diff --git a/data/genomics/homo_sapiens/README.md b/data/genomics/homo_sapiens/README.md
index 6389b9e0c..8d7d1e686 100644
--- a/data/genomics/homo_sapiens/README.md
+++ b/data/genomics/homo_sapiens/README.md
@@ -579,6 +579,75 @@ This dataset contains:
 
 This folder contains `AnnotFilterRule.pm` which comes from [The Broad](https://data.broadinstitute.org/Trinity/CTAT_RESOURCE_LIB/AnnotFilterRule.pm) and is used for filtering in `starfusion`. 
 
+### Gens test data
+
+These files are used to test the Gens input preprocessing module. 
+
+#### Binned coverage
+
+This file was obtained from the following WGS processing pipeline: [SMD WGS pipeline](https://github.com/SMD-Bioinformatics-Lund/nextflow_wgs).
+
+`data/genomics/homo_sapiens/illumina/gatk/hg002_chr20_90000_to_100000.standardizedCR.tsv`
+
+The relevant pipeline commands. Inputs is an aligned BAM-file, and an interval file specifying 100bp bins. It also requires a GATK format panel of normal.
+
+```
+gatk CollectReadCounts \\
+   -I $bam -L $params.COV_INTERVAL_LIST \\
+   --interval-merging-rule OVERLAPPING_ONLY -O ${bam}.hdf5
+
+gatk --java-options "-Xmx30g" DenoiseReadCounts \\
+   -I ${bam}.hdf5 --count-panel-of-normals ${PON[sex]} \\
+   --standardized-copy-ratios ${id}.standardizedCR.tsv \\
+   --denoised-copy-ratios ${id}.denoisedCR.tsv
+```
+
+This output is then processed to retrieve only chromsome 20 entries in the positions 90,000 - 100,000.
+
+```
+grep -E "^@|^20" hg002.standardizedCR.tsv | awk '$2 >= 90000 && $2 <= 100000' > hg002_chr20_90000_to_100000.standardizedCR.tsv
+```
+
+#### SNV calls (gGVCF)
+
+This file was obtained from the following WGS processing pipeline: [SMD WGS pipeline](https://github.com/SMD-Bioinformatics-Lund/nextflow_wgs).
+
+`data/genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz`
+
+Output from running DNA-scope on the aligned BAM file and then exacting the range 90000 to 100000 from chromosome 20.
+
+DNAscope is a reimplementation and slight improvement on GATK's HaplotypeCaller.
+
+Using masked hg38 as reference. Using base quality calibrated inputs.
+
+```
+sentieon driver \\
+   -r ${params.genome_file} \\
+   -q $bqsr \\
+   -i $bam \\
+   --algo DNAscope --emit_mode GVCF ${id}.dnascope.gvcf.gz
+```
+
+```
+zcat hg002.dnascope.gvcf.gz | grep -E "^#|^20" | awk '/^#/ || ($2 >= 90000 && $2 <= 100000>)' > hg002_chr20_90000_to_100000.dnascope.gvcf
+bgzip hg002_chr20_90000_to_100000.dnascope.gvcf
+tabix hg002_chr20_90000_to_100000.dnascope.gvcf.gz
+```
+
+#### B-allele frequency sampling locations
+
+* data/genomics/homo_sapiens/illumina/tab/gnomad_hg38_chr20_90000_to_100000.0.05.txt.gz
+
+Subset of the file https://github.com/SMD-Bioinformatics-Lund/gens/releases/download/v4.3.0/gnomad_hg38.0.05.txt.gz
+
+It is based on Gnomad (v2), where locations with an ALT allele frequency >= 0.05 is extracted. This file only contains the locations on these calls (i.e. col 1: chrom, col 2: position).
