From 82be711eba40ba1075cf2b515668a1a4537ae120 Mon Sep 17 00:00:00 2001 From: Olivier Coen Date: Sat, 17 May 2025 09:20:37 +0200 Subject: [PATCH] first commit --- README.md | 38 ++---------------- .../input/count.raw.cpm.quant_norm.parquet | Bin 0 -> 6530 bytes .../gene_statistics/input/gene_counts.csv | 28 +++++++++++++ test_data/gene_statistics/input/ks_stats.csv | 27 +++++++++++++ test_data/gene_statistics/input/mapping1.csv | 9 +++++ test_data/gene_statistics/input/mapping2.csv | 9 +++++ test_data/gene_statistics/input/mapping3.csv | 5 +++ test_data/gene_statistics/input/metadata1.csv | 5 +++ test_data/gene_statistics/input/metadata2.csv | 4 ++ .../idmapping/base/counts.ensembl_ids.csv | 4 ++ test_data/idmapping/base/counts.ncbi_ids.csv | 4 ++ .../idmapping/base/counts.uniprot_ids.csv | 4 ++ test_data/idmapping/custom/mapping.csv | 4 ++ test_data/idmapping/empty/counts.csv | 1 + test_data/idmapping/not_found/counts.csv | 4 ++ test_data/input_datasets/input.csv | 3 ++ .../input_datasets/microarray.normalised.csv | 10 +++++ .../microarray.normalised.design.csv | 13 ++++++ test_data/input_datasets/rnaseq.raw.csv | 10 +++++ .../input_datasets/rnaseq.raw.design.csv | 13 ++++++ test_data/merge_data/input/counts1.parquet | Bin 0 -> 3933 bytes test_data/merge_data/input/counts2.parquet | Bin 0 -> 3865 bytes test_data/merge_data/input/counts3.parquet | Bin 0 -> 3921 bytes test_data/merge_data/input/dataset_stat1.csv | 10 +++++ test_data/merge_data/input/dataset_stat2.csv | 10 +++++ test_data/merge_data/input/dataset_stat3.csv | 10 +++++ test_data/merge_data/input/design1.csv | 10 +++++ test_data/merge_data/input/design2.csv | 10 +++++ test_data/merge_data/input/design3.csv | 10 +++++ test_data/merge_data/output/all_counts.csv | 15 +++++++ .../merge_data/output/all_counts.parquet | Bin 0 -> 11036 bytes test_data/normalisation/base/counts.csv | 13 ++++++ test_data/normalisation/base/design.csv | 10 +++++ test_data/normalisation/many_zeros/counts.csv | 6 +++ test_data/normalisation/many_zeros/design.csv | 18 +++++++++ test_data/normalisation/one_group/counts.csv | 6 +++ test_data/normalisation/one_group/design.csv | 5 +++ .../quantile_normalisation/count.raw.cpm.csv | 10 +++++ 38 files changed, 304 insertions(+), 34 deletions(-) create mode 100644 