Workflow Steps and Code Snippets

202 tagged steps and code snippets that match keyword common

Snakemake workflow: dna-seq-gatk-variant-calling (v2.1.1) 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
import sys
sys.stderr = open(snakemake.log[0], "w")

import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
Python Pandas numpy matplotlib seaborn common From line 1 of scripts/plot-depths.py

Snakemake workflow: dna-seq-gatk-variant-calling (v2.1.1) 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
import sys
sys.stderr = open(snakemake.log[0], "w")

import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
Python Pandas numpy matplotlib seaborn common From line 1 of scripts/plot-depths.py

Snakemake workflow: dna-seq-gatk-variant-calling (v2.1.1) 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
import sys
sys.stderr = open(snakemake.log[0], "w")

import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
Python Pandas numpy matplotlib seaborn common From line 1 of scripts/plot-depths.py

Snakemake workflow: dna-seq-gatk-variant-calling (v2.1.1) 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
import sys
sys.stderr = open(snakemake.log[0], "w")

import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
Python Pandas numpy matplotlib seaborn common From line 1 of scripts/plot-depths.py

Snakemake workflow: dna-seq-gatk-variant-calling 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
Python Pandas numpy matplotlib seaborn common From line 1 of scripts/plot-depths.py

Snakemake workflow: dna-seq-gatk-variant-calling 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
import sys
sys.stderr = open(snakemake.log[0], "w")

import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
Python Pandas numpy matplotlib seaborn common From line 1 of scripts/plot-depths.py

Snakemake workflow: dna-seq-gatk-variant-calling (v2.1.1) 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
import sys
sys.stderr = open(snakemake.log[0], "w")

import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
Python Pandas numpy matplotlib seaborn common From line 1 of scripts/plot-depths.py

DNA-Seq GATK Variant Calling Workflow with Snakemake 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
import sys
sys.stderr = open(snakemake.log[0], "w")

import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
Python Pandas numpy matplotlib seaborn common From line 1 of scripts/plot-depths.py

Snakemake workflow: dna-seq-gatk-variant-calling (v2.1.1) 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
import sys
sys.stderr = open(snakemake.log[0], "w")

import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
Python Pandas numpy matplotlib seaborn common From line 1 of scripts/plot-depths.py

Snakemake workflow: dna-seq-gatk-variant-calling (v2.1.1) 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
import sys
sys.stderr = open(snakemake.log[0], "w")

import common
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import seaborn as sns

calls = pd.read_table(snakemake.input[0], header=[0, 1])
samples = [name for name in calls.columns.levels[0] if name != "VARIANT"]
sample_info = calls.loc[:, samples].stack([0, 1]).unstack().reset_index(1, drop=False)
sample_info = sample_info.rename({"level_1": "sample"}, axis=1)

sample_info = sample_info[sample_info["DP"] > 0]
sample_info["freq"] = sample_info["AD"] / sample_info["DP"]
sample_info.index = np.arange(sample_info.shape[0])

plt.figure()

sns.stripplot(x="sample", y="freq", data=sample_info, jitter=True)
plt.ylabel("allele frequency")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.freqs)

plt.figure()

sns.stripplot(x="sample", y="DP", data=sample_info, jitter=True)
plt.ylabel("read depth")
plt.xticks(rotation="vertical")

plt.savefig(snakemake.output.depths)
Python Pandas numpy matplotlib seaborn common From line 1 of scripts/plot-depths.py
tool / pypi

common

The MIT License (MIT) ===================== Copyright (c) 2016 Marcel Hellkamp Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT O

pypi common
URL https://pypi.python.org/pypi/common
email [email protected]
author: Marcel Hellkamp
library: python:common
license: UNKNOWN
version: 0.1.2
62 202 0 0
Are you the author of this tool? with a link to this page.
Insert the following code to your website to add tag icon with a link to this page.
    HTML Markdown