diff --git a/.gitignore b/.gitignore
index 8c51880..4d326e9 100644
--- a/.gitignore
+++ b/.gitignore
@@ -13,4 +13,4 @@ test.csv
 test2.csv
 .nf-test
 .nf-test.log
-nf-test-report.tap
+nf-test-report*
diff --git a/.zenodo.json b/.zenodo.json
index d48d7e5..ce10389 100644
--- a/.zenodo.json
+++ b/.zenodo.json
@@ -1,6 +1,6 @@
 {
     "upload_type": "software", 
-    "description": "v0.6.1 Release. See https://github.com/TheJacksonLaboratory/cs-nf-pipelines/wiki",
+    "description": "See https://github.com/TheJacksonLaboratory/cs-nf-pipelines/wiki",
     "title": "cs-nf-pipelines",
     "creators": [
         {
@@ -36,6 +36,10 @@
             "affiliation": "The Jackson Laboratory",
             "name": "Gabriel Rech"
         },
+        {
+            "affiliation": "The Jackson Laboratory",
+            "name": "Ardian Ferraj"
+        },
         {
             "affiliation": "The Jackson Laboratory",
             "name": "Anuj Srivastava"
diff --git a/README.md b/README.md
index 7946bd1..57b0b3e 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.11068737.svg)](https://doi.org/10.5281/zenodo.11068737)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.11068736.svg)](https://doi.org/10.5281/zenodo.11068736)
 
 # JAX NGS Operations Nextflow DSL2 Pipelines
 
diff --git a/ReleaseNotes.md b/ReleaseNotes.md
index 5484b84..bf97c6f 100644
--- a/ReleaseNotes.md
+++ b/ReleaseNotes.md
@@ -1,5 +1,30 @@
 # RELEASE NOTES
 
+## Release 0.6.3
+
+In this release we change the read disambiguation tool Xenome for Xengsort. Extensive benchmarking shows high concordance among results obtained from both tools.  
+
+Additionally, we correct an issue with the human PTA workflow when running the combination of the `--pdx` and `--split_fastq` options. Data run with this combination of options from version 0.6.0-0.6.2 should be re-run. 
+
+### Pipelines Added:
+
+None
+
+### Modules Added:
+
+1. xengsort/xengsort_classify.nf
+1. xengsort/xengsort_index.nf
+
+### Pipeline Changes:
+
+1. Xengsort replaces Xenome for all PDX based workflows (RNAseq, RNA fusion, Hs PTA, Somatic WES, Somatic WES PTA)
+1. Correction made for the Human PTA when running the combination of the `--pdx` and `--split_fastq` options.
+
+### Module Changes:
+
+None
+
+
 ## Release 0.6.2
 
 In this minor release we adjust memory and wall clock statements, and modified `bin/pta/merge-caller-vcfs.r` to correct for an edge case related bug.
diff --git a/bin/help/pta.nf b/bin/help/pta.nf
index 84249b5..44a8276 100644
--- a/bin/help/pta.nf
+++ b/bin/help/pta.nf
@@ -12,8 +12,10 @@ The following are human specific parameters. To see help for mouse, add `--gen_o
 
 --csv_input | /<FILE_PATH> | CSV delimited sample sheet that controls how samples are processed. The required input header is: patient,sex,status,sampleID,lane,fastq_1,fastq_2. See the repository wiki (https://github.com/TheJacksonLaboratory/cs-nf-pipelines/wiki) for additional information. 
 
---xenome_prefix | /projects/compsci/omics_share/human/GRCh38/supporting_files/xenome/trans_human_GRCh38_84_NOD_based_on_mm10_k25| Xenome index for deconvolution of human and mouse reads. Used when `--pdx` is run. 
---pdx | false | Options: false, true. If specified, 'Xenome' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. 
+--pdx | false | Options: false, true. If specified, 'Xengsort' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. 
+--xengsort_host_fasta | '/projects/compsci/omics_share/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' | Xengsort host fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false.  
+--xengsort_idx_path | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xengsort' | Xengsort index for deconvolution of human and mouse reads. Used when `--pdx` is run. If `null`, Xengsort Index is run using ref_fa and host_fa.  
+--xengsort_idx_name | 'hg38_GRCm39-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index
 
 --deduplicate_reads | false | Options: false, true. If specified, run bbmap clumpify on input reads. Clumpify will deduplicate reads prior to trimming. This can help with mapping and downstream steps when analyzing high coverage WGS data. 
 
diff --git a/bin/help/rna_fusion.nf b/bin/help/rna_fusion.nf
index 073939a..00bbb40 100644
--- a/bin/help/rna_fusion.nf
+++ b/bin/help/rna_fusion.nf
@@ -17,7 +17,6 @@ Parameter | Default | Description
 
 --gen_org | mouse | Options: mouse and human.
 
---xenome_prefix | /projects/compsci/omics_share/human/GRCh38/supporting_files/xenome/trans_human_GRCh38_84_NOD_based_on_mm10_k25| Xenome index for deconvolution of human and mouse reads. Used when `--pdx` is run. 
 --read_length | 150 | Options: 75, 100, 150. Changed relative to sample read length.
 --star_index | /projects/omics_share/human/GRCh38/transcriptome/indices/rna_fusion/star/star-2.7.4a-150bp | STAR index used by several tools. Change the index relative to sample read length. Read length options: 75, 100, 150. 
 --star_fusion_star_index | /projects/omics_share/human/GRCh38/transcriptome/indices/rna_fusion/starfusion/star-150 | STAR-fusion index. Change the index relative to sample read length. Read length options: 75, 100, 150. 
@@ -47,7 +46,11 @@ Parameter | Default | Description
 --fusion_report_opt | null | Additional fusion-report options can be provided. 
 --databases | /projects/compsci/omics_share/human/GRCh38/supporting_files/rna_fusion_dbs | Fusion-report databases of known fusion events. Used in report generation only. 
 
---pdx | false | Options: false, true. If specified, 'Xenome' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. 
+--pdx | false | Options: false, true. If specified, 'Xengsort' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. 
+--ref_fa | '/projects/compsci/omics_share/human/GRCh38/genome/sequence/gatk/Homo_sapiens_assembly38.fasta'| Xengsort graft fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false.  
+--xengsort_host_fasta | '/projects/compsci/omics_share/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' | Xengsort host fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false.  
+--xengsort_idx_path | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xengsort' | Xengsort index for deconvolution of human and mouse reads. Used when `--pdx` is run. If `null`, Xengsort Index is run using ref_fa and host_fa.  
+--xengsort_idx_name | 'hg38_GRCm39-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index
 
 '''
 }
diff --git a/bin/help/rnaseq.nf b/bin/help/rnaseq.nf
index 3cae8ea..5229183 100644
--- a/bin/help/rnaseq.nf
+++ b/bin/help/rnaseq.nf
@@ -18,9 +18,6 @@ Parameter | Default | Description
 --gen_org | mouse | Options: mouse and human.
 --genome_build | 'GRCm38' | Mouse specific. Options: GRCm38 or GRCm39. If gen_org == human, build defaults to GRCm38.
 
