Merge pull request #395 from genomic-medicine-sweden/fuseq_wes_update

feat: Fuseq wes update

config/config.yaml

@@ -127,7 +127,7 @@ filter_vcf:
   germline: "config/filters/config_hard_filter_germline_vep105.yaml"
 
 filter_fuseq_wes:
-  min_support: 30
+  min_support: 50
   filter_on_fusiondb: True
 
 fuseq_wes:
@@ -170,9 +170,6 @@ gatk_mutect2_gvcf:
 gatk_mutect2_merge_stats:
   container: "docker://hydragenetics/gatk4:4.1.9.0"
 
-gene_fuse:
-  container: "docker://hydragenetics/genefuse:0.6.1"
-
 hotspot_report:
   report_config: "config/reports/hotspot_report.yaml"
   levels:
@@ -289,9 +286,6 @@ report_fusions:
   star_fusion_low_support: 2
   star_fusion_low_support_inframe: 6
 
-report_gene_fuse:
-  min_unique_reads: 6
-
 samtools_merge_bam:
   extra: "-c -p"
 

config/output_files.yaml

@@ -247,18 +247,6 @@ files:
     types:
       - T
       - N
-  - name: GeneFuse report
-    input: fusions/report_gene_fuse/{sample}_{type}.gene_fuse_report.tsv
-    output: results/dna/{sample}_{type}/fusion/{sample}_{type}.gene_fuse_report.tsv
-    types:
-      - T
-      - N
-  - name: GeneFuse fusions TXT
-    input: fusions/gene_fuse/{sample}_{type}_gene_fuse_fusions.txt
-    output: results/dna/{sample}_{type}/additional_files/fusion/{sample}_{type}.gene_fuse_fusions.txt
-    types:
-      - T
-      - N
   - name: ID-SNP VCF RNA
     input: snv_indels/bcftools_id_snps/{sample}_{type}.id_snps.vcf
     output: results/rna/{sample}_{type}/id_snps/{sample}_{type}.id_snps.vcf

docs/dna_fusions.md

@@ -6,53 +6,8 @@ See the [fusions hydra-genetics module](https://hydra-genetics-fusions.readthedo
 
 ## Pipeline output files:
 
-* `results/dna/fusion/{sample}_{type}.gene_fuse_report.tsv`
 * `results/dna/fusion/{sample}_{type}.fuseq_wes.report.csv`
 
-## Fusions calling using GeneFuse
-DNA fusion calling is performed by **[GeneFuse](https://github.com/OpenGene/GeneFuse)** v0.6.1 on fastq-files. It uses a gene transcript target file to limit the number of targets to analyze.
-
-### Configuration
-
-**References**
-
-* [Fasta reference](references.md#genefuse_fasta) genome
-* [Gene transcript](references.md#genefuse_transcripts) file with genomic positions for all exons include in the analysis  
-
-<br />
-**Cluster resources**
-
-| **Options** | **Value** |
-|-------------|-|
-| mem_mb | 36864 |
-| mem_per_cpu | 6144 |
-| threads | 6 |
-| time | "8:00:00" |
-
-## GeneFuse Filtering and report
-The output from GeneFuse is filtered and then reported into a fusion report using the in-house script [report_gene_fuse.py](https://github.com/genomic-medicine-sweden/Twist_Solid/blob/develop/workflow/scripts/report_gene_fuse.py) ([rule and config](softwares.md#report_gene_fuse)). The following filter criteria is used:
-
-* Fusions must have at least 6 unique supporting reads.
-* Very noisy fusion pairs found in almost all samples (defined in [`filter_fusions_20230214.csv`](references.md#genefuse_filter_fusions)) are removed:
-    - NPM1::ALK
-    - CLTC::NTRK3
-    - MSH2_ALK
-    - MSH2_HIP1
-* Noisy fusion pairs found in some samples (defined in [`filter_fusions_20230214.csv`](references.md#genefuse_filter_fusions)) are filtered individually on the number of uniquely supporting reads:
-    - LMNA::EZR 9
-    - ABL1::STRN 7
-    - EZR::ALK 8
-    - RSPO2::BRAF 8
-    - LMNA::HIP1 12
-    - NPM1::BICC1 11
-    - RSPO2::ERG 13
-
-### Result file
-
-* `results/dna/fusion/{sample}_{type}.gene_fuse_report.tsv`
-
-<br />
-
 ## Fusions calling using FuSeq_WES
 DNA fusion calling is performed by **[FuSeq_WES](https://github.com/nghiavtr/FuSeq_WES)** v1.0.1 on bam-files. It uses a gene transcript target file to limit the number of targets to analyze.
 
