Skip to content

Commit 91d92df

Browse files
pjbriggspjbriggs
authored
Merge pull request #1104 from fls-bioinformatics-core/10x-extend-fastq-generation-protocols
WIP Extend 10x Genomics Fastq generation protocols to specify read lengths
2 parents b00a02b + 3065602 commit 91d92df

12 files changed

Lines changed: 1093 additions & 269 deletions

File tree

‎auto_process_ngs/bcl2fastq/pipeline.py‎

Lines changed: 104 additions & 191 deletions
Large diffs are not rendered by default.

‎auto_process_ngs/bcl2fastq/protocols.py‎

Lines changed: 275 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,275 @@
1+
#!/usr/bin/env python3
2+
#
3+
# bcl2fastq.protocols.py: Fastq generation protocol definitions
4+
# Copyright (C) University of Manchester 2025 Peter Briggs
5+
#
6+
7+
"""
8+
Defines the ``PROTOCOLS`` dictionary, which specifies the available Fastq
9+
generation protocols which can be used in the Fastq generation pipeline.
10+
11+
Each protocol is defined as a name (the dictionary key) and a dictionary
12+
of parameters (the dictionary value).
13+
14+
The following parameters compulsory for each protocol:
15+
16+
* description: free-text string describing the protocol
17+
* pipeline_variant: a string specifying which of the implemented sub-pipelines
18+
the protocol will use; must be one of: "standard", "10x_cellranger",
19+
"10x_cellranger-atc", "10x_cellranger-arc", "10x_spaceranger"
20+
* supported_indexes: a sequence (list or tuple) which specifies the types
21+
of sample sheet index that the protocol supports; must be one or more of:
22+
"ILLUMINA", "10X", "NONE"
23+
24+
The remaining parameters can be none or more of any of the possible lane
25+
subset attributes. Most commonly:
26+
27+
* r1_length
28+
* r2_length
29+
* r3_length
30+
* i1_length
31+
* i2_length
32+
* minimum_trimmed_read_lengths
33+
* mask_short_adapter_reads
34+
* no_lane_splitting
35+
* create_fastq_for_index_read
36+
* trim_adapters
37+
"""
38+
39+
PROTOCOLS = {
40+
"standard": {
41+
"description": "Standard Illumina sequencing data (default)",
42+
"pipeline_variant": "standard",
43+
"supported_indexes": ("ILLUMINA", "NONE"),
44+
},
45+
"mirna": {
46+
# miRNA-seq protocol
47+
# Set minimum trimmed read length and turn off masking
48+
"description": "miRNA-seq data",
49+
"pipeline_variant": "standard",
50+
"supported_indexes": ("ILLUMINA",),
51+
"minimum_trimmed_read_length": 10,
52+
"mask_short_adapter_reads": 0,
53+
},
54+
"10x_chromium_sc": {
55+
# 10xGenomics Chromium SC (GEX/Flex)
56+
# -- truncate R1 to 28 bases
57+
# -- truncate R2 to 90 bases
58+
# -- truncate I1 and I2 to 10 bases
59+
# -- minimum trimmed read length 8bp
60+
# -- minimum masked read length 8bp
61+
# -- no lane splitting
62+
# -- create Fastqs for index read
63+
# -- disable adapter trimming
64+
"description": "10x Genomics Chromium 3' and 5' single cell "
65+
"gene expression data",
66+
"pipeline_variant": "10x_cellranger",
67+
"supported_indexes": ("ILLUMINA", "10X"),
68+
"r1_length": 28,
69+
"r2_length": 90,
70+
"i1_length": 10,
71+
"i2_length": 10,
72+
"minimum_trimmed_read_length": 8,
73+
"mask_short_adapter_reads": 8,
74+
"no_lane_splitting": True,
75+
"create_fastq_for_index_read": True,
76+
"trim_adapters": False
77+
},
78+
"10x_atac": {
79+
# 10xGenomics ATAC-seq
80+
# -- convert I2 to R2
81+
# -- truncate R1 to 50 bases
82+
# -- truncate R2 to 16 bases
83+
# -- truncate R3 to 50 bases
84+
# -- truncate I1 to 8 bases
85+
# -- enable filter single index
86+
# -- no lane splitting
87+