---pdx | false | Options: true or false. If 'true' Xenome is run to remove mouse reads from samples. 
---xenome_prefix | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xenome/trans_human_GRCh38_84_NOD_based_on_mm10_k25' | Pre-compiled Xenome classification index files. Used if PDX analysis is specified. 
-
 --quality_phred | 15 | The quality value that is required for a base to pass. Default: 15 which is a phred quality score of >=Q15.
 --unqualified_perc | 40 | Percent of bases that are allowed to be unqualified (0~100). Default: 40 which is 40%.
 --detect_adapter_for_pe | false | If true, adapter auto-detection is used for paired end data. By default, paired-end data adapter sequence auto-detection is disabled as the adapters can be trimmed by overlap analysis. However, --detect_adapter_for_pe will enable it. Fastp will run a little slower if you specify the sequence adapters or enable adapter auto-detection, but usually result in a slightly cleaner output, since the overlap analysis may fail due to sequencing errors or adapter dimers.
@@ -50,8 +47,13 @@ Parameter | Default | Description
                  | Human: '/projects/omics_share/human/GRCh38/transcriptome/annotation/ensembl/v104/Homo_sapiens.GRCh38.104.chr_patch_hapl_scaff.rRNA.interval_list'
                  | The coverage metric calculation step requires this file. Refers to human assembly when --gen_org human. JAX users should not change this parameter.
 
---pdx | false | Options: false, true. If specified, 'Xenome' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. 
+--pdx | false | Options: false, true. If specified, 'Xengsort' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. 
 --classifier_table | '/projects/compsci/omics_share/human/GRCh38/supporting_files/rna_ebv_classifier/EBVlym_classifier_table_48.txt' | EBV expected gene signatures used in EBV classifier. Only used when '--pdx' is run. 
+--ref_fa | '/projects/compsci/omics_share/human/GRCh38/genome/sequence/gatk/Homo_sapiens_assembly38.fasta'| Xengsort graft fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false.  
+--xengsort_host_fasta | '/projects/compsci/omics_share/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' | Xengsort host fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false.  
+--xengsort_idx_path | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xengsort' | Xengsort index for deconvolution of human and mouse reads. Used when `--pdx` is run. If `null`, Xengsort Index is run using ref_fa and host_fa.  
+--xengsort_idx_name | 'hg38_GRCm39-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index
+
 
 There are two additional parameters that are human specific. They are: 
 
diff --git a/bin/help/somatic_wes.nf b/bin/help/somatic_wes.nf
index fd5704b..916b6c8 100644
--- a/bin/help/somatic_wes.nf
+++ b/bin/help/somatic_wes.nf
@@ -21,8 +21,10 @@ Parameter | Default | Description
 --unqualified_perc | 40 | Percent of bases that are allowed to be unqualified (0~100). Default: 40 which is 40%.
 --detect_adapter_for_pe | false | If true, adapter auto-detection is used for paired end data. By default, paired-end data adapter sequence auto-detection is disabled as the adapters can be trimmed by overlap analysis. However, --detect_adapter_for_pe will enable it. Fastp will run a little slower if you specify the sequence adapters or enable adapter auto-detection, but usually result in a slightly cleaner output, since the overlap analysis may fail due to sequencing errors or adapter dimers.
 
---pdx | false | Options: false, true. If specified, 'Xenome' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. 
---xenome_prefix | /projects/compsci/omics_share/human/GRCh38/supporting_files/xenome/trans_human_GRCh38_84_NOD_based_on_mm10_k25| Xenome index for deconvolution of human and mouse reads. Used when `--pdx` is run. 
+--pdx | false | Options: false, true. If specified, 'Xengsort' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. 
+--xengsort_host_fasta | '/projects/compsci/omics_share/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' | Xengsort host fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false.  
+--xengsort_idx_path = | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xengsort' | Xengsort index for deconvolution of human and mouse reads. Used when `--pdx` is run. If `null`, Xengsort Index is run using ref_fa and host_fa.  
+--xengsort_idx_name = | 'hg38_GRCm39-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index
 
 --genotype_targets | '/projects/compsci/omics_share/human/GRCh38/supporting_files/ancestry_panel/snp_panel_v2_targets_annotations.snpwt.bed.gz' | Target SNP bed file for the ancestry panel. Can contain annotation information. 
 --snpID_list | '/projects/compsci/omics_share/human/GRCh38/supporting_files/ancestry_panel/snp_panel_v2.list' | Target SNPs in list used in BCFtools filtering step
diff --git a/bin/help/somatic_wes_pta.nf b/bin/help/somatic_wes_pta.nf
index 820c4af..f272e15 100644
--- a/bin/help/somatic_wes_pta.nf
+++ b/bin/help/somatic_wes_pta.nf
@@ -21,8 +21,10 @@ Parameter | Default | Description
 --unqualified_perc | 40 | Percent of bases that are allowed to be unqualified (0~100). Default: 40 which is 40%.
 --detect_adapter_for_pe | false | If true, adapter auto-detection is used for paired end data. By default, paired-end data adapter sequence auto-detection is disabled as the adapters can be trimmed by overlap analysis. However, --detect_adapter_for_pe will enable it. Fastp will run a little slower if you specify the sequence adapters or enable adapter auto-detection, but usually result in a slightly cleaner output, since the overlap analysis may fail due to sequencing errors or adapter dimers.
 
---pdx | false | Options: false, true. If specified, 'Xenome' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. 
---xenome_prefix | /projects/compsci/omics_share/human/GRCh38/supporting_files/xenome/trans_human_GRCh38_84_NOD_based_on_mm10_k25| Xenome index for deconvolution of human and mouse reads. Used when `--pdx` is run. 
+--pdx | false | Options: false, true. If specified, 'Xengsort' is run on reads to deconvolute human and mouse reads. Human only reads are used in analysis. 
+--xengsort_host_fasta | '/projects/compsci/omics_share/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa' | Xengsort host fasta file. Used by Xengsort Index when `--pdx` is run, and xengsort_idx_path is `null` or false.  
+--xengsort_idx_path = | '/projects/compsci/omics_share/human/GRCh38/supporting_files/xengsort' | Xengsort index for deconvolution of human and mouse reads. Used when `--pdx` is run. If `null`, Xengsort Index is run using ref_fa and host_fa.  
+--xengsort_idx_name = | 'hg38_GRCm39-NOD_ShiLtJ' | Xengsort index name associated with files located in `xengsort_idx_path` or name given to outputs produced by Xengsort Index
 
 --genotype_targets | '/projects/compsci/omics_share/human/GRCh38/supporting_files/ancestry_panel/snp_panel_v2_targets_annotations.snpwt.bed.gz' | Target SNP bed file for the ancestry panel. Can contain annotation information. 
 --snpID_list | '/projects/compsci/omics_share/human/GRCh38/supporting_files/ancestry_panel/snp_panel_v2.list' | Target SNPs in list used in BCFtools filtering step
diff --git a/bin/log/pta.nf b/bin/log/pta.nf
index 2e98e8f..c3a0219 100644
--- a/bin/log/pta.nf
+++ b/bin/log/pta.nf
@@ -34,7 +34,9 @@ ______________________________________________________
 --quality_phred                 ${params.quality_phred}
 --unqualified_perc              ${params.unqualified_perc}
 --detect_adapter_for_pe         ${params.detect_adapter_for_pe}
---xenome_prefix                 ${params.xenome_prefix}
+--xengsort_host_fasta           ${params.xengsort_host_fasta}
+--xengsort_idx_path             ${params.xengsort_idx_path}
+--xengsort_idx_name             ${params.xengsort_idx_name}
 --ref_fa                        ${params.ref_fa}
 --ref_fa_indices                ${params.ref_fa_indices}
 --ref_fa_dict                   ${params.ref_fa_dict}
diff --git a/bin/log/rna_fusion.nf b/bin/log/rna_fusion.nf
index fbe1cfb..13695ca 100644
--- a/bin/log/rna_fusion.nf
+++ b/bin/log/rna_fusion.nf
@@ -27,7 +27,10 @@ ______________________________________________________
 --keep_intermediate                 ${params.keep_intermediate}
 -c                                  ${params.config}
 --multiqc_config                    ${params.multiqc_config}
---xenome_prefix                     ${params.xenome_prefix}
+--ref_fa                            ${params.ref_fa}
+--xengsort_host_fasta               ${params.xengsort_host_fasta}
+--xengsort_idx_path                 ${params.xengsort_idx_path}
+--xengsort_idx_name                 ${params.xengsort_idx_name}
 --read_length                       ${params.read_length}
 --star_index                        ${params.star_index}
 --star_fusion_star_index            ${params.star_fusion_star_index}
diff --git a/bin/log/rnaseq.nf b/bin/log/rnaseq.nf
index 3a851c7..c788944 100644
--- a/bin/log/rnaseq.nf
+++ b/bin/log/rnaseq.nf
@@ -47,7 +47,10 @@ ______________________________________________________
 --detect_adapter_for_pe      ${params.detect_adapter_for_pe}
 
