pcorfdrci               package:GeneNT               R Documentation

_T_w_o-_s_t_a_g_e _s_c_r_e_e_n_i_n_g _p_r_o_c_e_d_u_r_e _b_a_s_e_d _o_n _p_a_r_t_i_a_l _c_o_r_r_e_l_a_t_i_o_n _c_o_e_f_f_i_c_i_e_n_t _i_n _G_r_a_p_h_i_c _G_a_u_s_s_i_a_n _M_o_d_e_l _f_r_a_m_e_w_o_r_k

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

     This function implement the two-stage screening procedure based on
     partial correlation coefficient in the framework of Gaussian
     Graphic Model. Specifying a pair of FDR and MAS criteria, the
     algorithm provides an initial co-expression discovery that
     controls only FDR, which is then followed by a second stage
     co-expression discovery which controls both FDR and MAS.

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

     pcorfdrci(Q, pcormin)

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

       Q: The significant level

 pcormin: The specified minimum acceptable strength of association
          measured using partial correlation coefficient

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

     The data matrix file must be in the right format. The first row
     (header) must be one shorter than the rest rows. The first column
     must be gene names.

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

     The function returns a list of gene pairs that satisfies the FDR
     and MAS criteria simultaneously measured by partial correlation
     coefficient.  

    pG1 : The gene pairs that passes Stage I (FDR only) screening

    pG2 : The gene pairs that passed both Stage I (FDR) and II (MAS)
          screenings

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

     Dongxiao Zhu (<URL: http://www-personal.umich.edu/~zhud>)

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

     Fisher, R.A. (1921). On the 'probable error' of a coefficient of
     correlation deduced from a small sample. _Metron_, *1*, 1-32.

     Zhu, D., Hero, A.O., Qin, Z.S. and Swaroop, A. High throughput
     screening of co-expressed gene pairs with controlled False
     Discovery Rate (FDR) and Minimum Acceptable Strength (MAS).
     _Submitted_.

     Schfer, J., and K. Strimmer. (2004) An empirical Bayes approach
     to inferring large-scale gene association networks.
     _Bioinformatics_, *1*, 1-13.

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

     'corfdrci'

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

     # load GeneNT and GeneTS library
     library(GeneTS)
     library(GeneNT)

     #EITHER use the example dataset
     data(dat) 
     #OR use the following if you want to import external data 
     #dat <- read.table("gal.txt", h = T, row.names = 1) 
     #Note, data matrix name has to be "dat"

     #use (FDR, MAS) criteria (0.2, 0.2) as example to screen gene pairs 
     #g3 <- pcorfdrci(0.2, 0.2) 
     #G1 <- g3$G1.all
     #G2 is the dataset containing gene pairs that passed two-stage screening
     #G2 <- g3$G2  

