Skip to content

updated to be compatible with qiime2 2019-0.1 #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 3, 2019
Merged

updated to be compatible with qiime2 2019-0.1 #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 33 additions & 25 deletions q2_picrust2/_custom_tree_pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,6 @@ def custom_tree_pipeline(table: biom.Table,
threads: int = 1,
hsp_method: str = "mp",
max_nsti: float = 2.0) -> (biom.Table,
biom.Table,
biom.Table,
biom.Table):

Expand All @@ -34,50 +33,59 @@ def custom_tree_pipeline(table: biom.Table,

# Run hidden-state prediction step (on 16S, EC, and KO tables
# separately.
hsp_out_16S = path.join(picrust2_out, "16S_predicted")
system_call_check("hsp.py -i 16S -t " + newick_infile + " -p 1 -n "
"-o " + hsp_out_16S + " -m " + hsp_method)

hsp_out_EC = path.join(picrust2_out, "EC_predicted")
system_call_check("hsp.py -i EC -t " + newick_infile + " -p " +
str(threads) + " -o " + hsp_out_EC + " -m " +
hsp_method)

hsp_out_KO = path.join(picrust2_out, "KO_predicted")
system_call_check("hsp.py -i KO -t " + newick_infile + " -p " +
str(threads) + " -o " + hsp_out_KO + " -m " +
hsp_method)
hsp_out_16S = path.join(picrust2_out, "16S_predicted.tsv")
system_call_check("hsp.py -i 16S " +
" -t " + newick_infile +
" -p 1 " +
" -n " +
"-o " + hsp_out_16S +
" -m " + hsp_method)

hsp_out_EC = path.join(picrust2_out, "EC_predicted.tsv")
system_call_check("hsp.py -i EC " +
" -t " + newick_infile +
" -p " + str(threads) +
" -o " + hsp_out_EC +
" -m " + hsp_method)

hsp_out_KO = path.join(picrust2_out, "KO_predicted.tsv")
system_call_check("hsp.py -i KO " +
" -t " + newick_infile +
" -p " + str(threads) +
" -o " + hsp_out_KO +
" -m " + hsp_method)

# Run metagenome pipeline step.
EC_metagenome_out = path.join(picrust2_out, "EC_metagenome_out")
system_call_check("metagenome_pipeline.py -i " + biom_infile + " -m " +
hsp_out_16S + ".tsv -f " + hsp_out_EC + ".tsv -p " +
str(threads) + " -o " + EC_metagenome_out +
system_call_check("metagenome_pipeline.py -i " + biom_infile +
" -m " + hsp_out_16S +
" -f " + hsp_out_EC +
" -o " + EC_metagenome_out +
" --max_nsti " + str(max_nsti))

KO_metagenome_out = path.join(picrust2_out, "KO_metagenome_out")
system_call_check("metagenome_pipeline.py -i " + biom_infile + " -m " +
hsp_out_16S + ".tsv -f " + hsp_out_KO + ".tsv -p " +
str(threads) + " -o " + KO_metagenome_out +
system_call_check("metagenome_pipeline.py -i " + biom_infile +
" -m " + hsp_out_16S +
" -f " + hsp_out_KO +
" -o " + KO_metagenome_out +
" --max_nsti " + str(max_nsti))

# Run pathway inference step.
pathways_out = path.join(picrust2_out, "pathways_out")

EC_out = path.join(EC_metagenome_out, "pred_metagenome_unstrat.tsv")

system_call_check("run_minpath.py -i " + EC_out + " -o " +
pathways_out + " -p " + str(threads))
system_call_check("pathway_pipeline.py -i " + EC_out +
" -o " + pathways_out +
" -p " + str(threads))

# Read in output unstratified metagenome tables and return as BIOM
# objects.
KO_out = path.join(KO_metagenome_out, "pred_metagenome_unstrat.tsv")
pathabun_out = path.join(pathways_out, "path_abun_unstrat.tsv")
pathcov_out = path.join(pathways_out, "path_cov_unstrat.tsv")

ko_biom = biom.load_table(KO_out)
ec_biom = biom.load_table(EC_out)
pathabun_biom = biom.load_table(pathabun_out)
pathcov_biom = biom.load_table(pathcov_out)

return ko_biom, ec_biom, pathabun_biom, pathcov_biom
return ko_biom, ec_biom, pathabun_biom
73 changes: 23 additions & 50 deletions q2_picrust2/_full_pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,51 +7,27 @@
import subprocess
import sys
import picrust2.pipeline
from picrust2.default import (default_fasta, default_tree, default_hmm,
default_tables, default_map, default_regroup_map,
default_pathway_map)
from picrust2.default import (default_ref_dir, default_tables, default_map,
default_regroup_map, default_pathway_map)

def full_pipeline(table: biom.Table,
seq : pd.Series,
seq: pd.Series,
threads: int = 1,
hsp_method: str = "mp",
max_nsti: float = 2.0) -> (biom.Table,
biom.Table,
biom.Table,
biom.Table):
max_nsti: float = 2.0) -> (biom.Table,
biom.Table,
biom.Table):

# Check whether EPA-NG and GAPPA are installed. Exit with explanation if
# not.
missing_prog = []
try:
subprocess.check_call(['epa-ng', '--help'])
except OSError:
missing_prog.append("epa-ng")

try:
subprocess.check_call(['gappa', '--help'])
except OSError:
missing_prog.append("gappa")

if len(missing_prog) > 0:
sys.exit("Missing the following tools from your $PATH variable: " +
" and ".join(missing_prog) + ". Note that this QIIME2 " +
"command is for running the default PICRUSt2 pipeline, " +
"which includes steps for running sequence placement with " +
"EPA-NG. If you do not want to install the missing programs " +
"you can run sequence placement with q2-fragment-insertion " +
"and input this tree to the \"qiime picrust2 " +
"custom_tree_pipeline\" command")