 --pdx                        ${params.pdx}
---xenome_prefix              ${params.xenome_prefix}
+--ref_fa                     ${params.ref_fa}
+--xengsort_host_fasta        ${params.xengsort_host_fasta}
+--xengsort_idx_path          ${params.xengsort_idx_path}
+--xengsort_idx_name          ${params.xengsort_idx_name}
 
 --strandedness_ref           ${params.strandedness_ref}
 --strandedness_gtf           ${params.strandedness_gtf}
diff --git a/bin/log/somatic_wes.nf b/bin/log/somatic_wes.nf
index 02cf225..51e5484 100644
--- a/bin/log/somatic_wes.nf
+++ b/bin/log/somatic_wes.nf
@@ -27,7 +27,9 @@ ______________________________________________________
 --pubdir                        ${params.pubdir}
 --organize_by                   ${params.organize_by}
 --pdx                           ${params.pdx}
---xenome_index                  ${params.xenome_prefix}
+--xengsort_host_fasta           ${params.xengsort_host_fasta}
+--xengsort_idx_path             ${params.xengsort_idx_path}
+--xengsort_idx_name             ${params.xengsort_idx_name}
 --ref_fa                        ${params.ref_fa}
 --ref_fa_indices                ${params.ref_fa_indices}
 --quality_phred                 ${params.quality_phred}
diff --git a/bin/log/somatic_wes_pta.nf b/bin/log/somatic_wes_pta.nf
index 573e85d..dd3ea6b 100644
--- a/bin/log/somatic_wes_pta.nf
+++ b/bin/log/somatic_wes_pta.nf
@@ -22,7 +22,9 @@ ______________________________________________________
 --pubdir                        ${params.pubdir}
 --organize_by                   ${params.organize_by}
 --pdx                           ${params.pdx}
---xenome_index                  ${params.xenome_prefix}
+--xengsort_host_fasta           ${params.xengsort_host_fasta}
+--xengsort_idx_path             ${params.xengsort_idx_path}
+--xengsort_idx_name             ${params.xengsort_idx_name}
 --ref_fa                        ${params.ref_fa}
 --ref_fa_indices                ${params.ref_fa_indices}
 --quality_phred                 ${params.quality_phred}
diff --git a/bin/shared/multiqc/pta_multiqc.yaml b/bin/shared/multiqc/pta_multiqc.yaml
index e07d3d8..216616a 100644
--- a/bin/shared/multiqc/pta_multiqc.yaml
+++ b/bin/shared/multiqc/pta_multiqc.yaml
@@ -8,7 +8,7 @@ export_plots: true
 module_order:
   - fastp
   - fastqc
-  - xenome
+  - xengsort
   - conpair
   - gatk
   - picard
diff --git a/bin/shared/multiqc/rna_fusion_multiqc.yaml b/bin/shared/multiqc/rna_fusion_multiqc.yaml
index 3ba15cc..5d8ff97 100644
--- a/bin/shared/multiqc/rna_fusion_multiqc.yaml
+++ b/bin/shared/multiqc/rna_fusion_multiqc.yaml
@@ -7,7 +7,7 @@ export_plots: true
 
 module_order:
   - fastqc
-  - xenome
+  - xengsort
   - custom_content
 
 table_columns_visible:
diff --git a/bin/shared/multiqc/rnaseq_multiqc.yaml b/bin/shared/multiqc/rnaseq_multiqc.yaml
index 9022b85..8eb7a03 100644
--- a/bin/shared/multiqc/rnaseq_multiqc.yaml
+++ b/bin/shared/multiqc/rnaseq_multiqc.yaml
@@ -8,7 +8,7 @@ export_plots: true
 module_order:
   - fastp
   - fastqc
-  - xenome
+  - xengsort
   - star
   - rsem
   - picard
diff --git a/bin/shared/multiqc/somatic_wes_multiqc.yaml b/bin/shared/multiqc/somatic_wes_multiqc.yaml
index fcf2d7c..f3553ec 100644
--- a/bin/shared/multiqc/somatic_wes_multiqc.yaml
+++ b/bin/shared/multiqc/somatic_wes_multiqc.yaml
@@ -8,7 +8,7 @@ export_plots: true
 module_order:
   - fastp
   - fastqc
-  - xenome
+  - xengsort
   - gatk
   - picard
 
diff --git a/bin/shared/multiqc/somatic_wes_pta_multiqc.yaml b/bin/shared/multiqc/somatic_wes_pta_multiqc.yaml
index fcf2d7c..f3553ec 100644
--- a/bin/shared/multiqc/somatic_wes_pta_multiqc.yaml
+++ b/bin/shared/multiqc/somatic_wes_pta_multiqc.yaml
@@ -8,7 +8,7 @@ export_plots: true
 module_order:
   - fastp
   - fastqc
-  - xenome
+  - xengsort
   - gatk
   - picard
 
diff --git a/config/pta.config b/config/pta.config
index 2e8c555..f72fa3d 100644
--- a/config/pta.config
+++ b/config/pta.config
@@ -29,8 +29,10 @@ params {
     // NOTE: For PE data, the adapter sequence auto-detection is disabled by default since the adapters can be trimmed by overlap analysis. However, you can specify --detect_adapter_for_pe to enable it.
     //       For PE data, fastp will run a little slower if you specify the sequence adapters or enable adapter auto-detection, but usually result in a slightly cleaner output, since the overlap analysis may fail due to sequencing errors or adapter dimers.
 
-    // Xenome index
-    xenome_prefix=params.reference_cache+'/human/GRCh38/supporting_files/xenome/hg38_broad_NOD_based_on_mm10_k25'
+    // xengsort index  
+    xengsort_host_fasta = params.reference_cache+'/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa'
+    xengsort_idx_path = params.reference_cache+'/human/GRCh38/supporting_files/xengsort'
+    xengsort_idx_name = 'hg38_GRCm39-NOD_ShiLtJ'
 
     // Reference fasta
     ref_fa = params.reference_cache+'/human/GRCh38/genome/sequence/gatk/Homo_sapiens_assembly38.fasta'
diff --git a/config/rna_fusion.config b/config/rna_fusion.config
index a73aee7..b4a6069 100644
--- a/config/rna_fusion.config
+++ b/config/rna_fusion.config
@@ -2,7 +2,7 @@
 
 manifest {
     name = "rna_fusion"
-    description = 'Pipeline for processing of PDX RNASeq samples to call RNA Fusions, contains xenome step for processing PDX samples'
+    description = 'Pipeline for processing of PDX RNASeq samples to call RNA Fusions, contains xengsort step for processing PDX samples'
 }
 
 params {
@@ -21,8 +21,11 @@ params {
   // PDX
   pdx = false
   
-  // Xenome index  
-  xenome_prefix=params.reference_cache+'/human/GRCh38/supporting_files/xenome/hg38_broad_NOD_based_on_mm10_k25'
+  // xengsort index  
+  ref_fa = params.reference_cache+'/human/GRCh38/genome/sequence/gatk/Homo_sapiens_assembly38.fasta'
+  xengsort_host_fasta = params.reference_cache+'/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa'
+  xengsort_idx_path = params.reference_cache+'/human/GRCh38/supporting_files/xengsort'
+  xengsort_idx_name = 'hg38_GRCm39-NOD_ShiLtJ'
 
