def on_button_go_plot_clicked(self, widget): """ 04-19-05 06-14-05 use graphDotOutput() and insert it into the textbuffer 10-11-05 add cluster_id and go_no for each graph """ if self.cluster == None: print "Cluster not loaded in" return #first construct the graph subgraph = self.cluster_info_instance.graph_from_node_edge_set(\ self.cluster.vertex_set, self.cluster.edge_set) pathlist = [] treeselection_go_association = self.treeview_go_association.get_selection() treeselection_go_association.selected_foreach(foreach_cb, pathlist) if len(pathlist) >0: for i in range(len(pathlist)): go_no = self.liststore_go_association[pathlist[i][0]][0] graphSrcFname = '/tmp/GuiAnalyzer.dot' graphFname = '/tmp/GuiAnalyzer.ps' graphSrcF = open(graphSrcFname, 'w') graphDotOutput(graphSrcF, subgraph, \ self.gene_no2gene_id, self.gene_no2go_no, \ function=int(go_no), weighted=0) graphSrcF.close() #06-14-05 get the plot_type_command from the comboboxentry_plot_type entry = self.comboboxentry_plot_type.child plot_type_command = entry.get_text() if plot_type_command=='neato' or plot_type_command=='twopi': plot_type_command += ' -Goverlap=false' #06-14-05 -Goverlap=false passed to neato or twopi commandline = '%s -Tps %s -o %s'%(plot_type_command, graphSrcFname, graphFname) system_call(commandline) #10-11-05 temporary adding this block to draw pictures in png format outputfname = '/tmp/%s_%s.png'%(self.cluster.cluster_id, go_no) commandline = '%s -Tpng %s -o %s'%(plot_type_command, graphSrcFname, outputfname) system_call(commandline) textbuffer = self.textview_subgraph.get_buffer() im = Image.open(graphFname) ar = fromimage(im) pixbuf = gtk.gdk.pixbuf_new_from_array(ar, gtk.gdk.COLORSPACE_RGB, 8) startiter = textbuffer.get_start_iter() textbuffer.insert_pixbuf(startiter, pixbuf) startiter = textbuffer.get_start_iter() textbuffer.insert(startiter, "cluster_id:%s go_no:%s"%(self.cluster.cluster_id, go_no)) #cleanup the temporary files and others del im del ar
def node_fire(self, communicator, node_rank2cluster_no, netmine2nd_parameter_list):
"""
04-08-05
mpi form
05-16-05
os.system() might fail on some platforms, so use recursive system_call()
"""
# get the output filename prefix
ofname_prefix = netmine2nd_parameter_list[20]
# store the finished output files and send it back to node 0 later
ofname_list = []
if communicator.rank in node_rank2cluster_no: # check if it's necessary to ignite the node
# fire repeatedly
for cluster_no in node_rank2cluster_no[communicator.rank]:
jobrow = netmine2nd_parameter_list + ["-f", repr(cluster_no)]
sys.stderr.write("node %s working on cluster %s...\n" % (communicator.rank, cluster_no))
exit_code = system_call("%s" % " ".join(jobrow))
sys.stderr.write(
"node %s on cluster %s done, exit_code: %s\n" % (communicator.rank, cluster_no, exit_code)
)
ofname_list.append(
"%s_%sh" % (ofname_prefix, cluster_no)
) # 04-09-05 haiyan puts 'h' after cluster_no.??
# join the list by blank and send it back to node 0
communicator.send("%s" % " ".join(ofname_list), 0, communicator.rank)
def run_netmine(self, node, netmine_parameter_list):
"""
04-01-05
input: wl_list of netmine
output: number of clusters
nothing to do with mpi
05-16-05
os.system() might fail on some platforms, so use recursive system_call()
06-10-05
random select a big-memory node from 16 to 35 to run netmine
"""
sys.stderr.write("Running netmine...")
# wl = ['ssh', 'node%s'%node, '%s'%' '.join(netmine_parameter_list)]
"""
04-08-05 spawnvp gets dead under MPI, use system instead.
"""
random_node = random.randint(16, 35)
# return_code = os.spawnvp(os.P_WAIT, netmine_parameter_list[0], netmine_parameter_list)
commandline = "ssh node%s %s" % (random_node, " ".join(netmine_parameter_list))
if self.debug:
sys.stderr.write("The commandline of netmine is %s\n" % commandline)
exit_code = system_call(commandline) # 05-16-05 use the recursive one.
