snakefiles/analysis.smk at master · dorbarker/snakefiles · GitHub

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
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
import re
import os

include: 'cgmlst.smk'
include: 'assemble.smk'

fastq_files = sorted(os.listdir('fastqs'))

match_illumina = '(.+?)(_S\d+_L001)?_(R[12])(_001)?\.f(ast)?q\.?(gz)?'
sample_pattern = re.compile(match_illumina)

genome_samples = [re.sub(sample_pattern, '\\1', f)
				  for i, f in enumerate(fastq_files)
				  if i % 2 is 0]

# master rule
rule analyze:
	input:
		'pristine.csv',
		'cgf_prediction.csv',
		'pristine_distance_matrix.csv',
		'melted_distance_matrix.csv',
		'melted_pristine_distance_matrix.csv',
		'missing_data_histogram.png'

rule ecgf:
	input:
		expand('genomes/{sample}.fasta', sample=genome_samples)

	output:
		'cgf_prediction.csv'

	shell:
		"eCGF genomes {output}"

rule distance_matrix:
	input:
		'calls.csv'

	output:
		'distance_matrix.csv'

	script:
		'scripts/hamming_distance_matrix.py'

rule pristine_distance_matrix:
	input:
		'pristine.csv',
		'distance_matrix.csv'

	output:
		'pristine_distance_matrix.csv'

	run:
		import pandas as pd
		pristine_genomes = pd.read_csv(input[0], header=0, index_col=0).index
		calls_dm = pd.read_csv(input[1], header=0, index_col=0)
		pristine_dm = calls_dm.loc[pristine_genomes, pristine_genomes]
		pristine_dm.to_csv(output[0])

rule missing_data_histogram:
	input:
		'calls.csv'

	output:
		'missing_data_histogram.png'

	script:
		'scripts/missing_data_histogram.R'

rule melted_distance_matrix:
	input:
		'{dm}'

	output:
		'melted_{dm}'

	script:
		'scripts/melted_distance_matrix.R'