def outputCliqueInLatexTable(curs, region, clique_id, table_label, fig_label, stock_db, clique2ecotype_table, outf):
"""
2007-10-18
2007-10-21
shorten some label names
ecotypeid -> id
stockparent -> stkparent
add one more column, collector
"""
from pymodule.latex import outputMatrixInLatexTable
data_matrix = []
curs.execute("select e.id, e.name, e.nativename, e.stockparent, e.latitude, e.longitude, c.abbr, s.name, p.firstname, p.surname from %s.ecotype e, %s.address a, %s.site s, %s.country c, %s.person p, %s ce where e.siteid=s.id and s.addressid=a.id and a.countryid=c.id and e.id=ce.ecotypeid and p.id=e.collectorid and ce.clique_id=%s order by nativename, stockparent"%(stock_db, stock_db, stock_db, stock_db, stock_db, clique2ecotype_table, clique_id))
rows = curs.fetchall()
ecotype_id_ls = []
for row in rows:
ecotype_id = row[0]
ecotype_id_ls.append(ecotype_id)
new_row = list(row[:-4])
new_row.append('%s %s'%(row[-2], row[-1])) #firstname surname
new_row.append(row[-4]) #country
new_row.append(row[-3]) #site
data_matrix.append(new_row)
caption = 'haplotype clique %s has %s ecotypes from %s. check Figure~\\ref{%s}.'%(clique_id, len(ecotype_id_ls), region, fig_label)
header_ls = ['id', 'name', 'nativename', 'stkparent', 'lat', 'lon', 'collector', 'country', 'site']
outf.write(outputMatrixInLatexTable(data_matrix, caption, table_label, header_ls))
return ecotype_id_ls
def outputCliqueInLatexTable(curs, region, clique_id, table_label, fig_label,
stock_db, clique2ecotype_table, outf):
"""
2007-10-18
2007-10-21
shorten some label names
ecotypeid -> id
stockparent -> stkparent
add one more column, collector
"""
from pymodule.latex import outputMatrixInLatexTable
data_matrix = []
curs.execute(
"select e.id, e.name, e.nativename, e.stockparent, e.latitude, e.longitude, c.abbr, s.name, p.firstname, p.surname from %s.ecotype e, %s.address a, %s.site s, %s.country c, %s.person p, %s ce where e.siteid=s.id and s.addressid=a.id and a.countryid=c.id and e.id=ce.ecotypeid and p.id=e.collectorid and ce.clique_id=%s order by nativename, stockparent"
% (stock_db, stock_db, stock_db, stock_db, stock_db,
clique2ecotype_table, clique_id))
rows = curs.fetchall()
ecotype_id_ls = []
for row in rows:
ecotype_id = row[0]
ecotype_id_ls.append(ecotype_id)
new_row = list(row[:-4])
new_row.append('%s %s' % (row[-2], row[-1])) #firstname surname
new_row.append(row[-4]) #country
new_row.append(row[-3]) #site
data_matrix.append(new_row)
caption = 'haplotype clique %s has %s ecotypes from %s. check Figure~\\ref{%s}.' % (
clique_id, len(ecotype_id_ls), region, fig_label)
header_ls = [
'id', 'name', 'nativename', 'stkparent', 'lat', 'lon', 'collector',
'country', 'site'
]
outf.write(
outputMatrixInLatexTable(data_matrix, caption, table_label, header_ls))
return ecotype_id_ls
def OutputCliquesGroupedByRegion(curs, region2clique_id_ls, clique_id2size, clique2ecotype_table, component2clique_table, output_fname, fig_output_dir, stock_db='stock20071008', min_clique_size=3, need_to_draw_figures=0):
"""
2007-10-18
"""
from variation.src.common import draw_graph_on_map, get_ecotypeid2pos
from variation.src.common import get_pic_area
from pymodule.latex import outputFigureInLatex
import sys,os
ecotypeid2pos = get_ecotypeid2pos(curs, '%s.ecotype'%stock_db)
outf = open(output_fname, 'w')
no_of_regions = 0
clique_id2region = {} #for the cc2clique latex table
for region, clique_id_ls in region2clique_id_ls.iteritems():
