{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# DESeq2: Create count matrix and metadata data frame" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Objective: create a count matrix and metadata frame for the 2019 pilot data" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Load packages" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Registered S3 methods overwritten by 'ggplot2':\n", " method from \n", " [.quosures rlang\n", " c.quosures rlang\n", " print.quosures rlang\n", "── \u001b[1mAttaching packages\u001b[22m ─────────────────────────────────────── tidyverse 1.2.1 ──\n", "\u001b[32m✔\u001b[39m \u001b[34mggplot2\u001b[39m 3.1.1 \u001b[32m✔\u001b[39m \u001b[34mpurrr \u001b[39m 0.3.2\n", "\u001b[32m✔\u001b[39m \u001b[34mtibble \u001b[39m 2.1.2 \u001b[32m✔\u001b[39m \u001b[34mdplyr \u001b[39m 0.8.1\n", "\u001b[32m✔\u001b[39m \u001b[34mtidyr \u001b[39m 0.8.3 \u001b[32m✔\u001b[39m \u001b[34mstringr\u001b[39m 1.4.0\n", "\u001b[32m✔\u001b[39m \u001b[34mreadr \u001b[39m 1.3.1 \u001b[32m✔\u001b[39m \u001b[34mforcats\u001b[39m 0.4.0\n", "── \u001b[1mConflicts\u001b[22m ────────────────────────────────────────── tidyverse_conflicts() ──\n", "\u001b[31m✖\u001b[39m \u001b[34mdplyr\u001b[39m::\u001b[32mfilter()\u001b[39m masks \u001b[34mstats\u001b[39m::filter()\n", "\u001b[31m✖\u001b[39m \u001b[34mdplyr\u001b[39m::\u001b[32mlag()\u001b[39m masks \u001b[34mstats\u001b[39m::lag()\n" ] } ], "source": [ "library(tidyverse)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Import Counts" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/html": [ "/home/jovyan/work/scratch/analysis_output/out/hts-pilot-2019.RData: 'f617195665ef950ffb36a89f2d18a9ca'" ], "text/latex": [ "\\textbf{/home/jovyan/work/scratch/analysis\\textbackslash{}\\_output/out/hts-pilot-2019.RData:} 'f617195665ef950ffb36a89f2d18a9ca'" ], "text/markdown": [ "**/home/jovyan/work/scratch/analysis_output/out/hts-pilot-2019.RData:** 'f617195665ef950ffb36a89f2d18a9ca'" ], "text/plain": [ "/home/jovyan/work/scratch/analysis_output/out/hts-pilot-2019.RData \n", " \"f617195665ef950ffb36a89f2d18a9ca\" " ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
    \n", "\t
  1. 'genecounts'
    2. \n", "\t
  2. 'mapresults'
    3. \n", "
\n" ], "text/latex": [ "\\begin{enumerate*}\n", "\\item 'genecounts'\n", "\\item 'mapresults'\n", "\\end{enumerate*}\n" ], "text/markdown": [ "1. 'genecounts'\n", "2. 'mapresults'\n", "\n", "\n" ], "text/plain": [ "[1] \"genecounts\" \"mapresults\"" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "### Due to time constraints, we skip the import of the count files (see HTS tidyverse notebook)\n", "\n", "cntfile <- '/home/jovyan/work/scratch/analysis_output/out/hts-pilot-2019.RData'\n", "attach(cntfile)\n", "tools::md5sum(cntfile)\n", "ls(2)" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\n", "\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\n", "
A tibble: 8 × 5
expidCNAG_00001CNAG_00002CNAG_00003CNAG_00004
<chr><int><int><int><int>
1_2019_P_M1_S1_L001_ReadsPerGene.out.tab 03548223
1_2019_P_M1_S1_L002_ReadsPerGene.out.tab 04346227
1_2019_P_M1_S1_L003_ReadsPerGene.out.tab 04649232
1_2019_P_M1_S1_L004_ReadsPerGene.out.tab 03458222
10_2019_P_M1_S10_L001_ReadsPerGene.out.tab03036130
10_2019_P_M1_S10_L002_ReadsPerGene.out.tab03737117
10_2019_P_M1_S10_L003_ReadsPerGene.out.tab02931135
10_2019_P_M1_S10_L004_ReadsPerGene.out.tab02327131
\n" ], "text/latex": [ "A tibble: 8 × 5\n", "\\begin{tabular}{r|lllll}\n", " expid & CNAG\\_00001 & CNAG\\_00002 & CNAG\\_00003 & CNAG\\_00004\\\\\n", " & & & & \\\\\n", "\\hline\n", "\t 1\\_2019\\_P\\_M1\\_S1\\_L001\\_ReadsPerGene.out.tab & 0 & 35 & 48 & 223\\\\\n", "\t 1\\_2019\\_P\\_M1\\_S1\\_L002\\_ReadsPerGene.out.tab & 0 & 43 & 46 & 227\\\\\n", "\t 1\\_2019\\_P\\_M1\\_S1\\_L003\\_ReadsPerGene.out.tab & 0 & 46 & 49 & 232\\\\\n", "\t 1\\_2019\\_P\\_M1\\_S1\\_L004\\_ReadsPerGene.out.tab & 0 & 34 & 58 & 222\\\\\n", "\t 10\\_2019\\_P\\_M1\\_S10\\_L001\\_ReadsPerGene.out.tab & 0 & 30 & 36 & 130\\\\\n", "\t 10\\_2019\\_P\\_M1\\_S10\\_L002\\_ReadsPerGene.out.tab & 0 & 37 & 37 & 117\\\\\n", "\t 10\\_2019\\_P\\_M1\\_S10\\_L003\\_ReadsPerGene.out.tab & 0 & 29 & 31 & 135\\\\\n", "\t 10\\_2019\\_P\\_M1\\_S10\\_L004\\_ReadsPerGene.out.tab & 0 & 23 & 27 & 131\\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "A tibble: 8 × 5\n", "\n", "| expid <chr> | CNAG_00001 <int> | CNAG_00002 <int> | CNAG_00003 <int> | CNAG_00004 <int> |\n", "|---|---|---|---|---|\n", "| 1_2019_P_M1_S1_L001_ReadsPerGene.out.tab | 0 | 35 | 48 | 223 |\n", "| 1_2019_P_M1_S1_L002_ReadsPerGene.out.tab | 0 | 43 | 46 | 227 |\n", "| 1_2019_P_M1_S1_L003_ReadsPerGene.out.tab | 0 | 46 | 49 | 232 |\n", "| 1_2019_P_M1_S1_L004_ReadsPerGene.out.tab | 0 | 34 | 58 | 222 |\n", "| 10_2019_P_M1_S10_L001_ReadsPerGene.out.tab | 0 | 30 | 36 | 130 |\n", "| 10_2019_P_M1_S10_L002_ReadsPerGene.out.tab | 0 | 37 | 37 | 117 |\n", "| 