diff --git a/README.md b/README.md index 9065bb3b8..3a29d6a3c 100644 --- a/README.md +++ b/README.md @@ -1,38 +1,8 @@ # ![nfcore/test-datasets](docs/images/test-datasets_logo.png) -Test data to be used for automated testing with the nf-core pipelines -> ⚠️ **Do not merge your test data to `master`! Each pipeline has a dedicated branch (and a special one for modules)** +# test-datasets: stableexpression +This branch contains test data to be used for automated testing with the nf-core/stableexpression pipeline. -## Introduction +## Content of this repository -nf-core is a collection of high quality Nextflow pipelines. This repository contains various files for CI and unit testing of nf-core pipelines and infrastructure. - -The principle for nf-core test data is as small as possible, as large as necessary. Please see the [guidelines](https://nf-co.re/docs/contributing/test_data_guidelines) for more detailed information. Always ask for guidance on the [nf-core slack](https://nf-co.re/join) before adding new test data. - -## Documentation - -nf-core/test-datasets comes with documentation in the `docs/` directory: - -01. [Add a new test dataset](https://github.com/nf-core/test-datasets/blob/master/docs/ADD_NEW_DATA.md) -02. [Use an existing test dataset](https://github.com/nf-core/test-datasets/blob/master/docs/USE_EXISTING_DATA.md) - -## Downloading test data - -Due the large number of large files in this repository for each pipeline, we highly recommend cloning only the branches you would use. - -```bash -git clone --single-branch --branch -``` - -To subsequently clone other branches[^1] - -```bash -git remote set-branches --add origin [remote-branch] -git fetch -``` - -## Support - -For further information or help, don't hesitate to get in touch on our [Slack organisation](https://nf-co.re/join/slack) (a tool for instant messaging). - -[^1]: From [stackoverflow](https://stackoverflow.com/a/60846265/11502856) +All the data contained here were subsampled from datasets collected from Expression. In some cases, data were also generated randomly. diff --git a/test_data/dataset_statistics/input/count.raw.cpm.quant_norm.parquet b/test_data/dataset_statistics/input/count.raw.cpm.quant_norm.parquet new file mode 100644 index 000000000..43a77ae2d Binary files /dev/null and b/test_data/dataset_statistics/input/count.raw.cpm.quant_norm.parquet differ diff --git a/test_data/gene_statistics/input/gene_counts.csv b/test_data/gene_statistics/input/gene_counts.csv new file mode 100644 index 000000000..fad53618a --- /dev/null +++ b/test_data/gene_statistics/input/gene_counts.csv @@ -0,0 +1,28 @@ +sample,count +ARR029909,4 +ARR029910,4 +ARR029911,4 +ARR029912,4 +ARR029913,4 +ARR029914,4 +ARR029915,4 +ARR029916,4 +ARR029917,4 +URR029909,2 +URR029910,2 +URR029911,2 +URR029912,2 +URR029913,2 +URR029914,2 +URR029915,2 +URR029916,2 +URR029917,2 +ERR029909,3 +ERR029910,3 +ERR029911,3 +ERR029912,3 +ERR029913,3 +ERR029914,3 +ERR029915,3 +ERR029916,3 +ERR029917,3 diff --git a/test_data/gene_statistics/input/ks_stats.csv b/test_data/gene_statistics/input/ks_stats.csv new file mode 100644 index 000000000..119c4ae5b --- /dev/null +++ b/test_data/gene_statistics/input/ks_stats.csv @@ -0,0 +1,27 @@ +URR029909,0.99 +URR029910,0.58 +URR029911,0.24 +URR029912,0.12 +URR029913,0.05 +URR029914,0.0 +URR029915,0.897 +URR029916,0.999 +URR029917,0.23 +ERR029909,0.45 +ERR029910,0.87 +ERR029911,0.456 +ERR029912,0.457 +ERR029913,0.78 +ERR029914,0.32 +ERR029915,0.56 +ERR029916,0.45 +ERR029917,0.12 +ARR029909,0.21 +ARR029910,0.0000005 +ARR029911,0 +ARR029912,0.789 +ARR029913,0.987 +ARR029914,0.876 +ARR029915,0.123 +ARR029916,0.321 +ARR029917,0.156 diff --git a/test_data/gene_statistics/input/mapping1.csv b/test_data/gene_statistics/input/mapping1.csv new file mode 100644 index 000000000..d8abe7304 --- /dev/null +++ b/test_data/gene_statistics/input/mapping1.csv @@ -0,0 +1,9 @@ +original_gene_id,ensembl_gene_id +Q8VWG3,AT1G34790 +Q9FJA2,AT5G35550 +Q8RYD9,AT5G23260 +ABCD12,AT5G23261 +840386,AT1G34790 +833520,AT5G35550 +832390,AT5G23260 +123456,AT5G35550 diff --git a/test_data/gene_statistics/input/mapping2.csv b/test_data/gene_statistics/input/mapping2.csv new file mode 100644 index 000000000..305ccbea7 --- /dev/null +++ b/test_data/gene_statistics/input/mapping2.csv @@ -0,0 +1,9 @@ +original_gene_id,ensembl_gene_id +Q8VWG3,AT1G34790 +Q9FJA2,AT5G35550 +Q8RYD9,AT5G23260 +ABCD12,AT5G23261 +840386,AT1G34790 +833520,AT5G35550 +832390,AT5G23260 +457862,AT5G23260 diff --git a/test_data/gene_statistics/input/mapping3.csv b/test_data/gene_statistics/input/mapping3.csv new file mode 100644 index 000000000..e20257b0c --- /dev/null +++ b/test_data/gene_statistics/input/mapping3.csv @@ -0,0 +1,5 @@ +original_gene_id,ensembl_gene_id +Q8VWG3,AT1G34790 +Q9FJA2,AT5G35550 +Q8RYD9,AT5G23260 +152348,AT1G23260 diff --git a/test_data/gene_statistics/input/metadata1.csv b/test_data/gene_statistics/input/metadata1.csv new file mode 100644 index 000000000..ea4db477c --- /dev/null +++ b/test_data/gene_statistics/input/metadata1.csv @@ -0,0 +1,5 @@ +ensembl_gene_id,name,description +AT1G34790,TT1,C2H2 and C2HC zinc fingers superfamily protein +AT5G35550,TT2,Duplicated homeodomain-like superfamily protein +AT5G23260,TT16,K-box region and MADS-box transcription factor family protein +AT5G23261,TT23,blabla diff --git a/test_data/gene_statistics/input/metadata2.csv b/test_data/gene_statistics/input/metadata2.csv new file mode 100644 index 000000000..b5890d890 --- /dev/null +++ b/test_data/gene_statistics/input/metadata2.csv @@ -0,0 +1,4 @@ +ensembl_gene_id,name,description +AT1G34790,TT1,C2H2 and C2HC zinc fingers superfamily protein +AT5G35550,TT2,Duplicated homeodomain-like superfamily protein +AT5G23260,TT16,K-box region and MADS-box transcription factor family protein diff --git a/test_data/idmapping/base/counts.ensembl_ids.csv b/test_data/idmapping/base/counts.ensembl_ids.csv new file mode 100644 index 000000000..0a9dbca46 --- /dev/null +++ b/test_data/idmapping/base/counts.ensembl_ids.csv @@ -0,0 +1,4 @@ +ERR029909,ERR029910,ERR029911,ERR029912,ERR029913,ERR029914,ERR029915,ERR029916,ERR029917,ERR029918,ERR029920,ERR029921,ERR029922,ERR029923,ERR029924 +ENSRNA049434199,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 +ENSRNA049434246,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 +ENSRNA049434252,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 diff --git a/test_data/idmapping/base/counts.ncbi_ids.csv b/test_data/idmapping/base/counts.ncbi_ids.csv new file mode 100644 index 000000000..b52dfe8d5 --- /dev/null +++ b/test_data/idmapping/base/counts.ncbi_ids.csv @@ -0,0 +1,4 @@ +ERR029909,ERR029910,ERR029911,ERR029912,ERR029913,ERR029914,ERR029915,ERR029916,ERR029917,ERR029918,ERR029920,ERR029921,ERR029922,ERR029923,ERR029924 +840386,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 +833520,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 +832390,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 diff --git a/test_data/idmapping/base/counts.uniprot_ids.csv b/test_data/idmapping/base/counts.uniprot_ids.csv new file mode 100644 index 000000000..9a30df900 --- /dev/null +++ b/test_data/idmapping/base/counts.uniprot_ids.csv @@ -0,0 +1,4 @@ +ERR029909,ERR029910,ERR029911,ERR029912,ERR029913,ERR029914,ERR029915,ERR029916,ERR029917,ERR029918,ERR029920,ERR029921,ERR029922,ERR029923,ERR029924 +Q8VWG3,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 +Q9FJA2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 +Q8RYD9,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 diff --git a/test_data/idmapping/custom/mapping.csv b/test_data/idmapping/custom/mapping.csv new file mode 100644 index 000000000..9cb9aee4f --- /dev/null +++ b/test_data/idmapping/custom/mapping.csv @@ -0,0 +1,4 @@ +original_gene_id,ensembl_gene_id +ENSRNA049434199,SNSRNA049434199 +ENSRNA049434246,SNSRNA049434246 +ENSRNA049434252,SNSRNA049434252 diff --git a/test_data/idmapping/empty/counts.csv b/test_data/idmapping/empty/counts.csv new file mode 100644 index 000000000..b8d84b762 --- /dev/null +++ b/test_data/idmapping/empty/counts.csv @@ -0,0 +1 @@ +sample_1,sample_2,sample_3 diff --git a/test_data/idmapping/not_found/counts.csv b/test_data/idmapping/not_found/counts.csv new file mode 100644 index 000000000..2b8ebd504 --- /dev/null +++ b/test_data/idmapping/not_found/counts.csv @@ -0,0 +1,4 @@ +sample_1,sample_2,sample_3 +8173941,1,2,3 +8168737,1,2,3 +8067017,1,2,3 diff --git a/test_data/input_datasets/input.csv b/test_data/input_datasets/input.csv new file mode 100644 index 000000000..697e034b3 --- /dev/null +++ b/test_data/input_datasets/input.csv @@ -0,0 +1,3 @@ +counts,design,platform,normalised +tests/test_data/custom_datasets/microarray.normalised.csv,tests/test_data/custom_datasets/microarray.normalised.design.csv,microarray,true +tests/test_data/custom_datasets/rnaseq.raw.csv,tests/test_data/custom_datasets/rnaseq.raw.design.csv,rnaseq,false diff --git a/test_data/input_datasets/microarray.normalised.csv b/test_data/input_datasets/microarray.normalised.csv new file mode 100644 index 000000000..608699175 --- /dev/null +++ b/test_data/input_datasets/microarray.normalised.csv @@ -0,0 +1,10 @@ +,GSM1528575,GSM1528576,GSM1528579,GSM1528583,GSM1528584,GSM1528585,GSM1528580,GSM1528586,GSM1528582,GSM1528578,GSM1528581,GSM1528577 +ENSRNA049453121,20925.1255070264,136184.261516502,144325.370645564,89427.0987612997,164143.182734208,34178.6378088171,28842.7323281157,76973.395782103,41906.9367255656,44756.5602263121,252562.049703724,6953.65643340122 +ENSRNA049453138,196173.051628372,16607.8367703051,344972.83715281,22602.4535330758,13678.598561184,104546.421532852,15451.4637472048,71664.8857281649,160643.257448002,91459.0578537683,88396.7173963033,281623.08555275 +ENSRNA049454388,91547.4240932405,11625.4857392136,84483.143792525,80582.6604222701,218857.576978944,58304.7350856292,42234.0009090266,88475.1675656357,87306.1181782617,17513.436610296,90922.3378933406,76490.2207674135 +ENSRNA049454416,20925.1255070264,106290.155329953,193607.204524536,47170.3378081581,392119.825420608,190998.270108096,90648.5873169351,81397.1541603848,83813.8734511313,165404.67909724,111127.301869638,194702.380135234 +ENSRNA049454647,99394.3461583754,91343.1022366783,3520.13099135521,71738.2220832404,118547.854196928,20105.0810640101,81377.7090686122,15040.7784861581,66352.6498154789,110918.431865208,55563.6509348192,111258.50293442 +ENSRNA049454661,175247.926121346,66431.3470812206,24640.9169394865,52083.9146631746,360203.095444512,36189.1459152181,70046.6356539953,85820.9125386666,13968.9789085219,50594.3724297441,25256.2049703724,52152.4232505092 +ENSRNA049454747,117703.830977024,154452.881963838,281610.479308417,29481.4611300988,191500.379856576,152798.616086476,53565.0743236435,14156.0268105017,293348.557078959,155674.99209152,63140.5124259309,243377.975169043 +ENSRNA049454887,2615.6406883783,164417.584026021,28161.0479308417,82548.0911642767,50154.861391008,136714.551235268,97859.270398964,64586.872322914,328271.004350264,159566.866893808,151537.229822234,86920.7054175153 +ENSRNA049454931,177863.566809724,81378.4001744952,235848.776420799,88444.3833902964,18238.131414912,120630.48638406,82407.8066517592,50430.8455124123,118736.320722436,68107.8090400402,232357.085727426,163410.926184929 diff --git a/test_data/input_datasets/microarray.normalised.design.csv b/test_data/input_datasets/microarray.normalised.design.csv new file mode 100644 index 000000000..d31e5cef6 --- /dev/null +++ b/test_data/input_datasets/microarray.normalised.design.csv @@ -0,0 +1,13 @@ +sample,condition +GSM1528575,g1 +GSM1528576,g1 +GSM1528579,g1 +GSM1528583,g2 +GSM1528584,g2 +GSM1528585,g2 +GSM1528580,g3 +GSM1528586,g3 +GSM1528582,g3 +GSM1528578,g4 +GSM1528581,g4 +GSM1528577,g4 diff --git a/test_data/input_datasets/rnaseq.raw.csv b/test_data/input_datasets/rnaseq.raw.csv new file mode 100644 index 000000000..a9a6bdb4a --- /dev/null +++ b/test_data/input_datasets/rnaseq.raw.csv @@ -0,0 +1,10 @@ +,ESM1528575,ESM1528576,ESM1528579,ESM1528583,ESM1528584,ESM1528585,ESM1528580,ESM1528586,ESM1528582,ESM1528578,ESM1528581,ESM1528577 +ENSRNA049453121,1,82,8,82,4,68,88,73,46,57,25,22 +ENSRNA049453138,68,93,41,84,36,18,28,92,84,85,92,32 +ENSRNA049454388,38,10,0,23,11,17,95,57,25,82,10,70 +ENSRNA049454416,75,55,7,30,79,60,15,97,12,35,60,56 +ENSRNA049454647,35,64,55,91,48,95,68,100,24,26,100,47 +ENSRNA049454661,8,99,80,48,86,29,80,17,19,9,44,2 +ENSRNA049454747,67,7,98,53,3,10,52,87,4,80,22,15 +ENSRNA049454887,8,40,24,90,42,52,79,81,94,23,35,81 +ENSRNA049454931,45,49,67,73,26,76,41,16,34,47,36,25 diff --git a/test_data/input_datasets/rnaseq.raw.design.csv b/test_data/input_datasets/rnaseq.raw.design.csv new file mode 100644 index 000000000..469751d2f --- /dev/null +++ b/test_data/input_datasets/rnaseq.raw.design.csv @@ -0,0 +1,13 @@ +sample,condition +ESM1528575,g1 +ESM1528576,g1 +ESM1528579,g1 +ESM1528583,g2 +ESM1528584,g2 +ESM1528585,g2 +ESM1528580,g3 +ESM1528586,g3 +ESM1528582,g3 +ESM1528578,g4 +ESM1528581,g4 +ESM1528577,g4 diff --git a/test_data/merge_data/input/counts1.parquet b/test_data/merge_data/input/counts1.parquet new file mode 100644 index 000000000..e0db1417a Binary files /dev/null and b/test_data/merge_data/input/counts1.parquet differ diff --git a/test_data/merge_data/input/counts2.parquet b/test_data/merge_data/input/counts2.parquet new file mode 100644 index 000000000..18cd85d36 Binary files /dev/null and b/test_data/merge_data/input/counts2.parquet differ diff --git a/test_data/merge_data/input/counts3.parquet