region = ' and '.join(region) #region is tuple, convert it to string
sys.stderr.write("%s:\n"%region)
outf.write("\\subsection{%s}\n"%region)
size_clique_id_ls = []
for clique_id in clique_id_ls:
if clique_id2size[clique_id]>=min_clique_size:
size_clique_id_ls.append([clique_id2size[clique_id], clique_id])
outf.write('region %s has %s cliques in total but %s cliques above min size %s.\n'%(region, len(clique_id_ls), len(size_clique_id_ls), min_clique_size))
if len(size_clique_id_ls)==0:
continue
size_clique_id_ls.sort()
caption = 'region %s has %s cliques in total but %s cliques above min size %s.'%(region, len(clique_id_ls), len(size_clique_id_ls), min_clique_size)
no_of_regions += 1
table_label = 't_region_%s'%no_of_regions
clique_id_size_ls = [[row[1],row[0]] for row in size_clique_id_ls]
header_ls = ['clique_id', 'size']
outf.write(outputMatrixInLatexTable(clique_id_size_ls, caption, table_label, header_ls))
for size, clique_id in size_clique_id_ls:
sys.stderr.write("clique %s, size %s\n"%(clique_id, size))
#output the table and get ecotype_id_ls
fig_label = 'fclique%s'%clique_id
table_label = 'tclique%s'%clique_id
ecotype_id_ls = outputCliqueInLatexTable(curs, region, clique_id, table_label, fig_label, stock_db, clique2ecotype_table, outf)
#draw the clique
site_g, site2weight, site2pos = construct_site_graph_out_of_ecotype_id_ls(ecotype_id_ls, ecotypeid2pos)
fig_fname = 'haplotype_%s_size%s_%ssites_map'%(clique_id,len(ecotype_id_ls), len(site2pos)) #just the name without filetype extension, like png, eps etc.
if need_to_draw_figures:
draw_graph_on_map(site_g, site2weight, site2pos, 'clique %s, size %s, %s sites of %s'%(clique_id, len(ecotype_id_ls), len(site2pos), region), pic_area=get_pic_area(site2pos.values(), 30), output_fname_prefix=os.path.join(fig_output_dir, fig_fname))
#output the figure in latex
fig_fname = os.path.join('figures/', '%s.png'%fig_fname) #relative path of the figure to the latex file
caption = 'map of haplotype clique %s has %s ecotypes from %s sites of %s. check Table~\\ref{%s}.'%(clique_id, len(ecotype_id_ls), len(site2pos), region, table_label)
outf.write(outputFigureInLatex(fig_fname, caption, fig_label))
clique_id2region[clique_id] = region
del site_g, site2pos, site2weight, ecotype_id_ls
outf.write("\\subsection{which component the clique is from}\n")
cc_id_clique_id_region_ls = []
cc_id2clique_id_ls = {}
for clique_id, region in clique_id2region.iteritems():
curs.execute("select cc_id from %s where clique_id=%s"%(component2clique_table, clique_id))
rows = curs.fetchall()
cc_id = rows[0][0]
cc_id_clique_id_region_ls.append([cc_id, clique_id, region])
if cc_id not in cc_id2clique_id_ls:
cc_id2clique_id_ls[cc_id] = []
cc_id2clique_id_ls[cc_id].append(clique_id)
cc_id_clique_id_region_ls.sort()
caption = '%s components versus %s cliques'%(len(cc_id2clique_id_ls), len(cc_id_clique_id_region_ls))
table_label = 't_cc2clique_1'
header_ls = ['component id', 'clique id', 'region']
outf.write(outputMatrixInLatexTable(cc_id_clique_id_region_ls, caption, table_label, header_ls))
del outf
def run(self):
from FilterStrainSNPMatrix import FilterStrainSNPMatrix
FilterStrainSNPMatrix_instance = FilterStrainSNPMatrix()
import MySQLdb
#conn = MySQLdb.connect(db="stock",host='natural.uchicago.edu', user='******', passwd='iamhereatusc')
conn = MySQLdb.connect(db=self.dbname,host=self.hostname)
curs = conn.cursor()
if self.debug:
import pdb
pdb.set_trace()
nt_number2diff_matrix_index = self.get_nt_number2diff_matrix_index(nt2number)