10_2019_P_M1_S10_L003_ReadsPerGene.out.tab | 0 | 29 | 31 | 135 |\n", "| 10_2019_P_M1_S10_L004_ReadsPerGene.out.tab | 0 | 23 | 27 | 131 |\n", "\n" ], "text/plain": [ " expid CNAG_00001 CNAG_00002 CNAG_00003\n", "1 1_2019_P_M1_S1_L001_ReadsPerGene.out.tab 0 35 48 \n", "2 1_2019_P_M1_S1_L002_ReadsPerGene.out.tab 0 43 46 \n", "3 1_2019_P_M1_S1_L003_ReadsPerGene.out.tab 0 46 49 \n", "4 1_2019_P_M1_S1_L004_ReadsPerGene.out.tab 0 34 58 \n", "5 10_2019_P_M1_S10_L001_ReadsPerGene.out.tab 0 30 36 \n", "6 10_2019_P_M1_S10_L002_ReadsPerGene.out.tab 0 37 37 \n", "7 10_2019_P_M1_S10_L003_ReadsPerGene.out.tab 0 29 31 \n", "8 10_2019_P_M1_S10_L004_ReadsPerGene.out.tab 0 23 27 \n", " CNAG_00004\n", "1 223 \n", "2 227 \n", "3 232 \n", "4 222 \n", "5 130 \n", "6 117 \n", "7 135 \n", "8 131 " ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
    \n", "\t
  1. 144
    2. \n", "\t
  2. 8500
    3. \n", "
\n" ], "text/latex": [ "\\begin{enumerate*}\n", "\\item 144\n", "\\item 8500\n", "\\end{enumerate*}\n" ], "text/markdown": [ "1. 144\n", "2. 8500\n", "\n", "\n" ], "text/plain": [ "[1] 144 8500" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "### Look at the first five genes across the libraries\n", "\n", "genecounts[1:8, 1:5]\n", "dim(genecounts)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Filter out 2018 libraries from count file" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
    \n", "\t
  1. 96
    2. \n", "\t
  2. 8500
    3. \n", "
\n" ], "text/latex": [ "\\begin{enumerate*}\n", "\\item 96\n", "\\item 8500\n", "\\end{enumerate*}\n" ], "text/markdown": [ "1. 96\n", "2. 8500\n", "\n", "\n" ], "text/plain": [ "[1] 96 8500" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "genecounts %>% \n", " filter(str_detect(expid, \"2019\")) -> \n", " genecounts2019\n", "\n", "dim(genecounts2019)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Import metadata file" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "/data/hts_2019_data/hts2019_pilot_rawdata/2019_pilot_metadata.tsv: '757e63c2306c3c68a70b81dfcdbf7f22'" ], "text/latex": [ "\\textbf{/data/hts\\textbackslash{}\\_2019\\textbackslash{}\\_data/hts2019\\textbackslash{}\\_pilot\\textbackslash{}\\_rawdata/2019\\textbackslash{}\\_pilot\\textbackslash{}\\_metadata.tsv:} '757e63c2306c3c68a70b81dfcdbf7f22'" ], "text/markdown": [ "**/data/hts_2019_data/hts2019_pilot_rawdata/2019_pilot_metadata.tsv:** '757e63c2306c3c68a70b81dfcdbf7f22'" ], "text/plain": [ "/data/hts_2019_data/hts2019_pilot_rawdata/2019_pilot_metadata.tsv \n", " \"757e63c2306c3c68a70b81dfcdbf7f22\" " ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stderr", "output_type": "stream", "text": [ "Parsed with column specification:\n", "cols(\n", " .default = col_character(),\n", " sample_year = \u001b[32mcol_double()\u001b[39m,\n", " enrich_rep = \u001b[32mcol_double()\u001b[39m,\n", " RNA_sample_num = \u001b[32mcol_double()\u001b[39m,\n", " library_num = \u001b[32mcol_double()\u001b[39m,\n", " bio_replicate = \u001b[32mcol_double()\u001b[39m,\n", " Nanodrop_260_280 = \u001b[32mcol_double()\u001b[39m,\n", " Nanodrop_260_230 = \u001b[32mcol_double()\u001b[39m,\n", " Nanodrop_concentration_ng_ul = \u001b[32mcol_double()\u001b[39m,\n", " Bioanalyzer_concentration_ng_ul = \u001b[32mcol_double()\u001b[39m,\n", " RIN_lowered_threshold = \u001b[32mcol_double()\u001b[39m\n", ")\n", "See spec(...) for full column specifications.\n" ] }, { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\n", "\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\n", "
A spec_tbl_df: 36 × 22
Labelsample_yeargroupenrich_repRNA_sample_numgenotypeconditionlibprep_personenrichment_methodenrichment_short⋯i5_primeri7_primerlibrary_numbio_replicateNanodrop_260_280Nanodrop_260_230Nanodrop_concentration_ng_ulBioanalyzer_concentration_ng_ulRIN_normal_thresholdRIN_lowered_threshold
<chr><dbl><chr><dbl><dbl><chr><chr><chr><chr><chr>⋯<chr><chr><dbl><dbl><dbl><dbl><dbl><dbl><chr><dbl>
1_2019_P_M1 2019P1 1WT pH4CmRNA M⋯i501i701 112.141.52293 197N/A 9.8
2_2019_P_M1 2019P1 2WT pH4CmRNA M⋯i502i701 222.121.79290 225N/A 9.9
3_2019_P_M1 2019P1 3WT pH4CmRNA M⋯i503i701 332.112.49302 241N/A 9.9
4_2019_P_M1 2019P1 4WT pH4PmRNA M⋯i504i701 442.131.15296 189N/A 9.7
5_2019_P_M1 2019P1 5WT pH4PmRNA M⋯i505i701 552.092.42337 26810 10.0
6_2019_P_M1 2019P1 6WT pH4PmRNA M⋯i506i701 662.082.40319 27610 10.0
7_2019_P_M1 2019P1 7sre1dpH4CmRNA M⋯i507i701 712.132.23232 127N/A 9.9
8_2019_P_M1 2019P1 8sre1dpH4CmRNA M⋯i508i701 822.082.24320 311N/A10.0
9_2019_P_M1 2019P1 9sre1dpH4CmRNA M⋯i501i702 932.091.46342 3269.6 9.6
10_2019_P_M12019P110sre1dpH4PmRNA M⋯i502i7021042.161.25262 16810 10.0
11_2019_P_M12019P111sre1dpH4PmRNA M⋯i503i7021152.122.28212 23610 10.0
12_2019_P_M12019P112sre1dpH4PmRNA M⋯i504i7021262.122.57246 31210 10.0
13_2019_P_M12019P113WT pH8CmRNA M⋯i505i7021311.932.28465 436N/A10.0
14_2019_P_M12019P114WT pH8CmRNA M⋯i506i7021422.131.88170 99N/A 9.9
