,
Katarzyna Sidorczuk [aut] ,
Filip Pietluch [ctb] ,
Dominik Rafacz [ctb] ,
Mateusz Bakala [ctb] ,
Jadwiga Słowik [ctb] | Title: | Prediction of Anticancer Peptides |
|---|---|
| Description: | Predicts anticancer peptides using random forests trained on the n-gram encoded peptides. The implemented algorithm can be accessed from both the command line and shiny-based GUI. The CancerGram model is too large for CRAN and it has to be downloaded separately from the repository: <https://github.com/BioGenies/CancerGramModel>. For more information see: Burdukiewicz et al. (2020) <doi:10.3390/pharmaceutics12111045>. |
| Authors: | Michal Burdukiewicz [cre, aut]
,
Katarzyna Sidorczuk [aut] ,
Filip Pietluch [ctb] ,
Dominik Rafacz [ctb] ,
Mateusz Bakala [ctb] ,
Jadwiga Słowik [ctb] |
| Maintainer: | Michal Burdukiewicz <[email protected]> |
| License: | GPL-3 |
| Version: | 1.0.0 |
| Built: | 2024-11-11 04:31:08 UTC |
| Source: | https://github.com/biogenies/cancergram |
Antimicrobial peptides (AMPs) constitute a diverse group of bioactive molecules that provide multicellular organisms with protection against microorganisms, and microorganisms with weaponry for competition. Some AMPs can target cancer cells and they are called anticancer peptides (ACPs). Due to their small size, positive charge, hydrophobicity and amphipathicity, AMPs and ACPs interact with negatively charged components of biological membranes. AMPs preferentially permeabilize microbial membranes, but ACPs additionally target mitochondrial and plasma membrane of cancer cells. Taking into account the therapeutic potential of ACPs and millions of deaths due to cancer annually, it is of vital importance to find new cationic peptides that selectively destroy cancer cells. Therefore, efficient computational tools for ACP prediction are essential to identify the best ACP candidates without undertaking expensive experimental studies. CancerGram is a novel tool that uses stacked random forests and n-gram analysis for prediction of ACPs.
CancerGram is available as R function (predict.cancergram_model)
or shiny GUI (CancerGram_gui).
CancerGram requires the external package, CancerGramModel, which
contains models necessary to perform the prediction. The model
can be installed using install_CancerGramModel
Maintainer: Michal Burdukiewicz <[email protected]>
Burdukiewicz M, Sidorczuk K, Rafacz D, Pietluch F, Bakala M, Slowik J, Gagat P. (2020) CancerGram: an effective classifier for differentiating anticancer from antimicrobial peptides. (submitted)
Launches graphical user interface that predicts presence of anticancer peptides.
CancerGram_gui()CancerGram_gui()
No return value, called for side effects.
Any ad-blocking software may cause malfunctions.
Predictions made with the CancerGram methods.
A list of predictions for exemplary sequences.
#' Predictions for each protein are stored in objects of class
single_cancergram_pred. It consists of three elements:
Character vector of amino acid sequence of an analyzed peptide/protein
Matrix of predictions for each 5-mer (subsequence of 5 amino acids) of a sequence. Each row corresponds to one mer and columns to predicted classes (ACP, AMP or negative). Prediction value indicates probability that a 5-mer possesses anticancer activity (acp), antimicrobial activity (amp) or none of them (neg).
One row matrix of a single prediction value for a whole peptide/protein. Its value corresponds to the probability that a peptide/protein exhibits anticancer activity, antimicrobial activity or none of them.
Installs CancerGramModel package containing model required for prediction of anticancer peptides. Due to large size of our model and file size limit on CRAN, it needs to be stored in the external repository. See readme for more information or in case of installation problems.
install_CancerGramModel()install_CancerGramModel()
Convert predictions to data.frame Return predictions as data.frame
pred2df(x)pred2df(x)
x |
results of prediction as produced by |
a data.frame with two columns and number of rows corresponding to the number of peptides/proteins in the results of prediction. Columns contain following information:
Name of an analyzed sequence.
Probability that a protein/peptide possesses anticancer activity.
Probability that a protein/peptide possesses antimicrobial activity.
Probability that a protein/peptide do not possesses anticancer or antimicrobial activity.
Result of the prediction.
data(CancerGram_predictions) pred2df(CancerGram_predictions)data(CancerGram_predictions) pred2df(CancerGram_predictions)
Recognizes anticancer peptides using the CancerGram algorithm.
## S3 method for class 'cancergram_model' predict(object, newdata, ...)## S3 method for class 'cancergram_model' predict(object, newdata, ...)
object |
|
newdata |
|
... |
further arguments passed to or from other methods. |
CancerGram requires the external package, CancerGramModel, which
contains models necessary to perform the prediction. The model
can be installed using install_CancerGramModel.
Predictions for each protein are stored in objects of class
single_cancergram_pred. It consists of three elements:
Character vector of amino acid sequence of an analyzed peptide/protein
Matrix of predictions for each 5-mer (subsequence of 5 amino acids) of a sequence. Each row corresponds to one mer and columns to predicted classes (ACP, AMP or negative). Prediction value indicates probability that a 5-mer possesses anticancer activity (acp), antimicrobial activity (amp) or none of them (neg).
One row matrix of a single prediction value for a whole peptide/protein. Its value corresponds to the probability that a peptide/protein exhibits anticancer activity, antimicrobial activity or none of them.
list of objects of class single_cancergram_pred.
Each object of this class contains analyzed sequence, values of predictions
for 5-mers and result of the prediction for the whole peptide/protein.
Read sequence data in a fasta format saved in text file.
read_txt(connection)read_txt(connection)
connection |
a |
The input file should contain one or more amino acid sequences separated by empty line(s) in a fasta format.
a list of sequences.
(sequences <- read_txt(system.file("CancerGram/prots.txt", package = "CancerGram")))(sequences <- read_txt(system.file("CancerGram/prots.txt", package = "CancerGram")))