Identificantion of tissue-specific alternative polyadenylation sites

Documentation for package ‘TSAPA’ version 0.1.0

apa_context	Calculate the APA context feature
balanced_data	Balanced data for the unbalanced problem
classification_model	Select a classification model
extract_seq	Extract sequence around ploy(A) sites
feature_rank	Rank the individual feature for the predict accuracy
feature_selection	Select the feature selection algorithm
FHMM	Calculate the first-order heterogeneous Markov model(FHMM)
FHMM_feature	Calculate the motif probability for sequence
geneinfo	Extract annotation information for ploy(A) sites
Generic_model	Predict tissue-specific poly(A) sites using the generic classification model of rice japonica
gram	Compute the occurrence number of K-grams
Intergenic_model	Predict tissue-specific poly(A) sites in intergenic regions
mapPA2GFF	Map ploy(A) site to annotation file
model_rank	Rank the classification model by performance
nupop	Compute nucleosome occupancy scores base on sequence information
parseGFF	Normalize the annotation file
predict_result	Evaluate the classification model
pwm	Calculate the position weight matrix
pwm_feature	Calculate the PWM value of motifs in a given sequence file
roku_modeH	Calculate the information entropy(H) and adjusted information entropy(modeH)
select_tsPA	Select the tissue-specific or constitutive poly(A) sites
Zcurve	Calculate the Zcurve for sequence