test_data/dataset_statistics/input/count.raw.cpm.quant_norm.parquet create mode 100644 test_data/gene_statistics/input/gene_counts.csv create mode 100644 test_data/gene_statistics/input/ks_stats.csv create mode 100644 test_data/gene_statistics/input/mapping1.csv create mode 100644 test_data/gene_statistics/input/mapping2.csv create mode 100644 test_data/gene_statistics/input/mapping3.csv create mode 100644 test_data/gene_statistics/input/metadata1.csv create mode 100644 test_data/gene_statistics/input/metadata2.csv create mode 100644 test_data/idmapping/base/counts.ensembl_ids.csv create mode 100644 test_data/idmapping/base/counts.ncbi_ids.csv create mode 100644 test_data/idmapping/base/counts.uniprot_ids.csv create mode 100644 test_data/idmapping/custom/mapping.csv create mode 100644 test_data/idmapping/empty/counts.csv create mode 100644 test_data/idmapping/not_found/counts.csv create mode 100644 test_data/input_datasets/input.csv create mode 100644 test_data/input_datasets/microarray.normalised.csv create mode 100644 test_data/input_datasets/microarray.normalised.design.csv create mode 100644 test_data/input_datasets/rnaseq.raw.csv create mode 100644 test_data/input_datasets/rnaseq.raw.design.csv create mode 100644 test_data/merge_data/input/counts1.parquet create mode 100644 test_data/merge_data/input/counts2.parquet create mode 100644 test_data/merge_data/input/counts3.parquet create mode 100644 test_data/merge_data/input/dataset_stat1.csv create mode 100644 test_data/merge_data/input/dataset_stat2.csv create mode 100644 test_data/merge_data/input/dataset_stat3.csv create mode 100644 test_data/merge_data/input/design1.csv create mode 100644 test_data/merge_data/input/design2.csv create mode 100644 test_data/merge_data/input/design3.csv create mode 100644 test_data/merge_data/output/all_counts.csv create mode 100644 test_data/merge_data/output/all_counts.parquet create mode 100644 test_data/normalisation/base/counts.csv create mode 100644 test_data/normalisation/base/design.csv create mode 100644 test_data/normalisation/many_zeros/counts.csv create mode 100644 test_data/normalisation/many_zeros/design.csv create mode 100644 test_data/normalisation/one_group/counts.csv create mode 100644 test_data/normalisation/one_group/design.csv create mode 