15_2019_P_M12019P115WT pH8CmRNA M⋯i507i7021532.080.97300 190N/A10.0
16_2019_P_M12019P116WT pH8PmRNA M⋯i508i7021642.152.13236 129N/A10.0
17_2019_P_M12019P117WT pH8PmRNA M⋯i501i7031752.130.89233 111N/A10.0
18_2019_P_M12019P118WT pH8PmRNA M⋯i502i7031862.142.01213 134N/A10.0
19_2019_P_M12019P119sre1dpH8CmRNA M⋯i503i7031912.142.19236 80N/A10.0
20_2019_P_M12019P120sre1dpH8CmRNA M⋯i504i7032022.142.39172 131N/A10.0
21_2019_P_M12019P121sre1dpH8CmRNA M⋯i505i7032132.012.22397 295N/A10.0
22_2019_P_M12019P122sre1dpH8PmRNA M⋯i506i7032242.222.33567 49910 10.0
23_2019_P_M12019P123sre1dpH8PmRNA M⋯i507i7032352.132.56254 206N/A10.0
24_2019_P_M12019P124sre1dpH8PmRNA M⋯i508i7032462.112.16215 33610 10.0
2_2018_P_H1 2018P1 2WT YPDJRNaseHH⋯i501i704252 NA NA NA212010 NA
3_2018_P_H1 2018P1 3WT YPDJRNaseHH⋯i502i704263 NA NA NA150010 NA
4_2018_P_H1 2018P1 4WT YPDJRNaseHH⋯i503i704274 NA NA NA149010 NA
2_2018_P_H2 2018P2 2WT YPDJRNaseHH⋯i504i704282 NA NA NA212010 NA
3_2018_P_H2 2018P2 3WT YPDJRNaseHH⋯i505i704293 NA NA NA150010 NA
4_2018_P_H2 2018P2 4WT YPDJRNaseHH⋯i506i704304 NA NA NA149010 NA
2_2018_P_T1 2018P1 2WT YPDJTotal T⋯i507i704312 NA NA NA212010 NA
3_2018_P_T1 2018P1 3WT YPDJTotal T⋯i508i704323 NA NA NA150010 NA
4_2018_P_T1 2018P1 4WT YPDJTotal T⋯i501i705334 NA NA NA149010 NA
2_2018_P_M1 2018P1 2WT YPDJmRNA M⋯i502i705342 NA NA NA212010 NA
3_2018_P_M1 2018P1 3WT YPDJmRNA M⋯i503i705353 NA NA NA150010 NA
4_2018_P_M1 2018P1 4WT YPDJmRNA M⋯i504i705364 NA NA NA149010 NA
\n" ], "text/latex": [ "A spec_tbl_df: 36 × 22\n", "\\begin{tabular}{r|llllllllllllllllllllll}\n", " Label & sample\\_year & group & enrich\\_rep & RNA\\_sample\\_num & genotype & condition & libprep\\_person & enrichment\\_method & enrichment\\_short & i7\\_index & i5\\_index & i5\\_primer & i7\\_primer & library\\_num & bio\\_replicate & Nanodrop\\_260\\_280 & Nanodrop\\_260\\_230 & Nanodrop\\_concentration\\_ng\\_ul & Bioanalyzer\\_concentration\\_ng\\_ul & RIN\\_normal\\_threshold & RIN\\_lowered\\_threshold\\\\\n", " & & & & & & & & & & & & & & & & & & & & & \\\\\n", "\\hline\n", "\t 1\\_2019\\_P\\_M1 & 2019 & P & 1 & 1 & WT & pH4 & C & mRNA & M & ATTACTCG & AGGCTATA & i501 & i701 & 1 & 1 & 2.14 & 1.52 & 293 & 197 & N/A & 9.8\\\\\n", "\t 2\\_2019\\_P\\_M1 & 2019 & P & 1 & 2 & WT & pH4 & C & mRNA & M & ATTACTCG & GCCTCTAT & i502 & i701 & 2 & 2 & 2.12 & 1.79 & 290 & 225 & N/A & 9.9\\\\\n", "\t 3\\_2019\\_P\\_M1 & 2019 & P & 1 & 3 & WT & pH4 & C & mRNA & M & ATTACTCG & AGGATAGG & i503 & i701 & 3 & 3 & 2.11 & 2.49 & 302 & 241 & N/A & 9.9\\\\\n", "\t 4\\_2019\\_P\\_M1 & 2019 & P & 1 & 4 & WT & pH4 & P & mRNA & M & ATTACTCG & TCAGAGCC & i504 & i701 & 4 & 4 & 2.13 & 1.15 & 296 & 189 & N/A & 9.7\\\\\n", "\t 5\\_2019\\_P\\_M1 & 2019 & P & 1 & 5 & WT & pH4 & P & mRNA & M & ATTACTCG & CTTCGCCT & i505 & i701 & 5 & 5 & 2.09 & 2.42 & 337 & 268 & 10 & 10.0\\\\\n", "\t 6\\_2019\\_P\\_M1 & 2019 & P & 1 & 6 & WT & pH4 & P & mRNA & M & ATTACTCG & TAAGATTA & i506 & i701 & 6 & 6 & 2.08 & 2.40 & 319 & 276 & 10 & 10.0\\\\\n", "\t 7\\_2019\\_P\\_M1 & 2019 & P & 1 & 7 & sre1d & pH4 & C & mRNA & M & ATTACTCG & ACGTCCTG & i507 & i701 & 7 & 1 & 2.13 & 2.23 & 232 & 127 & N/A & 9.9\\\\\n", "\t 8\\_2019\\_P\\_M1 & 2019 & P & 1 & 8 & sre1d & pH4 & C & mRNA & M & ATTACTCG & GTCAGTAC & i508 & i701 & 8 & 2 & 2.08 & 2.24 & 320 & 311 & N/A & 10.0\\\\\n", "\t 9\\_2019\\_P\\_M1 & 2019 & P & 1 & 9 & sre1d & pH4 & C & mRNA & M & TCCGGAGA & AGGCTATA & i501 & i702 & 9 & 3 & 2.09 & 1.46 & 342 & 326 & 9.6 & 9.6\\\\\n", "\t 10\\_2019\\_P\\_M1 & 2019 & P & 1 & 10 & sre1d & pH4 & P & mRNA & M & TCCGGAGA & GCCTCTAT & i502 & i702 & 10 & 4 & 2.16 & 1.25 & 262 & 168 & 10 & 10.0\\\\\n", "\t 11\\_2019\\_P\\_M1 & 2019 & P & 1 & 11 & sre1d & pH4 & P & mRNA & M & TCCGGAGA & AGGATAGG & i503 & i702 & 11 & 5 & 2.12 & 2.28 & 212 & 236 & 10 & 10.0\\\\\n", "\t 12\\_2019\\_P\\_M1 & 2019 & P & 1 & 12 & sre1d & pH4 & P & mRNA & M & TCCGGAGA & TCAGAGCC & i504 & i702 & 12 & 6 & 2.12 & 2.57 & 246 & 312 & 10 & 10.0\\\\\n", "\t 13\\_2019\\_P\\_M1 & 2019 & P & 1 & 13 & WT & pH8 & C & mRNA & M & TCCGGAGA & CTTCGCCT & i505 & i702 & 13 & 1 & 1.93 & 2.28 & 465 & 436 & N/A & 10.0\\\\\n", "\t 14\\_2019\\_P\\_M1 & 2019 & P & 1 & 14 & WT & pH8 & C & mRNA & M & TCCGGAGA & TAAGATTA & i506 & i702 & 14 & 2 & 2.13 & 1.88 & 170 & 99 & N/A & 9.9\\\\\n", "\t 15\\_2019\\_P\\_M1 & 2019 & P & 1 & 15 & WT & pH8 & C & mRNA & M & TCCGGAGA & ACGTCCTG & i507 & i702 & 15 & 3 & 2.08 & 0.97 & 300 & 190 & N/A & 10.0\\\\\n", "\t 16\\_2019\\_P\\_M1 & 2019 & P & 1 & 16 & WT & pH8 & P & mRNA & M & TCCGGAGA & GTCAGTAC & i508 & i702 & 16 & 4 & 2.15 & 2.13 & 236 & 129 & N/A & 10.0\\\\\n", "\t 17\\_2019\\_P\\_M1 & 2019 & P & 1 & 17 & WT & pH8 & P & mRNA & M & CGCTCATT & AGGCTATA & i501 & i703 & 17 & 5 & 2.13 & 0.89 & 233 & 111 & N/A & 10.0\\\\\n", "\t 18\\_2019\\_P\\_M1 & 2019 & P & 1 & 18 & WT & pH8 & P & mRNA & M & CGCTCATT & GCCTCTAT & i502 & i703 & 18 & 6 & 2.14 & 2.01 & 213 & 134 & N/A & 