def run(self):
(conn, curs) = db_connect(self.hostname, self.dbname, self.schema)
id2chr_start_stop = self.get_id2chr_start_stop(curs, self.tax_id)
gene_id2gene_symbol = get_gene_id2gene_symbol(curs, self.tax_id)
mt_id2gene_symbol = self.get_mt_id2gene_symbol(curs,
gene_id2gene_symbol,
self.tax_id)
mt_id_gene_symbol2color_code = self.get_mt_id2color_code(
self.input_dir, self.color_code_list, mt_id2gene_symbol)
self.parse_files(self.input_dir, self.output_fname, id2chr_start_stop,
mt_id_gene_symbol2color_code, mt_id2gene_symbol)
def run(self):
(conn, curs) = db_connect(self.hostname, self.dbname, self.schema)
id2chr_start_stop = self.get_id2chr_start_stop(curs, self.tax_id)
gene_id2gene_symbol = get_gene_id2gene_symbol(curs, self.tax_id)
mt_id2gene_symbol = self.get_mt_id2gene_symbol(curs, gene_id2gene_symbol, self.tax_id)
mt_id_gene_symbol2color_code = self.get_mt_id2color_code(
self.input_dir, self.color_code_list, mt_id2gene_symbol
)
self.parse_files(
self.input_dir, self.output_fname, id2chr_start_stop, mt_id_gene_symbol2color_code, mt_id2gene_symbol
)
def run(self):
"""
--db_connect()
--get_gene_id2gene_symbol()
--get_go_id2name()
--get_mcl_id2pred_go_id2gene_id_set_from_db()
--get_prot_interaction_graph()
--get_gene_id_set()
--get_mt_no2gene_id_set()
--get_go_id2gene_set_from_db()
--get_mcl_id2mt_no_set()
--draw_all_patterns()
--draw_augmented_PI_graph()
--draw_pattern()
2006-11-21
add prot_interaction_graph
2006-12-29
split draw_all_patterns()
add another way to call draw_all_patterns() through pattern_id_list
"""
conn, curs = db_connect(self.hostname, self.dbname, self.schema)
gene_id2gene_symbol = get_gene_id2gene_symbol(curs, self.tax_id)
go_id2name = get_go_id2name(curs)
if not os.path.isdir(self.output_dir):
os.makedirs(self.output_dir)
#mcl_id2pred_go_id2gene_id_set = self.get_mcl_id2pred_go_id2gene_id_set(input_fname)
mcl_id2pred_go_id2gene_id_set = self.get_mcl_id2pred_go_id2gene_id_set_from_db(curs, self.input_fname, self.gene_p_table)
prot_interaction_graph = self.get_prot_interaction_graph(curs, self.prot_interaction_table, self.tax_id)
gene_id_set = self.get_gene_id_set(curs, self.gene_table)
comp_mt_no2gene_id_set = self.get_mt_no2gene_id_set(curs, self.comp_tf_mapping_table, gene_id_set)
expt_mt_no2gene_id_set = self.get_mt_no2gene_id_set(curs, self.expt_tf_mapping_table, gene_id_set)
go_id2gene_set = self.get_go_id2gene_set_from_db(curs, self.go_table)
comp_mcl_id2mt_no_set = self.get_mcl_id2mt_no_set(curs, self.comp_cluster_bs_table)
expt_mcl_id2mt_no_set = self.get_mcl_id2mt_no_set(curs, self.expt_cluster_bs_table)
for pattern_id in self.pattern_id_list:
self.draw_all_patterns(curs, pattern_id, mcl_id2pred_go_id2gene_id_set, comp_mt_no2gene_id_set, \
expt_mt_no2gene_id_set, go_id2gene_set, comp_mcl_id2mt_no_set, expt_mcl_id2mt_no_set,\
self.pattern_table, self.output_dir, gene_id2gene_symbol, go_id2name, prot_interaction_graph)
pattern_id = raw_input("Please input a pattern id:")
while pattern_id:
self.draw_all_patterns(curs, pattern_id, mcl_id2pred_go_id2gene_id_set, comp_mt_no2gene_id_set, \
expt_mt_no2gene_id_set, go_id2gene_set, comp_mcl_id2mt_no_set, expt_mcl_id2mt_no_set,\