100644 test_data/quantile_normalisation/count.raw.cpm.csv 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 0000000000000000000000000000000000000000..43a77ae2d5c36fae22759d53eff9d3a92fba21a5 GIT binary patch literal 6530 zcmc&(Pi))P8Glw~$H|<=b4pDHd@zKRC{QQXKT2k>HlyT-k}D~(>`)T7!5}GGqD)en z{#p(K6vI&T(8Cby&_fSBw>|DO3_}h@(L)bC6hV){;6o2RZ8v>7HwBX=YO0(Ufg`#M@;A|V#{SU-iRb?U|jxLu|esD-r% zdh43QD-&V;UgrRY0pR6dyWqPr=bm2n2jiIDWMPqC@AT^VT;GAGGmO_W}PRZ3j}+2y8W)OGbB z5*q1;NBYc2KQhvfj`X)i`s{E&>PMcH)wR`6XtYKxtukm~dG#Do%H>({{K@V4(nbGm zj$VARJ#}>hc2GpQ5PX*52O$h`#fCVWFLD00%k!~|{^~XQ8`s(to5KrYgbBu9U7n9z z^wW9z)I9?XrazCzF8cHm{d{2t7!e1?zc15&ygUPps3TS%EYW}Y#SAdE92k#Zr$48QVVCPu$${J#vs4W&z4WTPAikL}{GD&*F!p_h{| zHsXG=sgf{jduC88O@Mkm7( z(TrfXCc_fZj9}TxutYQ)*rCSY?-BAYak<>R{B7$t=l#zcoA_b5B*$^P@Z#q^ zjtg_KGMC`EG8ZqCu~=+K-o=A=2lDhT=;A&+#0!z9IIhcq9sFV^@k|V4(C4_MAM|6< zl%cmpUI-V0*^ZnPTC$nZ?rAYu?d>$AJad$)*2*b!ry?6AJ*9QaDTArV`3G31UCJLf z({WByLb-}!?!p+?wfh|)mGVp-{2z&XDU1yq16@^M{c0gb z{H6?6lMJC+iW7NDEaWQS!(ZG3zR9L0=9#J-%++N>A^rp*$EWwp+TjRyr3dy{y>gZQS*Y(*}_nxe23%=Abs3@I-(#RPki zPPYg(Q7mMg*oMrrmC|<6Z`Vfv{4&m*h{kcJSlA6_$Hkmy0y2NhrsKF4&tja;8K z!eO>*UAVGW9oH;|CG7SYCoM@Tjy2eHZ*B{IC5+0ypr6O$$Gjt zx0cSU$n8CAkGpW)+B&Zww@UY?b8G9&EVuS~6WY;XJ$Dq%+T&$j*AyesQ?0$TtL76u z#bE6^6LrPR*5zQB?Ejhlqjn}9?xsxG1L8YpaWsUU64W~~_8Cw0($!Qu)7xS3(F*4_ zoUisi4##jDpU3Gk9J{eDKAZ28V;c9jA7K3&{_y0y4&$bEKA*h3xw!?syW8YY2UFa^ zAL}`SpV-+xbb?3Yz0J<%CT?)=O=(}n{<6oW!r6xg~*Ou;45f9DO{HGHNiMYO_Jwuby2`G80)JAR^bdUue^|H=|NHWP&6|Va literal 0 HcmV?d00001 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 0000000000000000000000000000000000000000..e0db1417a9e5da1d904fbb354ee7a5399451ae75 GIT binary patch literal 3933 zcmcIneN0nV6u&K63MiuEKKo|bS3=|BCT-z?Y<~1YE232TD%3%yOdX}zJteVxRW!+7N0JfdZdKg*x4+QM4hjyxTLJyt5p?in&vO| zm-;f;wY*5S>&8OPcs}<$0e*Sh!5!{Wwm3`FOR?c~@6+$JX|ymgZf}O*^0Ga}=j?%LX5hbNPQ`Li8HG8KX0b?p&~Ra{l*Kv4G1t za%tj&p4{~TitX{)60u3s-S>(;=O;ZNeJ&5Zy!we|!G~*cJoY4jhT@1jvGX`kwvyi;Rr0nUCMVXDmzdAs=HL zD?XF)I|r}4jC|g>5p$j>D6!x}8nW#h9SVt?@{fFm%c=^SsjeWFueQI&}G$M1{<{8eDWXR7L z#40(RBTxHd`?0uAtUBj??#uC2EYZG_#ZES4QT*5P)x8fr8lcg{rlLmKNqUyTazl>_?KcJ>|VpLN*05w&&QBBneYAQCPnu-S0boPyEIP*e62YPZtE4?