10.0\\\\\n", "\t 19\\_2019\\_P\\_M1 & 2019 & P & 1 & 19 & sre1d & pH8 & C & mRNA & M & CGCTCATT & AGGATAGG & i503 & i703 & 19 & 1 & 2.14 & 2.19 & 236 & 80 & N/A & 10.0\\\\\n", "\t 20\\_2019\\_P\\_M1 & 2019 & P & 1 & 20 & sre1d & pH8 & C & mRNA & M & CGCTCATT & TCAGAGCC & i504 & i703 & 20 & 2 & 2.14 & 2.39 & 172 & 131 & N/A & 10.0\\\\\n", "\t 21\\_2019\\_P\\_M1 & 2019 & P & 1 & 21 & sre1d & pH8 & C & mRNA & M & CGCTCATT & CTTCGCCT & i505 & i703 & 21 & 3 & 2.01 & 2.22 & 397 & 295 & N/A & 10.0\\\\\n", "\t 22\\_2019\\_P\\_M1 & 2019 & P & 1 & 22 & sre1d & pH8 & P & mRNA & M & CGCTCATT & TAAGATTA & i506 & i703 & 22 & 4 & 2.22 & 2.33 & 567 & 499 & 10 & 10.0\\\\\n", "\t 23\\_2019\\_P\\_M1 & 2019 & P & 1 & 23 & sre1d & pH8 & P & mRNA & M & CGCTCATT & ACGTCCTG & i507 & i703 & 23 & 5 & 2.13 & 2.56 & 254 & 206 & N/A & 10.0\\\\\n", "\t 24\\_2019\\_P\\_M1 & 2019 & P & 1 & 24 & sre1d & pH8 & P & mRNA & M & CGCTCATT & GTCAGTAC & i508 & i703 & 24 & 6 & 2.11 & 2.16 & 215 & 336 & 10 & 10.0\\\\\n", "\t 2\\_2018\\_P\\_H1 & 2018 & P & 1 & 2 & WT & YPD & J & RNaseH & H & GAGATTCC & AGGCTATA & i501 & i704 & 25 & 2 & NA & NA & NA & 2120 & 10 & NA\\\\\n", "\t 3\\_2018\\_P\\_H1 & 2018 & P & 1 & 3 & WT & YPD & J & RNaseH & H & GAGATTCC & GCCTCTAT & i502 & i704 & 26 & 3 & NA & NA & NA & 1500 & 10 & NA\\\\\n", "\t 4\\_2018\\_P\\_H1 & 2018 & P & 1 & 4 & WT & YPD & J & RNaseH & H & GAGATTCC & AGGATAGG & i503 & i704 & 27 & 4 & NA & NA & NA & 1490 & 10 & NA\\\\\n", "\t 2\\_2018\\_P\\_H2 & 2018 & P & 2 & 2 & WT & YPD & J & RNaseH & H & GAGATTCC & TCAGAGCC & i504 & i704 & 28 & 2 & NA & NA & NA & 2120 & 10 & NA\\\\\n", "\t 3\\_2018\\_P\\_H2 & 2018 & P & 2 & 3 & WT & YPD & J & RNaseH & H & GAGATTCC & CTTCGCCT & i505 & i704 & 29 & 3 & NA & NA & NA & 1500 & 10 & NA\\\\\n", "\t 4\\_2018\\_P\\_H2 & 2018 & P & 2 & 4 & WT & YPD & J & RNaseH & H & GAGATTCC & TAAGATTA & i506 & i704 & 30 & 4 & NA & NA & NA & 1490 & 10 & NA\\\\\n", "\t 2\\_2018\\_P\\_T1 & 2018 & P & 1 & 2 & WT & YPD & J & Total & T & GAGATTCC & ACGTCCTG & i507 & i704 & 31 & 2 & NA & NA & NA & 2120 & 10 & NA\\\\\n", "\t 3\\_2018\\_P\\_T1 & 2018 & P & 1 & 3 & WT & YPD & J & Total & T & GAGATTCC & GTCAGTAC & i508 & i704 & 32 & 3 & NA & NA & NA & 1500 & 10 & NA\\\\\n", "\t 4\\_2018\\_P\\_T1 & 2018 & P & 1 & 4 & WT & YPD & J & Total & T & ATTCAGAA & AGGCTATA & i501 & i705 & 33 & 4 & NA & NA & NA & 1490 & 10 & NA\\\\\n", "\t 2\\_2018\\_P\\_M1 & 2018 & P & 1 & 2 & WT & YPD & J & mRNA & M & ATTCAGAA & GCCTCTAT & i502 & i705 & 34 & 2 & NA & NA & NA & 2120 & 10 & NA\\\\\n", "\t 3\\_2018\\_P\\_M1 & 2018 & P & 1 & 3 & WT & YPD & J & mRNA & M & ATTCAGAA & AGGATAGG & i503 & i705 & 35 & 3 & NA & NA & NA & 1500 & 10 & NA\\\\\n", "\t 4\\_2018\\_P\\_M1 & 2018 & P & 1 & 4 & WT & YPD & J & mRNA & M & ATTCAGAA & TCAGAGCC & i504 & i705 & 36 & 4 & NA & NA & NA & 1490 & 10 & NA\\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "A spec_tbl_df: 36 × 22\n", "\n", "| Label <chr> | sample_year <dbl> | group <chr> | enrich_rep <dbl> | RNA_sample_num <dbl> | genotype <chr> | condition <chr> | libprep_person <chr> | enrichment_method <chr> | enrichment_short <chr> | ⋯ ⋯ | i5_primer <chr> | i7_primer <chr> | library_num <dbl> | bio_replicate <dbl> | Nanodrop_260_280 <dbl> | Nanodrop_260_230 <dbl> | Nanodrop_concentration_ng_ul <dbl> | Bioanalyzer_concentration_ng_ul <dbl> | RIN_normal_threshold <chr> | RIN_lowered_threshold <dbl> |\n", "|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n", "| 1_2019_P_M1 | 2019 | P | 1 | 1 | WT | pH4 | C | mRNA | M | ⋯ | i501 | i701 | 1 | 1 | 2.14 | 1.52 | 293 | 197 | N/A | 9.8 |\n", "| 2_2019_P_M1 | 2019 | P | 1 | 2 | WT | pH4 | C | mRNA | M | ⋯ | i502 | i701 | 2 | 2 | 2.12 | 1.79 | 290 | 225 | N/A | 9.9 |\n", "| 3_2019_P_M1 | 2019 | P | 1 | 3 | WT | pH4 | C | mRNA | M | ⋯ | i503 | i701 | 3 | 3 | 2.11 | 2.49 | 302 | 241 | N/A | 9.9 |\n", "| 4_2019_P_M1 | 2019 | P | 1 | 4 | WT | pH4 | P | mRNA | M | ⋯ | i504 | i701 | 4 | 4 | 2.13 | 1.15 | 296 | 189 | N/A | 9.7 |\n", "| 5_2019_P_M1 | 2019 | P | 1 | 5 | WT | pH4 | P | mRNA | M | ⋯ | i505 | i701 | 5 | 5 | 2.09 | 2.42 | 337 | 268 | 10 | 10.0 |\n", "| 6_2019_P_M1 | 2019 | P | 1 | 6 | WT | pH4 | P | mRNA | M | ⋯ | i506 | i701 | 6 | 6 | 2.08 | 2.40 | 319 | 276 | 10 | 10.0 |\n", "| 7_2019_P_M1 | 2019 | P | 1 | 7 | sre1d | pH4 | C | mRNA | M | ⋯ | i507 | i701 | 7 | 1 | 2.13 | 2.23 | 232 | 127 | N/A | 9.9 |\n", "| 8_2019_P_M1 | 2019 | P | 1 | 8 | sre1d | pH4 | C | mRNA | M | ⋯ | i508 | i701 | 8 | 2 | 2.08 | 2.24 | 320 | 311 | N/A | 10.0 |\n", "| 9_2019_P_M1 | 2019 | P | 1 | 9 | sre1d | pH4 | C | mRNA | M | ⋯ | i501 | i702 | 9 | 3 | 2.09 | 1.46 | 342 | 326 | 9.6 | 9.6 |\n", "| 10_2019_P_M1 | 2019 | P | 1 | 10 | sre1d | pH4 | P | mRNA | M | ⋯ | i502 | i702 | 10 | 4 | 2.16 | 1.25 | 262 | 168 | 10 | 10.0 |\n", "| 11_2019_P_M1 | 2019 | P | 1 | 11 | sre1d | pH4 | P | mRNA | M | ⋯ | i503 | i702 | 11 | 5 | 2.12 | 2.28 | 212 | 236 | 10 | 10.0 |\n", "| 