SNPpos2col_index, snpid2col_index, snp_acc_ls, snp_index2snp_info_ls = self.setup_SNP_dstruc(curs, self.snp_locus_table)
ecotype_id2accession_id, ecotype_id2row_index, ecotype_id2info_ls, ecotype_id_ls, accession_id2row_index, accession_id_ls, accession_id2ecotype_id_ls = self.setup_accession_ecotype_dstruc(curs, self.accession2ecotype_table, self.ecotype_table, self.calls_table)
ecotype_X_snp_matrix, ecotype_X_snp_matrix_touched = self.get_ecotype_X_snp_matrix(curs, ecotype_id2row_index, snpid2col_index, self.calls_table)
if self.sub_justin_output_fname:
header = ['ecotype_id', 'ecotype_id'] + snp_acc_ls
FilterStrainSNPMatrix_instance.write_data_matrix(ecotype_X_snp_matrix, self.sub_justin_output_fname, header, ecotype_id_ls, ecotype_id_ls)
alignment_id2positions_to_be_checked_ls, alignment_id2start = self.get_alignment_id2positions_to_be_checked_ls(curs, self.alignment_table)
accession_X_snp_matrix, accession_X_snp_matrix_touched, snp_index2alignment_id= self.get_accession_X_snp_matrix(curs, accession_id2row_index, SNPpos2col_index, self.sequence_table, self.alignment_table, alignment_id2positions_to_be_checked_ls)
if self.output_fname:
header = ['accession_id', 'accession_id'] + snp_acc_ls
FilterStrainSNPMatrix_instance.write_data_matrix(accession_X_snp_matrix, self.output_fname, header, accession_id_ls, accession_id_ls)
summary_diff_matrix_ls, diff_details_ls = self.cmp_two_matricies(accession_X_snp_matrix, accession_X_snp_matrix_touched, ecotype_X_snp_matrix, ecotype_X_snp_matrix_touched, nt_number2diff_matrix_index, ecotype_id2accession_id, ecotype_id2row_index, accession_id2row_index, diff_details_ls_type=2)
print "diff_matrix_touched_accession_vs_touched_ecotype"
print summary_diff_matrix_ls[0]
print "diff_matrix_touched_accession_vs_untouched_ecotype"
print summary_diff_matrix_ls[1]
print "diff_matrix_untouched_accession_vs_touched_ecotype"
print summary_diff_matrix_ls[2]
print "diff_matrix_untouched_accession_vs_untouched_ecotype"
print summary_diff_matrix_ls[3]
summary_diff_matrix_caption_ls = ['PCR-tried vs sequenom-tried', 'PCR-tried vs sequenom-untried', 'PCR-untried vs sequenom-tried', 'PCR-untried vs sequenom-untried']
if self.latex_output_fname:
outf = open(self.latex_output_fname, 'w')
outf.write('\\section{2010 PCR versus sequenom. summary} \\label{section_summary}\n')
for i in range(len(summary_diff_matrix_ls)):
from pymodule.latex import outputMatrixInLatexTable
wrapped_diff_matrix = self.wrap_diff_matrix_with_row_col_names(summary_diff_matrix_ls[i])
table_label = 'table_dm%s'%i
outf.write(outputMatrixInLatexTable(wrapped_diff_matrix, summary_diff_matrix_caption_ls[i], table_label))
table_no = i
#output the whole diff_details_ls
outf.write('\\section{Real Mismatches between pcr and sequenom (deletion/NA excluded)} \\label{section_real_mismatch}\n')
diff_details_ls = self.beautify_snp_diff_details_ls(diff_details_ls, ecotype_id2info_ls, snp_index2snp_info_ls, alignment_id2start, snp_index2alignment_id)
table_label = 'table_dm%s'%table_no
caption = 'mismatches between pcr and sequenom data (deletion/NA excluded, sorted by accession id)'
outf.write(outputMatrixInLatexTable(diff_details_ls, caption, table_label, header_ls=['nativename', 'stkparent', 'ecotype_id', 'duplicate', 'accession_id', 'SNP', 'chromosome', 'position', 'alignment_id', 'alignment_start', 'pcr_call', 'sequenom_call']))
#Strain-wise comparison