=#J>Q>@*e#(}Z56(``hclD&v8?1g zo|Bvp<|gOEdHguxj4nv7-_B30bGtgSX4an0&b>SzF2O>(=>jZdHEtlqvq6`WUAhP*!z8NOX_N}~)FrP`7e;zQyq}g?qVTAcx z!W>o1FlqKn{)8W!9;b37Hy^uzYYzPAtKIli*R~za9a~(7okjR`i=Yr9 z1b<@Levo@~oPsQu)(O!iDusYi7fT{&-;MfeAzBi4oiJ90QH4>&D@r3O*af&tnz>% literal 0 HcmV?d00001 diff --git a/test_data/merge_data/input/counts2.parquet b/test_data/merge_data/input/counts2.parquet new file mode 100644 index 0000000000000000000000000000000000000000..18cd85d36b63fd4fe69e14642e54273e39803afc GIT binary patch literal 3865 zcmcInZA_b06uzxc$~Oq_weRfaN2Jb7M_YLLP`33#J7imdmeK{1i3}Nzk1_ceuq+W0 ze{9L3#BZZNsxJBieh_v0VbI`WTr{wthRiG)Nk)vnOf}4pI1c2g($^}<6+1ufUm_~L3U=c&}N*|24*Z%aApMvF@s|^)*XR**@Ay^BEf5iV=kB$_@2>jLx zZ=@sdyOp(v(wjlY@Vxo!mo8}rIz)_!$o=B1_w9{(oeq~%(lMFNb%J!*X!cRJsr_&>;{J`|drt?=L`3eU^TzRS)hzg*czVtpunZbgiUDEqr+|HO{_^g1de9jk?0hsc%rjdUz+ z-zdFCupa9t&EFp1<20y;KwkN+J@bc0Dm@}c_g*R`9nm7LL&VDbYM~jL&Q`PJcC3dg zM5ToAfUSn6+P1oo42v!TuxJi4EDkro;>^mhICB7tqa?%PNB}H$xD1P(39#6BGAuR_ zz+ykhuy~&Ui`OK>qTB$B>cwC?9Z}9eeTZtOQL_>;#q7!SxILW_w}2T@8EVDY=;-@eP4;JXrhcYtF`Z^l-1o`eoAkN66&t-wmA%9f zvFK=$z4qu^NHcjC(#%=)G)dlC^dqGCl+!F^>1mR@bm$_|+~PFLIeMBT?+m(zG#}e= zQLA}+nj~93y@fP?a++v?o+inTO<%SH%_SApOcv>Bl5Dti7HQTw&9tJYNwQzk&ynVX zZJ>rOXH$#AO3&sNV;8XHuwbz1@T0?BPj?S=+Rj@`@iWG}j4>a4S=A}<#{+1B&xZ~& zHq7c6gJ*#4YR336#2XmviNy`Vv(Arh5Qm$`YQc9xI6I0Qbpi0bT^QWYGk88HuSCAn zIJikx&rKid39#A*28r#=dWB%Sg%^$+4yu%Pw z>c_OrdQ7CQ9=P>VR1XxLl6o+0s~!`4>+wwon+ZO?R`|KidExsN79C(-Osx-(cDchN qZ3E-S+TG#N_HgydcEQhz9s`yo zLb5+xvP7d%aT?=;C>b*$lld1Wx)>MDSTsUrmidSy#F&K`!|)Z1=UjT}kM`%%#L#U0 z-E+@5-}CvM-pA%+0S8T_M``muYNCXYg3E;~TZ=ss`85SB7Iah>6_=LV)#@TuRh>o7 z5=S+D+Y`vv%|5ebVGAWRhuR*2>?~@eMr#QvNMXU%c)JCL;RK;=_7h?N!z39J<_S$x zRAS6hESasxdt1AjI~&_tkGD1+dzz-nCi#ve{~_5-75}XX)%Vd5RwtsmX<+0ETZ6Maxt=BC+qwCNlYGF^J8k&-rH|AIOP)l2US$zMA|(Cu=iG0vR7>Q8 zf*2TwUBFzBY@5St zQZk1T`Pw3SFl_rX^CJv@rL!MC)c#JJQxB&7&yk6W*O*I$gp>4PoEn&GDI7+xh#t)R z(%sWD&m+vM3n9})Ua=mGaEaiN>to(I)vXUxq=8vToTSO0LtoZe-O;z|ay}~Yk zdbVt*9*hWbeXOXBw*#(ls6I@w24*;e!-#xs5j~j9#p^e_ZUh0wxVK*_{KT&ZBU~c* z-3QX&zxHfEA4b){oX_GgB2Qa{!yI0}o4ThTcZN>lZkpJ2#s1V6bGu0R#IiZ0@TnqV zL`2cw6}yM-f6yhK(YxDGB6ubx+ten`BQ&&i^qMo1w^De6U~`sE7`{2S!>-pH;d=SE zhLrCfEp>&H^qW&EU|@I8=5QFjB1*Oa&Zo7rm5;+mE+vXg2oG30{}jvGfu(he^9J1F z2+_L52>@=fskLsgC&4YYnbs|K3%JF?*Sf{h2Dey>TDMqH;1-KR>lQyQxW#X!b&HmR zTXZk%w#sKDdKwx;6stU(K*y!%_Oq}7PAM0&7+S=7*IcF-w&j52X#ys$sm7N58(2ql~`P5#c>%)iVfqoApmBCa!t8Bvp9pJ0nUDsJN;BD_vy+JJH?uDR2FQ%;~ z*W-}+VFpA!n1@e40z))@!Dk!3{{Yl&V}RlZbeQyn4%D@?q1s@_;C_7N+EZ9xGy(K* z64YP@U=Cm&JOklZ;s{Wo1bN^sK^M3g+k;7g(4GTcca2&b^f=Jon10|(Y)n7A*oBSh z$I!