# exit_code = os.system('%s'%' '.join(netmine_parameter_list))
op = netmine_parameter_list[8] # the 8th is the output file
no_of_clusters = 0
of = open(op, "r")
for line in of:
no_of_clusters += 1
sys.stderr.write("total clusters:%s. exit_code: %s.\n" % (no_of_clusters, exit_code))
return no_of_clusters
def uniqueSort(self, inputfile, outputfile, tmpdir='/scratch'):
"""
08-07-05
sort the file (unique it simutaneouly)
"""
sys.stderr.write("Starting to sort and unique %s..."%inputfile)
commandline = 'sort -T %s -u %s -o %s'%(tmpdir, inputfile, outputfile)
exit_code = system_call(commandline)
#os.remove(inputfile)
sys.stderr.write("Done.\n")
def run_netmine2nd(cluster_no, netmine2nd_parameter_list):
"""
05-19-05
similar to node_fire() of class netmine_wrapper
"""
import sys
# get the output filename prefix
ofname_prefix = netmine2nd_parameter_list[20]
jobrow = netmine2nd_parameter_list + ["-f", repr(cluster_no)]
exit_code = system_call("%s" % " ".join(jobrow))
ofname = "%s_%sh" % (ofname_prefix, cluster_no) # 04-09-05 haiyan puts 'h' after cluster_no.??
return ofname
def collect_and_merge_output(self, of_name_list, final_ofname):
"""
04-08-05
only for rank 0
1. receive the concatenated ofname_list from all nodes
2. cat all files together into final_ofname and delete the intermediary files.
05-16-05
os.system() might fail on some platforms, so use recursive system_call()
05-19-05
collecting output filenames is NOT necessary, it's done in distribute_jobs()
(via mpi_schedule_jobs())
"""
sys.stderr.write("Catting them together...")
# 05-22-05 remove the final_ofname first to avoid '>>' to add up
if os.path.isfile(final_ofname):
os.remove(final_ofname)
for ofname in of_name_list:
# do it one by one because 'cat * >final_ofname' might cause error 'Argument list too long'
# which is the case for 'rm' when there're thousands of files represented by '*'.
exit_code = system_call("cat %s >> %s" % (ofname, final_ofname)) # it's >> not >
exit_code = system_call("rm %s" % ofname) # delete it immediately
sys.stderr.write("Done.\n")
def callTightClust(go_no, parameter_list):
"""
06-03-05
the node_function for mpi_schedule_jobs()
"""
import sys
output_dir = parameter_list[0]
no_of_nas = parameter_list[1]
top_percentage = parameter_list[2]
input_file = os.path.join(output_dir, 'edge_data_%s'%go_no)
output_file = os.path.join(output_dir, 'edge_data_%s.2'%go_no)
preprocess_instance = PreprocessEdgeData(input_file, output_file, no_of_nas, top_percentage)
preprocess_instance.run()
tightClust_path = os.path.join(os.path.expanduser('~/script/annot/bin/tightClust'), 'tightClust')
job_list = [tightClust_path, '%s/'%output_dir, 'edge_data_%s.2'%go_no] + parameter_list[3:]
exit_code = system_call("%s"%' '.join(job_list))
tightClust_output_file = '%s.tightClust'%output_file
del preprocess_instance
return tightClust_output_file
def output_p_gene_id_list(self, curs, schema_instance1, schema_instance2, p_gene_id_list, writer, pic_output_dir,\
pga_instance1, pga_instance2, cluster_info_instance, simple):
"""
10-15-05
add score1 and is_accepted1
10-17-05
score and is_accepted depend on whether pga_instance is None or not
10-17-05 add simple to allow no graph pictures output
also get prediction from schema_instance1 and calculate the score if prediction is available
10-18-05
sort the p_gene_id_list first
"""
#10-15-05 following sentence slightly different from PredictionFilterByClusterSize.py in the trailing edge_gradient
#and d_matrix is a placeholder
sql_sentence1 = "SELECT p.p_gene_id, p.gene_no, p.go_no, p.is_correct, p.is_correct_l1, \
p.is_correct_lca, p.avg_p_value, p.no_of_clusters, p.cluster_array, p.p_value_cut_off, p.recurrence_cut_off, \
p.connectivity_cut_off, p.cluster_size_cut_off, p.unknown_cut_off, p.depth_cut_off, p.mcl_id, p.lca_list, \
