Download All

Code covered by the BSD License

Highlights from
MGraph

MGraph.m MGraph Toolbox
MGraph_gauss.m bellow is object handle
MGraph_logline.m bellow is object handle
MGraph_properties.m
marray_debug.m
G=MGraph_add_best_edge_to_pat...
G=MGraph_remove_worst_edge_in... Input
MGraph_BGscore(d,G)
MGraph_export2Pjart(filename,... %export data to Pajrt
MGraph_model2Graph(selected_m... make graph from G-logline model
V_n=MGraph_GaussEstimate_vari... Input: sample_var is the original sample variance matrix
[G,max_score]=MGraph_add_best...
[G,max_score]=MGraph_remove_w... Input: G is a DAG, isordered==1 means input variables are ordered
[a,mtc]=wang_nexksb(n,k,a,mtc... generate subsets of a sets n with k elements
[color,time,d,f,phi,back_edge... Depth-first search of the graph
[color,time,d,f,phi,idx,back_... it is for directed graph
[cond_density,T0,TL]=gnt_scor... Input: u0 is estimated mean, v is estimated variance, b is the regression coefficient,
[data,varnames,casenames]=mgr... deblank
[diffV ,adjecentV,record_idx]... find adjecent edge of add_edge1 in new_model
[diffV ,adjecentV]=test_adjec... find adjecent edge of add_edge1 in new_model
[marked, marked_data]=dnr_mak... Categorical assessments,
[old_parcorrf,delet_edge,reco... Graphical GAussian model for continues data
[old_parcorrf,delet_edge,reco... Graphical GAussian model for continues data
[old_parcorrf,delet_edge,reco... Graphical GAussian model for continues data
[old_parcorrf,delet_edge,reco... Graphical GAussian model for continues data
[old_parcorrf,delet_edge,reco... P/181, Graphical models in applied multivariate statistics
[old_parcorrf,delet_edge,reco... Input: old_var is the covariance of the data
[old_parcorrf,delet_edge,reco... Input: old_var is the covariance of the data
[old_parcorrf,delet_edge,reco... Input: old_var is the covariance of the data
[old_parcorrf,delet_edge,reco... Input: old_var is the covariance of the data
[old_parcorrf,delet_edge,reco... P/181, Graphical models in applied multivariate statistics
[old_parcorrf,pdag ,GG, maxSc... check whether have edges go from high order to lower order and remove it
[old_parcorrf,pdag ,GG, maxSc... Input: d is the data, G is the initial pattern graph, it should use pattern at here
[old_parcorrf,pdag ,GG, maxSc... Input: d is the data, G is the initial pattern graph, it should use pattern at here
[old_parcorrf,pdag ,GG, maxSc...
[old_parcorrf,pdag ,GG, maxSc...
[old_parcorrf,pdag ,GG, maxSc...
[pdag ,GG, maxScore,ischanged...
[removeEG, needtestEG]=MGraph... because in the out results, the device is arranged as ABCDEF.. order in the matrise
arrow(varargin) ARROW Draw a line with an arrowhead.
arrow(varargin) ARROW Draw a line with an arrowhead.
b=gnt_graph_to_coeffiecent_b(... Input: adj_matrix of the graph
c_n_alpha=gnt_C(n,alpha) compute the normalization coefficent C(n,alpha)
children(adj_mat, i, t) CHILDREN Return the indices of a node's children in sorted order
condP=gnt_scoring_uncompleteG... %Input: c is the network structure, sigma and alpha is effective sample size of mean and the variance,
cond_density=gnt_conditional_... compute the conditional density based on the network structure
cond_indep_fisher_z(X, Y, S, ... COND_INDEP_FISHER_Z Test if X indep Y given Z using Fisher's Z test
device=MGraph_loglineMakeDevi... make device for both row or both column data
device=MGraph_loglineMakeDevi... make device for one row or one column data
distchck(nparms,arg1,arg2,arg... DISTCHCK Checks the argument list for the probability functions.
draw_graph(adj, labels, node_... DRAW_LAYOUT Draws a layout for a graph
dsep(X, Y, S, G)
family(A,i,t) FAMILY Return the indices of parents and self in sorted order
find_equiv_posns(vsmall, vlar... FIND_EQUIV_POSNS p[i] = the place where vsmall[i] occurs in vlarge.
gama=gnt_gama_function(x) compute the gama function
gp2_idxgp=MGraph_loglineSortI...
graph_separated(G, X, Y, S)
isDecomposable=isDecomposable... Input adj_mat of Graph
isSim=isSimplical_node(G,i) test node i whether it is simplical node in graph G