<01DD&FmZdVJBrVuFvS4!-WOU-){3m-aI^rdEggTb!Z3`mVtv m4bD)1L#X^j17kag#pvtqZ0hM%F2ePEk3ZygG9fEr?97++;(7IstzPEE{W@l#CPP$&f z?!0;LoqOiKd(XS`AXmzd6M}{Nyimu@79s^gNc5R0&&Qpe%999wFf^sYxETqFDQU4u zGZK=LlHwEMljGtO64^zEbt*3q!<6u_{=+%-b#LzL9~$DNa~JNe~YSOSENu^QFC^2W)P0!fsAOjE}a&z1fkoV^+xVc$GBL=@hmT1 z=j^>9>B&AUdwjQ2LlGY4p9UR%H zu-df##`Zt7bvkeq&bxX2{IJt|u5qN|cmD}CFpEcK&7A#F7-NPLwFW)Ryw((+;lC3e z|E8|eG}vHGs}*X;n==o82*HNqw=WMrzN_Pgqw?0RsXxDPm4uM0rrA7=yIWhQaR!bF zjN=}*rtb}991%$y<{pk)yuJ6qgufr?yiC^=lL5od{cDaKR49hOCH*TqrprM#P20I* z>AcSzIPuQXMaQyYzH;!Sy(DXNm62T{da#AFKN!x~;asgzVAsS6+coS$qb&=5+xtez ziEa~iKRuyg7u>Wns&oFEoemtos?z=EPfvX5c>JMTJaCR>ZNZ&WqjoK?8)EQY661G} z7eC?b$3~_n`!MVA-ck)eSm5sA_imJoybJuS-`v<1*11}ZJr^Xc;yq=YJSyh*jn8Yp zKI4ESeb*#OlhI{oIeT{mbD4smvE-qoONR>=(!x%>^EFUfvT$h1j;qZoC9iaF&%2nj zIR36<|IoV&-N!$6;5>Pjk90^uW{?iGqZu=ts5R(ew#wUCD5cs}_b8mZ)J%E_YA#L; zBGR2#U;O9pC}j;@dgX28?9Dbt3nyu_Lz$8+w6Gb# z8a^7sC?SH@lIa@y5n8V`jM#d7#Jb!rUuvscLu96iEv(_87Z@`$gC1s;-fO68pFu8; zY87oz=+nB#?OndaR^CN#{Y;}~NKaARR?glsj?pu-YD&*c_T&)rqSu$;dNz4edLFTb zbp?7g;~70Ot3VGn`FC}jyqWOHn|u;as+CP1)fUB7C%R-?#K{?VDytp%8%z=g6aL)& zogZnoFm$L#fMLsj!r8Axu`S<>hiN3Dpjs^`u}X4yMI!d%c%1!X=3 z5kPCu!%SDmse)*TM6W_l8K;w8vqBC%rsyveah2 ziU>mp*2XY;W>!tzW+sbrhIqN{yVSpuUWIA>JB9HwGY7mNHTLOJLzN)C-^xDc$Z58f z`m28l0wi1vAsN4D`aCGO?8c>-FGnexg-lZ|fjgiCj$`?NbB&vYPXEjXnh8uF%51i} zNKcVxs(*>hi)L0mtE=1mRiVTx*F0VOkY`=GA~QvqAzf=y7&9}2p7pKPt*fH>R=GH8bsTpRSx! zWf28eai3QyfaCP?tSbf3Z%PFWrNF*)<~KyJT2xD>lvF)bYFYWU(CtMDdvQDpun$U# z@&cuk(-*pm5z5AjHLuZVffuLA2dig2QaBThMELxJ3gVIJe-EU?Bw5 zv~EFa8rx=W(R6 z>)O%k+-955i1#0jQO6v5K^@aFPH4q3HRILmD^bD|yk8%!j=w!o*|ed#K8Mi_1F>*pL;d_rNG8BFgmBTPS!YQ_D90JD20WpjRn5k{#f z{hz6dM<`4agXtM%gz4wer`SMYdKpZeXoS&LZhnp{#Wo7lkWC+|&1!^EUTgiIEsFOk zOb>(EJw}C*b5H$O82@L1Vs#O~oSQ}2yg$|e)8F$u@i2w?mcg{YXoOM1&;MbYc$&hT zevPtu=OrVI5`O*<#l#j0^N7J*pJ0UP=i!yuMPW|OrfeEsHp2AtL`i%`VIDA;hd(mH zC@&%YkAK92#Q;;EL)p|#Ho_?3=l`@utfw&D45s51Ba9M${!dlJW(xEE9LnZEoC+gL ztr~v*4?)Cs3UiOav?mx~RQ20+eaB0iiPL91Wu5D3A! z^L|{uY-Q=%CDs;U3jJ)6vL#7!!CxtLGi~S5OK7uOuSrt5lp#s*nyH5Ei|P+ezHDWs4J&G(Sb>iVib8+&7^{ciq4T6nI(0_zre*QP v8%x%1d3}C-@uvC3X=U>zX)3XX=B{6}WJ5WeVZrfZ!2ggQsG)P=|Hb|fLYxsb literal 0 HcmV?d00001 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