self.pattern_table, self.output_dir, gene_id2gene_symbol, go_id2name, prot_interaction_graph)
pattern_id = raw_input("Please input a pattern id:")
def run(self): """ 09-28-05 12-19-05 use class_list and output_fname_list to ease program writing 12-30-05 fix a bug in indexing darwin_instance_list 2006-09-25 2007-02-08 add context_prediction_csv_format """ tf_darwin_ofname = os.path.join(self.output_dir, '%s.tf.darwin'%self.cluster_bs_table) cluster_darwin_ofname = os.path.join(self.output_dir, '%s.cluster.darwin'%os.path.basename(self.input_fname)) prediction_darwin_ofname = os.path.join(self.output_dir, '%s.prediction.darwin'%os.path.basename(self.input_fname)) pattern_darwin_ofname = os.path.join(self.output_dir, '%s.pattern.darwin'%self.pattern_table) if not os.path.isdir(self.output_dir): os.makedirs(self.output_dir) conn, curs = db_connect(self.hostname, self.dbname, self.schema) tax_id = org2tax_id(self.organism) #gene_no2id = get_gene_no2gene_id(curs) #Watch, if unigene, should use this. gene_id2symbol = get_gene_id2gene_symbol(curs, tax_id) gene_id2symbol = self.replace_prime_in_gene_id2symbol(gene_id2symbol) #01-26-06 #gene_no2symbol = dict_transfer(gene_no2id, gene_id2symbol) #Jasmine wants the gene symbol 09-28-05 #gene_id is integer in gene.gene table and same as gene_no, so just use it. go_no2name = get_go_no2name(curs) #09-28-05 Jasmine wants the go_name, not go_id #2006-09-25 use gene_id2symbol to replace mt_no2tf_name #mt_no2tf_name = get_mt_no2tf_name() mt_no2tf_name = gene_id2symbol class_list = [tf_darwin_format, cluster_darwin_format, prediction_darwin_format, pattern_darwin_format, context_prediction_csv_format] context_prediction_csv_fname = os.path.join(self.output_dir, '%s.context.csv'%self.input_fname) output_fname_list = [tf_darwin_ofname, cluster_darwin_ofname, prediction_darwin_ofname, pattern_darwin_ofname, context_prediction_csv_fname] darwin_instance_list = [] for i in range(len(self.running_bit)): if self.running_bit[i] == '1': darwin_instance_list.append(class_list[i](self.hostname, self.dbname, self.schema, self.pattern_table,\ self.cluster_bs_table, self.input_fname, self.lm_bit, self.acc_cut_off, \ output_fname_list[i], gene_id2symbol, go_no2name, mt_no2tf_name, debug, report)) #2006-09-25 current_pos = len(darwin_instance_list)-1 #12-30-05 darwin_instance_list[current_pos].start() for i in range(len(darwin_instance_list)): darwin_instance_list[i].join()
def run(self):
"""
12-28-05
"""
conn, curs = db_connect(self.hostname, self.dbname, self.schema)
organism = get_org_from_tax_id(curs, self.tax_id)
#get the key_map
gene_id2symbol = get_gene_id2gene_symbol(curs, self.tax_id)
#open output here
outf = open(self.output_fname, 'w')
if len(self.running_bit)>=1 and self.running_bit[0] =='1':
gene_id2go_bp_term = get_gene_id2go_term(curs, term_type='biological_process', organism=organism)
self.dict2darwin(gene_id2go_bp_term, 'go_bp', gene_id2symbol, outf)
if len(self.running_bit)>=2 and self.running_bit[1] =='1':
gene_id2go_cc_term = get_gene_id2go_term(curs, term_type='cellular_component', organism=organism)
self.dict2darwin(gene_id2go_cc_term, 'go_cc', gene_id2symbol, outf)
if len(self.running_bit)>=3 and self.running_bit[2] =='1':
