-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathsnakefile
158 lines (141 loc) · 4.38 KB
/
snakefile
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
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
import pandas
num_workers = 4
assays = ['RNA', 'ATAC']
project = 'card_sc_brain_atlas'
input_table = 'input/random_samples.csv'
samples = pandas.read_csv(input_table, header=None).loc[:, 0].tolist()[1:]
rule all:
input:
'plots/qc_plot1.pdf',
'plots/qc_plot2.pdf',
'output/seurat_wnn_integrated_cluster_markers.csv',
'plots/seurat_wnn_seurat_clusters_sample_batch_umap.pdf'
rule preprocess_first:
input:
samples=input_table
output:
seurat_object='objects/seurat_object_{sample}_rna_preprocessed_01.rds'
params:
soup_rate=0.10,
sample='{sample}'
conda:
'envs/multiome.yml'
script:
'scripts/main/preprocess_first.R'
rule preprocess_second:
input:
seurat_object='objects/seurat_object_{sample}_rna_preprocessed_01.rds'
output:
seurat_object='objects/seurat_object_{sample}_atac_preprocessed_02.rds'
conda:
'envs/multiome.yml'
script:
'scripts/main/preprocess_second.R'
rule call_doublets:
input:
seurat_object=expand('objects/seurat_object_{sample}_atac_preprocessed_02.rds', sample=samples)
output:
metadata='output/unfiltered_metadata.csv'
params:
project_name=project
conda:
'envs/multiome.yml'
threads:
num_workers
script:
'scripts/main/gmm_doublet_calling.R'
rule plot_qc:
input:
metadata='output/unfiltered_metadata.csv'
output:
plot_1='plots/qc_plot1.pdf', plot_2='plots/qc_plot2.pdf'
params:
project_name=project
conda:
'envs/multiome.yml'
threads:
num_workers
script:
'scripts/main/plot_qc_metrics.R'
rule preprocess_third:
input:
metadata='output/unfiltered_metadata.csv',
seurat_object='objects/seurat_object_{sample}_atac_preprocessed_02.rds'
output:
peaks='output/{sample}_peaks.rds',
seurat_object='objects/seurat_object_{sample}_atac_preprocessed_filtered_03.rds'
conda:
'envs/multiome.yml'
script:
'scripts/main/preprocess_third.R'
rule merge_peaks:
input:
peaks=expand('output/{sample}_peaks.rds', sample=samples)
output:
merged_peaks='output/merged_atac_peaks.rds'
conda:
'envs/multiome.yml'
threads:
num_workers
script:
'scripts/main/merge_peaks.R'
rule rebuild_atac:
input:
merged_peaks='output/merged_atac_peaks.rds',
seurat_object='objects/seurat_object_{sample}_atac_preprocessed_filtered_03.rds'
output:
seurat_object='objects/seurat_object_{sample}_preprocessed_filtered_rebuilt_04.rds'
conda:
'envs/multiome.yml'
threads:
num_workers
script:
'scripts/main/rebuild_atac_assay.R'
rule process:
input:
seurat_object='objects/seurat_object_{sample}_preprocessed_filtered_rebuilt_04.rds'
output:
seurat_object='objects/seurat_object_{sample}_preprocessed_filtered_rebuilt_normalized_{assay}_05.rds'
conda:
'envs/multiome.yml'
threads:
num_workers
script:
'scripts/main/{wildcards.assay}_process.R'
rule harmony:
input:
expand('objects/seurat_object_{sample}_preprocessed_filtered_rebuilt_normalized_{assay}_05.rds', sample=samples, assay=assays)
output:
'reductions/{assay}_harmony.rds'
threads:
num_workers * 2
shell:
'''
source /data/abbass2/mambaforge/bin/activate harmony
Rscript scripts/main/{wildcards.assay}_harmony.R {input} {output} {threads}
'''
rule wnn:
input:
reduction=expand('reductions/{assay}_harmony.rds', assay=assays),
seurat_object=expand('objects/seurat_object_{sample}_preprocessed_filtered_rebuilt_04.rds', sample=samples)
output:
metadata='output/final_metadata.csv',
seurat_object='objects/seurat_object_preprocessed_filtered_wnn_integrated_06.rds'
conda:
'envs/multiome.yml'
threads:
num_workers
script:
'scripts/main/wnn.R'
rule markers:
input:
seurat_object='objects/seurat_object_preprocessed_filtered_wnn_integrated_06.rds'
output:
markers='output/seurat_wnn_integrated_cluster_markers.csv',
umap='plots/seurat_wnn_seurat_clusters_sample_batch_umap.pdf'
conda:
'envs/multiome.yml'
threads:
num_workers * 4
script:
'scripts/main/markers.R'