quantileNormalize            package:HELP            R Documentation

_Q_u_a_n_t_i_l_e _n_o_r_m_a_l_i_z_a_t_i_o_n

_D_e_s_c_r_i_p_t_i_o_n:

     Apply quantile normalization to multiple bins of data, divided by
     a sliding window approach

_U_s_a_g_e:

     quantileNormalize(x, y, ...)

_A_r_g_u_m_e_n_t_s:

       x: the vector of numerical data to be normalized. If 'x' is a
          matrix it is interpreted as a vector. 'x' can also be of
          class '"ExpressionSet"'. 

       y: an additional vector of numerical data to be used for
          binning. If 'y' is a matrix it is interpreted as a vector.
          'y' can also be of class '"ExpressionSet"'. 

     ...: Arguments to be passed to methods (see
          'quantileNormalize-methods'):

          '_e_l_e_m_e_n_t' which element of 'AssayData' to use for a given
               'ExpressionSet' input (default is '"exprs"') 

          '_s_a_m_p_l_e' which element of 'sampleNames' to use as data
               (default is 1). Can be a character matching a sample
               name or simply an integer indicating which sample to
               choose. See 'getSamples'. 

          '_f_e_a_t_u_r_e' which element of 'featureData' to use as binning
               variable (default is 1). Can be a character matching
               'varLabel' or simply an integer indicating which feature
               to choose. See 'getFeatures'. 

          '_n_u_m._b_i_n_s' number of bins (default is 10) used to divide the
               data 

          '_n_u_m._s_t_e_p_s' number of steps (default is 3) used to create bin
               offsets, resulting in bins of sliding windows 

          '_m_o_d_e' the binning mode to be used. This must be either
               '"continuous"' (default) or '"discrete"'. '"continuous"'
               mode will divide the data into density-dependent bins. 
               '"discrete"' mode will divide the data uniformly by
               binning data values. 

          '_t_y_p_e' an integer between 1 and 9 (default is 7) selecting
               one of the nine quantile algorithms: see 'quantile'. 

          '_n_a._r_m' logical; if 'TRUE', missing values are removed from x
               and y. If 'FALSE' any missing values cause an error. 

          '...' other arguments to be passed to 'quantile'. See
               'quantile'.

_V_a_l_u_e:

     Returns a vector of normalized numerical data according to input
     parameters.

_A_u_t_h_o_r(_s):

     Reid F. Thompson (rthompso@aecom.yu.edu)

_S_e_e _A_l_s_o:

     'quantileNormalize-methods', 'quantile'

_E_x_a_m_p_l_e_s:

     #demo(pipeline,package="HELP")

     x <- rep(1:100,10)+10*rep(1:10,each=100)
     y <- rep(1:20,each=50)
     d <- density(quantileNormalize(x,y,num.bins=20,num.steps=1,mode="discrete"))
     plot(density(x))
     lines(d$x,d$y/3,col="red")

     #rm(x,y,d)