+
+Then the target range is extracted:
+
+```
+zcat gnomad_hg38.0.05.txt.gz | awk '$1 == 20 && ($2 >= 90000 && $2 <= 100000)' | gzip > gnomad_hg38_chr20_90000_to_100000.0.05.txt.gz
+```
+
 ### Missing files
 
 1. Single-end reads
diff --git a/data/genomics/homo_sapiens/illumina/gatk/hg002_chr20_90000_to_100000.standardizedCR.tsv b/data/genomics/homo_sapiens/illumina/gatk/hg002_chr20_90000_to_100000.standardizedCR.tsv
new file mode 100644
index 000000000..fe9409feb
--- /dev/null
+++ b/data/genomics/homo_sapiens/illumina/gatk/hg002_chr20_90000_to_100000.standardizedCR.tsv
@@ -0,0 +1,297 @@
+@HD	VN:1.6
+@SQ	SN:1	LN:248956422
+@SQ	SN:2	LN:242193529
+@SQ	SN:3	LN:198295559
+@SQ	SN:4	LN:190214555
+@SQ	SN:5	LN:181538259
+@SQ	SN:6	LN:170805979
+@SQ	SN:7	LN:159345973
+@SQ	SN:8	LN:145138636
+@SQ	SN:9	LN:138394717
+@SQ	SN:10	LN:133797422
+@SQ	SN:11	LN:135086622
+@SQ	SN:12	LN:133275309
+@SQ	SN:13	LN:114364328
+@SQ	SN:14	LN:107043718
+@SQ	SN:15	LN:101991189
+@SQ	SN:16	LN:90338345
+@SQ	SN:17	LN:83257441
+@SQ	SN:18	LN:80373285
+@SQ	SN:19	LN:58617616
+@SQ	SN:20	LN:64444167
+@SQ	SN:21	LN:46709983
+@SQ	SN:22	LN:50818468
+@SQ	SN:X	LN:156040895
+@SQ	SN:Y	LN:57227415
+@SQ	SN:M	LN:16569
+@SQ	SN:1_KI270706v1_random	LN:175055
+@SQ	SN:1_KI270707v1_random	LN:32032
+@SQ	SN:1_KI270708v1_random	LN:127682
+@SQ	SN:1_KI270709v1_random	LN:66860
+@SQ	SN:1_KI270710v1_random	LN:40176
+@SQ	SN:1_KI270711v1_random	LN:42210
+@SQ	SN:1_KI270712v1_random	LN:176043
+@SQ	SN:1_KI270713v1_random	LN:40745
+@SQ	SN:1_KI270714v1_random	LN:41717
+@SQ	SN:2_KI270715v1_random	LN:161471
+@SQ	SN:2_KI270716v1_random	LN:153799
+@SQ	SN:3_GL000221v1_random	LN:155397
+@SQ	SN:4_GL000008v2_random	LN:209709
+@SQ	SN:5_GL000208v1_random	LN:92689
+@SQ	SN:9_KI270717v1_random	LN:40062
+@SQ	SN:9_KI270718v1_random	LN:38054
+@SQ	SN:9_KI270719v1_random	LN:176845
+@SQ	SN:9_KI270720v1_random	LN:39050
+@SQ	SN:11_KI270721v1_random	LN:100316
+@SQ	SN:14_GL000009v2_random	LN:201709
+@SQ	SN:14_GL000225v1_random	LN:211173
+@SQ	SN:14_KI270722v1_random	LN:194050
+@SQ	SN:14_GL000194v1_random	LN:191469
+@SQ	SN:14_KI270723v1_random	LN:38115
+@SQ	SN:14_KI270724v1_random	LN:39555
+@SQ	SN:14_KI270725v1_random	LN:172810
+@SQ	SN:14_KI270726v1_random	LN:43739
+@SQ	SN:15_KI270727v1_random	LN:448248
+@SQ	SN:16_KI270728v1_random	LN:1872759
+@SQ	SN:17_GL000205v2_random	LN:185591
+@SQ	SN:17_KI270729v1_random	LN:280839
+@SQ	SN:17_KI270730v1_random	LN:112551
+@SQ	SN:22_KI270731v1_random	LN:150754
+@SQ	SN:22_KI270732v1_random	LN:41543
+@SQ	SN:22_KI270733v1_random	LN:179772
+@SQ	SN:22_KI270734v1_random	LN:165050
