diff --git a/tools/sniffles/sniffles.xml b/tools/sniffles/sniffles.xml index 0d68dc9cd85..ba538bca70e 100644 --- a/tools/sniffles/sniffles.xml +++ b/tools/sniffles/sniffles.xml @@ -1,4 +1,4 @@ - + Structural variation caller using third generation sequencing 2.4 @@ -16,8 +16,8 @@ Use a genome fasta file from the current history - +
- - - - + + + + +
- +
@@ -90,6 +95,7 @@ sniffles + @@ -130,103 +136,136 @@ Sniffles What is Sniffles? ***************** + Sniffles is a SV caller for long reads. Sniffles2 accurately detect SVs on germline, somatic and population-level for PacBio and Oxford Nanopore read data. SV are larger events on the genome (e.g. deletions, duplications, insertions, inversions and translocations). Sniffles can detect all of these type and more such as nested SVs (e.g. inversion flanked by deletions or an inverted duplication). +---- + Inputs ****** Known to work with Minimap2 bam as input +Optional reference fasta with matching contig names will allow deletions to be determined. + +---- Parameters ********** + General ------- -+---------------------------+-----------------------------------------------------------------------+ -| Parameter | Description | -+===========================+=======================================================================+ -| Minimum Support | Minimum number of reads supporting a SV to be reported. Default:auto | -+---------------------------+-----------------------------------------------------------------------+ -| Maximum Number of Splits | Maximum number of split segments per kb a read is aligned at before | -| | it is ignored. Default: 7 | -+---------------------------+-----------------------------------------------------------------------+ -| Minimum SV Length | Minimum length of SV to be reported. Default: 50bp | -+---------------------------+-----------------------------------------------------------------------+ -| Minimum Mapping Quality | Minimum mapping quality of alignment to be taken into account. | -| | Default: 20 | -+---------------------------+-----------------------------------------------------------------------+ -| Minimum alignment length | Reads with less length aligned will be ignored. Default 100 | -+---------------------------+-----------------------------------------------------------------------+ ++----------------------------+-------------------------------------------------------------------------+ +| Parameter | Description | ++============================+=========================================================================+ +| Minimum Support | Minimum number of reads supporting a SV to be reported. Default:auto | ++----------------------------+-------------------------------------------------------------------------+ +| Maximum Number of Splits | Maximum number of split segments per kb a read is aligned at before | +| | it is ignored. Default: 7 | ++----------------------------+-------------------------------------------------------------------------+ +| Minimum SV Length | Minimum length of SV to be reported. Default: 50bp | ++----------------------------+-------------------------------------------------------------------------+ +| Minimum Mapping Quality | Minimum mapping quality of alignment to be taken into account. | +| | Default: 20 | ++----------------------------+-------------------------------------------------------------------------+ +| Minimum alignment length | Reads with less length aligned will be ignored. Default 100 | ++----------------------------+-------------------------------------------------------------------------+ + + Clustering Options ------------------ -+----------------------------------------+-----------------------------------------------------------------------+ -| Parameter | Description | -+========================================+=======================================================================+ -| Cluster bin size | Initial cluster bin size. Default 100 | -+----------------------------------------+-----------------------------------------------------------------------+ -| Cluster Multiplier | Multiplier for SV start position standard deviation criterion in | -| | cluster merging [2.5] | -+----------------------------------------+-----------------------------------------------------------------------+ ++---------------------+------------------------------------------------------------------------+ +| Parameter | Description | ++=====================+========================================================================+ +| Cluster bin size | Initial cluster bin size. Default 100 | ++---------------------+------------------------------------------------------------------------+ +| Cluster Multiplier | Multiplier for SV start position standard deviation criterion in | +| | cluster merging [2.5] | ++---------------------+------------------------------------------------------------------------+ + + Advanced Options ---------------- -+----------------------------------------+------------------------------------------------------------------------------+ -| Parameter | Description | -+========================================+==============================================================================+ -| Mosaic | Set Sniffles run mode to detect rare, somatic and mosaic SVs (default: False)| -+----------------------------------------+------------------------------------------------------------------------------+ ++-------------+--------------------------------------------------------------------------------+ +| Parameter | Description | ++=============+================================================================================+ +| Mosaic | Set Sniffles run mode to detect rare, somatic and mosaic SVs (default: False)| ++-------------+--------------------------------------------------------------------------------+ + + +---- + +VCF information fields from the VCF header +****************************************** ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| Field | Type | Description | ++==================+===========+===============================================================================================+ +| PRECISE | Flag | Structural variation with precise breakpoints | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| IMPRECISE | Flag | Structural variation with imprecise breakpoints | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| MOSAIC | Flag | Structural variation classified as putative mosaic | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| SVLEN | Integer | Length of structural variation | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| SVTYPE | String | Type of structural variation | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| CHR2 | String | Mate chromsome for BND SVs | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| SUPPORT | Integer| Number of reads supporting the structural variation | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| SUPPORT_INLINE | Integer| Number of reads supporting an INS/DEL SV (non-split events only) | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| SUPPORT_LONG | Integer| Number of soft-clipped reads putatively supporting the long insertion SV | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| END | Integer| End position of structural variation | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| STDEV_POS | Float | Standard deviation of structural variation start position | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| STDEV_LEN | Float | Standard deviation of structural variation length | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| COVERAGE | Float | Coverage near upstream start, center, end, downstream of structural variation | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| STRAND | String | Strands of supporting reads for structural variant | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| AC | Integer| Allele count summed up over all samples | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| SUPP_VEC | String | List of read support for all samples | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| CONSENSUS_SUP | Integer| Number of reads that support the generated insertion (INS) consensus sequence | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| RNAMES | String | Names of supporting reads (if enabled with --output-rnames) | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| AF | Float | Allele Frequency | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| NM | Float | Mean number of query alignment length adjusted mismatches of supporting reads | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ +| PHASE | String | Phasing information derived from supporting reads | ++------------------+-----------+-----------------------------------------------------------------------------------------------+ -Output + +---- + + +Source ****** -VCF Info field description - -Sniffles report multiple information in the Info field. The entries are delimited by: - -+-------------------+------------------------------------------------------------------------------------------------------+ -| IMPRECISE/PRECISE | Indicates the confidence of the exact breakpoint positions (bp). | -+-------------------+------------------------------------------------------------------------------------------------------+ -| CHR2= | The chromosome of the second breakpoint of the SV reported. | -+-------------------+------------------------------------------------------------------------------------------------------+ -| END= | The position (bp) of the second breakpoint of the SV reported. | -+-------------------+------------------------------------------------------------------------------------------------------+ -| ZMW= | For PacBio based reads, shows the number of ZMW that support the SV. | -+-------------------+------------------------------------------------------------------------------------------------------+ -| SVTYPE= | The type of the SV. (see Alt field above) | -+-------------------+------------------------------------------------------------------------------------------------------+ -| SUPTYPE= | Indicates what evidence supports the SVs (SR: Split Reads, AL: Alignment, NR: Noisy Region). | -+-------------------+------------------------------------------------------------------------------------------------------+ -| STD_quant_start= | The standard deviation of the start breakpoints. | -+-------------------+------------------------------------------------------------------------------------------------------+ -| STD_quant_stop= | The standard deviation of the stop breakpoints. | -+-------------------+------------------------------------------------------------------------------------------------------+ -| RNAMES= | A comma separated list of read names that support the SV event. Controlled by -n Parameter. | -+-------------------+------------------------------------------------------------------------------------------------------+ -| SVLEN= | Indicates the length of SVs. | -+-------------------+------------------------------------------------------------------------------------------------------+ -| STRANDS= | Strand information at both breakpoints. | -+-------------------+------------------------------------------------------------------------------------------------------+ -| SEQ= | If reportable shows the sequence of the indels. | -+-------------------+------------------------------------------------------------------------------------------------------+ -| RE= | Number of reads supporting the variance. | -+-------------------+------------------------------------------------------------------------------------------------------+ -| AF= | Allele frequency (only if run with –genotype) | -+-------------------+------------------------------------------------------------------------------------------------------+ - -Source: https://github.com/fritzsedlazeck/Sniffles +https://github.com/fritzsedlazeck/Sniffles + ]]> diff --git a/tools/sniffles/test-data/expected_outcome3.vcf b/tools/sniffles/test-data/expected_outcome3.vcf index 397a6ea9969..7e025bfc75a 100644 --- a/tools/sniffles/test-data/expected_outcome3.vcf +++ b/tools/sniffles/test-data/expected_outcome3.vcf @@ -1,7 +1,7 @@ ##fileformat=VCFv4.2 ##source=Sniffles2_2.4 -##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpy46o57ly/job_working_directory/000/6/outputs/dataset_e1aae210-b20c-453b-91cd-8b3e215c9cbf.dat --allow-overwrite --minsupport 1 --max-splits-kb 0.1 --minsvlen 50 --mapq 20 --min-alignment-length 100 --cluster-binsize 100 --cluster-r 2.5" -##fileDate="2024/09/26 18:22:15" +##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpbu008nw6/job_working_directory/000/6/outputs/dataset_85e708bb-74e2-4686-8dca-f0e9404b4e44.dat --allow-overwrite --minsupport 1 --max-splits-kb 0.1 --minsvlen 50 --mapq 20 --min-alignment-length 100 --cluster-binsize 100 --cluster-r 2.5" +##fileDate="2024/09/28 23:19:48" ##contig= ##contig= ##contig= diff --git a/tools/sniffles/test-data/expected_outcome4.vcf b/tools/sniffles/test-data/expected_outcome4.vcf index dbd43aa661f..fd2cc1d8cc7 100644 --- a/tools/sniffles/test-data/expected_outcome4.vcf +++ b/tools/sniffles/test-data/expected_outcome4.vcf @@ -1,7 +1,7 @@ ##fileformat=VCFv4.2 ##source=Sniffles2_2.4 -##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpy46o57ly/job_working_directory/000/8/outputs/dataset_ffe443bd-f07b-4644-a417-8bd2aec4cfab.dat --allow-overwrite --minsupport auto --max-splits-kb 0.1 --minsvlen 50 --mapq 20 --min-alignment-length 100 --cluster-binsize 5 --cluster-r 2.5" -##fileDate="2024/09/26 