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):
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):
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 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)
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 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 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):
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 writeMSAFiles(pangenome,
output,
cpu=1,
partition="core",
tmpdir="/tmp",
source="protein",
force=False,
show_bar=True):
needPartitions = False
if partition in ["persistent", "shell", "cloud"]:
needPartitions = True
outname = output + f"/msa_{partition}_{source}/"
mkOutdir(outname, force=force)
checkPangenomeInfo(pangenome,
needAnnotations=True,
needFamilies=True,
needPartitions=needPartitions,
needGeneSequences=True,
show_bar=show_bar)
logging.getLogger().info(f"computing msa for {partition} families...")
families = getFamiliesToWrite(pangenome, partitionFilter=partition)
#this must exist since we loaded the pangenome and families are required
code = pangenome.parameters["cluster"]["translation_table"]
computeMSA(families,
outname,
cpu=cpu,
tmpdir=tmpdir,
source=source,
code=code,
show_bar=show_bar)
logging.getLogger().info(f"Done writing all {partition} MSA in: {outname}")
def write_nem_input_files(tmpdir, organisms, sm_degree):
mkOutdir(tmpdir, force=False)
total_edges_weight = 0
with open(tmpdir + "/column_org_file", "w") as org_file:
org_file.write(" ".join([f'"{org.name}"' for org in organisms]) + "\n")
logging.getLogger().debug(
"Writing nem_file.str nem_file.index nem_file.nei and nem_file.dat files"
)
with open(tmpdir+"/nem_file.str", "w") as str_file,\
open(tmpdir+"/nem_file.index", "w") as index_file,\
open(tmpdir+"/nem_file.nei", "w") as nei_file,\
open(tmpdir+"/nem_file.dat", "w") as dat_file:
nei_file.write("1\n")
index_fam = {}
index_org = {}
default_dat = []
for index, org in enumerate(organisms):
default_dat.append('0')
index_org[org] = index
for fam in pan.geneFamilies:
#could use bitarrays if this part is limiting?
if not organisms.isdisjoint(fam.organisms):
currDat = list(default_dat)
curr_orgs = fam.organisms & organisms
for org in curr_orgs:
currDat[index_org[org]] = "1"
dat_file.write("\t".join(currDat) + "\n")
index_fam[fam] = len(index_fam) + 1
index_file.write(f"{len(index_fam)}\t{fam.name}\n")
for fam in index_fam.keys():
row_fam = []
row_dist_score = []
neighbor_number = 0
sum_dist_score = 0
for edge in fam.edges: #iter on the family's edges.
coverage = sum([
len(gene_list)
for org, gene_list in edge.organisms.items()
if org in organisms
])
if coverage == 0:
continue #nothing interesting to write, this edge does not exist with this subset of organisms.
distance_score = coverage / len(organisms)
sum_dist_score += distance_score
row_fam.append(
str(index_fam[edge.target if fam ==
edge.source else edge.source]))
row_dist_score.append(str(round(distance_score, 4)))
neighbor_number += 1
if neighbor_number > 0 and float(neighbor_number) < sm_degree:
total_edges_weight += sum_dist_score
nei_file.write('\t'.join([
str(item)
for sublist in [[index_fam[fam]], [neighbor_number],
row_fam, row_dist_score]
for item in sublist
]) + "\n")
else:
nei_file.write(str(index_fam[fam]) + "\t0\n")
str_file.write("S\t" + str(len(index_fam)) + "\t" +
str(len(organisms)) + "\n")
return total_edges_weight / 2, len(index_fam)
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 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)
