Immunogenicity: Immunogenicity score.

In masato-ogishi/Repitope: Epitope immunogenicity prediction through in silico TCR-peptide contact potential profiling

Immunogenicity score.

Description

Immunogenicity_TrainModels performes preprocessing, trains extremely randomized tree models, and internally predicts immunogenicity scores on the entire dataset provided.
Immunogenicity_SummarizeInternalScores summarizes internally calculated immunogenicity scores.
Immunogenicity_Score is a wrapper function of Immunogenicity_TrainModels and Immunogenicity_SummarizeInternalScores.
Immunogenicity_Score_Cluster is similar to Immunogenicity_Score, but takes clusterDF to filter peptides based on their similarities.
Immunogenicity_Predict predicts immunogenicity scores on external datasets. Models trained by Immunogenicity_TrainModels are necessary. Note that, due to Java constraints, models have to be constructed in each new R session.

Usage

Immunogenicity_TrainModels(
  featureDF,
  metadataDF,
  featureSet = "all",
  seedSet = 1:5,
  coreN = parallel::detectCores(logical = F)
)

Immunogenicity_SummarizeInternalScores(trainModelResults)

Immunogenicity_Score(
  featureDF,
  metadataDF,
  featureSet = "all",
  seedSet = 1:5,
  coreN = parallel::detectCores(logical = F)
)

Immunogenicity_Score_Cluster(
  featureDF,
  metadataDF,
  clusterDF,
  featureSet = "all",
  seedSet = 1:5,
  coreN = parallel::detectCores(logical = F)
)

Immunogenicity_Predict(externalFeatureDFList, trainModelResults)

Arguments

featureDF	A dataframe of features generated by Features.
metadataDF	A dataframe containing metadata, consisting of "Peptide" and "Immunogenicity" columns. Other columns if provided would be used as features.
featureSet	A set of features used for model training. Set "all" to shortcut.
seedSet	A set of random seeds.
coreN	The number of cores to be used for parallelization. Set NULL to disable.
trainModelResults	The model training result returned by Immunogenicity_TrainModels.
clusterDF	A dataframe containing cluster metadata, consisting of "Peptide" and "Cluster" columns.
externalFeatureDFList	The feature dataframes for which immunogenicity is to be predicted.

masato-ogishi/Repitope documentation built on Feb. 14, 2023, 5:47 a.m.