+@SQ	SN:22_KI270735v1_random	LN:42811
+@SQ	SN:22_KI270736v1_random	LN:181920
+@SQ	SN:22_KI270737v1_random	LN:103838
+@SQ	SN:22_KI270738v1_random	LN:99375
+@SQ	SN:22_KI270739v1_random	LN:73985
+@SQ	SN:Y_KI270740v1_random	LN:37240
+@SQ	SN:Un_KI270302v1	LN:2274
+@SQ	SN:Un_KI270304v1	LN:2165
+@SQ	SN:Un_KI270303v1	LN:1942
+@SQ	SN:Un_KI270305v1	LN:1472
+@SQ	SN:Un_KI270322v1	LN:21476
+@SQ	SN:Un_KI270320v1	LN:4416
+@SQ	SN:Un_KI270310v1	LN:1201
+@SQ	SN:Un_KI270316v1	LN:1444
+@SQ	SN:Un_KI270315v1	LN:2276
+@SQ	SN:Un_KI270312v1	LN:998
+@SQ	SN:Un_KI270311v1	LN:12399
+@SQ	SN:Un_KI270317v1	LN:37690
+@SQ	SN:Un_KI270412v1	LN:1179
+@SQ	SN:Un_KI270411v1	LN:2646
+@SQ	SN:Un_KI270414v1	LN:2489
+@SQ	SN:Un_KI270419v1	LN:1029
+@SQ	SN:Un_KI270418v1	LN:2145
+@SQ	SN:Un_KI270420v1	LN:2321
+@SQ	SN:Un_KI270424v1	LN:2140
+@SQ	SN:Un_KI270417v1	LN:2043
+@SQ	SN:Un_KI270422v1	LN:1445
+@SQ	SN:Un_KI270423v1	LN:981
+@SQ	SN:Un_KI270425v1	LN:1884
+@SQ	SN:Un_KI270429v1	LN:1361
+@SQ	SN:Un_KI270442v1	LN:392061
+@SQ	SN:Un_KI270466v1	LN:1233
+@SQ	SN:Un_KI270465v1	LN:1774
+@SQ	SN:Un_KI270467v1	LN:3920
+@SQ	SN:Un_KI270435v1	LN:92983
+@SQ	SN:Un_KI270438v1	LN:112505
+@SQ	SN:Un_KI270468v1	LN:4055
+@SQ	SN:Un_KI270510v1	LN:2415
+@SQ	SN:Un_KI270509v1	LN:2318
+@SQ	SN:Un_KI270518v1	LN:2186
+@SQ	SN:Un_KI270508v1	LN:1951
+@SQ	SN:Un_KI270516v1	LN:1300
+@SQ	SN:Un_KI270512v1	LN:22689
+@SQ	SN:Un_KI270519v1	LN:138126
+@SQ	SN:Un_KI270522v1	LN:5674
+@SQ	SN:Un_KI270511v1	LN:8127
+@SQ	SN:Un_KI270515v1	LN:6361
+@SQ	SN:Un_KI270507v1	LN:5353
+@SQ	SN:Un_KI270517v1	LN:3253
+@SQ	SN:Un_KI270529v1	LN:1899
+@SQ	SN:Un_KI270528v1	LN:2983
+@SQ	SN:Un_KI270530v1	LN:2168
+@SQ	SN:Un_KI270539v1	LN:993
+@SQ	SN:Un_KI270538v1	LN:91309
+@SQ	SN:Un_KI270544v1	LN:1202
+@SQ	SN:Un_KI270548v1	LN:1599
+@SQ	SN:Un_KI270583v1	LN:1400
+@SQ	SN:Un_KI270587v1	LN:2969
+@SQ	SN:Un_KI270580v1	LN:1553
+@SQ	SN:Un_KI270581v1	LN:7046
+@SQ	SN:Un_KI270579v1	LN:31033
+@SQ	SN:Un_KI270589v1	LN:44474
+@SQ	SN:Un_KI270590v1	LN:4685
+@SQ	SN:Un_KI270584v1	LN:4513
+@SQ	SN:Un_KI270582v1	LN:6504
+@SQ	SN:Un_KI270588v1	LN:6158
+@SQ	SN:Un_KI270593v1	LN:3041
+@SQ	SN:Un_KI270591v1	LN:5796
+@SQ	SN:Un_KI270330v1	LN:1652
+@SQ	SN:Un_KI270329v1	LN:1040
+@SQ	SN:Un_KI270334v1	LN:1368
+@SQ	SN:Un_KI270333v1	LN:2699
+@SQ	SN:Un_KI270335v1	LN:1048
+@SQ	SN:Un_KI270338v1	LN:1428
+@SQ	SN:Un_KI270340v1	LN:1428
+@SQ	SN:Un_KI270336v1	LN:1026
+@SQ	SN:Un_KI270337v1	LN:1121
+@SQ	SN:Un_KI270363v1	LN:1803
+@SQ	SN:Un_KI270364v1	LN:2855
+@SQ	SN:Un_KI270362v1	LN:3530
+@SQ	SN:Un_KI270366v1	LN:8320
+@SQ	SN:Un_KI270378v1	LN:1048
+@SQ	SN:Un_KI270379v1	LN:1045