18:22:53" +##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpbu008nw6/job_working_directory/000/8/outputs/dataset_76b2ed7a-d091-4613-bda7-505cd86d4277.dat --allow-overwrite --minsupport auto --max-splits-kb 0.1 --minsvlen 50 --mapq 20 --min-alignment-length 100 --cluster-binsize 5 --cluster-r 2.5" +##fileDate="2024/09/28 23:20:28" ##contig= ##contig= ##contig= diff --git a/tools/sniffles/test-data/expected_outcome5.vcf b/tools/sniffles/test-data/expected_outcome5.vcf index 2515bd3097a..cd2c7e50003 100644 --- a/tools/sniffles/test-data/expected_outcome5.vcf +++ b/tools/sniffles/test-data/expected_outcome5.vcf @@ -1,7 +1,7 @@ ##fileformat=VCFv4.2 ##source=Sniffles2_2.4 -##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpy46o57ly/job_working_directory/000/10/outputs/dataset_8b1d2d1f-49f4-47d9-8390-b933099f1342.dat --allow-overwrite --minsupport auto --max-splits-kb 0.1 --minsvlen 50 --mapq 20 --min-alignment-length 100 --cluster-binsize 100 --cluster-r 2.5 --mosaic" -##fileDate="2024/09/26 18:23:34" +##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpbu008nw6/job_working_directory/000/10/outputs/dataset_a9aaaabe-54e2-4f60-9a73-0454076bd7c5.dat --allow-overwrite --minsupport auto --max-splits-kb 0.1 --minsvlen 50 --mapq 20 --min-alignment-length 100 --cluster-binsize 100 --cluster-r 2.5 --mosaic" +##fileDate="2024/09/28 23:21:10" ##contig= ##contig= ##contig= diff --git a/tools/sniffles/test-data/expected_outcome6.vcf b/tools/sniffles/test-data/expected_outcome6.vcf index 00440cf40fc..f30fa668b4e 100644 --- a/tools/sniffles/test-data/expected_outcome6.vcf +++ b/tools/sniffles/test-data/expected_outcome6.vcf @@ -1,7 +1,7 @@ ##fileformat=VCFv4.2 ##source=Sniffles2_2.4 -##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpy46o57ly/job_working_directory/000/13/outputs/dataset_43c28376-bced-457b-9bc3-79b482047f0a.dat --allow-overwrite --reference /tmp/tmpy46o57ly/files/d/8/7/dataset_d879002d-9f55-45f7-a278-e6c9b6881fe8.dat --minsupport auto --max-splits-kb 0.1 --minsvlen 50 --mapq 20 --min-alignment-length 100 --cluster-binsize 100 --cluster-r 2.5" -##fileDate="2024/09/26 18:24:13" +##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpbu008nw6/job_working_directory/000/13/outputs/dataset_93c07e69-9ce4-4394-84c8-8a51cb2e2c89.dat --allow-overwrite --reference reference.fa --minsupport auto --max-splits-kb 0.1 --minsvlen 50 --mapq 20 --min-alignment-length 100 --cluster-binsize 100 --cluster-r 2.5" +##fileDate="2024/09/28 23:21:51" ##contig= ##contig= ##contig= diff --git a/tools/sniffles/test-data/expected_output.vcf b/tools/sniffles/test-data/expected_output.vcf index 5202433f18b..4248228b629 100644 --- a/tools/sniffles/test-data/expected_output.vcf +++ b/tools/sniffles/test-data/expected_output.vcf @@ -1,7 +1,7 @@ ##fileformat=VCFv4.2 ##source=Sniffles2_2.4 -##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpy46o57ly/job_working_directory/000/2/outputs/dataset_b3c7245e-3129-45a7-9a94-f6e837049557.dat --allow-overwrite --minsupport auto --max-splits-kb 0.1 --minsvlen 50 --mapq 20 --min-alignment-length 100 --cluster-binsize 100 --cluster-r 2.5" -##fileDate="2024/09/26 18:20:57" +##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpbu008nw6/job_working_directory/000/2/outputs/dataset_c3cc0dff-254a-4e6b-837f-fa8a4db7f051.dat --allow-overwrite --minsupport auto --max-splits-kb 0.1 --minsvlen 50 --mapq 20 --min-alignment-length 100 --detect-large-ins 0 --cluster-binsize 100 --cluster-r 2.5" +##fileDate="2024/09/28 23:18:28" ##contig= ##contig= ##contig= diff --git a/tools/sniffles/test-data/expected_output2.vcf b/tools/sniffles/test-data/expected_output2.vcf index ea8f80517f7..912799f5f9d 100644 --- a/tools/sniffles/test-data/expected_output2.vcf +++ b/tools/sniffles/test-data/expected_output2.vcf @@ -1,7 +1,7 @@ ##fileformat=VCFv4.2 ##source=Sniffles2_2.4 -##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpy46o57ly/job_working_directory/000/4/outputs/dataset_f76d3b7c-c912-4135-91ca-b3ca11aa77f2.dat --allow-overwrite --minsupport auto --max-splits-kb 0.1 --minsvlen 50 --mapq 0 --min-alignment-length 100 --cluster-binsize 100 --cluster-r 2.5" -##fileDate="2024/09/26 18:21:36" +##command="/home/ross/miniconda3/envs/__sniffles@2.4/bin/sniffles -t 1 -i input.bam -v /tmp/tmpbu008nw6/job_working_directory/000/4/outputs/dataset_02006b89-2710-4fcc-9ac1-52a711eebee9.dat --allow-overwrite --minsupport auto --max-splits-kb 0.1 --minsvlen 50 --mapq 0 --min-alignment-length 100 --cluster-binsize 100 --cluster-r 2.5" +##fileDate="2024/09/28 23:19:08" ##contig= ##contig= ##contig=