   // READ LENGTH ADJUSTMENTS: 
   read_length = 150 // change relative to sample being processed. 75, 100, 125, and 150 are supported. 
diff --git a/config/rnaseq.config b/config/rnaseq.config
index d2b23aa..468014d 100644
--- a/config/rnaseq.config
+++ b/config/rnaseq.config
@@ -21,7 +21,7 @@ params {
     csv_input = null
   
 
-    pdx = false // if PDX, gen_org == human and xenome is run to remove mouse reads from the sample(s). 
+    pdx = false // if PDX, gen_org == human and xengsort is run to remove mouse reads from the sample(s). 
 
     multiqc_config = "${projectDir}/bin/shared/multiqc/rnaseq_multiqc.yaml"
 
@@ -105,8 +105,11 @@ if (params.gen_org=='human' && params.pdx){
     params.strandedness_ref = params.reference_cache+'/human/GRCh38/transcriptome/indices/ensembl/v104/kallisto/kallisto_index'
     params.strandedness_gtf = params.reference_cache+'/human/GRCh38/transcriptome/annotation/ensembl/v104/Homo_sapiens.GRCh38.104.gtf'
 
-    // Xenome
-    params.xenome_prefix=params.reference_cache+'/human/GRCh38/supporting_files/xenome/hg38_broad_NOD_based_on_mm10_k25'
+    // include for Xengsort index
+    params.ref_fa = params.reference_cache+'/human/GRCh38/genome/sequence/gatk/Homo_sapiens_assembly38.fasta'
+    params.xengsort_host_fasta = params.reference_cache+'/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa'
+    params.xengsort_idx_path = params.reference_cache+'/human/GRCh38/supporting_files/xengsort'
+    params.xengsort_idx_name = 'hg38_GRCm39-NOD_ShiLtJ'
 
     // General RSEM 
     params.seed_length = '25'
diff --git a/config/somatic_wes.config b/config/somatic_wes.config
index 5feffbe..fa401ae 100644
--- a/config/somatic_wes.config
+++ b/config/somatic_wes.config
@@ -40,8 +40,10 @@ params {
   // Genome Window File
   hg38_windows = params.reference_cache+'/human/GRCh38/genome/annotation/intervals/hg38_chrom_sizes.window.1000000.bed'
 
-  // Xenome index  
-  xenome_prefix=params.reference_cache+'/human/GRCh38/supporting_files/xenome/hg38_broad_NOD_based_on_mm10_k25'
+  // Xengsort index
+  xengsort_host_fasta = params.reference_cache+'/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa'
+  xengsort_idx_path = params.reference_cache+'/human/GRCh38/supporting_files/xengsort'
+  xengsort_idx_name = 'hg38_GRCm39-NOD_ShiLtJ'
 
   // WES capture array BED and GATK intervals lists
   target_gatk = params.reference_cache+'/human/GRCh38/supporting_files/capture_kit_files/agilent/v7/S31285117_MergedProbes_no_gene_names.bed'
diff --git a/config/somatic_wes_pta.config b/config/somatic_wes_pta.config
index e20d96f..ebf354b 100644
--- a/config/somatic_wes_pta.config
+++ b/config/somatic_wes_pta.config
@@ -37,8 +37,10 @@ params {
   // FFPE 
   ffpe = false
 
-  // Xenome index  
-  xenome_prefix=params.reference_cache+'/human/GRCh38/supporting_files/xenome/hg38_broad_NOD_based_on_mm10_k25'
+  // include for Xengsort index
+  xengsort_host_fasta = params.reference_cache+'/mouse/GRCm39/genome/sequence/imputed/rel_2112_v8/NOD_ShiLtJ.39.fa'
+  xengsort_idx_path = params.reference_cache+'/human/GRCh38/supporting_files/xengsort'
+  xengsort_idx_name = 'hg38_GRCm39-NOD_ShiLtJ'
 
   // WES capture array BED and GATK intervals lists
   target_gatk = params.reference_cache+'/human/GRCh38/supporting_files/capture_kit_files/agilent/v7/S31285117_MergedProbes_no_gene_names.bed'
diff --git a/modules/gbrs/gbrs_bam2emase.nf b/modules/gbrs/gbrs_bam2emase.nf
index 2542e45..11c6285 100644
--- a/modules/gbrs/gbrs_bam2emase.nf
+++ b/modules/gbrs/gbrs_bam2emase.nf
@@ -2,7 +2,7 @@ process GBRS_BAM2EMASE {
     tag "$sampleID"
 
     cpus 1
-    memory { params.read_type == 'SE' ? 12.GB : 200.GB }
+    memory 200.GB
     time 6.hour
     errorStrategy {(task.exitStatus == 140) ? {log.info "\n\nError code: ${task.exitStatus} for task: ${task.name}. Likely caused by the task wall clock: ${task.time} or memory: ${task.memory} being exceeded.\nAttempting orderly shutdown.\nSee .command.log in: ${task.workDir} for more info.\n\n"; return 'finish'}.call() : 'finish'}
 
diff --git a/modules/gbrs/gbrs_compress.nf b/modules/gbrs/gbrs_compress.nf
index 8ee6823..dfd24eb 100644
--- a/modules/gbrs/gbrs_compress.nf
+++ b/modules/gbrs/gbrs_compress.nf
@@ -2,7 +2,7 @@ process GBRS_COMPRESS {
     tag "$sampleID"
 
     cpus 1
-    memory { params.read_type == 'SE' ? 12.GB : 250.GB }
+    memory { params.read_type == 'SE' ? 50.GB : 250.GB }
     time 5.hour
     errorStrategy {(task.exitStatus == 140) ? {log.info "\n\nError code: ${task.exitStatus} for task: ${task.name}. Likely caused by the task wall clock: ${task.time} or memory: ${task.memory} being exceeded.\nAttempting orderly shutdown.\nSee .command.log in: ${task.workDir} for more info.\n\n"; return 'finish'}.call() : 'finish'}
 
diff --git a/modules/jaffa/jaffa.nf b/modules/jaffa/jaffa.nf
index 6749f14..296601a 100644
--- a/modules/jaffa/jaffa.nf
+++ b/modules/jaffa/jaffa.nf
@@ -26,7 +26,7 @@ process JAFFA {
 
     bpipe run -v \
     -n ${task.cpus} \
-    -p fastqInputFormat='%_*.${ext}' \
+    -p fastqInputFormat='*.${ext}' \
     -p refBase=${params.jaffa_ref_dir} \
     -p genome=hg38 \
     -p annotation=genCode22 \
@@ -38,4 +38,4 @@ process JAFFA {
     mv jaffa_results.fasta ${sampleID}_jaffa_fusions.fasta ; 
 
     """
-}
\ No newline at end of file
+}
diff --git a/modules/utility_modules/gzip.nf b/modules/utility_modules/gzip.nf
index a7dc16a..b2cebec 100644
--- a/modules/utility_modules/gzip.nf
+++ b/modules/utility_modules/gzip.nf
@@ -9,7 +9,7 @@ process GZIP {
 
   container "quay.io/jaxcompsci/py3_perl_pylibs:v2"
 