@@ -91,6 +46,7 @@ The output from FuSeq_WES is filtered and then reported into a fusion report usi
 |-------------|-|-|
 | filter_on_fusiondb | True | Only keep fusions found in the fusion database |
 | gene_white_list | [`fuseq_wes_gene_white_list.txt`](references.md#fuseq_wes_white_list) | Only keep fusions with at least one gene in the gene white list |
+| gene_fusion_black_list | [`false_positive_fusion_pairs.txt`](references.md#gene_fusion_black_list) | Remove fusions pairs in fusion pair gene black list |
 | gtf | [`hg19.refGene.gtf`](references.md#filter_report_fuseq_wes) | Transcript annotation |
 | min_support | 30 | Minimal total number of supporting reads |
 | transcript_black_list | [`fuseq_wes_transcript_black_list.txt`](references.md#fuseq_wes_transcript_black_list) | Transcripts that should not be used in annotation |

docs/references.md

@@ -79,6 +79,7 @@ The following reference files, panel of normals and design files are needed to r
 |_ _| <div id="fuseq_wes_paralog_db">paralog database</div> | `ensmbl_paralogs_grch37.RData` |
 | <div id="filter_report_fuseq_wes">filter_report_fuseq_wes</div> | transcript annotation | `hg19.refGene.gtf` |
 | | <div id="fuseq_wes_white_list">gene white list</div> | `fuseq_wes_gene_white_list.txt` |
+| | <div id="gene_fusion_black_list">fusion gene pair black list</div> | `false_positive_fusion_pairs.txt` |
 |_ _| <div id="fuseq_wes_transcript_black_list">transcript black list</div> | `fuseq_wes_transcript_black_list.txt` |
 | <div id="hotspot_file">hotspot_annotation</div> | hotspots | `Hotspots_combined_regions_nodups.csv` |
 | <div id="hotspot_report">hotspot_report</div> | hotspot_mutations | `Hotspots_combined_regions_nodups.csv` |
@@ -296,7 +297,7 @@ singularity docker://hydragenetics/purecn:2.2.0 Rscript $PURECN/IntervalFile.R -
 | intervals | Target interval file | File created by the command described above |
 
 ## Pipeline specific files
-These are design files and other pipeline specific only available to download from the Uppsala Owncloud solution.
+These are design files and other pipeline specific files only available to download from out [git](https://github.com/genomic-medicine-sweden/Twist_Solid_pipeline_files) or the Uppsala Owncloud solution.
 
 | File type | File | Description |
 |-|-|-|
@@ -312,6 +313,7 @@ These are design files and other pipeline specific only available to download fr
 | | `filter_fusions_20221114.csv` | Filtering criteria for false positive prone fusion partners |
 | FuSeq_WES | `fuseq_params.txt` | Filtering parameters used by FuSeq_WES |
 | FuSeq_WES_report | `fuseq_wes_gene_white_list.txt` | Gene list for filtering of fusion |
+| | `false_positive_fusion_pairs.txt` | Gene list for filtering of fusion |
 |_ _| `fuseq_wes_transcript_black_list.txt` | Transcripts that should not be used in annotation |
 | CNVkit | `cnvkit_germline_blacklist_20221221.bed` | List of regions excluded from the germline vcf file |
 | GATK CNV | `gnomad_SNP_0.001_target.annotated.interval_list` | Bed file with CNV backbone SNPs which are selected from <br />GnomAD with over 0.1% global population frequency |

docs/softwares.md

@@ -208,29 +208,6 @@ Make a combined report of filtered fusion calls from all RNA fusion callers. App
 
 ---
 
-## report_gene_fuse
-The output from GeneFuse is filtered and then made into a fusion report. See further [DNA fusions report info](dna_fusions.md#filtering-and-report).
-
-### :snake: Rule
-
-#SNAKEMAKE_RULE_SOURCE__report_gene_fuse__report_gene_fuse#
-
-#### :left_right_arrow: input / output files
-
-#SNAKEMAKE_RULE_TABLE__report_gene_fuse__report_gene_fuse#
-
-### :wrench: Configuration
-
-#### Software settings (`config.yaml`)
-
-#CONFIGSCHEMA__report_gene_fuse#
-
-#### Resources settings (`resources.yaml`)
-
-#RESOURCESSCHEMA__report_gene_fuse#
-
----
-
 ## purecn_modify_vcf
 Increases the MQB (mean base quality) value by 5 as the qualities are so bad for our samples.
 