# -- create Fastqs for index read
88+
# -- disable adapter trimming
89+
"description": "10x Genomics Chromium single cell ATAC-seq data",
90+
"pipeline_variant": "10x_cellranger-atac",
91+
"supported_indexes": ("10X",),
92+
"r1_length": 50,
93+
"r2_length": 16,
94+
"r3_length": 50,
95+
"i1_length": 8,
96+
"override_template": "RIRR",
97+
"tenx_filter_single_index": True,
98+
"no_lane_splitting": True,
99+
"create_fastq_for_index_read": True,
100+
"trim_adapters": False
101+
},
102+
"10x_multiome": {
103+
# 10xGenomics multiome
104+
# -- set bases mask to "auto"
105+
# -- no lane splitting
106+
# -- create Fastqs for index read
107+
# -- disable adapter trimming
108+
"description": "10x Genomics single cell multiome data "
109+
"(unpooled data i.e. ATAC or GEX data only in single run)",
110+
"pipeline_variant": "10x_cellranger-arc",
111+
"supported_indexes": ("10X",),
112+
"bases_mask": "auto",
113+
"no_lane_splitting": True,
114+
"create_fastq_for_index_read": True,
115+
"trim_adapters": False
116+
},
117+
"10x_multiome_atac": {
118+
# 10xGenomics multiome (ATAC)
119+
# -- convert I2 to R2
120+
# -- truncate R1 to 50 bases
121+
# -- truncate R2 to 24 bases
122+
# -- truncate R3 to 49 bases
123+
# -- truncate I1 to 8 bases
124+
# -- enable filter single index
125+
# -- no lane splitting
126+
# -- create Fastqs for index read
127+
# -- disable adapter trimming
128+
"description": "10x Genomics single cell multiome ATAC-seq data "
129+
"(run with pooled GEX and ATAC data)",
130+
"pipeline_variant": "10x_cellranger-arc",
131+
"supported_indexes": ("10X",),
132+
"r1_length": 50,
133+
"r2_length": 24,
134+
"r3_length": 49,
135+
"i1_length": 8,
136+
"override_template": "RIRR",
137+
"tenx_filter_single_index": True,
138+
"no_lane_splitting": True,
139+
"create_fastq_for_index_read": True,
140+
"trim_adapters": False
141+
},
142+
"10x_multiome_gex": {
143+
# 10xGenomics multiome (GEX)
144+
# -- truncate I1 and I2 to 10 bases
145+
# -- truncate R1 to 28 bases
146+
# -- truncate R2 to 90 bases
147+
# -- enable filter dual index
148+
# -- no lane splitting
149+
# -- create Fastqs for index read
150+
# -- disable adapter trimming
151+
"description": "10x Genomics single cell multiome GEX data "
152+
"(run with pooled GEX and ATAC data)",
153+
"pipeline_variant": "10x_cellranger-arc",
154+
"supported_indexes": ("10X",),
155+
"r1_length": 28,
156+
"r2_length": 90,
157+
"i1_length": 10,
158+
"i2_length": 10,
159+
"tenx_filter_dual_index": True,
160+
"no_lane_splitting": True,
161+
"create_fastq_for_index_read": True,
162+
"trim_adapters": False
163+
},
164+
"10x_visium": {
165+
# 10xGenomics Visium
166+
# -- truncate R1 to 28 bases
167+
# -- truncate R2 to 50 bases
168+
# -- truncate I1 and I2 to 10 bases
169+
# -- minimum trimmed read length 8bp
170+
# -- minimum masked read length 8bp
171+
# -- no lane splitting
172+
# -- create Fastqs for index read
173+
# -- disable adapter trimming
174+
"description": "10x Genomics Visium CytAssist FFPE, Fresh Frozen, Fixed "
175+
"Frozen spatial GEX or FFPE PEX data",
176+
"pipeline_variant": "10x_spaceranger",
177+
"supported_indexes": ("ILLUMINA", "10X"),
178+
"r1_length": 28,
179+
"r2_length": 50,
180+
"i1_length": 10,
181+
"i2_length": 10,
182+
"minimum_trimmed_read_length": 8,
183+
"mask_short_adapter_reads": 8,
184+
"no_lane_splitting": True,
185+
"create_fastq_for_index_read": True,
186+
"trim_adapters": False
187+
},
188+
"10x_visium_v1": {
189+
# 10xGenomics Visium v1
190+
# -- truncate R1 to 28 bases
191+
# -- truncate R2 to 90 bases
192+
