#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from bioodo import bamtools, odo, DataFrame
from pytest_ngsfixtures.config import application_fixtures
import utils
fixtures = application_fixtures(application="bamtools")
bamtools_data = utils.fixture_factory([x for x in fixtures])
bamtools_aggregate_data = utils.aggregation_fixture_factory(
[x for x in fixtures], 2)
def test_bamtools(bamtools_data):
module, command, version, end, pdir = bamtools_data
df = odo(str(pdir.listdir()[0]), DataFrame)
n = 59499 if end == "se" else 119413
assert df.loc["Mapped reads", "value"] == n
def test_bamtools_aggregate(bamtools_aggregate_data):
module, command, version, end, pdir = bamtools_aggregate_data
df = bamtools.aggregate(
[str(x.listdir()[0]) for x in pdir.listdir() if x.isdir()],
regex=".*/(?P<repeat>[0-9]+)/medium.stats")
assert sorted(list(df["repeat"].unique())) == ['0', '1']
def test_bamtools_pivot(bamtools_data):
module, command, version, end, pdir = bamtools_data
df = odo(str(pdir.listdir()[0]),
DataFrame,
# Copyright (C) 2015 by Per Unneberg
from bioodo import sga, odo, DataFrame
from pytest_ngsfixtures.config import application_fixtures
import utils
fixtures = application_fixtures(application="sga")
sga_preprocess_data = utils.fixture_factory(
[x for x in fixtures if "preprocess" in x[1]])
sga_filter_data = utils.fixture_factory(
[x for x in fixtures if "filter" in x[1]])
sga_aggregate_filter_data = utils.aggregation_fixture_factory(
[x for x in fixtures if "filter" in x[1]], 2)
def test_sga_preprocess(sga_preprocess_data):
module, command, version, end, pdir = sga_preprocess_data
df = odo(str(pdir.listdir()[0]), DataFrame)
n = 10000 if end == "se" else 20000
assert df.loc["Reads parsed", "value"] == n
def test_sga_filter(sga_filter_data):
_filter_stats = {'0.10.13': {'se': 9400, 'pe': 16670}}
module, command, version, end, pdir = sga_filter_data
df = odo(str(pdir.listdir()[0]), DataFrame)
assert (df.loc["Reads failed kmer check",
"value"] == _filter_stats[version][end])
def test_sga_aggregate_filter(sga_aggregate_filter_data):
# Copyright (C) 2015 by Per Unneberg
import os
from bioodo import rseqc, odo, DataFrame
from pytest_ngsfixtures.config import application_fixtures
import utils
blacklist = ["rseqc_junction_annotation", "rseqc_read_duplication"]
fixtures = application_fixtures(application="rseqc")
fixture_list = [f for f in fixtures if f[1] not in blacklist]
data = utils.fixture_factory(fixture_list, scope="function")
rseqc_aggregate_data = utils.aggregation_fixture_factory(
[x for x in fixture_list], 2)
def test_rseqc_parse(data):
module, command, version, end, pdir = data
fn = pdir.listdir()[0]
if command == "rseqc_read_duplication":
odo(str(fn), DataFrame)
fn = pdir.listdir()[1]
odo(str(fn), DataFrame)
else:
odo(str(fn), DataFrame)
def test_rseqc_aggregate(rseqc_aggregate_data):
module, command, version, end, pdir = rseqc_aggregate_data
infiles = [str(x.listdir()[0]) for x in pdir.listdir() if x.isdir()]
df = rseqc.aggregate(infiles,
regex=".*/(?P<repeat>[0-9]+)/" +
os.path.basename(infiles[0]))
# Copyright (C) 2015 by Per Unneberg
from bioodo import bcftools, odo, DataFrame
from pytest_ngsfixtures.config import application_fixtures
import utils
fixtures = application_fixtures(application="bcftools")
stat_fixtures = [x for x in fixtures if x[1] == "bcftools_stats"]