-  publishDir "${params.pubdir}/${ params.organize_by=='sample' ? sampleID+'/processed_reads' : 'xenome' }", pattern: "*.gz", mode:'copy'
+  publishDir "${params.pubdir}/${ params.organize_by=='sample' ? sampleID+'/processed_reads' : 'xengsort' }", pattern: "*.gz", mode:'copy'
 
   input:
   tuple val(sampleID), path(reads)
diff --git a/modules/xengsort/xengsort_classify.nf b/modules/xengsort/xengsort_classify.nf
new file mode 100644
index 0000000..7b7950d
--- /dev/null
+++ b/modules/xengsort/xengsort_classify.nf
@@ -0,0 +1,65 @@
+process XENGSORT_CLASSIFY {
+    
+    tag "$sampleID"
+
+    // resource utilization
+    cpus 32
+    memory 60.GB
+    time 48.h
+    errorStrategy {(task.exitStatus == 140) ? {log.info "\n\nError code: ${task.exitStatus} for task: ${task.name}. Likely caused by the task wall clock: ${task.time} or memory: ${task.memory} being exceeded.\nAttempting orderly shutdown.\nSee .command.log in: ${task.workDir} for more info.\n\n"; return 'finish'}.call() : 'finish'}
+
+    // load xengsort container
+    container 'quay.io/biocontainers/xengsort:2.0.5--pyhdfd78af_0'
+
+    // output directory
+    // publishDir "${params.pubdir}/${ params.organize_by=='sample' ? sampleID+'/xengsort/xengsort_classify' : 'xengsort'}", pattern: "*.fq", mode: "copy"
+    publishDir "${params.pubdir}/${ params.organize_by=='sample' ? sampleID + '/stats': 'xengsort' }", pattern: "*.txt", mode:'copy'
+
+    // inputs
+    input:
+    path(xengsort_index)
+    tuple val(sampleID), path(trimmed)
+
+    output:
+    tuple val(sampleID), path("fastq-graft.*.fq"), emit: xengsort_human_fastq
+    tuple val(sampleID), path("fastq-host.*.fq"), emit: xengsort_mouse_fastq
+    tuple val(sampleID), path("*.txt"), emit: xengsort_log
+    
+    script:
+
+    // specify single-end or paired-end data
+    if (params.read_type == "SE")
+
+        """
+        
+        xengsort classify \
+        --index ${xengsort_index}/${xengsort_index} \
+        --fastq ${trimmed[0]} \
+        --prefix ${sampleID} \
+        --mode count \
+        --threads ${task.cpus}
+        --out fastq \
+        --chunksize 32.0 \
+        --compression none &> ${sampleID}_xengsort_log.txt
+
+        """
+
+    else if (params.read_type == "PE")
+
+        """
+
+        xengsort classify \
+        --index ${xengsort_index}/${params.xengsort_idx_name} \
+        --fastq ${trimmed[0]} \
+        --pairs ${trimmed[1]} \
+        --prefix ${sampleID} \
+        --mode count \
+        --threads ${task.cpus} \
+        --out fastq \
+        --chunksize 32.0 \
+        --compression none &> ${sampleID}_xengsort_log.txt
+
+        """
+
+    else error "${params.read_type} is invalid, specify either SE or PE"
+}
\ No newline at end of file
diff --git a/modules/xengsort/xengsort_index.nf b/modules/xengsort/xengsort_index.nf
new file mode 100644
index 0000000..8361a8c
--- /dev/null
+++ b/modules/xengsort/xengsort_index.nf
@@ -0,0 +1,37 @@
+process XENGSORT_INDEX {
+
+    // resource utilization
+    cpus 32
+    memory 60.GB
+    time 1.h
+    errorStrategy {(task.exitStatus == 140) ? {log.info "\n\nError code: ${task.exitStatus} for task: ${task.name}. Likely caused by the task wall clock: ${task.time} or memory: ${task.memory} being exceeded.\nAttempting orderly shutdown.\nSee .command.log in: ${task.workDir} for more info.\n\n"; return 'finish'}.call() : 'finish'}
+
+    // load xengsort container
+    container 'quay.io/biocontainers/xengsort:2.0.5--pyhdfd78af_0'
+
+    // output directory
+    publishDir "${params.pubdir}/xengsort/", mode: 'copy'
+
+    // inputs
+    input:
+    path(xengsort_host_fasta)
+    path(graft_fasta)
+
+    output:
+    // index output
+    path("xengsort_index/"), emit: xengsort_index
+
+    script:
+    """
+    xengsort index \
+    --index ${params.xengsort_idx_name} \
+    -H ${xengsort_host_fasta} \
+    -G ${graft_fasta} \
+    -k 25 \
+    -n 4_500_000_000 \
+    -W ${task.cpus}
+
+    mkdir xengsort_index
+    mv *.info *.hash xengsort_index/
+    """
+}
\ No newline at end of file
diff --git a/nextflow.config b/nextflow.config
index c479adc..16a7401 100644
--- a/nextflow.config
+++ b/nextflow.config
@@ -46,7 +46,7 @@ manifest {
     mainScript = "main.nf"
     nextflowVersion = "!>=22.04.3"
     version = "0.6.2"
-    author = 'Michael Lloyd, Brian Sanderson, Barry Guglielmo, Sai Lek, Peter Fields, Harshpreet Chandok, Carolyn Paisie, Gabriel Rech, Anuj Srivastava. Copyright Jackson Laboratory 2024'
+    author = 'Michael Lloyd, Brian Sanderson, Barry Guglielmo, Sai Lek, Peter Fields, Harshpreet Chandok, Carolyn Paisie, Gabriel Rech, Ardian Ferraj, Anuj Srivastava. Copyright Jackson Laboratory 2024'
 }
 
 profiles {
diff --git a/subworkflows/hs_pta.nf b/subworkflows/hs_pta.nf
index 6f71642..62e1218 100644
--- a/subworkflows/hs_pta.nf
+++ b/subworkflows/hs_pta.nf
@@ -6,7 +6,8 @@ include {CLUMPIFY} from "${projectDir}/modules/bbmap/bbmap_clumpify"
 include {FASTP} from "${projectDir}/modules/fastp/fastp"
 include {FASTQC} from "${projectDir}/modules/fastqc/fastqc"
 include {READ_GROUPS} from "${projectDir}/modules/utility_modules/read_groups"
-include {XENOME_CLASSIFY} from "${projectDir}/modules/xenome/xenome"
+include {XENGSORT_INDEX} from "${projectDir}/modules/xengsort/xengsort_index"
+include {XENGSORT_CLASSIFY} from "${projectDir}/modules/xengsort/xengsort_classify"
 include {BWA_MEM} from "${projectDir}/modules/bwa/bwa_mem"
 include {PICARD_SORTSAM} from "${projectDir}/modules/picard/picard_sortsam"
 include {SAMTOOLS_MERGE} from "${projectDir}/modules/samtools/samtools_merge"
@@ -151,8 +152,8 @@ workflow HS_PTA {
         // PDX CASES TO ADD AND VALIDATE: 
         // Normal samples should PASS the PDX step. 
 