outf.write('\\section{2010 PCR versus sequenom for each strain} \\label{section_strain_wise}\n')
accession_id_ls.sort()
for accession_id in accession_id_ls:
ecotype_id_ls = accession_id2ecotype_id_ls[accession_id]
outf.write('\\subsection{strain %s(accession id=%s)}\n'%(ecotype_id2info_ls[ecotype_id_ls[0]][0], accession_id))
for ecotype_id in ecotype_id_ls:
outf.write('\\subsubsection{corresponding ecotype %s(stkparent=%s, ecotype id=%s, duplicate=%s)}\n'%(ecotype_id2info_ls[ecotype_id][0], ecotype_id2info_ls[ecotype_id][1], ecotype_id[0], ecotype_id[1]))
e_row_index = ecotype_id2row_index[ecotype_id]
a_row_index = accession_id2row_index[accession_id]
diff_matrix_ls, diff_details_ls= self.cmp_two_lists(accession_X_snp_matrix[a_row_index,:], accession_X_snp_matrix_touched[a_row_index,:], ecotype_X_snp_matrix[e_row_index,:], ecotype_X_snp_matrix_touched[e_row_index,:], nt_number2diff_matrix_index)
wrapped_diff_matrix = self.wrap_diff_matrix_with_row_col_names(diff_matrix_ls[0])
table_no += 1
table_label = 'table_dm%s'%table_no
caption = 'accession id=%s vs ecotype id=%s, duplicate=%s(nativename=%s, stockparent=%s)'%(accession_id, ecotype_id[0], ecotype_id[1], ecotype_id2info_ls[ecotype_id][0], ecotype_id2info_ls[ecotype_id][1])
outf.write(outputMatrixInLatexTable(wrapped_diff_matrix, caption, table_label))
if diff_details_ls:
diff_details_ls = self.beautify_diff_details_ls(diff_details_ls, snp_index2snp_info_ls, alignment_id2start, snp_index2alignment_id)
table_no += 1
table_label = 'table_dm%s'%table_no
caption = 'detailed difference for accession id=%s vs ecotype id=%s, duplicate=%s'%(accession_id, ecotype_id[0], ecotype_id[1])
outf.write(outputMatrixInLatexTable(diff_details_ls, caption, table_label, header_ls=['snp', 'chromosome', 'position', 'alignment_id', 'alignment_start', 'pcr_call', 'sequenom_call']))
#SNP-wise comparison
outf.write('\\section{2010 PCR versus sequenom for each SNP} \\label{section_snp_wise}\n')
for snp_column in range(accession_X_snp_matrix.shape[1]):
snp_acc, chromosome, position = snp_index2snp_info_ls[snp_column]
alignment_id = snp_index2alignment_id[snp_column]
alignment_start = alignment_id2start[alignment_id]
outf.write('\\subsection{SNP %s(chrom=%s, pos=%s, alignment id=%s, alignment start=%s)}\n'%(snp_acc, chromosome, position, alignment_id, alignment_start))
diff_matrix_ls, diff_details_ls = self.cmp_two_matricies(accession_X_snp_matrix, accession_X_snp_matrix_touched, ecotype_X_snp_matrix, ecotype_X_snp_matrix_touched, nt_number2diff_matrix_index, ecotype_id2accession_id, ecotype_id2row_index, accession_id2row_index, snp_column=snp_column, diff_details_ls_type=1)
wrapped_diff_matrix = self.wrap_diff_matrix_with_row_col_names(diff_matrix_ls[0])
table_no += 1
table_label = 'table_dm%s'%table_no
caption = 'SNP %s(chromosome=%s, position=%s, alignment id=%s, alignment start=%s)'%(snp_acc, chromosome, position, alignment_id, alignment_start)
outf.write(outputMatrixInLatexTable(wrapped_diff_matrix, caption, table_label))
if diff_details_ls:
diff_details_ls = self.beautify_snp_diff_details_ls(diff_details_ls, ecotype_id2info_ls)
table_no += 1
table_label = 'table_dm%s'%table_no
caption = 'detailed difference for SNP %s'%(snp_acc)
header_ls = ['nativename', 'stkparent', 'ecotype_id', 'duplicate', 'accession_id', 'pcr_call', 'sequenom_call']
outf.write(outputMatrixInLatexTable(diff_details_ls, caption, table_label, header_ls))
del outf
def OutputCliquesGroupedByRegion(curs,
region2clique_id_ls,
clique_id2size,