12_2019_P_M1 | 2019 | P | 1 | 12 | sre1d | pH4 | P | mRNA | M | ⋯ | i504 | i702 | 12 | 6 | 2.12 | 2.57 | 246 | 312 | 10 | 10.0 |\n", "| 13_2019_P_M1 | 2019 | P | 1 | 13 | WT | pH8 | C | mRNA | M | ⋯ | i505 | i702 | 13 | 1 | 1.93 | 2.28 | 465 | 436 | N/A | 10.0 |\n", "| 14_2019_P_M1 | 2019 | P | 1 | 14 | WT | pH8 | C | mRNA | M | ⋯ | i506 | i702 | 14 | 2 | 2.13 | 1.88 | 170 | 99 | N/A | 9.9 |\n", "| 15_2019_P_M1 | 2019 | P | 1 | 15 | WT | pH8 | C | mRNA | M | ⋯ | i507 | i702 | 15 | 3 | 2.08 | 0.97 | 300 | 190 | N/A | 10.0 |\n", "| 16_2019_P_M1 | 2019 | P | 1 | 16 | WT | pH8 | P | mRNA | M | ⋯ | i508 | i702 | 16 | 4 | 2.15 | 2.13 | 236 | 129 | N/A | 10.0 |\n", "| 17_2019_P_M1 | 2019 | P | 1 | 17 | WT | pH8 | P | mRNA | M | ⋯ | i501 | i703 | 17 | 5 | 2.13 | 0.89 | 233 | 111 | N/A | 10.0 |\n", "| 18_2019_P_M1 | 2019 | P | 1 | 18 | WT | pH8 | P | mRNA | M | ⋯ | i502 | i703 | 18 | 6 | 2.14 | 2.01 | 213 | 134 | N/A | 10.0 |\n", "| 19_2019_P_M1 | 2019 | P | 1 | 19 | sre1d | pH8 | C | mRNA | M | ⋯ | i503 | i703 | 19 | 1 | 2.14 | 2.19 | 236 | 80 | N/A | 10.0 |\n", "| 20_2019_P_M1 | 2019 | P | 1 | 20 | sre1d | pH8 | C | mRNA | M | ⋯ | i504 | i703 | 20 | 2 | 2.14 | 2.39 | 172 | 131 | N/A | 10.0 |\n", "| 21_2019_P_M1 | 2019 | P | 1 | 21 | sre1d | pH8 | C | mRNA | M | ⋯ | i505 | i703 | 21 | 3 | 2.01 | 2.22 | 397 | 295 | N/A | 10.0 |\n", "| 22_2019_P_M1 | 2019 | P | 1 | 22 | sre1d | pH8 | P | mRNA | M | ⋯ | i506 | i703 | 22 | 4 | 2.22 | 2.33 | 567 | 499 | 10 | 10.0 |\n", "| 23_2019_P_M1 | 2019 | P | 1 | 23 | sre1d | pH8 | P | mRNA | M | ⋯ | i507 | i703 | 23 | 5 | 2.13 | 2.56 | 254 | 206 | N/A | 10.0 |\n", "| 24_2019_P_M1 | 2019 | P | 1 | 24 | sre1d | pH8 | P | mRNA | M | ⋯ | i508 | i703 | 24 | 6 | 2.11 | 2.16 | 215 | 336 | 10 | 10.0 |\n", "| 2_2018_P_H1 | 2018 | P | 1 | 2 | WT | YPD | J | RNaseH | H | ⋯ | i501 | i704 | 25 | 2 | NA | NA | NA | 2120 | 10 | NA |\n", "| 3_2018_P_H1 | 2018 | P | 1 | 3 | WT | YPD | J | RNaseH | H | ⋯ | i502 | i704 | 26 | 3 | NA | NA | NA | 1500 | 10 | NA |\n", "| 4_2018_P_H1 | 2018 | P | 1 | 4 | WT | YPD | J | RNaseH | H | ⋯ | i503 | i704 | 27 | 4 | NA | NA | NA | 1490 | 10 | NA |\n", "| 2_2018_P_H2 | 2018 | P | 2 | 2 | WT | YPD | J | RNaseH | H | ⋯ | i504 | i704 | 28 | 2 | NA | NA | NA | 2120 | 10 | NA |\n", "| 3_2018_P_H2 | 2018 | P | 2 | 3 | WT | YPD | J | RNaseH | H | ⋯ | i505 | i704 | 29 | 3 | NA | NA | NA | 1500 | 10 | NA |\n", "| 4_2018_P_H2 | 2018 | P | 2 | 4 | WT | YPD | J | RNaseH | H | ⋯ | i506 | i704 | 30 | 4 | NA | NA | NA | 1490 | 10 | NA |\n", "| 2_2018_P_T1 | 2018 | P | 1 | 2 | WT | YPD | J | Total | T | ⋯ | i507 | i704 | 31 | 2 | NA | NA | NA | 2120 | 10 | NA |\n", "| 3_2018_P_T1 | 2018 | P | 1 | 3 | WT | YPD | J | Total | T | ⋯ | i508 | i704 | 32 | 3 | NA | NA | NA | 1500 | 10 | NA |\n", "| 4_2018_P_T1 | 2018 | P | 1 | 4 | WT | YPD | J | Total | T | ⋯ | i501 | i705 | 33 | 4 | NA | NA | NA | 1490 | 10 | NA |\n", "| 2_2018_P_M1 | 2018 | P | 1 | 2 | WT | YPD | J | mRNA | M | ⋯ | i502 | i705 | 34 | 2 | NA | NA | NA | 2120 | 10 | NA |\n", "| 3_2018_P_M1 | 2018 | P | 1 | 3 | WT | YPD | J | mRNA | M | ⋯ | i503 | i705 | 35 | 3 | NA | NA | NA | 1500 | 10 | NA |\n", "| 4_2018_P_M1 | 2018 | P | 1 | 4 | WT | YPD | J | mRNA | M | ⋯ | i504 | i705 | 36 | 4 | NA | NA | NA | 1490 | 10 | NA |\n", "\n" ], "text/plain": [ " Label sample_year group enrich_rep RNA_sample_num genotype condition\n", "1 1_2019_P_M1 2019 P 1 1 WT pH4 \n", "2 2_2019_P_M1 2019 P 1 2 WT pH4 \n", "3 3_2019_P_M1 2019 P 1 3 WT pH4 \n", "4 4_2019_P_M1 2019 P 1 4 WT pH4 \n", "5 5_2019_P_M1 2019 P 1 5 WT pH4 \n", "6 6_2019_P_M1 2019 P 1 6 WT pH4 \n", "7 7_2019_P_M1 2019 P 1 7 sre1d pH4 \n", "8 8_2019_P_M1 2019 P 1 8 sre1d pH4 \n", "9 9_2019_P_M1 2019 P 1 9 sre1d pH4 \n", "10 10_2019_P_M1 2019 P 1 10 sre1d pH4 \n", "11 11_2019_P_M1 2019 P 1 11 sre1d pH4 \n", "12 12_2019_P_M1 2019 P 1 12 sre1d pH4 \n", "13 13_2019_P_M1 2019 P 1 13 WT pH8 \n", "14 14_2019_P_M1 2019 P 1 14 WT pH8 \n", "15 15_2019_P_M1 2019 P 1 15 WT pH8 \n", "16 16_2019_P_M1 2019 P 1 16 WT pH8 \n", "17 17_2019_P_M1 2019 P 1 17 WT pH8 \n", "18 18_2019_P_M1 2019 P 1 18 WT pH8 \n", "19 19_2019_P_M1 2019 P 1 19 sre1d pH8 \n", "20 20_2019_P_M1 2019 P 1 20 sre1d pH8 \n", "21 21_2019_P_M1 2019 P 1 21 sre1d pH8 \n", "22 22_2019_P_M1 2019 P 1 22 sre1d pH8 \n", "23 23_2019_P_M1 2019 P 1 23 sre1d pH8 \n", "24 24_2019_P_M1 2019 P 1 24 sre1d pH8 \n", "25 2_2018_P_H1 2018 P 1 2 WT YPD \n", "26 3_2018_P_H1 2018 P 1 3 WT YPD \n", "27 4_2018_P_H1 2018 P 1 4 WT YPD \n", "28 2_2018_P_H2 2018 P 2 2 WT YPD \n", "29 3_2018_P_H2 2018 P 2 3 WT YPD \n", "30 4_2018_P_H2 2018 P 2 4 WT YPD \n", "31 2_2018_P_T1 2018 P 1 2 WT YPD \n", "32 3_2018_P_T1 2018 P 1 3 WT YPD \n", "33 4_2018_P_T1 2018 P 1 4 WT YPD \n", "34 2_2018_P_M1 2018 P 1 2 WT YPD \n", "35 3_2018_P_M1 2018 P 1 3 WT YPD \n", "36 4_2018_P_M1 2018 P 1 4 WT YPD \n", " libprep_person enrichment_method enrichment_short ⋯ i5_primer i7_primer\n", "1 C