-        // ** Step 2a: Xenome if PDX data used.
-        ch_XENOME_CLASSIFY_multiqc = Channel.empty() //optional log file. 
+        // ** Step 2a: Xengsort if PDX data used.
+        ch_XENGSORT_CLASSIFY_multiqc = Channel.empty() //optional log file. 
         if (params.pdx){
 
             FASTP.out.trimmed_fastq.join(meta_ch).branch{
@@ -162,11 +163,19 @@ workflow HS_PTA {
 
             normal_fastqs = fastq_files.normal.map{it -> [it[0], it[1]] }
 
-            // Xenome Classification
-            XENOME_CLASSIFY(fastq_files.tumor.map{it -> [it[0], it[1]] })
-            ch_XENOME_CLASSIFY_multiqc = XENOME_CLASSIFY.out.xenome_stats // set log file for multiqc
+            // Generate Xengsort Index if needed
+            if (params.xengsort_idx_path) {
+                xengsort_index = params.xengsort_idx_path
+            } else {
+                XENGSORT_INDEX(params.xengsort_host_fasta, params.ref_fa)
+                xengsort_index = XENGSORT_INDEX.out.xengsort_index
+            }
+            
+            // Xengsort Classification
+            XENGSORT_CLASSIFY(xengsort_index, fastq_files.tumor.map{it -> [it[0], it[1]] })
+            ch_XENGSORT_CLASSIFY_multiqc = XENGSORT_CLASSIFY.out.xengsort_log
 
-            bwa_mem_mapping = XENOME_CLASSIFY.out.xenome_human_fastq.mix(normal_fastqs).join(READ_GROUPS.out.read_groups)
+            bwa_mem_mapping = XENGSORT_CLASSIFY.out.xengsort_human_fastq.mix(normal_fastqs).join(READ_GROUPS.out.read_groups)
                               .map{it -> [it[0], it[1], 'aln', it[2]]}
 
         } else { 
@@ -178,7 +187,7 @@ workflow HS_PTA {
 
         if (params.split_fastq) {
             if (params.read_type == 'PE') {
-            split_fastq_files = FASTP.out.trimmed_fastq
+            split_fastq_files = bwa_mem_mapping
                                 .map{it -> [it[0], it[1][0], it[1][1]]}
                                 .splitFastq(by: params.split_fastq_bin_size, file: true, pe: true)
                                 .map{it -> [it[0], [it[1], it[2]], it[1].name.split('\\.')[-2]]}
@@ -187,7 +196,7 @@ workflow HS_PTA {
                                 // splitFastq adds an increment between *R* and .fastq. 
                                 // This can be used to set an 'index' value to make file names unique. 
             } else {
-            split_fastq_files = FASTP.out.trimmed_fastq
+            split_fastq_files = bwa_mem_mapping
                                 .map{it -> [it[0], it[1]]}
                                 .splitFastq(by: params.split_fastq_bin_size, file: true)
                                 .map{it -> [it[0], it[1], it[1].name.split('\\.')[-2]]}
@@ -864,7 +873,7 @@ workflow HS_PTA {
         ch_multiqc_files = Channel.empty()
         ch_multiqc_files = ch_multiqc_files.mix(FASTP.out.quality_json.collect{it[1]}.ifEmpty([]))
         ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.quality_stats.collect{it[1]}.ifEmpty([]))
-        ch_multiqc_files = ch_multiqc_files.mix(ch_XENOME_CLASSIFY_multiqc.collect{it[1]}.ifEmpty([]))
+        ch_multiqc_files = ch_multiqc_files.mix(ch_XENGSORT_CLASSIFY_multiqc.collect{it[1]}.ifEmpty([]))
         ch_multiqc_files = ch_multiqc_files.mix(GATK_BASERECALIBRATOR.out.table.collect{it[1]}.ifEmpty([]))
         ch_multiqc_files = ch_multiqc_files.mix(PICARD_COLLECTALIGNMENTSUMMARYMETRICS.out.txt.collect{it[1]}.ifEmpty([]))
         ch_multiqc_files = ch_multiqc_files.mix(PICARD_COLLECTWGSMETRICS.out.txt.collect{it[1]}.ifEmpty([]))
diff --git a/subworkflows/pdx_rnaseq.nf b/subworkflows/pdx_rnaseq.nf
index 0a84098..10392a1 100644
--- a/subworkflows/pdx_rnaseq.nf
+++ b/subworkflows/pdx_rnaseq.nf
@@ -8,7 +8,8 @@ include {READ_GROUPS as READ_GROUPS_HUMAN;
 include {FASTQC} from "${projectDir}/modules/fastqc/fastqc"
 include {GET_READ_LENGTH} from "${projectDir}/modules/utility_modules/get_read_length"
 include {CHECK_STRANDEDNESS} from "${projectDir}/modules/python/python_check_strandedness"
-include {XENOME_CLASSIFY} from "${projectDir}/modules/xenome/xenome"
+include {XENGSORT_INDEX} from "${projectDir}/modules/xengsort/xengsort_index"
+include {XENGSORT_CLASSIFY} from "${projectDir}/modules/xengsort/xengsort_classify"
 // include {GZIP as GZIP_HUMAN;
 //          GZIP as GZIP_MOUSE} from "${projectDir}/modules/utility_modules/gzip"
 include {RSEM_ALIGNMENT_EXPRESSION as RSEM_ALIGNMENT_EXPRESSION_HUMAN;
@@ -30,15 +31,15 @@ workflow PDX_RNASEQ {
         read_ch
 
     main:
-    // Step 1: Read trim, Get read group information, Run Xenome
+    // Step 1: Read trim, Get read group information, Run xengsort
     FASTP(read_ch)
     
     GET_READ_LENGTH(read_ch)
     
     if (params.read_type == 'PE') {
-      xenome_input = FASTP.out.trimmed_fastq
+      xengsort_input = FASTP.out.trimmed_fastq
     } else {
-      xenome_input = FASTP.out.trimmed_fastq
+      xengsort_input = FASTP.out.trimmed_fastq
     }
 
     // QC is assess on all reads. Mouse/human is irrelevant here. 
@@ -46,22 +47,27 @@ workflow PDX_RNASEQ {
 
     CHECK_STRANDEDNESS(FASTP.out.trimmed_fastq)
 
-    // Xenome Classification
-    XENOME_CLASSIFY(xenome_input)
+    // Generate Xengsort Index if needed
+    if (params.xengsort_idx_path) {
+        xengsort_index = params.xengsort_idx_path
+    } else {
+        XENGSORT_INDEX(params.xengsort_host_fasta, params.ref_fa)
+        xengsort_index = XENGSORT_INDEX.out.xengsort_index
+    }
 
-    human_reads = XENOME_CLASSIFY.out.xenome_human_fastq
+    // Xengsort Classification
+    XENGSORT_CLASSIFY(xengsort_index, xengsort_input) 
+
+    human_reads = XENGSORT_CLASSIFY.out.xengsort_human_fastq
                   .join(CHECK_STRANDEDNESS.out.strand_setting)
                   .join(GET_READ_LENGTH.out.read_length)
                   .map{it -> tuple(it[0]+'_human', it[1], it[2], it[3])}
 
-    mouse_reads = XENOME_CLASSIFY.out.xenome_mouse_fastq
+    mouse_reads = XENGSORT_CLASSIFY.out.xengsort_mouse_fastq
                   .join(CHECK_STRANDEDNESS.out.strand_setting)
                   .join(GET_READ_LENGTH.out.read_length)
                   .map{it -> tuple(it[0]+'_mouse', it[1], it[2], it[3])}
 
-    // GZIP_HUMAN(XENOME_CLASSIFY.out.xenome_human_fastq)
-    // GZIP_MOUSE(XENOME_CLASSIFY.out.xenome_mouse_fastq)
-
     // Step 2: RSEM Human and Stats: 
 
