CancerGram identifies anticancer peptides using n-gram encoding and random forests. It can be also accessed as a web-based service http://biongram.biotech.uni.wroc.pl/CancerGram/.
Please use: Burdukiewicz, M., Sidorczuk, K., Rafacz, D., Pietluch, F., Bąkała, M., Słowik, J., and Gagat, P. (2020). CancerGram: An Effective Classifier for Differentiating Anticancer from Antimicrobial Peptides. Pharmaceutics 12, 1045, https://doi.org/10.3390/pharmaceutics12111045.
You can install the latest development version of the package:
source("https://raw.githubusercontent.com/r-lib/remotes/master/install-github.R")$value("BioGenies/CancerGram")
After installation GUI can be accessed locally:
library(CancerGram)
CancerGram_gui()
To be able to use CancerGram properly, you should have installed the 'CancerGramModel' package available via GitHub. CancerGramModel contains stacked random forest model and informative n-grams required for prediction of anticancer peptides. Due to the large size of a model, it needs to be stored in the external repository, as CRAN do not allow upload of files larger than 5 MB.
You can install CancerGramModel using the install_CancerGramModel function:
install_CancerGramModel()
Anticancer peptides might be also identified in the batch mode:
library(CancerGram)
library(CancerGramModel)
# if you do not have CancerGramModel use:
# install_CancerGramModel()
sequences <- read_txt(system.file("CancerGram/prots.txt", package = "CancerGram"))
predict(CancerGram_model, sequences)
The curl library is one of the dependencies of the CancerGram package and requires additional, non-R software. If you encounter an error concerning curl, please follow instructions below to install curl (adapted from https://github.com/jeroen/curl).
Binary packages for OS-X or Windows can be installed directly from CRAN:
install.packages("curl")
Installation from source on Linux requires libcurl
. On Debian or Ubuntu use libcurl4-openssl-dev:
sudo apt-get install -y libcurl-dev
On Fedora, CentOS or RHEL use libcurl-devel:
sudo yum install libcurl-devel
On OS-X libcurl is included with the system so nothing extra is needed. However if you want to build against the most recent version of libcurl, install and force-link curl from homebrew:
brew install curl
brew link --force curl
Note that on OS-X you must recompile the R package from source after force-linking curl, otherwise you get a version conflict with the system version of libcurl.
This work was supported by National Science Centre grants 2017/26/D/NZ8/00444, 2018/31/N/NZ2/01338 and 2019/35/N/NZ8/03366 to FP.
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.