicting RGP in your genome")
for org in singleOrgPang.organisms:
genomeRGP = compute_org_rgp(
org, pangenome.parameters["RGP"]["persistent_penalty"],
pangenome.parameters["RGP"]["variable_gain"],
pangenome.parameters["RGP"]["min_length"],
pangenome.parameters["RGP"]["min_score"], genomeMultigenics)
if filetype == "gff":
#reread the file and insert sequence_feature objects corresponding to the predicted regions
logging.getLogger().info("Writing the RGP in a gff file...")
writeGffRegions(annotation, genomeRGP, output)
elif filetype == "gbff":
logging.getLogger().info("Writing the RGP in a gbff file...")
writeGbffRegions(annotation, genomeRGP, output)
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)
def launch(args):
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
computeNeighborsGraph(pangenome, args.remove_high_copy_number, args.force, show_bar=args.show_prog_bars)
writePangenome(pangenome, pangenome.file, args.force, show_bar=args.show_prog_bars)
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)
def o_pang():
return Pangenome()
def launch(args):
logging.getLogger().debug(f"Ram used at the start : {getCurrentRAM()}")
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
computeNeighborsGraph(pangenome, args.remove_high_copy_number, args.force)
writePangenome(pangenome, pangenome.file, args.force)
def launch(args):
mkOutdir(args.output, args.force)
pangenome = Pangenome()
pangenome.addFile(args.pangenome)
align(pangenome, args.proteins, args.output, args.tmpdir, args.identity,
args.coverage, args.defrag, args.cpu)
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)