p.vertex_gradient, p.edge_gradient, m.vertex_set, s.edge_set, 'd_matrix', 'r' from %s p, %s s, %s m where \
p.mcl_id=s.splat_id and p.mcl_id=m.mcl_id"%(schema_instance1.p_gene_table, \
schema_instance1.splat_table, schema_instance1.mcl_table)
sql_sentence2 = "SELECT p.p_gene_id, p.gene_no, p.go_no, p.is_correct, p.is_correct_l1, \
p.is_correct_lca, p.avg_p_value, p.no_of_clusters, p.cluster_array, p.p_value_cut_off, p.recurrence_cut_off, \
p.connectivity_cut_off, p.cluster_size_cut_off, p.unknown_cut_off, p.depth_cut_off, p.mcl_id, p.lca_list, \
p.vertex_gradient, p.edge_gradient, m.vertex_set, s.edge_set, 'd_matrix', 'r' from %s p, %s s, %s m where \
p.mcl_id=s.splat_id and p.mcl_id=m.mcl_id"%(schema_instance2.p_gene_table, \
schema_instance2.splat_table, schema_instance2.mcl_table)
writer.writerow(['p_gene_id', 'gene_no', 'go_no', 'is_correct_lca', 'p_value', 'recurrence', 'connectivity',\
'cluster_size', 'unknown_ratio', 'mcl_id', 'lca_list', 'edge_gradient', 'score1', 'is_accepted1', 'score2', 'is_accepted2'])
p_gene_id_list.sort()
for p_gene_id in p_gene_id_list:
#sql_sentence1's prediction infomation is not gonna be displayed
curs.execute("%s and p.p_gene_id=%s"%(sql_sentence1, p_gene_id))
rows = curs.fetchall()
if rows:
p_attr_instance1 = prediction_attributes(rows[0], type=3)
else:
p_attr_instance1 = None
#sql_sentence2's prediction infomation is going to be displayed
curs.execute("%s and p.p_gene_id=%s"%(sql_sentence2, p_gene_id))
rows = curs.fetchall()
if rows:
p_attr_instance2 = prediction_attributes(rows[0], type=3)
if pga_instance1 and p_attr_instance1:
(is_accepted1, score1) = pga_instance1.prediction_accepted(p_attr_instance1.go_no, \
[-math.log(p_attr_instance1.p_value_cut_off), p_attr_instance1.recurrence_cut_off, \
p_attr_instance1.connectivity_cut_off, p_attr_instance1.cluster_size_cut_off, \
p_attr_instance1.edge_gradient])
else:
is_accepted1, score1 = None, None
if pga_instance2:
(is_accepted2, score2) = pga_instance2.prediction_accepted(p_attr_instance2.go_no, \
[-math.log(p_attr_instance2.p_value_cut_off), p_attr_instance2.recurrence_cut_off, \
p_attr_instance2.connectivity_cut_off, p_attr_instance2.cluster_size_cut_off, \
p_attr_instance2.edge_gradient])
else:
is_accepted2, score2 = None, None
writer.writerow([p_attr_instance2.p_gene_id, p_attr_instance2.gene_no, p_attr_instance2.go_no, \
p_attr_instance2.is_correct_lca, p_attr_instance2.avg_p_value, p_attr_instance2.recurrence_cut_off,\
p_attr_instance2.connectivity_cut_off, p_attr_instance2.cluster_size_cut_off, p_attr_instance2.unknown_cut_off,\
p_attr_instance2.mcl_id, p_attr_instance2.lca_list, p_attr_instance2.edge_gradient, score1, is_accepted1, \
score2, is_accepted2])
if not simple:
#prepare vertex_set and edge_set to draw graphs
vertex_set = p_attr_instance2.vertex_set[1:-1].split(',')
vertex_set = map(int, vertex_set)
edge_set = p_attr_instance2.edge_set[2:-2].split('},{')
for i in range(len(edge_set)):
edge_set[i] = edge_set[i].split(',')
edge_set[i] = map(int, edge_set[i])
#following copied from GuiAnalyzer.py
subgraph = cluster_info_instance.graph_from_node_edge_set(vertex_set, edge_set)
graphSrcFname = '/tmp/GuiAnalyzer.dot'
graphFname = os.path.join(pic_output_dir, '%s_%s_%s_%s.png'%(p_attr_instance2.p_gene_id, \
p_attr_instance2.gene_no, p_attr_instance2.go_no, p_attr_instance2.mcl_id))
graphSrcF = open(graphSrcFname, 'w')
graphDotOutput(graphSrcF, subgraph, \
self.gene_no2gene_id, self.gene_no2go_no, \
centralnode=p_attr_instance2.gene_no, function=p_attr_instance2.go_no, weighted=0, )
graphSrcF.close()
plot_type_command='neato -Goverlap=false'
commandline = '%s -Tpng %s -o %s'%(plot_type_command, graphSrcFname, graphFname)
system_call(commandline)
