-
Notifications
You must be signed in to change notification settings - Fork 1
/
0005_process_signalp_data.Rmd
255 lines (206 loc) · 6.69 KB
/
0005_process_signalp_data.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
---
title: "Untitled"
author: "Ruth Kristianingsih"
date: "10/12/2019"
knit: (function(inputFile, encoding) { rmarkdown::render(inputFile, encoding = encoding, output_dir = here::here("reports", stringr::str_remove(getwd(), here::here("scripts/r-scripts/")))) })
output:
md_document:
variant: markdown_github
---
# Process in Getting SignalP data
```{r setup, include = FALSE}
# Load libraries
library(tidyverse)
```
## Background
After getting a prediction for SignalP, we need to process the result into dataframe, so that it can be easily read for all the results. And it is also explained how the signalP pipeline works with all the `.bash` scripts.
## Function
```{r}
# This function is used to get all of signalP results
get_signalp_predictions <- function(organism_names_path, all_fasta_path, signalp_preds_path, organism) {
# Organism names
data_organism_names <- data.table::fread(
organism_names_path,
header = FALSE
) %>%
`colnames<-`(c("organism_name", "ID")) %>%
as_tibble() %>%
dplyr::select(ID, organism_name)
# Sequences from FASTA
data_seqs_raw <- Biostrings::readAAStringSet(all_fasta_path)
data_seqs <- data.frame(
ID_raw = names(data_seqs_raw),
sequence = paste(data_seqs_raw)
) %>%
as_tibble() %>%
dplyr::mutate(sequence = sequence %>% as.character()) %>%
dplyr::rowwise() %>%
tidyr::separate(
col = ID_raw,
into = c("ID", "trash"),
sep = " pep "
) %>%
dplyr::select(-trash)
# SignalP predictions
if (organism == "bacteria") {
data_signalp_preds <- data.table::fread(
signalp_preds_path,
header = FALSE
) %>%
`colnames<-`(c("ID", "prediction", "signalp_prob", "cleavage")) %>%
as_tibble() %>%
# Clean features
dplyr::mutate(
ID = ID %>%
stringr::str_remove_all(">"),
prediction = prediction %>%
stringr::str_remove_all("Prediction: "),
signalp_prob = signalp_prob %>%
stringr::str_remove_all("Signal peptide probability: ") %>%
as.numeric(),
cleavage = cleavage %>%
stringr::str_remove_all("Max cleavage site probability: ")
) %>%
tidyr::separate(
col = cleavage,
into = c("cleavage_prob", "position_start", "position_end"),
sep = " between pos. | and ",
convert = TRUE
)
} else {
data_signalp_preds <- data.table::fread(
signalp_preds_path,
header = FALSE
) %>%
`colnames<-`(c("ID", "prediction", "signalp_prob", "signal_anchor", "cleavage")) %>%
as_tibble() %>%
dplyr::select(-c(signal_anchor)) %>%
# Clean features
dplyr::mutate(
ID = ID %>%
stringr::str_remove_all(">"),
prediction = prediction %>%
stringr::str_remove_all("Prediction: "),
signalp_prob = signalp_prob %>%
stringr::str_remove_all("Signal peptide probability: ") %>%
as.numeric(),
cleavage = cleavage %>%
stringr::str_remove_all("Max cleavage site probability: ")
) %>%
tidyr::separate(
col = cleavage,
into = c("cleavage_prob", "position_start", "position_end"),
sep = " between pos. | and ",
convert = TRUE
)
}
# Join all data
data_full_table <-
full_join(
data_organism_names,
data_seqs,
by = "ID"
) %>%
left_join(
data_signalp_preds,
by = "ID"
) %>%
dplyr::filter(!is.na(signalp_prob))
return(data_full_table)
}
```
## Pipeline explanation
This following steps is used to get all of the signalP predicition.
### SignalP predictions
The file is generated by running the script
```bash
sh signalp_to_csv.sh gram- bacteria
```
This does the following:
- Split the FASTA files into smaller chunks with AWK so that `signalp-3.0` can process them.
- Use `signalp` to make the predictions.
- Summarise the results with `sed` and `grep`.
### Sequences with Biostrings
This file is simply all FASTA files concatenated into a single one by running
```bash
combine_fasta_files.sh bacteria
```
### Organism names
For this step we created a CSV with the original filenames of the FASTA files and the IDs of each of the sequences contained in them:
```bash
sh get_organism_names.sh bacteria
```
## Run function
### Bacteria
```{r}
bacteria_full_table <- get_signalp_predictions(
organism_names_path = "../../../data/secreted_data/updated_signalp_results/bacteria_organism_names.csv",
all_fasta_path = "../../../data/secreted_data/updated_signalp_results/bacteria_all_fasta.fa",
signalp_preds_path = "../../../data/secreted_data/updated_signalp_results/bacteria_signalp_results.csv",
organism = "bacteria"
)
```
```r
bacteria_full_table %>%
data.table::fwrite("../../../data/secreted_data/updated_signalp_results/bacteria_full_table.csv")
```
```{r}
bacteria_full_table <-
data.table::fread("../../../data/secreted_data/signalp-pipeline/bacteria_full_table.csv")
```
Check percentage of signal peptides:
```{r}
bacteria_full_table %>%
dplyr::group_by(prediction) %>%
dplyr::summarise(count = n())
```
### Fungi
```{r}
fungi_full_table <- get_signalp_predictions(
organism_names_path = "../../../data/secreted_data/updated_signalp_results/fungi_organism_names.csv",
all_fasta_path = "../../../data/secreted_data/updated_signalp_results/fungi_all_fasta.fa",
signalp_preds_path = "../../../data/secreted_data/updated_signalp_results/fungi_signalp_results.csv",
organism = "fungi"
)
```
```{r}
fungi_full_table %>%
data.table::fwrite("../../../data/secreted_data/updated_signalp_results/fungi_full_table.csv")
```
```{r}
# Testing the file
fungi_full_table <-
data.table::fread("../../../data/secreted_data/updated_signalp_results/fungi_full_table.csv")
```
Check percentage of signal peptides:
```{r}
fungi_full_table %>%
dplyr::group_by(prediction) %>%
dplyr::summarise(count = n()) %>%
knitr::kable()
```
### Oomycete / Prostist
```{r}
oomycete_full_table <- get_signalp_predictions(
organism_names_path = "../../../data/secreted_data/updated_signalp_results/protists_organism_names.csv",
all_fasta_path = "../../../data/secreted_data/updated_signalp_results/protists_all_fasta.fa",
signalp_preds_path = "../../../data/secreted_data/updated_signalp_results/protists_signalp_results.csv",
organism = "prostist"
)
```
```{r}
oomycete_full_table %>%
data.table::fwrite("../../../data/secreted_data/updated_signalp_results/protist_full_table.csv")
```
```{r}
# Testing the file
protist_full_table <-
data.table::fread("../../../data/secreted_data/updated_signalp_results/protist_full_table.csv")
```
Check percentage of signal peptides:
```{r}
protist_full_table %>%
dplyr::group_by(prediction) %>%
dplyr::summarise(count = n()) %>%
knitr::kable()
```