gene_id2no_of_events = get_gene_id2no_of_events(curs, self.tax_id, ensembl2no_of_events_table='graph.ensembl2no_of_events')
self.dict2darwin(gene_id2no_of_events, 'as', gene_id2symbol, outf)
if len(self.running_bit)>=4 and self.running_bit[3] =='1':
gene_id2no_of_promoters = get_gene_id2no_of_promoters(curs, self.tax_id)
#get_gene_id2no_of_events(curs, self.tax_id, ensembl2no_of_events_table='graph.ensembl_id2no_of_promoters')
self.dict2darwin(gene_id2no_of_promoters, 'dp', gene_id2symbol, outf)
if len(self.running_bit)>=5 and self.running_bit[4] =='1':
tg_tax_id2ca_depth_tax_id_short_org = get_tg_tax_id2ca_depth_tax_id_short_org(curs, self.tax_id)
gene_id2ortholog_tax_id_set = get_gene_id2ortholog_tax_id_set(curs, self.tax_id, homologene_table='homologene.homologene')
#convert gene_id2ortholog_tax_id_set to gene_id2ca_depth_tax_id_short_org_list
gene_id2ca_depth_tax_id_short_org_list = {}
for gene_id, ortholog_tax_id_set in gene_id2ortholog_tax_id_set.iteritems():
ca_depth_tax_id_short_org_list = dict_map(tg_tax_id2ca_depth_tax_id_short_org, list(ortholog_tax_id_set))
ca_depth_tax_id_short_org_list.sort()
gene_id2ca_depth_tax_id_short_org_list[gene_id] = ca_depth_tax_id_short_org_list
self.dict2darwin(gene_id2ca_depth_tax_id_short_org_list, 'gene_age', gene_id2symbol, outf)
if len(self.running_bit)>=6 and self.running_bit[5] =='1':
gene_id2tissue_list = get_gene_id2tissue_list(curs, self.tax_id)
self.dict2darwin(gene_id2tissue_list, 'gene_tissue', gene_id2symbol, outf)
if len(self.running_bit)>=7 and self.running_bit[6] =='1':
gene_id2family_size = get_gene_id2family_size(curs, self.tax_id)
self.dict2darwin(gene_id2family_size, 'gene_family_size', gene_id2symbol, outf)
if len(self.running_bit)>=8 and self.running_bit[7] =='1':
gnf_gene_id2tissue = get_gnf_gene_id2tissue_list(curs, self.tax_id)
self.dict2darwin(gnf_gene_id2tissue, 'gnf_gene_tissue', gene_id2symbol, outf)
#close output
outf.close()
def run(self):
"""
09-05-05
2006-09-21 add fuzzyDense_flag
2006-11-02 add tfbs_association_type
2006-11-02 differentiate good_cluster_table as pattern_xxx or good_xxx for pattern id
--db_connect()
--get_gene_no2bs_no_block()
--construct_two_dicts()
--input_node()
--fetch_cluster_block()
--computing_node()
--node_fire()
--cluster_bs_analysis()
--create_cluster_bs_table()
--output_node()
--submit_cluster_bs_table()
"""
communicator = MPI.world.duplicate()
node_rank = communicator.rank
free_computing_nodes = range(1,communicator.size-1)
print self.tfbs_association_type
if node_rank == 0:
(conn, curs) = db_connect(self.hostname, self.dbname, self.schema)
if self.tfbs_association_type==1: #2006-11-02
gene_no2bs_no_block = self.get_gene_no2bs_no_block(curs)
elif self.tfbs_association_type==2:
gene_no2bs_no_block = get_gene_no2bs_no_block_from_expt_tf_mapping(curs)
for node in range(1, communicator.size-1): #send it to the computing_node
communicator.send(gene_no2bs_no_block, node, 0)
if self.fuzzyDense_flag: #2006-09-21 add fuzzyDense_flag
#12-18-05 get edge2encodedOccurrence
MpiCrackSplat_instance = MpiCrackSplat()
edge2encodedOccurrence = {}
min_sup = 5 #need to expose them
max_sup = 40