is_SDordering=MGraph_isSDorde... test function of SD-ordering
isundirected=MGraph_isundirec... check whether the input G is undirected graph
ksubset=wang_kSubset(nb,k) Generate the subsets of a sets nb with k elements
layout_dag(adj) MAKE_LAYOUT Creates a layout from an adjacency matrix
marray_debuge(str)
moralize(G) MORALIZE Ensure that for every child, all its parents are married, and drop directionality of edges.
mysetdiff(A,B) MYSETDIFF Set difference of two sets of positive integers (much faster than built-in setdiff)
myunion(A,B) MYUNION Union of two sets of positive integers (much faster than built-in union)
needtestEG=MGraph_loglineOutp... above is the initial values
neighbors(adj_mat, i) NEIGHBORS Find the parents and children of a node in a graph.
new_model3=MGraph_makeSubGrap... INPUT: oldmodel cliques, delet_edge
new_out=MGraph_loglineMergeEd... make new partiation of raw data based on new model of the data
normcdf(x,mu,sigma) NORMCDF Normal cumulative distribution function (cdf).
norminv(p,mu,sigma); NORMINV Inverse of the normal cumulative distribution function (cdf).
numberVector=MGraph_string2nu...
outdata=MGraph_loadDataforGau... make a function for input data in logline
outdata=MGraph_loadDataforLog... make a function for input data in logline
parents(adj_mat, i) PARENTS Return the list of parents of node i
partial_corr_coef(S, i, j, Y) PARTIAL_CORR_COEF Compute a partial correlation coefficient
pdag=mgraph_meek4ruls(G,pdag) Input G: is undirected adjecent matrix, pdag is the pattern
reachability_graph(G)
result=Chisq(x,n)
result=MGraph_MainGaussloglin... Graphical logline modle for discrete data
result=MGraph_logloneMakeTabl... Input: numofGin_X: number of subtypes in each group
selected_model=MGraph_logline... For current version there is something wrong
setdiag(M, v) SETDIAG Set the diagonal of a matrix to a specified scalar/vector.
som_denormalize(sD,varargin) SOM_DENORMALIZE Denormalize data.
som_norm_variable(x, method, ... SOM_NORM_VARIABLE Normalize or denormalize a scalar variable.
som_normalize(sD,method,comps... SOM_NORMALIZE (Re)normalize data or add new normalizations.
som_set(sS, varargin) SOM_SET Create and check SOM Toolbox structs, give values to their fields.
stringVector=MGraph_num2strin... input number of edge location
w=gnt_make_precision_matrix(v... estimated the precision matrix cov^-1 for gnt
wang_learn_struct_pdag_pc(con... LEARN_STRUCT_PDAG_PC Learn a partially oriented DAG (pattern) using the PC algorithm
wang_learn_struct_pdag_pc_bak... LEARN_STRUCT_PDAG_PC Learn a partially oriented DAG (pattern) using the PC algorithm
wang_learn_struct_undirect2pd... LEARN_STRUCT_PDAG_PC Learn a partially oriented DAG (pattern) using the PC algorithm
Contents.m
leaveOneOut_testGnet_fil.m
leaveOneOut_testGnet_hog.m
leaveOneOut_testGnet_phe.m
leaveOneOut_testGnet_pkc.m
test_baysein_network.m
test_decomposable.m
test_samplesGauss.m
test_samplesLogline.m
View all files

Be the first to rate this file! 4 Downloads (last 30 days) File Size: 915.19 KB File ID: #14635

MGraph

by junbai wang

12 Apr 2007 (Updated 17 Jul 2009)

Probabilistic graphical models for reconstruction of genetic regulatory networks using DNA microarra

| Watch this File

File Information
Description	This toolbox includes: Gaussian Networks; PC algorithms; Gaussian Graphical Models; Graphical Log-linear Models and Independence Graphical Modles
Required Products	Bioinformatics Toolbox
MATLAB release	MATLAB 7 (R14)

Tags for This File
Everyone's Tags	graphical models for microarray data analysis, probability, statistics
Tags I've Applied
Add New Tags	Please login to tag files.

Please login to add a comment or rating.

Updates
18 Jun 2009	Removed other license file
17 Jul 2009	Removed other license

Tag Activity for this File
Tag	Applied By	Date/Time
statistics	junbai wang	22 Oct 2008 09:09:10
probability	junbai wang	22 Oct 2008 09:09:10
graphical models for microarray data analysis	junbai wang	22 Oct 2008 09:09:10

Highlights from MGraph

MGraph

Highlights from
MGraph