compareSpmCollection         package:KCsmart         R Documentation

_K_C_s_m_a_r_t _C_o_m_p_a_r_a_t_i_v_e _c_a_l_c_u_l_a_t_e _n_u_l_l _d_i_s_t_r_i_b_u_t_i_o_n

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

     Compare the samples of one class in the sample point matrix
     collection to the samples in the other class and calculate the
     null distribution

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

     compareSpmCollection(spmCollection, nperms=20, method=c("siggenes", "perm"), siggenes.args=NULL, altcl=NULL)

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

spmCollection: An spmCollection object as created by the
          'calcSpmCollection' function

  nperms: The number of permutations to be used to calculate the null
          distribution 

   altcl: Instead of using the class vector from the spmCollection
          object an alternative vector can be used

  method: The method to be used to calculate the null distribution

siggenes.args: Optional additional arguments to the siggenes function 

_D_e_t_a_i_l_s:

     The method to be used to determine significant regions can either
     be the SAM methodology from the siggenes package or a
     signal-to-noise/permutation based method. For more information
     regarding the siggenes method please check the corresponding
     package.

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

     Returns a compKc object which returns the original data and,
     depending on the method used, the permuted data or the fdr-delta
     value combinations as calculated by the siggenes package.

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

     Jorma de Ronde

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

     'compareSpmCollection',  'getSigRegionsCompKC'

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

     data(hsSampleData)
     data(hsMirrorLocs)

     spmc1mb <- calcSpmCollection(hsSampleData, hsMirrorLocs, cl=c(rep(0,10),rep(1,10)))
     spmcc1mb <- compareSpmCollection(spmc1mb, nperms=3)
     spmcc1mbSigRegions <- getSigRegionsCompKC(spmcc1mb)

     plot(spmcc1mb, sigRegions=spmcc1mbSigRegions)

