moduleNetwork              package:nem              R Documentation

_I_n_f_e_r_s _a _p_h_e_n_o_t_y_p_i_c _h_i_e_r_a_r_c_h_y _u_s_i_n_g _t_h_e _m_o_d_u_l_e _n_e_t_w_o_r_k

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

     Function 'moduleNetwork' estimates the hierarchy using a divide
     and conquer approach. In each step only a subset of nodes (called
     module) is involved and no exhaustive enumeration of model space
     is needed as in function 'score'.

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

     moduleNetwork(D,type="mLL",Pe=NULL,Pm=NULL,lambda=0,para=NULL,hyperpara=NULL,selEGenes=FALSE,verbose=TRUE)

     #S3 methods for class 'moduleNetwork'
     print.ModuleNetwork(x,...)

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

       D: data matrix. Columns correspond to the nodes in the silencing
          scheme. Rows are phenotypes.

    type: (1.) marginal likelihood "mLL" (only for cout matrix D), or
          (2.) full marginal likelihood "FULLmLL" integrated over a and
          b and depending on hyperparameters a0, a1, b0, b1 (only for
          count matrix D), or (3.) "CONTmLL" marginal likelihood for
          probability matrices, or (4.) "CONTmLLDens" marginal
          likelihood for probability density matrices, or (5.)
          "CONTmLLRatio" for log-odds ratio matrices

      Pe: prior position of effect reporters. Default: uniform over
          nodes in hierarchy

      Pm: prior on model graph (n x n matrix) with entries 0 <=
          priorPhi[i,j] <= 1 describing the probability of an edge
          between gene i and gene j.

  lambda: regularization parameter to incorporate prior assumptions.

    para: vector with parameters a and b for "mLL", if count matrices
          are used

hyperpara: vector with hyperparameters a0, b0, a1, b1 for "FULLmLL"

selEGenes: optimize selection of E-genes for each model

 verbose: do you want to see progress statements printed or not?
          Default: TRUE

       x: nem object

     ...: other arguments to pass

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

     'moduleNetwork' is an alternative to exhaustive search  by the
     function 'score' and more accurate than 'pairwise.posterior'.  It
     uses clustering to sucessively split the network into smaller
     modules, which can then be estimated completely. Connections
     between modules are estimated pairwise between nodes of two
     different modules.

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

   graph: the inferred directed graph (graphNEL object)

     pos: posterior over effect positions

  mappos: MAP estimate of effect positions

    type: as used in function call

    para: as used in function call

hyperpara: as used in function call

  lambda: as in function call

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

     Holger Froehlich

_R_e_f_e_r_e_n_c_e_s:

     Froehlich H, Fellmann M, Sueltmann H, Poustka A, Beissbarth T:
     Large Scale Statistical Inference of Signaling Pathways from RNAi
     and Microarray Data. BMC Bioinformatics, 2007.

     Froehlich H, Fellmann M, Sueltmann H, Poustka A, Beissbarth T:
     Estimating Large Scale Signaling Networks through Nested Effects
     Models from Intervention Effects in Microarray Data. Proc. German
     Conf. Bioinformatics (GCB), pp. 45 - 54, 2007.

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

     'score', 'nem'

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

        data("BoutrosRNAi2002") 
        res <- moduleNetwork(BoutrosRNAiDiscrete[,9:16],para=c(.13,.05))
        
        # plot graph
        plot(res,what="graph")
        
        # plot posterior over effect positions
        plot(res,what="pos")
        
        # estimate of effect positions
        res$mappos
        