mRNA M ⋯ i501 i701 \n", "2 C mRNA M ⋯ i502 i701 \n", "3 C mRNA M ⋯ i503 i701 \n", "4 P mRNA M ⋯ i504 i701 \n", "5 P mRNA M ⋯ i505 i701 \n", "6 P mRNA M ⋯ i506 i701 \n", "7 C mRNA M ⋯ i507 i701 \n", "8 C mRNA M ⋯ i508 i701 \n", "9 C mRNA M ⋯ i501 i702 \n", "10 P mRNA M ⋯ i502 i702 \n", "11 P mRNA M ⋯ i503 i702 \n", "12 P mRNA M ⋯ i504 i702 \n", "13 C mRNA M ⋯ i505 i702 \n", "14 C mRNA M ⋯ i506 i702 \n", "15 C mRNA M ⋯ i507 i702 \n", "16 P mRNA M ⋯ i508 i702 \n", "17 P mRNA M ⋯ i501 i703 \n", "18 P mRNA M ⋯ i502 i703 \n", "19 C mRNA M ⋯ i503 i703 \n", "20 C mRNA M ⋯ i504 i703 \n", "21 C mRNA M ⋯ i505 i703 \n", "22 P mRNA M ⋯ i506 i703 \n", "23 P mRNA M ⋯ i507 i703 \n", "24 P mRNA M ⋯ i508 i703 \n", "25 J RNaseH H ⋯ i501 i704 \n", "26 J RNaseH H ⋯ i502 i704 \n", "27 J RNaseH H ⋯ i503 i704 \n", "28 J RNaseH H ⋯ i504 i704 \n", "29 J RNaseH H ⋯ i505 i704 \n", "30 J RNaseH H ⋯ i506 i704 \n", "31 J Total T ⋯ i507 i704 \n", "32 J Total T ⋯ i508 i704 \n", "33 J Total T ⋯ i501 i705 \n", "34 J mRNA M ⋯ i502 i705 \n", "35 J mRNA M ⋯ i503 i705 \n", "36 J mRNA M ⋯ i504 i705 \n", " library_num bio_replicate Nanodrop_260_280 Nanodrop_260_230\n", "1 1 1 2.14 1.52 \n", "2 2 2 2.12 1.79 \n", "3 3 3 2.11 2.49 \n", "4 4 4 2.13 1.15 \n", "5 5 5 2.09 2.42 \n", "6 6 6 2.08 2.40 \n", "7 7 1 2.13 2.23 \n", "8 8 2 2.08 2.24 \n", "9 9 3 2.09 1.46 \n", "10 10 4 2.16 1.25 \n", "11 11 5 2.12 2.28 \n", "12 12 6 2.12 2.57 \n", "13 13 1 1.93 2.28 \n", "14 14 2 2.13 1.88 \n", "15 15 3 2.08 0.97 \n", "16 16 4 2.15 2.13 \n", "17 17 5 2.13 0.89 \n", "18 18 6 2.14 2.01 \n", "19 19 1 2.14 2.19 \n", "20 20 2 2.14 2.39 \n", "21 21 3 2.01 2.22 \n", "22 22 4 2.22 2.33 \n", "23 23 5 2.13 2.56 \n", "24 24 6 2.11 2.16 \n", "25 25 2 NA NA \n", "26 26 3 NA NA \n", "27 27 4 NA NA \n", "28 28 2 NA NA \n", "29 29 3 NA NA \n", "30 30 4 NA NA \n", "31 31 2 NA NA \n", "32 32 3 NA NA \n", "33 33 4 NA NA \n", "34 34 2 NA NA \n", "35 35 3 NA NA \n", "36 36 4 NA NA \n", " Nanodrop_concentration_ng_ul Bioanalyzer_concentration_ng_ul\n", "1 293 197 \n", "2 290 225 \n", "3 302 241 \n", "4 296 189 \n", "5 337 268 \n", "6 319 276 \n", "7 232 127 \n", "8 320 311 \n", "9 342 326 \n", "10 262 168 \n", "11 212 236 \n", "12 246 312 \n", "13 465 436 \n", "14 170 99 \n", "15 300 190 \n", "16 236 129 \n", "17 233 111 \n", "18 213 134 \n", "19 236 80 \n", "20 172 131 \n", "21 397 295 \n", "22 567 499 \n", "23 254 206 \n", "24 215 336 \n", "25 NA 2120 \n", "26 NA 1500 \n", "27 NA 1490 \n", "28 NA 2120 \n", "29 NA 1500 \n", "30 NA 1490 \n", "31 NA 2120 \n", "32 NA 1500 \n", "33 NA 1490 \n", "34 NA 2120 \n", "35 NA 1500 \n", "36 NA 1490 \n", " RIN_normal_threshold RIN_lowered_threshold\n", "1 N/A 9.8 \n", "2 N/A 9.9 \n", "3 N/A 9.9 \n", "4 N/A 9.7 \n", "5 10 10.0 \n", "6 10 10.0 \n", "7 N/A 9.9 \n", "8 N/A 10.0 \n", "9 9.6 9.6 \n", "10 10 10.0 \n", "11 10 10.0 \n", "12 10 10.0 \n", "13 N/A 10.0 \n", "14 N/A 9.9 \n", "15 N/A 10.0 \n", "16 N/A 10.0 \n", "17 N/A 10.0 \n", "18 N/A 10.0 \n", "19 N/A 10.0 \n", "20 N/A 10.0 \n", "21 N/A 10.0 \n", "22 10 10.0 \n", "23 N/A 10.0 \n", "24 10 10.0 \n", "25 10 NA \n", "26 10 NA \n", "27 10 NA \n", "28 10 NA \n", "29 10 NA \n", "30 10 NA \n", "31 10 NA \n", "32 10 NA \n", "33 10 NA \n", "34 10 NA \n", "35 10 NA \n", "36 10 NA " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "metadtfile <- '/data/hts_2019_data/hts2019_pilot_rawdata/2019_pilot_metadata.tsv'\n", "tools::md5sum(metadtfile)\n", "\n", "mtdf<-readr::read_tsv(metadtfile)\n", "\n", "mtdf" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### filter out 2018 samples" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
    \n", "\t
  1. 24
    2. \n", "\t
  2. 22
    3. \n", "
\n" ], "text/latex": [ "\\begin{enumerate*}\n", "\\item 24\n", "\\item 22\n", "\\end{enumerate*}\n" ], "text/markdown": [ "1. 24\n", "2. 22\n", "\n", "\n" ], "text/plain": [ "[1] 24 22" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "mtdf %>%\n", " filter(str_detect(Label, \"2019\")) -> \n", " mtdf2019\n", "\n", "dim(mtdf2019)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Add a label column to the counts object so that it can be merged with the metadata" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
    \n", "\t
  1. 96
    2. \n", "\t
  2. 8500
    3. \n", "
\n" ], "text/latex": [ "\\begin{enumerate*}\n", "\\item 96\n", "\\item 8500\n", "\\end{enumerate*}\n" ], "text/markdown": [ "1. 96\n", "2. 8500\n", "\n", "\n" ], "text/plain": [ "[1] 96 8500" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
    \n", "\t
  1. 96
    2. \n", "\t
  2. 8501
    3. \n", "
\n" ], "text/latex": [ "\\begin{enumerate*}\n", "\\item 96\n", "\\item 8501\n", "\\end{enumerate*}\n" ], "text/markdown": [ "1. 96\n", "2. 8501\n", "\n", "\n" ], "text/plain": [ "[1] 96 8501" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "myregex <- \"_S[1-9][0-9]{0,2}_L00[1-4]_ReadsPerGene.out.tab\"\n", "\n", "\n", "### dim before adding label column\n", "dim(genecounts2019)\n", "\n", "genecounts2019 %>% \n", " mutate(Label=str_replace(expid, myregex, \"\")) -> \n", " genecounts2019\n", "\n", "### dim before adding label column\n", "\n", "dim(genecounts2019)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\n", "\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\n", "