total_vertex_set = self.return_total_vertex_set(curs, self.good_cluster_table)
edge2encodedOccurrence, no_of_datasets = self.fill_edge2encodedOccurrence(\
self.sig_vector_fname, min_sup, max_sup, total_vertex_set)
edge2encodedOccurrence_pickle = cPickle.dumps(edge2encodedOccurrence, -1)
for node in free_computing_nodes: #send it to the computing_node
communicator.send(edge2encodedOccurrence_pickle, node, 0)
elif node_rank>0 and node_rank<communicator.size-1:
data, source, tag, count = communicator.receive(Numeric.Int, 0, 0)
gene_no2bs_no_set, bs_no2gene_no_set = self.construct_two_dicts(node_rank, data)
if self.fuzzyDense_flag: #2006-09-21
#12-18-05
data, source, tag = communicator.receiveString(0, 0)
edge2encodedOccurrence = cPickle.loads(data)
elif node_rank==communicator.size-1: #establish connection before pursuing
(conn, curs) = db_connect(self.hostname, self.dbname, self.schema)
#12-20-05 for darwin output
gene_id2symbol = get_gene_id2gene_symbol(curs, self.tax_id)
dataset_no2desc = get_dataset_no2desc(curs)
mpi_synchronize(communicator)
if node_rank == 0:
if self.good_cluster_table.find('pattern')!=-1: #2006-11-02 it's pattern_xxx table, use id as pattern_id
curs.execute("DECLARE crs CURSOR FOR select distinct id, vertex_set, recurrence_array\
from %s "%(self.good_cluster_table))
else: #2006-11-02 it's good_xxx table, use mcl_id as pattern_id
curs.execute("DECLARE crs CURSOR FOR select distinct mcl_id, vertex_set, recurrence_array\
from %s "%(self.good_cluster_table))
input_node(communicator, curs, free_computing_nodes, self.size, self.report)
curs.execute("close crs")
elif node_rank<=communicator.size-2: #exclude the last node
if self.fuzzyDense_flag: #2006-09-21
fuzzyDense_instance = fuzzyDense(edge2encodedOccurrence)
else:
fuzzyDense_instance = None
parameter_list = [gene_no2bs_no_set, bs_no2gene_no_set, self.ratio_cutoff, \
self.top_number, self.p_value_cut_off, fuzzyDense_instance, self.degree_cut_off, self.fuzzyDense_flag]
computing_node(communicator, parameter_list, self.computing_node_handler, report=self.report)
elif node_rank==communicator.size-1:
#12-20-05 comment out
if self.new_table:
self.create_cluster_bs_table(curs, self.cluster_bs_table)
parameter_list = [curs, self.cluster_bs_table]
output_node(communicator, free_computing_nodes, parameter_list, self.submit_cluster_bs_table, report=self.report)
if self.commit:
curs.execute("end")
"""
def run(self):
"""
10-31-05
2006-09-26
modify it to be compatible with the modified pipeline from haifeng
2006-11-06
add type
2006-12-13
use font_path and font_size
--form_schema_tables()
--db_connect()
--get_char_dimension()
--get_no_of_p_funcs_gene_no_go_no_list()
--get_recurrence_go_no_rec_array_cluster_id_ls()
--get_go_no2name()
--draw_function_map()
--draw_gene_function_map()
--get_recurrence_rec_array_bs_no_list()
--get_mt_no2tf_name()
--draw_tf_map()
"""
schema_instance = form_schema_tables(self.inputfname, self.acc_cutoff, self.lm_bit)
(conn, curs) = db_connect(self.hostname, self.dbname, self.schema)
font = ImageFont.truetype(self.font_path, self.font_size)
char_dimension = font.getsize('a')
#char_dimension = get_char_dimension()
#go_no2name = get_go_no2name(curs)
go_no2name = get_go_id2name(curs)