# -- truncate I1 and I2 to 10 bases
193+
# -- minimum trimmed read length 8bp
194+
# -- minimum masked read length 8bp
195+
# -- no lane splitting
196+
# -- create Fastqs for index read
197+
# -- disable adapter trimming
198+
"description": "10x Genomics Visium Fresh Frozen Spatial GEX (v1) "
199+
"data (no CytAssist)",
200+
"pipeline_variant": "10x_spaceranger",
201+
"supported_indexes": ("ILLUMINA", "10X"),
202+
"r1_length": 28,
203+
"r2_length": 90,
204+
"i1_length": 10,
205+
"i2_length": 10,
206+
"minimum_trimmed_read_length": 8,
207+
"mask_short_adapter_reads": 8,
208+
"no_lane_splitting": True,
209+
"create_fastq_for_index_read": True,
210+
"trim_adapters": False
211+
},
212+
"10x_visium_hd": {
213+
# 10xGenomics Visium (HD)
214+
# -- truncate R1 to 43 bases
215+
# -- truncate R2 to 50 bases
216+
# -- truncate I1 and I2 to 10 bases
217+
# -- minimum trimmed read length 8bp
218+
# -- minimum masked read length 8bp
219+
# -- no lane splitting
220+
# -- create Fastqs for index read
221+
# -- disable adapter trimming
222+
"description": "10x Genomics Visium CytAssist FFPE HD spatial GEX "
223+
"data",
224+
"pipeline_variant": "10x_spaceranger",
225+
"supported_indexes": ("ILLUMINA", "10X"),
226+
"r1_length": 43,
227+
"r2_length": 50,
228+
"i1_length": 10,
229+
"i2_length": 10,
230+
"minimum_trimmed_read_length": 8,
231+
"mask_short_adapter_reads": 8,
232+
"no_lane_splitting": True,
233+
"create_fastq_for_index_read": True,
234+
"trim_adapters": False
235+
},
236+
"10x_visium_hd_3prime": {
237+
# 10xGenomics Visium (HD 3')
238+
# -- truncate R1 to 43 bases
239+
# -- truncate R2 to 75 bases
240+
# -- truncate I1 and I2 to 10 bases
241+
# -- minimum trimmed read length 8bp
242+
# -- minimum masked read length 8bp
243+
# -- no lane splitting
244+
# -- create Fastqs for index read
245+
# -- disable adapter trimming
246+
"description": "10x Visium CytAssist FFPE HD 3' spatial GEX data",
247+
"pipeline_variant": "10x_spaceranger",
248+
"supported_indexes": ("ILLUMINA", "10X"),
249+
"r1_length": 43,
250+
"r2_length": 75,
251+
"i1_length": 10,
252+
"i2_length": 10,
253+
"minimum_trimmed_read_length": 8,
254+
"mask_short_adapter_reads": 8,
255+
"no_lane_splitting": True,
256+
"create_fastq_for_index_read": True,
257+
"trim_adapters": False
258+
},
259+
"parse_evercode": {
260+
# Parse Evercode
261+
# Disable adapter trimming
262+
"description": "Parse Evercode single cell data",
263+
"pipeline_variant": "standard",
264+
"supported_indexes": ("ILLUMINA",),
265+
"trim_adapters": False,
266+
},
267+
"biorad_ddseq": {
268+
# Bio-Rad ddSEQ
269+
# Disable adapter trimming
270+
"description": "Bio-Rad ddSEQ single cell data",
271+
"pipeline_variant": "standard",
272+
"supported_indexes": ("ILLUMINA",),
273+
"trim_adapters": False,
274+
}
275+
}

‎auto_process_ngs/commands/make_fastqs_cmd.py‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -291,8 +291,15 @@ def make_fastqs(ap,protocol='standard',platform=None,
291291

292292
# Bases mask
293293
if bases_mask is not None:
294+
# Bases mask was explicitly specified, so update the value stored
295+
# in params
294296
ap.params['bases_mask'] = bases_mask
297+
# Use the bases mask from params
295298
bases_mask = ap.params.bases_mask
299+
if bases_mask == "auto":
300+
# Interpret "auto" as don't set it explicitly, let the pipeline do it
301+
# automatically
302+
bases_mask = None
296303

297304
# Default trimming/masking values
298305
if minimum_trimmed_read_length is None:

0 commit comments

Comments
 (0)