A tibble: 8 × 6
expidCNAG_00001CNAG_00002CNAG_00003CNAG_00004Label
<chr><int><int><int><int><chr>
1_2019_P_M1_S1_L001_ReadsPerGene.out.tab 035482231_2019_P_M1
1_2019_P_M1_S1_L002_ReadsPerGene.out.tab 043462271_2019_P_M1
1_2019_P_M1_S1_L003_ReadsPerGene.out.tab 046492321_2019_P_M1
1_2019_P_M1_S1_L004_ReadsPerGene.out.tab 034582221_2019_P_M1
10_2019_P_M1_S10_L001_ReadsPerGene.out.tab0303613010_2019_P_M1
10_2019_P_M1_S10_L002_ReadsPerGene.out.tab0373711710_2019_P_M1
10_2019_P_M1_S10_L003_ReadsPerGene.out.tab0293113510_2019_P_M1
10_2019_P_M1_S10_L004_ReadsPerGene.out.tab0232713110_2019_P_M1
\n" ], "text/latex": [ "A tibble: 8 × 6\n", "\\begin{tabular}{r|llllll}\n", " expid & CNAG\\_00001 & CNAG\\_00002 & CNAG\\_00003 & CNAG\\_00004 & Label\\\\\n", " & & & & & \\\\\n", "\\hline\n", "\t 1\\_2019\\_P\\_M1\\_S1\\_L001\\_ReadsPerGene.out.tab & 0 & 35 & 48 & 223 & 1\\_2019\\_P\\_M1 \\\\\n", "\t 1\\_2019\\_P\\_M1\\_S1\\_L002\\_ReadsPerGene.out.tab & 0 & 43 & 46 & 227 & 1\\_2019\\_P\\_M1 \\\\\n", "\t 1\\_2019\\_P\\_M1\\_S1\\_L003\\_ReadsPerGene.out.tab & 0 & 46 & 49 & 232 & 1\\_2019\\_P\\_M1 \\\\\n", "\t 1\\_2019\\_P\\_M1\\_S1\\_L004\\_ReadsPerGene.out.tab & 0 & 34 & 58 & 222 & 1\\_2019\\_P\\_M1 \\\\\n", "\t 10\\_2019\\_P\\_M1\\_S10\\_L001\\_ReadsPerGene.out.tab & 0 & 30 & 36 & 130 & 10\\_2019\\_P\\_M1\\\\\n", "\t 10\\_2019\\_P\\_M1\\_S10\\_L002\\_ReadsPerGene.out.tab & 0 & 37 & 37 & 117 & 10\\_2019\\_P\\_M1\\\\\n", "\t 10\\_2019\\_P\\_M1\\_S10\\_L003\\_ReadsPerGene.out.tab & 0 & 29 & 31 & 135 & 10\\_2019\\_P\\_M1\\\\\n", "\t 10\\_2019\\_P\\_M1\\_S10\\_L004\\_ReadsPerGene.out.tab & 0 & 23 & 27 & 131 & 10\\_2019\\_P\\_M1\\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "A tibble: 8 × 6\n", "\n", "| expid <chr> | CNAG_00001 <int> | CNAG_00002 <int> | CNAG_00003 <int> | CNAG_00004 <int> | Label <chr> |\n", "|---|---|---|---|---|---|\n", "| 1_2019_P_M1_S1_L001_ReadsPerGene.out.tab | 0 | 35 | 48 | 223 | 1_2019_P_M1 |\n", "| 1_2019_P_M1_S1_L002_ReadsPerGene.out.tab | 0 | 43 | 46 | 227 | 1_2019_P_M1 |\n", "| 1_2019_P_M1_S1_L003_ReadsPerGene.out.tab | 0 | 46 | 49 | 232 | 1_2019_P_M1 |\n", "| 1_2019_P_M1_S1_L004_ReadsPerGene.out.tab | 0 | 34 | 58 | 222 | 1_2019_P_M1 |\n", "| 10_2019_P_M1_S10_L001_ReadsPerGene.out.tab | 0 | 30 | 36 | 130 | 10_2019_P_M1 |\n", "| 10_2019_P_M1_S10_L002_ReadsPerGene.out.tab | 0 | 37 | 37 | 117 | 10_2019_P_M1 |\n", "| 10_2019_P_M1_S10_L003_ReadsPerGene.out.tab | 0 | 29 | 31 | 135 | 10_2019_P_M1 |\n", "| 10_2019_P_M1_S10_L004_ReadsPerGene.out.tab | 0 | 23 | 27 | 131 | 10_2019_P_M1 |\n", "\n" ], "text/plain": [ " expid CNAG_00001 CNAG_00002 CNAG_00003\n", "1 1_2019_P_M1_S1_L001_ReadsPerGene.out.tab 0 35 48 \n", "2 1_2019_P_M1_S1_L002_ReadsPerGene.out.tab 0 43 46 \n", "3 1_2019_P_M1_S1_L003_ReadsPerGene.out.tab 0 46 49 \n", "4 1_2019_P_M1_S1_L004_ReadsPerGene.out.tab 0 34 58 \n", "5 10_2019_P_M1_S10_L001_ReadsPerGene.out.tab 0 30 36 \n", "6 10_2019_P_M1_S10_L002_ReadsPerGene.out.tab 0 37 37 \n", "7 10_2019_P_M1_S10_L003_ReadsPerGene.out.tab 0 29 31 \n", "8 10_2019_P_M1_S10_L004_ReadsPerGene.out.tab 0 23 27 \n", " CNAG_00004 Label \n", "1 223 1_2019_P_M1 \n", "2 227 1_2019_P_M1 \n", "3 232 1_2019_P_M1 \n", "4 222 1_2019_P_M1 \n", "5 130 10_2019_P_M1\n", "6 117 10_2019_P_M1\n", "7 135 10_2019_P_M1\n", "8 131 10_2019_P_M1" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
    \n", "\t
  1. 96
    2. \n", "\t
  2. 8501
    3. \n", "
\n" ], "text/latex": [ "\\begin{enumerate*}\n", "\\item 96\n", "\\item 8501\n", "\\end{enumerate*}\n" ], "text/markdown": [ "1. 96\n", "2. 8501\n", "\n", "\n" ], "text/plain": [ "[1] 96 8501" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "### Look at the first five genes across the libraries\n", "\n", "genecounts2019[1:8, c(1:5, ncol(genecounts2019))]\n", "dim(genecounts2019)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Add counts across lanes " ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [], "source": [ "genecounts2019 %>% \n", " group_by(Label) %>%\n", " summarize_each(sum, -expid) -> \n", " cnt2019" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\n", "\n", "\t\n", "\t\n", "\t\n", "\t\n", "\n", "
A tibble: 4 × 5
LabelCNAG_00001CNAG_00002CNAG_00003CNAG_00004
<chr><int><int><int><int>
1_2019_P_M1 0158201904
10_2019_P_M10119131513
11_2019_P_M10 90121573
12_2019_P_M10 81151533