bcftools_stats = utils.fixture_factory(stat_fixtures)
bcftools_aggregate_QUAL_data = utils.aggregation_fixture_factory(
[x for x in stat_fixtures], 2)
def test_basic_statistics(bcftools_stats):
module, command, version, end, pdir = bcftools_stats
fn = str(pdir.join("medium.call.stats"))
df = odo(fn, DataFrame)
assert (list(df.index)[0] == 'number of samples')
n = 10667 if end == "pe" else 7400
assert (df.loc["number of records", "value"] == n)
def test_TSTV(bcftools_stats):
module, command, version, end, pdir = bcftools_stats
fn = str(pdir.join("medium.call.stats"))
df = odo(fn, DataFrame, key="TSTV")
tstv = 2.12 if end == "pe" else 2.19
assert (df.loc[0]["ts/tv"] == tstv)
def test_IDD(bcftools_stats):
# Copyright (C) 2015 by Per Unneberg
from bioodo import star, odo, DataFrame
from pytest_ngsfixtures.config import application_fixtures
import utils
fixtures = application_fixtures(application="star")
data = utils.fixture_factory(fixtures)
aggregate_data = utils.aggregation_fixture_factory([
tuple([x[0], x[1], x[2], x[3], {
'final': x[4]['final']
}]) for x in fixtures
], 2)
def test_star_final_log(data):
module, command, version, end, pdir = data
fn = pdir.join("medium.Log.final.out")
df = odo(str(fn), DataFrame)
assert df.loc["Number of input reads", "value"] == 30483
def test_star_aggregate(aggregate_data):
module, command, version, end, pdir = aggregate_data
df = star.aggregate(
[str(x.listdir()[0]) for x in pdir.listdir() if x.isdir()],
regex=".*/(?P<repeat>[0-9]+)/medium.Log.final.out")
assert sorted(list(df["repeat"].unique())) == ['0', '1']
from pytest_ngsfixtures.config import application_fixtures
import utils
fixtures = application_fixtures(application="qualimap")
# Separate pe and se cases
outputs = {'pe': {}, 'se': {}}
newfixtures = []
for x in fixtures:
for k, v in x[4].items():
y = tuple([x[0], x[1], x[2], x[3], {k: v}])
newfixtures.append(y)
data = utils.fixture_factory(newfixtures, scope="function", unique=True)
qualimap_aggregate_data = utils.aggregation_fixture_factory(
[x for x in newfixtures if "homopolymer_indels" in x[4].keys()], 2)
def test_qualimap(data):
module, command, version, end, pdir = data
if command.startswith("qualimap_bamqc_genome_results"):
fn = pdir.listdir()[0]
df = odo(str(fn), DataFrame, key='Coverage_per_contig')
assert list(df.columns) == ['chrlen', 'mapped_bases',
'mean_coverage', 'sd']
assert list(df.index)[0] == 'scaffold1'
else:
fn = pdir.listdir()[0]
df = odo(str(fn), DataFrame)
assert "#" not in df.columns[0]
# Copyright (C) 2015 by Per Unneberg
from bioodo import picard, odo, DataFrame
from pytest_ngsfixtures.config import application_fixtures
import utils
fixtures = application_fixtures(application="picard")
insert_metrics = utils.fixture_factory(
[x for x in fixtures if "CollectInsertSizeMetrics" in x[1]])
align_metrics = utils.fixture_factory(
[x for x in fixtures if "CollectAlignmentSummaryMetrics" in x[1]])
aggregate_data_insert = utils.aggregation_fixture_factory(
[x for x in fixtures if "CollectInsertSizeMetrics" in x[1]], 2)
def test_hist_metrics(insert_metrics):
module, command, version, end, pdir = insert_metrics
fn = pdir.join("medium.insert_size_metrics")
metrics = odo(str(fn), DataFrame)
hist = odo(str(fn), DataFrame, key="hist")
assert all(metrics["MEDIAN_INSERT_SIZE"] == [367])