+@SQ	SN:Un_KI270389v1	LN:1298
+@SQ	SN:Un_KI270390v1	LN:2387
+@SQ	SN:Un_KI270387v1	LN:1537
+@SQ	SN:Un_KI270395v1	LN:1143
+@SQ	SN:Un_KI270396v1	LN:1880
+@SQ	SN:Un_KI270388v1	LN:1216
+@SQ	SN:Un_KI270394v1	LN:970
+@SQ	SN:Un_KI270386v1	LN:1788
+@SQ	SN:Un_KI270391v1	LN:1484
+@SQ	SN:Un_KI270383v1	LN:1750
+@SQ	SN:Un_KI270393v1	LN:1308
+@SQ	SN:Un_KI270384v1	LN:1658
+@SQ	SN:Un_KI270392v1	LN:971
+@SQ	SN:Un_KI270381v1	LN:1930
+@SQ	SN:Un_KI270385v1	LN:990
+@SQ	SN:Un_KI270382v1	LN:4215
+@SQ	SN:Un_KI270376v1	LN:1136
+@SQ	SN:Un_KI270374v1	LN:2656
+@SQ	SN:Un_KI270372v1	LN:1650
+@SQ	SN:Un_KI270373v1	LN:1451
+@SQ	SN:Un_KI270375v1	LN:2378
+@SQ	SN:Un_KI270371v1	LN:2805
+@SQ	SN:Un_KI270448v1	LN:7992
+@SQ	SN:Un_KI270521v1	LN:7642
+@SQ	SN:Un_GL000195v1	LN:182896
+@SQ	SN:Un_GL000219v1	LN:179198
+@SQ	SN:Un_GL000220v1	LN:161802
+@SQ	SN:Un_GL000224v1	LN:179693
+@SQ	SN:Un_KI270741v1	LN:157432
+@SQ	SN:Un_GL000226v1	LN:15008
+@SQ	SN:Un_GL000213v1	LN:164239
+@SQ	SN:Un_KI270743v1	LN:210658
+@SQ	SN:Un_KI270744v1	LN:168472
+@SQ	SN:Un_KI270745v1	LN:41891
+@SQ	SN:Un_KI270746v1	LN:66486
+@SQ	SN:Un_KI270747v1	LN:198735
+@SQ	SN:Un_KI270748v1	LN:93321
+@SQ	SN:Un_KI270749v1	LN:158759
+@SQ	SN:Un_KI270750v1	LN:148850
+@SQ	SN:Un_KI270751v1	LN:150742
+@SQ	SN:Un_KI270752v1	LN:27745
+@SQ	SN:Un_KI270753v1	LN:62944
+@SQ	SN:Un_KI270754v1	LN:40191
+@SQ	SN:Un_KI270755v1	LN:36723
+@SQ	SN:Un_KI270756v1	LN:79590
+@SQ	SN:Un_KI270757v1	LN:71251
+@SQ	SN:Un_GL000214v1	LN:137718
+@SQ	SN:Un_KI270742v1	LN:186739
+@SQ	SN:Un_GL000216v2	LN:176608
+@SQ	SN:Un_GL000218v1	LN:161147
+@SQ	SN:EBV	LN:171823
+@RG	ID:GATKCopyNumber	SM:hg002
+20	90001	90100	-0.082386
+20	90101	90200	-0.042729
+20	90201	90300	0.246508
+20	90301	90400	-0.133577
+20	90401	90500	-0.248078
+20	90501	90600	-0.377049
+20	90601	90700	-0.030020
+20	90701	90800	-0.205219
+20	90801	90900	0.096751
+20	90901	91000	0.276859
+20	91001	91100	-0.076416
+20	91101	91200	0.435519
+20	91201	91300	-0.260407
+20	91301	91400	0.314984
+20	91401	91500	0.036276
+20	91501	91600	-0.190666
+20	91601	91700	0.278775
+20	91701	91800	0.115213
+20	91801	91900	-0.097977
+20	91901	92000	0.419661
+20	92001	92100	0.391919
+20	92101	92200	0.114558
+20	92201	92300	0.309484
+20	92301	92400	-0.121151
+20	92401	92500	-0.019289
+20	92501	92600	-0.590304
+20	92601	92700	-0.222244
+20	92701	92800	-0.351925
+20	92801	92900	0.225040
+20	92901	93000	0.104344
+20	93001	93100	-0.158730
+20	93101	93200	0.559246
+20	93201	93300	0.407682
+20	93301	93400	-0.083459
+20	93401	93500	0.344357
+20	93501	93600	-0.230986
+20	93601	93700	-0.033631
+20	93701	93800	-0.243347