clique2ecotype_table,
component2clique_table,
output_fname,
fig_output_dir,
stock_db='stock20071008',
min_clique_size=3,
need_to_draw_figures=0):
"""
2007-10-18
"""
from variation.src.common import draw_graph_on_map, get_ecotypeid2pos
from variation.src.common import get_pic_area
from pymodule.latex import outputFigureInLatex
import sys, os
ecotypeid2pos = get_ecotypeid2pos(curs, '%s.ecotype' % stock_db)
outf = open(output_fname, 'w')
no_of_regions = 0
clique_id2region = {} #for the cc2clique latex table
for region, clique_id_ls in region2clique_id_ls.iteritems():
region = ' and '.join(region) #region is tuple, convert it to string
sys.stderr.write("%s:\n" % region)
outf.write("\\subsection{%s}\n" % region)
size_clique_id_ls = []
for clique_id in clique_id_ls:
if clique_id2size[clique_id] >= min_clique_size:
size_clique_id_ls.append(
[clique_id2size[clique_id], clique_id])
outf.write(
'region %s has %s cliques in total but %s cliques above min size %s.\n'
% (region, len(clique_id_ls), len(size_clique_id_ls),
min_clique_size))
if len(size_clique_id_ls) == 0:
continue
size_clique_id_ls.sort()
caption = 'region %s has %s cliques in total but %s cliques above min size %s.' % (
region, len(clique_id_ls), len(size_clique_id_ls), min_clique_size)
no_of_regions += 1
table_label = 't_region_%s' % no_of_regions
clique_id_size_ls = [[row[1], row[0]] for row in size_clique_id_ls]
header_ls = ['clique_id', 'size']
outf.write(
outputMatrixInLatexTable(clique_id_size_ls, caption, table_label,
header_ls))
for size, clique_id in size_clique_id_ls:
sys.stderr.write("clique %s, size %s\n" % (clique_id, size))
#output the table and get ecotype_id_ls
fig_label = 'fclique%s' % clique_id
table_label = 'tclique%s' % clique_id
ecotype_id_ls = outputCliqueInLatexTable(curs, region, clique_id,
table_label, fig_label,
stock_db,
clique2ecotype_table,
outf)
#draw the clique
site_g, site2weight, site2pos = construct_site_graph_out_of_ecotype_id_ls(
ecotype_id_ls, ecotypeid2pos)
fig_fname = 'haplotype_%s_size%s_%ssites_map' % (
clique_id, len(ecotype_id_ls), len(site2pos)
) #just the name without filetype extension, like png, eps etc.
if need_to_draw_figures:
draw_graph_on_map(
site_g,
site2weight,
site2pos,
'clique %s, size %s, %s sites of %s' %
(clique_id, len(ecotype_id_ls), len(site2pos), region),
pic_area=get_pic_area(site2pos.values(), 30),
output_fname_prefix=os.path.join(fig_output_dir,
fig_fname))
#output the figure in latex
fig_fname = os.path.join(
'figures/', '%s.png' %
fig_fname) #relative path of the figure to the latex file
caption = 'map of haplotype clique %s has %s ecotypes from %s sites of %s. check Table~\\ref{%s}.' % (
clique_id, len(ecotype_id_ls), len(site2pos), region,
table_label)
outf.write(outputFigureInLatex(fig_fname, caption, fig_label))
clique_id2region[clique_id] = region
del site_g, site2pos, site2weight, ecotype_id_ls
outf.write("\\subsection{which component the clique is from}\n")
cc_id_clique_id_region_ls = []
cc_id2clique_id_ls = {}
for clique_id, region in clique_id2region.iteritems():
curs.execute("select cc_id from %s where clique_id=%s" %
(component2clique_table, clique_id))
rows = curs.fetchall()
cc_id = rows[0][0]
cc_id_clique_id_region_ls.append([cc_id, clique_id, region])
if cc_id not in cc_id2clique_id_ls:
cc_id2clique_id_ls[cc_id] = []
cc_id2clique_id_ls[cc_id].append(clique_id)
cc_id_clique_id_region_ls.sort()
caption = '%s components versus %s cliques' % (