assert all(hist["insert_size"][0:3] == [19, 22, 23])
def test_metrics(align_metrics):
module, command, version, end, pdir = align_metrics
fn = pdir.join("medium.align_metrics")
metrics = odo(str(fn), DataFrame)
if end == "pe":
assert metrics.loc["FIRST_OF_PAIR"]["MEAN_READ_LENGTH"] - 92.29 < 0.01
else:
assert metrics.loc["UNPAIRED"]["MEAN_READ_LENGTH"] - 92.29975 < 0.001
# Copyright (C) 2015 by Per Unneberg
from bioodo import cutadapt, odo, DataFrame
from pytest_ngsfixtures.config import application_fixtures
import utils
fixtures = application_fixtures(application="cutadapt")
cutadapt_metrics = utils.fixture_factory(fixtures)
cutadapt_aggregate_data = utils.aggregation_fixture_factory(
[x for x in fixtures], 2)
def test_cutadapt(cutadapt_metrics):
module, command, version, end, pdir = cutadapt_metrics
fn = str(pdir.join("cutadapt_metrics.txt"))
df = odo(fn, DataFrame)
if end == "se":
assert df.loc["Reads with adapters"]["value"] == 792
elif end == "pe":
assert df.loc["Read 1 with adapter"]["value"] == 792
def test_cutadapt_aggregate(cutadapt_aggregate_data):
module, command, version, end, pdir = cutadapt_aggregate_data
df = cutadapt.aggregate(
[str(x.listdir()[0]) for x in pdir.listdir() if x.isdir()],
regex=".*/(?P<repeat>[0-9]+)/cutadapt_metrics.txt")
assert sorted(list(df["repeat"].unique())) == ['0', '1']
# Copyright (C) 2015 by Per Unneberg
from bioodo import mapdamage, odo, DataFrame
from pytest_ngsfixtures.config import application_fixtures
import utils
fixtures = application_fixtures(application="mapdamage2")
mapdamage_data = utils.fixture_factory(fixtures)
mapdamage_agg_data_misincorp = utils.aggregation_fixture_factory(
[x for x in fixtures], 2, keys=["misincorp"])
def test_mapdamage_runtime(mapdamage_data):
module, command, version, end, pdir = mapdamage_data
fn = pdir.join("Runtime_log.txt")
odo(str(fn), DataFrame)
def test_mapdamage_3pGtoA(mapdamage_data):
module, command, version, end, pdir = mapdamage_data
fn = pdir.join("3pGtoA_freq.txt")
df = odo(str(fn), DataFrame)
assert (df.index.name == "pos")
def test_mapdamage_5pCtoT(mapdamage_data):
module, command, version, end, pdir = mapdamage_data
fn = pdir.join("5pCtoT_freq.txt")
df = odo(str(fn), DataFrame)
assert (df.index.name == "pos")
# Copyright (C) 2015 by Per Unneberg
from bioodo import vsearch, odo, DataFrame
from pytest_ngsfixtures.config import application_fixtures
import utils
blacklist = ['vsearch_fastqc_filter']
fixtures = [x for x in application_fixtures(application="vsearch")
if x[1] not in blacklist]
data = utils.fixture_factory(fixtures)
aggregate_data = utils.aggregation_fixture_factory(
fixtures, 2)
def test_vsearch_fastq_stats(data):
module, command, version, end, pdir = data
fn = pdir.join("medium.fastq_stats.txt")
df = odo(str(fn), DataFrame)
assert list(df.columns) == ["N", "Pct", "AccPct"]
assert df.index.name == "L"
df = odo(str(fn), DataFrame, key="Truncate at first Q")
assert list(df.columns) == ["Q=5", "Q=10", "Q=15", "Q=20"]
assert df.index.name == "Len"
def test_vsearch_aggregate(aggregate_data):
module, command, version, end, pdir = aggregate_data
df = vsearch.aggregate(
[str(x.listdir()[0]) for x in pdir.listdir()
if x.isdir()],
regex=".*/(?P<repeat>[0-9]+)/medium.fastq_stats.txt")
assert sorted(list(df["repeat"].unique())) == ['0', '1']