b/test_data/merge_data/input/counts3.parquet new file mode 100644 index 000000000..d57fe0410 Binary files /dev/null and b/test_data/merge_data/input/counts3.parquet differ diff --git a/test_data/merge_data/input/dataset_stat1.csv b/test_data/merge_data/input/dataset_stat1.csv new file mode 100644 index 000000000..feca6c83d --- /dev/null +++ b/test_data/merge_data/input/dataset_stat1.csv @@ -0,0 +1,10 @@ +sample,count,skewness,kolmogorov_smirnov_to_uniform_dist_pvalue +ARR029909,1,1,1 +ARR029910,2,3,1 +ARR029911,3,5,1 +ARR029912,4,4,9 +ARR029913,5,1,5 +ARR029914,6,6,6 +ARR029915,7,1,9 +ARR029916,8,8,1 +ARR029917,9,3,9 diff --git a/test_data/merge_data/input/dataset_stat2.csv b/test_data/merge_data/input/dataset_stat2.csv new file mode 100644 index 000000000..a7c0ea8ba --- /dev/null +++ b/test_data/merge_data/input/dataset_stat2.csv @@ -0,0 +1,10 @@ +sample,count,skewness,kolmogorov_smirnov_to_uniform_dist_pvalue +URR029909,1,1,1 +URR029910,2,2,2 +URR029911,3,2,3 +URR029912,4,4,4 +URR029913,5,5,5 +URR029914,6,6,3 +URR029915,7,7,7 +URR029916,8,8,8 +URR029917,9,9,9 diff --git a/test_data/merge_data/input/dataset_stat3.csv b/test_data/merge_data/input/dataset_stat3.csv new file mode 100644 index 000000000..28be67310 --- /dev/null +++ b/test_data/merge_data/input/dataset_stat3.csv @@ -0,0 +1,10 @@ +sample,count,skewness,kolmogorov_smirnov_to_uniform_dist_pvalue +ERR029909,1,1,1 +ERR029910,2,2,2 +ERR029911,3,3,3 +ERR029912,4,9,4 +ERR029913,5,5,5 +ERR029914,6,6,6 +ERR029915,7,7,7 +ERR029916,8,8,1 +ERR029917,9,9,9 diff --git a/test_data/merge_data/input/design1.csv b/test_data/merge_data/input/design1.csv new file mode 100644 index 000000000..f9b61c495 --- /dev/null +++ b/test_data/merge_data/input/design1.csv @@ -0,0 +1,10 @@ +sample,condition +ARR029909,g1 +ARR029910,g1 +ARR029911,g1 +ARR029912,g2 +ARR029913,g2 +ARR029914,g2 +ARR029915,g3 +ARR029916,g3 +ARR029917,g3 diff --git a/test_data/merge_data/input/design2.csv b/test_data/merge_data/input/design2.csv new file mode 100644 index 000000000..dcb29ec87 --- /dev/null +++ b/test_data/merge_data/input/design2.csv @@ -0,0 +1,10 @@ +sample,condition +URR029909,g1 +URR029910,g1 +URR029911,g1 +URR029912,g2 +URR029913,g2 +URR029914,g2 +URR029915,g3 +URR029916,g3 +URR029917,g3 diff --git a/test_data/merge_data/input/design3.csv b/test_data/merge_data/input/design3.csv new file mode 100644 index 000000000..75caca86b --- /dev/null +++ b/test_data/merge_data/input/design3.csv @@ -0,0 +1,10 @@ +batch,sample,condition +batch3,ERR029909,g1 +batch3,ERR029910,g1 +batch3,ERR029911,g1 +batch3,ERR029912,g2 +batch3,ERR029913,g2 +batch3,ERR029914,g2 +batch3,ERR029915,g3 +batch3,ERR029916,g3 +batch3,ERR029917,g3 diff --git a/test_data/merge_data/output/all_counts.csv b/test_data/merge_data/output/all_counts.csv new file mode 100644 index 000000000..0ba6456ad --- /dev/null +++ b/test_data/merge_data/output/all_counts.csv @@ -0,0 +1,15 @@ +ensembl_gene_id,URR029909,URR029910,URR029911,URR029912,URR029913,URR029914,URR029915,URR029916,URR029917,ERR029909,ERR029910,ERR029911,ERR029912,ERR029913,ERR029914,ERR029915,ERR029916,ERR029917,ARR029909,ARR029910,ARR029911,ARR029912,ARR029913,ARR029914,ARR029915,ARR029916,ARR029917 +AT1G34790,0.60113057,0.64080682,0.6,0.6197164000000003,0.60115891,0.63052843,0.61002869,0.65849011,0.66239896,0.60113057,0.64080682,0.6348181099999999,0.6519716400000001,0.60115891,0.63052843,0.61002869,0.65849011,0.66239896,0.60113057,0.64080682,0.6348181099999999,0.6519716400000001,0.20115891000000002,0.93052843,0.71002869,0.65849011,0.16239896 +AT5G35550,0.7148504699999999,0.21713193,0.03318757,0.18404821999999998,0.70246917,0.0,0.8336608,0.00340416,0.23179154000000002,0.0,0.21713193,0.03318757,0.18404821999999998,0.70246917,0.7555268599999999,0.8336608,0.00340416,0.23179154000000002,0.7148504699999999,0.21713193,0.03318757,0.18404821999999998,0.70246917,0.7555268599999999,0.8336608,0.00340416,0.23179154000000002 +AT5G23260,0.71122807,0.47981484,0.85599454,0.69023553,0.40420572,0.30220852000000004,0.73996866,0.08559519,0.80013134,0.71122807,0.47981484,0.85599454,0.69023553,0.40420572,0.30220852000000004,0.73996866,0.08559519,0.80013134,0.71122807,0.47981484,0.85599454,0.69023553,0.40420572,0.30220852000000004,0.73996866,0.08559519,0.80013134 +AT1G34791,0.60113057,0.64080682,0.9348181099999999,0.35197164000000003,0.20115891000000002,0.93052843,0.71002869,0.65849011,0.16239896,0.60113057,0.64080682,0.9348181099999999,0.35197164000000003,0.20115891000000002,0.93052843,0.71002869,0.65849011,0.16239896,0.60113057,0.64080682,0.9348181099999999,0.35197164000000003,0.20115891000000002,0.93052843,0.71002869,0.65849011,0.16239896 +AT5G35551,0.7148504699999999,0.21713193,0.03318757,0.18404821999999998,0.70246917,0.7555268599999999,0.0,0.00340416,0.23179154000000002,0.7148504699999999,0.21713193,0.03318757,0.18404821999999998,0.70246917,0.7555268599999999,0.8336608,0.00340416,0.23179154000000002,0.7148504699999999,0.21713193,0.03318757,0.18404821999999998,0.70246917,0.7555268599999999,0.8336608,0.00340416,0.23179154000000002 +AT5G23261,0.71122807,0.47981484,0.85599454,0.69023553,0.40420572,0.30220852000000004,0.73996866,0.08559519,0.80013134,0.71122807,0.47981484,0.85599454,0.69023553,0.40420572,0.30220852000000004,0.73996866,0.08559519,0.80013134,0.71122807,0.47981484,0.85599454,0.69023553,0.40420572,0.30220852000000004,0.73996866,0.08559519,0.80013134 +AT1G34792,0.60113057,0.64080682,0.9348181099999999,0.35197164000000003,0.0,0.93052843,0.71002869,0.65849011,0.16239896,0.60113057,0.64080682,0.9348181099999999,0.35197164000000003,0.20115891000000002,0.93052843,0.71002869,0.65849011,0.16239896,0.60113057,0.64080682,0.9348181099999999,0.35197164000000003,0.20115891000000002,0.93052843,0.71002869,0.65849011,0.16239896 +AT5G35552,0.7148504699999999,0.21713193,0.03318757,0.18404821999999998,0.70246917,0.7555268599999999,0.8336608,0.00340416,0.23179154000000002,0.7148504699999999,0.21713193,0.03318757,0.18404821999999998,0.70246917,0.7555268599999999,0.8336608,0.00340416,0.23179154000000002,0.7148504699999999,0.21713193,0.03318757,0.18404821999999998,0.70246917,0.7555268599999999,0.8336608,0.00340416,0.23179154000000002 +AT5G23262,0.0,0.47981484,0.85599454,0.69023553,0.0,0.30220852000000004,0.73996866,0.08559519,0.80013134,0.71122807,0.47981484,0.85599454,0.0,0.0,0.0,0.73996866,0.0,0.0,0.0,0.0,0.0,0.69023553,0.40420572,0.30220852000000004,0.73996866,0.08559519,0.80013134 +AT1G34793,0.60113057,0.64080682,0.9348181099999999,0.35197164000000003,0.0,0.93052843,0.71002869,0.65849011,0.16239896,0.60113057,0.64080682,0.9348181099999999,0.35197164000000003,0.20115891000000002,0.93052843,0.71002869,0.65849011,0.16239896,0.60113057,0.64080682,0.9348181099999999,0.35197164000000003,0.20115891000000002,0.93052843,0.71002869,0.65849011,0.16239896 +AT5G35553,,0.21713193,,,,,,,,,,,,,0,,,,,0.9348181099999999,,,0.35197164000000003,,,,0.0 +AT5G35554,,0.01713193,,,,,,,,,,,,,0.01,,,,,0.15,,,0.151,,,,0.0114 +AT5G35555,,0.01713193,,,,,0.0,,,,,,,,0.01,,,,,0.0,,,0.151,,,,0.011 +AT5G23263,,,,,,,,,,,,,,,,,,,,,,,,,,, diff --git a/test_data/merge_data/output/all_counts.parquet b/test_data/merge_data/output/all_counts.parquet new file mode 100644 index 000000000..65e1301e4 Binary files /dev/null and b/test_data/merge_data/output/all_counts.parquet differ diff --git a/test_data/normalisation/base/counts.csv b/test_data/normalisation/base/counts.csv new file mode 100644 index 000000000..ba76be4e0 --- /dev/null +++ b/test_data/normalisation/base/counts.csv @@ -0,0 +1,13 @@ +,E_MTAB_5038_rnaseq_SRR1586392,E_MTAB_5038_rnaseq_SRR1586393,E_MTAB_5038_rnaseq_SRR1586394,E_MTAB_5038_rnaseq_SRR1586395,E_MTAB_5038_rnaseq_SRR1586396,E_MTAB_5038_rnaseq_SRR1586397,E_MTAB_5038_rnaseq_SRR1586400,E_MTAB_5038_rnaseq_SRR1586401,E_MTAB_5038_rnaseq_SRR1586402 +ENSRNA549434199,14,25,27,47,39,34,38,19,64 +ENSRNA549434200,91,37,78,84,6,51,18,2,57 +ENSRNA549434201,98,48,69,7,73,48,57,92,36 +ENSRNA549434202,52,15,41,19,8,100,85,83,97 +ENSRNA549434203,86,71,53,16,66,23,12,42,33 +ENSRNA549434204,62,2,25,89,74,32,45,56,26 +ENSRNA549434205,98,42,79,76,74,85,3,91,56 +ENSRNA549434206,42,49,4,88,82,34,27,83,98 +ENSRNA549434207,82,93,85,14,38,8,98,97,30 +ENSRNA549434208,72,36,4,60,25,7,14,76,47 +ENSRNA549434209,65,12,99,82,72,52,24,79,31 +ENSRNA549434210,0,0,0,0,0,0,0,0,0 diff --git a/test_data/normalisation/base/design.csv b/test_data/normalisation/base/design.csv new file mode 100644 index 000000000..ef161acb9 --- /dev/null +++ b/test_data/normalisation/base/design.csv @@ -0,0 +1,10 @@ +batch,condition,sample +E_MTAB_5038_rnaseq,g1,E_MTAB_5038_rnaseq_SRR1586392 +E_MTAB_5038_rnaseq,g1,E_MTAB_5038_rnaseq_SRR1586393 +E_MTAB_5038_rnaseq,g1,E_MTAB_5038_rnaseq_SRR1586394 +E_MTAB_5038_rnaseq,g2,E_MTAB_5038_rnaseq_SRR1586395 +E_MTAB_5038_rnaseq,g2,E_MTAB_5038_rnaseq_SRR1586396 +E_MTAB_5038_rnaseq,g2,E_MTAB_5038_rnaseq_SRR1586397 +E_MTAB_5038_rnaseq,g3,E_MTAB_5038_rnaseq_SRR1586400 +E_MTAB_5038_rnaseq,g3,E_MTAB_5038_rnaseq_SRR1586401 +E_MTAB_5038_rnaseq,g3,E_MTAB_5038_rnaseq_SRR1586402 diff --git a/test_data/normalisation/many_zeros/counts.csv b/test_data/normalisation/many_zeros/counts.csv new file mode 100644 index 000000000..261de1aa6 --- /dev/null +++ b/test_data/normalisation/many_zeros/counts.csv @@ -0,0 +1,6 @@ +,E_CURD_1_rnaseq_ERR274309,E_CURD_1_rnaseq_ERR274310,E_CURD_1_rnaseq_SRR070570,E_CURD_1_rnaseq_SRR070571,E_CURD_1_rnaseq_SRR1001909,E_CURD_1_rnaseq_SRR1001910,E_CURD_1_rnaseq_SRR1019221,E_CURD_1_rnaseq_SRR1046909,E_CURD_1_rnaseq_SRR1046910,E_CURD_1_rnaseq_SRR1105822,E_CURD_1_rnaseq_SRR1105823,E_CURD_1_rnaseq_SRR1106559,E_CURD_1_rnaseq_SRR1159821,E_CURD_1_rnaseq_SRR1159827,E_CURD_1_rnaseq_SRR1159831,E_CURD_1_rnaseq_SRR1159837,E_CURD_1_rnaseq_SRR949993 +AT1G80990,0,0,1,0,1,1,0,0,1,1,3,0,0,1,1,1,0 +AT2G01008,11,24,3,4,6,4,0,0,2,0,0,1,4,2,4,4,0 +AT2G01010,9,1,195,195,8,33,0,14,7,0,0,2,1,0,0,0,0 +AT2G01020,34,27,41,55,58,107,2,10,20,1,3,1,4,2,3,0,0 +AT2G01021,22,10,0,0,0,0,0,106,20,0,0,1,0,0,0,0,0 diff --git a/test_data/normalisation/many_zeros/design.csv b/test_data/normalisation/many_zeros/design.csv new file mode 100644 index 000000000..a6473d3af --- /dev/null +++ b/test_data/normalisation/many_zeros/design.csv @@ -0,0 +1,18 @@ +batch,condition,sample +E_CURD_1_rnaseq,g2,E_CURD_1_rnaseq_ERR274309 +E_CURD_1_rnaseq,g3,E_CURD_1_rnaseq_ERR274310 +E_CURD_1_rnaseq,g23,E_CURD_1_rnaseq_SRR070570 +E_CURD_1_rnaseq,g23,E_CURD_1_rnaseq_SRR070571 +E_CURD_1_rnaseq,g55,E_CURD_1_rnaseq_SRR1001909 +E_CURD_1_rnaseq,g55,E_CURD_1_rnaseq_SRR1001910 +E_CURD_1_rnaseq,g56,E_CURD_1_rnaseq_SRR1019221 +E_CURD_1_rnaseq,g48,E_CURD_1_rnaseq_SRR1046909 +E_CURD_1_rnaseq,g48,E_CURD_1_rnaseq_SRR1046910 +E_CURD_1_rnaseq,g50,E_CURD_1_rnaseq_SRR1105822 +E_CURD_1_rnaseq,g50,E_CURD_1_rnaseq_SRR1105823 +E_CURD_1_rnaseq,g50,E_CURD_1_rnaseq_SRR1106559 +E_CURD_1_rnaseq,g6,E_CURD_1_rnaseq_SRR1159821 +E_CURD_1_rnaseq,g6,E_CURD_1_rnaseq_SRR1159827 +E_CURD_1_rnaseq,g6,E_CURD_1_rnaseq_SRR1159831 +E_CURD_1_rnaseq,g6,E_CURD_1_rnaseq_SRR1159837 +E_CURD_1_rnaseq,g44,E_CURD_1_rnaseq_SRR949993 diff --git a/test_data/normalisation/one_group/counts.csv b/test_data/normalisation/one_group/counts.csv new file mode 100644 index 000000000..0ec999c94 --- /dev/null +++ b/test_data/normalisation/one_group/counts.csv @@ -0,0 +1,6 @@ +sampleA,sampleB,sampleC,sampleD +ENSG00000000003,14,4,4,10 +ENSG00000000005,0,0,0,0 +ENSG00000000419,562,584,523,616 +ENSG00000000457,586,377,207,491 +ENSG00000000460,130,55,28,77 diff --git a/test_data/normalisation/one_group/design.csv b/test_data/normalisation/one_group/design.csv new file mode 100644 index 000000000..9aaadb1d4 --- /dev/null +++ b/test_data/normalisation/one_group/design.csv @@ -0,0 +1,5 @@ +batch,condition,sample +batch1,g1,sampleA +batch1,g1,sampleB +batch1,g1,sampleC +batch1,g1,sampleD diff --git a/test_data/quantile_normalisation/count.raw.cpm.csv b/test_data/quantile_normalisation/count.raw.cpm.csv new file mode 100644 index 000000000..e8ecde055 --- /dev/null +++ b/test_data/quantile_normalisation/count.raw.cpm.csv @@ -0,0 +1,10 @@ +,sample_63,sample_64,sample_65,sample_66,sample_67,sample_68,sample_69,sample_70 +ENSRNA049454747,9.07095165125094,56.5509090498679,12.6897789869867,15.7656784862991,4.55005160208214,5.21967362537592,8.87627280506172,6.33326316409849 +ENSRNA049454887,0.740485849081709,1.66326203087847,0.229679257683017,0.785665040845472,2.20608562525195,2.37257892062542,0.365278716257684,0.139192597013154 +ENSRNA049454931,1.20328950475778,2.61369747709473,0.574198144207542,1.46657474291155,2.0682052736737,3.32161048887559,0.620973817638062,0.591568537305903 +ENSRNA049454947,1.48097169816342,2.1384797539866,0.459358515366033,1.57133008169094,2.89548738314318,3.08435259681304,0.474862331134989,0.452375940292749 +ENSRNA049454955,1.29585023589299,2.61369747709473,0.516778329786788,1.09993105718366,3.8606498441909,4.03338416506321,0.584445946012294,0.452375940292749 +ENSRNA049454963,1.38841096702821,4.51456836952727,1.43549536051885,2.7236388082643,4.96369265681688,5.45693151743846,1.35153125015343,1.25273337311838 +ENSRNA049454974,1.66609316043385,3.564132923311,2.52647183451318,2.46175046131581,5.51521406312986,12.5746682793147,1.71680996641111,1.53111856714469 +ENSRNA049455639,0.185121462270427,0.237608861554067,0.803877401890558,1.15230872657336,0.137880351578247,0.237257892062542,0.438334459509221,0.417577791039461 +ENSRNA049455690,0.0925607311352137,1.18804430777033,0.746457587469804,2.98552715521279,0.137880351578247,0.237257892062542,0.876668919018441,0.487174089546038