annotate 5_per_base_sequence_content.Rmd @ 5:0ac073bef19d draft

planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit 9285c2b8ad41a486dde2a87600a6b8267841c8b5-dirty
author mingchen0919
date Tue, 08 Aug 2017 11:45:41 -0400
parents d732d4526c6d
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
1 ---
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
2 title: "Per Base Sequence Content"
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
3 output: html_document
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
4 ---
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
5
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
6 ```{r setup, include=FALSE, warning=FALSE, message=FALSE}
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
7 knitr::opts_chunk$set(echo = ECHO)
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
8 ```
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
9
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
10 ## Per Base Sequence Content
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
11
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
12 ```{r}
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
13 PBSC_df = data.frame()
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
14 PBSC_file_paths = read.csv('PBSC_file_paths.txt',
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
15 header = TRUE, stringsAsFactors = FALSE)
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
16 for(i in 1:nrow(PBSC_file_paths)) {
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
17 # file_path = paste0('REPORT_OUTPUT_DIR/', PBSC_file_paths[i,2])
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
18 file_path = PBSC_file_paths[i,2]
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
19 pbsc_df = read.csv(file_path,
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
20 sep='\t', header=TRUE, stringsAsFactors = FALSE) %>%
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
21 mutate(Base1=as.numeric(str_split_fixed(X.Base, '-', 2)[,1]),
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
22 Base2=as.numeric(str_split_fixed(X.Base, '-', 2)[,2])) %>%
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
23 (function (df) {
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
24 df1 = select(df, -Base2)
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
25 df2 = select(df, -Base1) %>% filter(Base2 != '')
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
26 colnames(df1) = c(colnames(df1)[1:5], 'Base')
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
27 colnames(df2) = c(colnames(df2)[1:5], 'Base')
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
28 res = rbind(df1, df2) %>% arrange(Base)
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
29 return(res)
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
30 })
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
31 pbsc_df$sample_id = rep(PBSC_file_paths[i,1], nrow(pbsc_df))
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
32 PBSC_df = rbind(PBSC_df, pbsc_df)
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
33 }
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
34 ```
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
35
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
36
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
37 ```{r out.width="100%"}
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
38 PBSC_df_2 = select(PBSC_df, -X.Base) %>%
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
39 melt(id = c('Base', 'sample_id'), value.name = 'base_percentage')
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
40 p = ggplot(data = PBSC_df_2, aes(x = Base, y = base_percentage, group = variable, color = variable)) +
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
41 geom_line() +
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
42 facet_wrap(~ sample_id)
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
43 ggplotly(p)
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
44 ```
d732d4526c6d planemo upload for repository https://github.com/statonlab/docker-GRReport/tree/master/my_tools/rmarkdown_fastqc_site commit ddb1f6aca7619aea2e660b1729367841b56ba4c9-dirty
mingchen0919
parents:
diff changeset
45