annotate 01_htseq_count_analysis.Rmd @ 11:5409f7a3aa9b draft default tip

planemo upload commit bb4923aaeb8563e3b8ecd44483f788b2992f9e98-dirty
author mingchen0919
date Sat, 01 Dec 2018 01:27:08 -0500
parents 467a1895c718
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
5
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
1 ---
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
2 title: 'HTSeq-count Analysis'
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
3 output:
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
4 html_document:
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
5 highlight: pygments
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
6 ---
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
7
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
8 ## Job script
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
9
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
10 ```{bash, echo=FALSE}
6
a40d5db8687e planemo upload commit 7d411a114317ebd9dfc6a20a7f132e653ccad986-dirty
mingchen0919
parents: 5
diff changeset
11 sh ${TOOL_INSTALL_DIR}/build-and-run-job-scripts.sh > ${REPORT_FILES_PATH}/log.txt 2>&1
5
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
12 ```
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
13
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
14 ```{r echo=FALSE, comment='', results='asis'}
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
15 cat('```bash\n')
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
16 cat(readLines(paste0(Sys.getenv('REPORT_FILES_PATH'), '/htseq-count.sh')), sep = '\n')
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
17 cat('\n```')
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
18 ```
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
19
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
20 ## Counts
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
21
9
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
22 Write data into a CSV file.
5
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
23
9
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
24 ```{r, echo=TRUE}
5
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
25 count_data = read.table(paste0(opt$X_d, '/counts.txt'), row.names = 1)
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
26 sample_names = trimws(strsplit(opt$X_B, ',')[[1]])
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
27 colnames(count_data) = rep(sample_names, length = ncol(count_data))
9
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
28
5
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
29
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
30 # modify column names
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
31 count_data = data.frame(feature_id = rownames(count_data), count_data)
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
32 write.csv(count_data,
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
33 file = paste0(Sys.getenv('REPORT_FILES_PATH'), '/count_data.csv'),
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
34 quote = FALSE, row.names = FALSE)
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
35 ```
cf3fde5d0834 planemo upload commit 104ae24ee30761a0099eeb91362ed1e3e13aba4b-dirty
mingchen0919
parents:
diff changeset
36
9
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
37 Display the top 1000 rows with largest average counts.
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
38
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
39 ```{r echo=TRUE}
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
40 # Sort count table by count average
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
41 rownames(count_data) = count_data$feature_id
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
42 count_data = count_data[, -1]
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
43 sorted_ct_table = count_data[order(rowMeans(count_data), decreasing = TRUE), ]
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
44 DT::datatable(head(sorted_ct_table, 1000))
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
45 ```
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
46
467a1895c718 planemo upload commit bd7e129777e3ef6403f055251e17b541d222d7d0-dirty
mingchen0919
parents: 6
diff changeset
47