     RSEM_ALIGNMENT_EXPRESSION_HUMAN(human_reads, params.rsem_ref_files_human, params.rsem_star_prefix_human, params.rsem_ref_prefix_human)
@@ -107,7 +113,7 @@ workflow PDX_RNASEQ {
     ch_multiqc_files = Channel.empty()
     ch_multiqc_files = ch_multiqc_files.mix(FASTP.out.quality_json.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.quality_stats.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files = ch_multiqc_files.mix(XENOME_CLASSIFY.out.xenome_stats.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files = ch_multiqc_files.mix(XENGSORT_CLASSIFY.out.xengsort_log.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(RSEM_ALIGNMENT_EXPRESSION_HUMAN.out.rsem_cnt.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(RSEM_ALIGNMENT_EXPRESSION_HUMAN.out.star_log.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(PICARD_COLLECTRNASEQMETRICS_HUMAN.out.picard_metrics.collect{it[1]}.ifEmpty([]))
diff --git a/tests/workflows/pta.nf.test b/tests/workflows/pta.nf.test
index b50bc62..5c7fe23 100644
--- a/tests/workflows/pta.nf.test
+++ b/tests/workflows/pta.nf.test
@@ -47,7 +47,6 @@ nextflow_workflow {
     
     test("Full Workflow -- Human -- Deduplicate and Coverage Cap") {
         tag "GRCh38"
-        tag "pdx"
         tag "options"
         when {
             params {
diff --git a/tests/workflows/rnaseq.nf.test b/tests/workflows/rnaseq.nf.test
index af0f2a3..2f49a48 100644
--- a/tests/workflows/rnaseq.nf.test
+++ b/tests/workflows/rnaseq.nf.test
@@ -69,7 +69,7 @@ nextflow_workflow {
             params {
                 outdir = "tests/results"
                 gen_org = "human"
-                sample_folder = "${baseDir}/test/rna/human"
+                sample_folder = "${baseDir}/test/rna/human/pdx"
                 pubdir = "tests/results"
                 pdx = true
                 pipeline = 'rnaseq'
diff --git a/tests/workflows/somatic_wes_pta.nf.test b/tests/workflows/somatic_wes_pta.nf.test
index ad39a9f..b4785e3 100644
--- a/tests/workflows/somatic_wes_pta.nf.test
+++ b/tests/workflows/somatic_wes_pta.nf.test
@@ -26,6 +26,7 @@ nextflow_workflow {
     test("Full Workflow -- PDX") {
         tag "GRCh38"
         tag "primary"
+        tag "pdx"
         when {
             params {
                 outdir = "tests/results"
diff --git a/workflows/rna_fusion.nf b/workflows/rna_fusion.nf
index 46db643..5fec7d6 100644
--- a/workflows/rna_fusion.nf
+++ b/workflows/rna_fusion.nf
@@ -10,7 +10,8 @@ include {FILE_DOWNLOAD} from "${projectDir}/subworkflows/aria_download_parse"
 include {CONCATENATE_LOCAL_FILES} from "${projectDir}/subworkflows/concatenate_local_files"
 include {CONCATENATE_READS_PE} from "${projectDir}/modules/utility_modules/concatenate_reads_PE"
 include {GUNZIP} from "${projectDir}/modules/utility_modules/gunzip"
-include {XENOME_CLASSIFY} from "${projectDir}/modules/xenome/xenome"
+include {XENGSORT_INDEX} from "${projectDir}/modules/xengsort/xengsort_index"
+include {XENGSORT_CLASSIFY} from "${projectDir}/modules/xengsort/xengsort_classify"
 include {STAR_ALIGN as STAR_ARRIBA;
          STAR_ALIGN as STAR_SQUID;
          STAR_ALIGN as STAR_STARFUSION} from "${projectDir}/modules/star/star_align"
@@ -105,14 +106,23 @@ workflow RNA_FUSION {
 
     FASTQC(GUNZIP.out.gunzip_fastq)
 
-    // Step 1a: Xenome if PDX data used.
-    ch_XENOME_CLASSIFY_multiqc = Channel.empty() //optional log file. 
+    // Step 1a: Xengsort if PDX data used.
+    ch_XENGSORT_CLASSIFY_multiqc = Channel.empty() //optional log file.
     if (params.pdx){
-        // Xenome Classification
-        XENOME_CLASSIFY(GUNZIP.out.gunzip_fastq)
-        ch_XENOME_CLASSIFY_multiqc = XENOME_CLASSIFY.out.xenome_stats //set log file for multiqc
 
-        fusion_tool_input = XENOME_CLASSIFY.out.xenome_human_fastq
+        // Generate Xengsort Index if needed
+        if (params.xengsort_idx_path) {
+            xengsort_index = params.xengsort_idx_path
+        } else {
+            XENGSORT_INDEX(params.xengsort_host_fasta, params.ref_fa)
+            xengsort_index = XENGSORT_INDEX.out.xengsort_index
+        }
+
+        // Xengsort Classification
+        XENGSORT_CLASSIFY(xengsort_index, GUNZIP.out.gunzip_fastq)
+        ch_XENGSORT_CLASSIFY_multiqc = XENGSORT_CLASSIFY.out.xengsort_log
+
+        fusion_tool_input = XENGSORT_CLASSIFY.out.xengsort_human_fastq
 
     } else { 
         fusion_tool_input = GUNZIP.out.gunzip_fastq
@@ -155,9 +165,9 @@ workflow RNA_FUSION {
 
     // Step 5: MultiQC
     ch_multiqc_files = Channel.empty()
+    ch_multiqc_files = ch_multiqc_files.mix(ch_XENGSORT_CLASSIFY_multiqc.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(FUSION_REPORT.out.summary_fusions_mq.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.quality_stats.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files = ch_multiqc_files.mix(ch_XENOME_CLASSIFY_multiqc.collect{it[1]}.ifEmpty([]))
 
     MULTIQC (
         ch_multiqc_files.collect()
diff --git a/workflows/somatic_wes.nf b/workflows/somatic_wes.nf
index 8e6270c..626f46b 100755
--- a/workflows/somatic_wes.nf
+++ b/workflows/somatic_wes.nf
@@ -12,7 +12,8 @@ include {CONCATENATE_READS_PE} from "${projectDir}/modules/utility_modules/conca
 include {CONCATENATE_READS_SE} from "${projectDir}/modules/utility_modules/concatenate_reads_SE"
 include {FASTP} from "${projectDir}/modules/fastp/fastp"
 include {FASTQC} from "${projectDir}/modules/fastqc/fastqc"
-include {XENOME_CLASSIFY} from "${projectDir}/modules/xenome/xenome"
+include {XENGSORT_INDEX} from "${projectDir}/modules/xengsort/xengsort_index"
+include {XENGSORT_CLASSIFY} from "${projectDir}/modules/xengsort/xengsort_classify"
 // include {GZIP} from "${projectDir}/modules/utility_modules/gzip"
 include {READ_GROUPS} from "${projectDir}/modules/utility_modules/read_groups"
 include {BWA_MEM} from "${projectDir}/modules/bwa/bwa_mem"
@@ -161,27 +162,31 @@ workflow SOMATIC_WES {
 
     // Step 1: Read Trim
     FASTP(read_ch)
-
-    xenome_input = FASTP.out.trimmed_fastq
     
     FASTQC(FASTP.out.trimmed_fastq)
 
     // Step 3: Get Read Group Information
     READ_GROUPS(FASTP.out.trimmed_fastq, "gatk")
 
-    // Step 1a: Xenome if PDX data used.
-    ch_XENOME_CLASSIFY_multiqc = Channel.empty() //optional log file. 
+    // Step 1a: Run Xengsort if PDX data used.
+    ch_XENGSORT_CLASSIFY_multiqc = Channel.empty() //optional log file. 
     if (params.pdx){
-        // Xenome Classification
-        XENOME_CLASSIFY(FASTP.out.trimmed_fastq)
-        ch_XENOME_CLASSIFY_multiqc = XENOME_CLASSIFY.out.xenome_stats //set log file for multiqc
 