workflow/Snakefile

@@ -15,7 +15,6 @@ include: "rules/fix_vcf_ad_for_qci.smk"
 include: "rules/hotspot_report.smk"
 include: "rules/house_keeping_gene_coverage.smk"
 include: "rules/purecn_modify_vcf.smk"
-include: "rules/report_gene_fuse.smk"
 include: "rules/report_fusions.smk"
 
 

workflow/schemas/config.schema.yaml

@@ -273,15 +273,6 @@ properties:
         type: string
         description: parameters that should be forwarded
 
-  gene_fuse:
-    type: object
-    properties:
-      genes:
-        type: string
-        description: path to gene files used by gene_fuse
-      required:
-        - genes
-
   house_keeping_gene_coverage:
     type: object
     properties:
@@ -560,19 +551,6 @@ properties:
         type: integer
         description: lower limit of supporting reads to flag filter fusion that are inframe for StarFusion
 
-  report_gene_fuse:
-    description: report results from genefuse
-    type: object
-    properties:
-      filter_fusions:
-        type: string
-        description: file specifying fusions that should be filtered completely (value 0 in column 2) or have higher limit (value >0 in column 2)
-      min_unique_reads:
-        type: integer
-        description: lower limit of uniquely supporting reads to report fusion
-    required:
-      - min_unique_reads
-
   trimmer_software:
     description: trimmer software that should be used
     pattern: "^(fastp_pe|None)$"
@@ -612,13 +590,11 @@ required:
   - filter_vcf
   - gatk_collect_allelic_counts
   - gatk_denoise_read_counts
-  - gene_fuse
   - hotspot_annotation
   - hotspot_info
   - hotspot_report
   - msisensor_pro
   - multiqc
   - reference
-  - report_gene_fuse
   - trimmer_software
   - vep

workflow/schemas/resources.schema.yaml

@@ -228,9 +228,9 @@ properties:
         type: integer
         description:  number of threads to be available
 
-  report_gene_fuse:
+  sample_mixup_check:
     type: object
-    description: resource definitions for generating a gene fuse report
+    description: resource definitions for sample_mixup_check
     properties:
       mem_mb:
         type: integer
@@ -248,25 +248,5 @@ properties:
         type: integer
         description:  number of threads to be available
 
-  sample_mixup_check:
-    type: object
-    description: resource definitions for sample_mixup_check
-    properties:
-      mem_mb:
-        type: integer
-        description: max memory in MB to be available
-      mem_per_cpu:
-        type: integer
-        description: memory in MB used per cpu
-      partition:
-        type: string
-        description: partition to use on cluster
-      threads:
-        type: integer
-        description: number of threads to be available
-      time:
-        type: string
-        description: max execution time
-
 required:
   - default_resources

workflow/schemas/rules.schema.yaml

@@ -230,25 +230,6 @@ properties:
             type: string
             description: Excel frienly text report with filtered fusion calls from respective caller
 
-  report_gene_fuse:
-    type: object
-    description: input and output parameters for report_gene_fuse
-    properties:
-      input:
-        type: object
-        description: list of inputs
-        properties:
-          fusions:
-            type: string
-            description: Called fusions by GeneFuse
-      output:
-        type: object
-        description: list of outputs
-        properties:
-          report:
-            type: string
-            description: Excel friendly text report with filtered fusion calls from GeneFuse
-
   purecn_modify_vcf:
     type: object
     description: input and output parameters for purecn_modify_vcf

workflow/schemas/singularity.schema.yaml

@@ -206,17 +206,6 @@ properties:
       required:
         - container
 
-  gene_fuse:
-    type: object
-    properties:
-      container:
-        type: string
-        description: name or path to a default docker/singularity container
-        pattern: >-
-            hydragenetics/genefuse:0\.6\.1$|hydragenetics_genefuse_0\.6\.1\.sif$
-      required:
-        - container
-
   manta_config_t:
     type: object
     properties:
@@ -455,7 +444,6 @@ required:
   - gatk_mutect2
   - gatk_mutect2_gvcf
   - gatk_model_segments
-  - gene_fuse
   - manta_config_t
   - manta_run_workflow_t
   - mosdepth_bed