predict_on_whole_proteome: A function to predict and annotate whole proteom PTM sites

Description Usage Arguments Details Examples

View source: R/predict_whole_proteom.R

Description

A function to predict and annotate whole proteom PTM sites

Usage

1
2
3
4
predict_on_whole_proteome(ptm_site, flanking_size = 12, SPIDER = T,
  positive_info_file, protein_fasta_file, n_fold = 2, lower_bound = -1,
  upper_bound = 1, liblinear_dir, feature_file_path, cvlog_path_name,
  specificity_level = 0.99, output_label)

Arguments

ptm_site

The target amino acid of the given PTM type, in upper-case single letter representation.

flanking_size

The number of residues surrounding each side of the center residue, The total window size will be 2*flanking_size+1 (default to 12).

SPIDER

A boolean variable indicating whether to use SPIDER3 features (default set to TRUE.)

positive_info_file

A text file containing the positive PTM sites in the required format.

protein_fasta_file

A text file containing the protein sequences of interest in fasta format.

n_fold

The number of folds used for training and prediction in cross validation stage (default set to 2).

lower_bound

The lower bound of the scaled data range (default to -1).

upper_bound

The upper bound of the scaled data range (default to 1).

liblinear_dir

The path for the Liblinear tool.

feature_file_path

The path for the feature files.

cvlog_path_name

The path and name of the log files, which hold the details of Liblinear procedures.

specificity_level

A number ranges from 0 to 1 indicating the specificity user requires the classifier to achieve (default to 0.99).

output_label

The string to tag the output files.

Details

This function outputs the features generated from input files.

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
predict_on_whole_proteome(ptm_site = "S",
                         flanking_size = 12,
                         SPIDER = T,
                         positive_info_file = "ps_PSP.tsv",
                         protein_fasta_file = "S_sp_fasta.tsv",
                         n_fold = 2,
                         lower_bound = -1,
                         upper_bound = 1,
                         liblinear_dir = "/data/ginny/liblinear-2.11/",
                         feature_file_path = "/data/ginny/test_package/",
                         cvlog_path_name = "/data/ginny/test_package/cvlog.txt",
                         specificity_level = 0.99,
                         output_label = "ps_0103")

ginnyintifa/PTMscape documentation built on Nov. 9, 2021, 10:39 p.m.