-        // GZIP(XENOME_CLASSIFY.out.xenome_human_fastq)
+        // Generate Xengsort Index if needed
+        if (params.xengsort_idx_path) {
+            xengsort_index = params.xengsort_idx_path
+        } else {
+            XENGSORT_INDEX(params.xengsort_host_fasta, params.ref_fa)
+            xengsort_index = XENGSORT_INDEX.out.xengsort_index
+        }
 
+        // Xengsort Classification
+        XENGSORT_CLASSIFY(xengsort_index, FASTP.out.trimmed_fastq) 
+        ch_XENGSORT_CLASSIFY_multiqc = XENGSORT_CLASSIFY.out.xengsort_log
+        
         // Step 4: BWA-MEM Alignment
-        bwa_mem_mapping = XENOME_CLASSIFY.out.xenome_human_fastq.join(READ_GROUPS.out.read_groups)
+        bwa_mem_mapping = XENGSORT_CLASSIFY.out.xengsort_human_fastq.join(READ_GROUPS.out.read_groups)
                           .map{it -> [it[0], it[1], 'aln', it[2]]}
-
     } else { 
         bwa_mem_mapping = FASTP.out.trimmed_fastq.join(READ_GROUPS.out.read_groups)
                           .map{it -> [it[0], it[1], 'aln', it[2]]}
@@ -255,7 +260,6 @@ workflow SOMATIC_WES {
     GATK_VARIANTFILTRATION_INDEL(var_filter_indel, 'INDEL')
 
     // Step 9: Post Variant Calling Processing - Part 1
-    // 
     SNPSIFT_ANNOTATE_SNP_DBSNP(GATK_VARIANTFILTRATION_SNP.out.vcf, params.dbSNP, params.dbSNP_index, 'dbsnpID')
     SNPSIFT_ANNOTATE_SNP_COSMIC(SNPSIFT_ANNOTATE_SNP_DBSNP.out.vcf, params.cosmic, params.cosmic_index, 'cosmicID')
     SNPEFF_SNP(SNPSIFT_ANNOTATE_SNP_COSMIC.out.vcf, 'SNP', 'vcf')
@@ -285,10 +289,10 @@ workflow SOMATIC_WES {
     ch_multiqc_files = Channel.empty()
     ch_multiqc_files = ch_multiqc_files.mix(FASTP.out.quality_json.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.quality_stats.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files = ch_multiqc_files.mix(ch_XENGSORT_CLASSIFY_multiqc.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(GATK_BASERECALIBRATOR.out.table.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(PICARD_COLLECTHSMETRICS.out.hsmetrics.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(PICARD_MARKDUPLICATES.out.dedup_metrics.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files = ch_multiqc_files.mix(ch_XENOME_CLASSIFY_multiqc.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(GATK_FILTERMUECTCALLS.out.stats.collect{it[1]}.ifEmpty([]))
 
     MULTIQC (
diff --git a/workflows/somatic_wes_pta.nf b/workflows/somatic_wes_pta.nf
index a54ea66..e81c6dc 100755
--- a/workflows/somatic_wes_pta.nf
+++ b/workflows/somatic_wes_pta.nf
@@ -9,7 +9,8 @@ include {CONCATENATE_PTA_FASTQ} from "${projectDir}/subworkflows/concatenate_pta
 
 include {FASTP} from "${projectDir}/modules/fastp/fastp"
 include {FASTQC} from "${projectDir}/modules/fastqc/fastqc"
-include {XENOME_CLASSIFY} from "${projectDir}/modules/xenome/xenome"
+include {XENGSORT_INDEX} from "${projectDir}/modules/xengsort/xengsort_index"
+include {XENGSORT_CLASSIFY} from "${projectDir}/modules/xengsort/xengsort_classify"
 // include {GZIP} from "${projectDir}/modules/utility_modules/gzip"
 include {READ_GROUPS} from "${projectDir}/modules/utility_modules/read_groups"
 include {BWA_MEM} from "${projectDir}/modules/bwa/bwa_mem"
@@ -112,8 +113,8 @@ workflow SOMATIC_WES_PTA {
     // Step 3: Get Read Group Information
     READ_GROUPS(FASTP.out.trimmed_fastq, "gatk")
 
-    // Step 1a: Xenome if PDX data used.
-    ch_XENOME_CLASSIFY_multiqc = Channel.empty() //optional log file. 
+    // Step 1a: Xengsort if PDX data used.
+    ch_XENGSORT_CLASSIFY_multiqc = Channel.empty() //optional log file.
     if (params.pdx){
         FASTP.out.trimmed_fastq.join(meta_ch).branch{
             normal: it[2].status == 0
@@ -122,16 +123,21 @@ workflow SOMATIC_WES_PTA {
 
         normal_fastqs = fastq_files.normal.map{it -> [it[0], it[1]] }
 
-        // Xenome Classification
-        XENOME_CLASSIFY(fastq_files.tumor.map{it -> [it[0], it[1]] })
-        ch_XENOME_CLASSIFY_multiqc = XENOME_CLASSIFY.out.xenome_stats //set log file for multiqc
+        // Generate Xengsort Index if needed
+        if (params.xengsort_idx_path) {
+            xengsort_index = params.xengsort_idx_path
+        } else {
+            XENGSORT_INDEX(params.xengsort_host_fasta, params.ref_fa)
+            xengsort_index = XENGSORT_INDEX.out.xengsort_index
+        }
 
-        // GZIP(XENOME_CLASSIFY.out.xenome_human_fastq)
+        // Xengsort Classification
+        XENGSORT_CLASSIFY(xengsort_index, fastq_files.tumor.map{it -> [it[0], it[1]] }) 
+        ch_XENGSORT_CLASSIFY_multiqc = XENGSORT_CLASSIFY.out.xengsort_log
 
         // Step 4: BWA-MEM Alignment
-        bwa_mem_mapping = XENOME_CLASSIFY.out.xenome_human_fastq.mix(normal_fastqs).join(READ_GROUPS.out.read_groups)
+        bwa_mem_mapping = XENGSORT_CLASSIFY.out.xengsort_human_fastq.mix(normal_fastqs).join(READ_GROUPS.out.read_groups)
                           .map{it -> [it[0], it[1], 'aln', it[2]]}
-
     } else { 
         bwa_mem_mapping = FASTP.out.trimmed_fastq.join(READ_GROUPS.out.read_groups)
                           .map{it -> [it[0], it[1], 'aln', it[2]]}
@@ -314,10 +320,10 @@ workflow SOMATIC_WES_PTA {
     ch_multiqc_files = Channel.empty()
     ch_multiqc_files = ch_multiqc_files.mix(FASTP.out.quality_json.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.quality_stats.collect{it[1]}.ifEmpty([]))
+    ch_multiqc_files = ch_multiqc_files.mix(ch_XENGSORT_CLASSIFY_multiqc.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(GATK_BASERECALIBRATOR.out.table.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(PICARD_COLLECTHSMETRICS.out.hsmetrics.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(PICARD_MARKDUPLICATES.out.dedup_metrics.collect{it[1]}.ifEmpty([]))
-    ch_multiqc_files = ch_multiqc_files.mix(ch_XENOME_CLASSIFY_multiqc.collect{it[1]}.ifEmpty([]))
     ch_multiqc_files = ch_multiqc_files.mix(GATK_FILTERMUECTCALLS.out.stats.collect{it[1]}.ifEmpty([]))
 
     MULTIQC (