if self.type==1:
go_no2go_id = get_go_no2go_id(curs)
given_p_gene_set = p_gene_id_set_from_gene_p_table(curs, schema_instance.gene_p_table)
no_of_p_funcs_gene_no_go_no_list, mcl_id2go_no_set = self.get_no_of_p_funcs_gene_no_go_no_list_from_db(curs, \
schema_instance.p_gene_table, given_p_gene_set, go_no2go_id)
elif self.type==2:
no_of_p_funcs_gene_no_go_no_list, mcl_id2go_no_set = self.get_no_of_p_funcs_gene_no_go_no_list_from_file(self.inputfname)
recurrence_go_no_rec_array_cluster_id_ls, no_of_datasets, mcl_id2enc_recurrence = \
self.get_recurrence_go_no_rec_array_cluster_id_ls(curs, self.pattern_table, mcl_id2go_no_set)
no_of_functions = len(recurrence_go_no_rec_array_cluster_id_ls)
function_map_output_fname = '%s.function_map.png'%self.output_prefix
go_no2index, function_name_region = self.draw_function_map(recurrence_go_no_rec_array_cluster_id_ls, no_of_datasets,\
go_no2name, function_map_output_fname, self.function_name_length, char_dimension, no_of_functions, font)
gene_function_map_output_fname = '%s.gene_function_map.png'%self.output_prefix
self.draw_gene_function_map(no_of_p_funcs_gene_no_go_no_list, go_no2index, function_name_region,\
gene_function_map_output_fname, self.function_name_length, char_dimension, no_of_functions, font)
#tf_map requires mcl_id2enc_recurrence and no_of_datasets from above
recurrence_rec_array_bs_no_list = self.get_recurrence_rec_array_bs_no_list(curs, self.cluster_bs_table, mcl_id2enc_recurrence)
mt_no2tf_name = get_gene_id2gene_symbol(curs, tax_id=9606)
#mt_no2tf_name = get_mt_no2tf_name()
tf_map_output_fname = '%s.tf_map.png'%self.output_prefix
self.draw_tf_map(recurrence_rec_array_bs_no_list, no_of_datasets, mt_no2tf_name, \
tf_map_output_fname, self.function_name_length, char_dimension, font)
vertex_list = map(int, vertex_list)
recurrence_array = recurrence_array[1:-1].split(',')
recurrence_array = map(float, recurrence_array)
fuzzyDense_instance = fuzzyDense(edge2encodedOccurrence, debug)
core_vertex_ls, recurrent_and_on_datasets_ls = fuzzyDense_instance.get_core_vertex_set(vertex_list, recurrence_array, degree_cut_off)
from MpiClusterBsStat import MpiClusterBsStat
MpiClusterBsStat_instance = MpiClusterBsStat()
gene_no2bs_no_block = MpiClusterBsStat_instance.get_gene_no2bs_no_block(curs)
gene_no2bs_no_set, bs_no2gene_no_set = MpiClusterBsStat_instance.construct_two_dicts(0, gene_no2bs_no_block)
from TF_functions import cluster_bs_analysis
ls_to_return = cluster_bs_analysis(core_vertex_ls, gene_no2bs_no_set, bs_no2gene_no_set, ratio_cutoff, \
top_number, p_value_cut_off)
gene_id2symbol = get_gene_id2gene_symbol(curs, tax_id)
dataset_no2desc = get_dataset_no2desc(curs)
dataset_no_desc_ls = []
for dataset_index in recurrent_and_on_datasets_ls:
dataset_no = dataset_index +1
dataset_no_desc_ls.append([dataset_no, dataset_no2desc[dataset_no]])
outf = open(output_file, 'w')
outf.write("out:=[\n")
for i in range(len(ls_to_return)):
row = ls_to_return[i]
score, score_type, bs_no_list, target_gene_no_list, global_ratio, local_ratio, expected_ratio, unknown_ratio = row
core_vertex_symbol_ls = dict_map(gene_id2symbol, core_vertex_ls)
bs_no_symbol_list = dict_map(gene_id2symbol, bs_no_list)