+20	93801	93900	0.339796
+20	93901	94000	0.219763
+20	94001	94100	0.163647
+20	94101	94200	0.284660
+20	94201	94300	0.077820
+20	94301	94400	-0.108470
+20	94401	94500	0.040518
+20	94501	94600	0.137304
+20	94601	94700	-0.420225
+20	94701	94800	-0.237642
+20	94801	94900	-0.337373
+20	94901	95000	0.484378
+20	95001	95100	-0.351364
+20	95101	95200	-0.540956
+20	95201	95300	0.411661
+20	95301	95400	0.145571
+20	95401	95500	0.400021
+20	95501	95600	-0.149275
+20	95601	95700	-0.042284
+20	95701	95800	0.126260
+20	95801	95900	-0.123011
+20	95901	96000	0.260356
+20	96001	96100	-0.092015
+20	96101	96200	0.316630
+20	96201	96300	-0.262502
+20	96301	96400	-0.098632
+20	96401	96500	-0.436316
+20	96501	96600	0.180802
+20	96601	96700	-0.314259
+20	96701	96800	-0.056099
+20	96801	96900	0.222985
+20	96901	97000	0.256015
+20	97001	97100	0.234977
+20	97101	97200	0.015928
+20	97201	97300	0.542067
+20	97301	97400	0.052211
+20	97401	97500	0.347509
+20	97501	97600	0.139405
+20	97601	97700	-0.402959
+20	97701	97800	0.025147
+20	97801	97900	-0.340951
+20	97901	98000	-0.085121
+20	98001	98100	-0.314344
+20	98101	98200	-0.281636
+20	98201	98300	0.147276
+20	98301	98400	0.229243
+20	98401	98500	-0.196340
+20	98501	98600	0.139677
+20	98601	98700	0.164471
+20	98701	98800	-0.072459
+20	98801	98900	0.230651
+20	98901	99000	-0.079648
+20	99001	99100	0.026914
+20	99101	99200	-0.662400
+20	99201	99300	0.485609
+20	99301	99400	-0.168460
+20	99401	99500	-0.186852
+20	99501	99600	0.164201
+20	99601	99700	-0.247786
+20	99701	99800	0.229623
+20	99801	99900	0.395136
+20	99901	100000	0.323178
diff --git a/data/genomics/homo_sapiens/illumina/tab/gnomad_hg38_chr20_90000_to_100000.0.05.txt.gz b/data/genomics/homo_sapiens/illumina/tab/gnomad_hg38_chr20_90000_to_100000.0.05.txt.gz
new file mode 100644
index 000000000..86b689634
Binary files /dev/null and b/data/genomics/homo_sapiens/illumina/tab/gnomad_hg38_chr20_90000_to_100000.0.05.txt.gz differ
diff --git a/data/genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz b/data/genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz
new file mode 100644
index 000000000..8642e6c86
Binary files /dev/null and b/data/genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz differ
diff --git a/data/genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz.tbi b/data/genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz.tbi
new file mode 100644
index 000000000..5e157dcd2
Binary files /dev/null and b/data/genomics/homo_sapiens/illumina/vcf/hg002_chr20_90000_to_100000.dnascope.gvcf.gz.tbi differ