https://github.com/leonjessen/peptools

PepTools - An Immunoinformatics (Immunological Bioinformatics) R-package for working with peptide data
https://github.com/leonjessen/peptools

bioinformatics datascience encoding-peptides epitope-prediction-methods immunoinformatics immunological-bioinformatics peptide-data peptides r research rstats vaccine

Last synced: about 5 hours ago
JSON representation

PepTools - An Immunoinformatics (Immunological Bioinformatics) R-package for working with peptide data

• Host: GitHub
• URL: https://github.com/leonjessen/peptools
• Owner: leonjessen
• License: gpl-3.0
• Created: 2017-11-16T19:33:47.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2018-02-21T09:55:30.000Z (over 6 years ago)
• Last Synced: 2023-10-20T21:13:40.086Z (about 1 year ago)
• Topics: bioinformatics, datascience, encoding-peptides, epitope-prediction-methods, immunoinformatics, immunological-bioinformatics, peptide-data, peptides, r, research, rstats, vaccine
• Language: R
• Homepage:
• Size: 234 KB
• Stars: 16
• Watchers: 2
• Forks: 9
• Open Issues: 2
• Metadata Files:
  • Readme: README.Rmd
  • License: LICENSE

Awesome Lists containing this project

README

        
---

title: "PepTools - An Immunoinformatics (Immunological Bioinformatics) R-package for working with peptide data"

output: github_document

---

```{r setup, include=FALSE}

knitr::opts_chunk$set(echo = TRUE)

```

# PepTools

The aim of this package is to supply a set of tools, which will ease working with peptide data within the field of immunoinformatics.

## Getting started

Using Hadley Wickham's brilliant `devtools` package, we can easily install `PepTools` like so:

```{r eval=FALSE}

install.packages("devtools")

devtools::install_github("leonjessen/PepTools")

```

Once the package has been installed, we can simply load it like so:

```{r load_libraries, message=FALSE}

library("PepTools")

```

## PSSM Examples

`PepTools` comes with an example data set of 5,000 9-mer peptides, which have been predicted by [NetMHCpan 4.0 Server](http://www.cbs.dtu.dk/services/NetMHCpan-4.0/) to be strong binders to HLA-A*02:01.

We can view the first 10 peptides like so

```{r view_test_peps}

PEPTIDES %>% head(10)

```

and derive the count matrix:

```{r pssm_counts}

PEPTIDES %>% pssm_counts %>% .[1:9,1:10]

```

and the frequency matrix:

```{r pssm_freqs}

PEPTIDES %>% pssm_freqs %>% .[1:9,1:10]

```

and the bits of information matrix;

```{r pssm_bits}

PEPTIDES %>% pssm_freqs %>% pssm_bits %>% .[1:9,1:10]

```

## Sequence Logo Examples

Using the `ggseqlogo` package, we can visualise the bits matrix:

```{r man_peps_logo, fig.width=5, fig.height=3, fig.align='center'}

PEPTIDES %>% pssm_freqs %>% pssm_bits %>% t %>% ggseqlogo(method="custom")

```

and compare with the `ggseqlogo` build in peptide-to-bits conversion:

```{r auto_peps_logo, fig.width=5, fig.height=3, fig.align='center'}

PEPTIDES %>% ggseqlogo

```

## Peptide Encoding for Deep Learning

`PepTools` also contain function for encoding peptides:

 

```{r pep_encode}

PEPTIDES %>% pep_encode %>% dim

```

As can be seen from the dimensions, `pep_encode` creates a 3D array or a tensor with 5,000 rows, 9 columns and 20 slices, corresponding to `n_peptides x l_peptide x l_enc`, where the encoding is the `BLOSUM62` matrix. This way each peptide is encoded as an'image', which can then be used as input to a Deep Learning model. To get a better understanding of what is going on, we can plot the 3 first encoded peptide 'images':

```{r plot_peptide_images, fig.width=5, fig.height=10, fig.align='center'}

PEPTIDES %>% pep_plot_images

```