\n" ], "text/latex": [ "A tibble: 4 × 5\n", "\\begin{tabular}{r|lllll}\n", " Label & CNAG\\_00001 & CNAG\\_00002 & CNAG\\_00003 & CNAG\\_00004\\\\\n", " & & & & \\\\\n", "\\hline\n", "\t 1\\_2019\\_P\\_M1 & 0 & 158 & 201 & 904\\\\\n", "\t 10\\_2019\\_P\\_M1 & 0 & 119 & 131 & 513\\\\\n", "\t 11\\_2019\\_P\\_M1 & 0 & 90 & 121 & 573\\\\\n", "\t 12\\_2019\\_P\\_M1 & 0 & 81 & 151 & 533\\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "A tibble: 4 × 5\n", "\n", "| Label <chr> | CNAG_00001 <int> | CNAG_00002 <int> | CNAG_00003 <int> | CNAG_00004 <int> |\n", "|---|---|---|---|---|\n", "| 1_2019_P_M1 | 0 | 158 | 201 | 904 |\n", "| 10_2019_P_M1 | 0 | 119 | 131 | 513 |\n", "| 11_2019_P_M1 | 0 | 90 | 121 | 573 |\n", "| 12_2019_P_M1 | 0 | 81 | 151 | 533 |\n", "\n" ], "text/plain": [ " Label CNAG_00001 CNAG_00002 CNAG_00003 CNAG_00004\n", "1 1_2019_P_M1 0 158 201 904 \n", "2 10_2019_P_M1 0 119 131 513 \n", "3 11_2019_P_M1 0 90 121 573 \n", "4 12_2019_P_M1 0 81 151 533 " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "cnt2019[1:4, 1:5]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Check to make sure that every label in your count file has an entry in the metadata file" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/html": [], "text/latex": [], "text/markdown": [], "text/plain": [ "character(0)" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [], "text/latex": [], "text/markdown": [], "text/plain": [ "character(0)" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "setdiff(cnt2019$Label, mtdf2019$Label)\n", "setdiff(mtdf2019$Label, cnt2019$Label)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Save objects to image file" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/html": [ "'/home/jovyan/work/scratch/analysis_output/img/pilotcnt2019.RData'" ], "text/latex": [ "'/home/jovyan/work/scratch/analysis\\_output/img/pilotcnt2019.RData'" ], "text/markdown": [ "'/home/jovyan/work/scratch/analysis_output/img/pilotcnt2019.RData'" ], "text/plain": [ "[1] \"/home/jovyan/work/scratch/analysis_output/img/pilotcnt2019.RData\"" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "curdir <- \"/home/jovyan/work/scratch/analysis_output\"\n", "imgdir <- file.path(curdir, \"img\")\n", "\n", "imgfile <- file.path(imgdir, \"pilotcnt2019.RData\")\n", "\n", "imgfile" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/html": [ "/home/jovyan/work/scratch/analysis_output/img/pilotcnt2019.RData: '0d1cdfc8bb97baf52ca4f8f33e2c0ae4'" ], "text/latex": [ "\\textbf{/home/jovyan/work/scratch/analysis\\textbackslash{}\\_output/img/pilotcnt2019.RData:} '0d1cdfc8bb97baf52ca4f8f33e2c0ae4'" ], "text/markdown": [ "**/home/jovyan/work/scratch/analysis_output/img/pilotcnt2019.RData:** '0d1cdfc8bb97baf52ca4f8f33e2c0ae4'" ], "text/plain": [ "/home/jovyan/work/scratch/analysis_output/img/pilotcnt2019.RData \n", " \"0d1cdfc8bb97baf52ca4f8f33e2c0ae4\" " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "save(cnt2019, mtdf2019, file = imgfile)\n", "\n", "tools::md5sum(imgfile)" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "R version 3.6.0 (2019-04-26)\n", "Platform: x86_64-pc-linux-gnu (64-bit)\n", "Running under: Debian GNU/Linux 9 (stretch)\n", "\n", "Matrix products: default\n", "BLAS: /usr/lib/openblas-base/libblas.so.3\n", "LAPACK: /usr/lib/libopenblasp-r0.2.19.so\n", "\n", "locale:\n", " [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C \n", " [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8 \n", " [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8 \n", " [7] LC_PAPER=en_US.UTF-8 LC_NAME=C \n", " [9] LC_ADDRESS=C LC_TELEPHONE=C \n", "[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C \n", "\n", "attached base packages:\n", "[1] stats graphics grDevices utils datasets methods base \n", "\n", "other attached packages:\n", "[1] forcats_0.4.0 stringr_1.4.0 dplyr_0.8.1 purrr_0.3.2 \n", "[5] readr_1.3.1 tidyr_0.8.3 tibble_2.1.2 ggplot2_3.1.1 \n", "[9] tidyverse_1.2.1\n", "\n", "loaded via a namespace (and not attached):\n", " [1] Rcpp_1.0.1 cellranger_1.1.0 plyr_1.8.4 pillar_1.4.1 \n", " [5] compiler_3.6.0 base64enc_0.1-3 tools_3.6.0 zeallot_0.1.0 \n", " [9] digest_0.6.19 uuid_0.1-2 lubridate_1.7.4 jsonlite_1.6 \n", "[13] evaluate_0.14 nlme_3.1-139 gtable_0.3.0 lattice_0.20-38 \n", "[17] pkgconfig_2.0.2 rlang_0.3.4 cli_1.1.0 rstudioapi_0.10 \n", "[21] IRdisplay_0.7.0 IRkernel_1.0.1 haven_2.1.0 withr_2.1.2 \n", "[25] xml2_1.2.0 httr_1.4.0 repr_1.0.1 vctrs_0.1.0 \n", "[29] hms_0.4.2 generics_0.0.2 grid_3.6.0 tidyselect_0.2.5\n", "[33] glue_1.3.1 R6_2.4.0 readxl_1.3.1 pbdZMQ_0.3-3 \n", "[37] modelr_0.1.4 magrittr_1.5 backports_1.1.4 scales_1.0.0 \n", "[41] htmltools_0.3.6 rvest_0.3.4 assertthat_0.2.1 colorspace_1.4-1\n", "[45] stringi_1.4.3 lazyeval_0.2.2 munsell_0.5.0 broom_0.5.2 \n", "[49] crayon_1.3.4 " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "sessionInfo()" ] } ], "metadata": { "kernelspec": { "display_name": "R", "language": "R", "name": "ir" }, "language_info": { "codemirror_mode": "r", "file_extension": ".r", "mimetype": "text/x-r-source", "name": "R", "pygments_lexer": "r", "version": "3.6.0" } }, "nbformat": 4, "nbformat_minor": 2 }