# Need to write out BIOM table and fasta to be used in pipeline.
# Write out BIOM table and FASTA to be used in pipeline.
with TemporaryDirectory() as temp_dir:
# Write out biom table:

# Write out BIOM table:
biom_infile = path.join(temp_dir, "intable.biom")
with biom.util.biom_open(biom_infile, 'w') as out_biom:
table.to_hdf5(h5grp=out_biom, generated_by="PICRUSt2 QIIME2 Plugin")
table.to_hdf5(h5grp=out_biom,
generated_by="PICRUSt2 QIIME2 Plugin")

# Write out Pandas series as fasta:
# Write out Pandas series as FASTA:
seq_outfile = path.join(temp_dir, "seqs.fna")

with open(seq_outfile, "w") as outfile_fh:
Expand All @@ -65,9 +41,7 @@ def full_pipeline(table: biom.Table,
input_table=biom_infile,
output_folder=picrust2_out,
threads=threads,
ref_msa=default_fasta,
tree=default_tree,
hmm=default_hmm,
ref_dir=default_ref_dir,
in_traits="EC,KO",
custom_trait_tables=None,
marker_gene_table=default_tables["16S"],
Expand All @@ -76,23 +50,22 @@ def full_pipeline(table: biom.Table,
regroup_map=default_regroup_map,
no_regroup=False,
stratified=False,
alignment_tool="hmmalign",
max_nsti=max_nsti,
min_reads=1,
min_samples=1,
hsp_method=hsp_method,
calculate_NSTI=True,
confidence=False,
seed=198,
skip_nsti=False,
no_gap_fill=False,
skip_minpath=False,
coverage=False,
per_sequence_contrib=False,
no_descrip=True,
verbose=False)
verbose=True)

# Convert the returned unstratified tables to biom tables.
ko_biom = biom.load_table(func_outputs["KO"])
ec_biom = biom.load_table(func_outputs["EC"])
# Convert the returned unstratified tables to BIOM tables.
# Note that the 0-index in the func table returned objects corresponds
# to the path to the unstratified table.
ko_biom = biom.load_table(func_outputs["KO"][0])
ec_biom = biom.load_table(func_outputs["EC"][0])
pathabun_biom = biom.load_table(pathway_outputs["unstrat_abun"])
pathcov_biom = biom.load_table(pathway_outputs["unstrat_cov"])

return ko_biom, ec_biom, pathabun_biom, pathcov_biom
return ko_biom, ec_biom, pathabun_biom
20 changes: 7 additions & 13 deletions q2_picrust2/plugin_setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@

plugin = Plugin(
name='picrust2',
version="0.0.0",
version="0.0.3",
website='https://github.com/gavinmdouglas/q2-picrust2',
package='q2_picrust2',
description=('This QIIME 2 plugin wraps the default 16S PICRUSt2 pipeline to run '
Expand All @@ -32,12 +32,9 @@
'hsp_method': Str % Choices(HSP_METHODS),
'max_nsti': Float % Range(0.0, None)},

outputs=[
('ko_metagenome', FeatureTable[Frequency]),
('ec_metagenome', FeatureTable[Frequency]),
('pathway_abundance', FeatureTable[Frequency]),
('pathway_coverage', FeatureTable[Frequency])
],
outputs=[('ko_metagenome', FeatureTable[Frequency]),
('ec_metagenome', FeatureTable[Frequency]),
('pathway_abundance', FeatureTable[Frequency])],

input_descriptions={
'table': ('The feature table containing sequence abundances per sample.'),
Expand All @@ -53,8 +50,7 @@

output_descriptions={'ko_metagenome': 'Predicted metagenome for KEGG orthologs',
'ec_metagenome': 'Predicted metagenome for E.C. numbers',
'pathway_abundance': 'Predicted MetaCyc pathway abundances',
'pathway_coverage': 'Predicted MetaCyc pathway coverages'},
'pathway_abundance': 'Predicted MetaCyc pathway abundances'},

name='Default 16S PICRUSt2 Pipeline',

Expand All @@ -77,8 +73,7 @@
outputs=[
('ko_metagenome', FeatureTable[Frequency]),
('ec_metagenome', FeatureTable[Frequency]),
('pathway_abundance', FeatureTable[Frequency]),
('pathway_coverage', FeatureTable[Frequency])
('pathway_abundance', FeatureTable[Frequency])
],

input_descriptions={
Expand All @@ -94,8 +89,7 @@

output_descriptions={'ko_metagenome': 'Predicted metagenome for KEGG orthologs',
'ec_metagenome': 'Predicted metagenome for E.C. numbers',
'pathway_abundance': 'Predicted MetaCyc pathway abundances',
'pathway_coverage': 'Predicted MetaCyc pathway coverages'},
'pathway_abundance': 'Predicted MetaCyc pathway abundances'},

name='16S PICRUSt2 pipeline with custom tree',

Expand Down
2 changes: 1 addition & 1 deletion setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

setup(
name="q2-picrust2",
version="0.0.2",
version="0.0.3",
packages=find_packages(),
package_data={'q2_picrust2': ['citations.bib']},
author="Gavin Douglas",
Expand Down