len(cc_id2clique_id_ls), len(cc_id_clique_id_region_ls))
table_label = 't_cc2clique_1'
header_ls = ['component id', 'clique id', 'region']
outf.write(
outputMatrixInLatexTable(cc_id_clique_id_region_ls, caption,
table_label, header_ls))
del outf
def run(self):
from FilterStrainSNPMatrix import FilterStrainSNPMatrix
FilterStrainSNPMatrix_instance = FilterStrainSNPMatrix()
import MySQLdb
#conn = MySQLdb.connect(db="stock",host='natural.uchicago.edu', user='******', passwd='iamhereatusc')
conn = MySQLdb.connect(db=self.dbname, host=self.hostname)
curs = conn.cursor()
if self.debug:
import pdb
pdb.set_trace()
nt_number2diff_matrix_index = self.get_nt_number2diff_matrix_index(
nt2number)
SNPpos2col_index, snpid2col_index, snp_acc_ls, snp_index2snp_info_ls = self.setup_SNP_dstruc(
curs, self.snp_locus_table)
ecotype_id2accession_id, ecotype_id2row_index, ecotype_id2info_ls, ecotype_id_ls, accession_id2row_index, accession_id_ls, accession_id2ecotype_id_ls = self.setup_accession_ecotype_dstruc(
curs, self.accession2ecotype_table, self.ecotype_table,
self.calls_table)
ecotype_X_snp_matrix, ecotype_X_snp_matrix_touched = self.get_ecotype_X_snp_matrix(
curs, ecotype_id2row_index, snpid2col_index, self.calls_table)
if self.sub_justin_output_fname:
header = ['ecotype_id', 'ecotype_id'] + snp_acc_ls
FilterStrainSNPMatrix_instance.write_data_matrix(
ecotype_X_snp_matrix, self.sub_justin_output_fname, header,
ecotype_id_ls, ecotype_id_ls)
alignment_id2positions_to_be_checked_ls, alignment_id2start = self.get_alignment_id2positions_to_be_checked_ls(
curs, self.alignment_table)
accession_X_snp_matrix, accession_X_snp_matrix_touched, snp_index2alignment_id = self.get_accession_X_snp_matrix(
curs, accession_id2row_index, SNPpos2col_index,
self.sequence_table, self.alignment_table,
alignment_id2positions_to_be_checked_ls)
if self.output_fname:
header = ['accession_id', 'accession_id'] + snp_acc_ls
FilterStrainSNPMatrix_instance.write_data_matrix(
accession_X_snp_matrix, self.output_fname, header,
accession_id_ls, accession_id_ls)
summary_diff_matrix_ls, diff_details_ls = self.cmp_two_matricies(
accession_X_snp_matrix,
accession_X_snp_matrix_touched,
ecotype_X_snp_matrix,
ecotype_X_snp_matrix_touched,
nt_number2diff_matrix_index,
ecotype_id2accession_id,
ecotype_id2row_index,
accession_id2row_index,
diff_details_ls_type=2)
print "diff_matrix_touched_accession_vs_touched_ecotype"
print summary_diff_matrix_ls[0]
print "diff_matrix_touched_accession_vs_untouched_ecotype"
print summary_diff_matrix_ls[1]
print "diff_matrix_untouched_accession_vs_touched_ecotype"
print summary_diff_matrix_ls[2]
print "diff_matrix_untouched_accession_vs_untouched_ecotype"
print summary_diff_matrix_ls[3]
summary_diff_matrix_caption_ls = [
'PCR-tried vs sequenom-tried', 'PCR-tried vs sequenom-untried',
'PCR-untried vs sequenom-tried', 'PCR-untried vs sequenom-untried'
]
if self.latex_output_fname:
outf = open(self.latex_output_fname, 'w')
outf.write(
'\\section{2010 PCR versus sequenom. summary} \\label{section_summary}\n'
)
for i in range(len(summary_diff_matrix_ls)):
from pymodule.latex import outputMatrixInLatexTable
wrapped_diff_matrix = self.wrap_diff_matrix_with_row_col_names(
summary_diff_matrix_ls[i])
table_label = 'table_dm%s' % i
outf.write(
outputMatrixInLatexTable(wrapped_diff_matrix,
summary_diff_matrix_caption_ls[i],
table_label))
table_no = i
#output the whole diff_details_ls
outf.write(
'\\section{Real Mismatches between pcr and sequenom (deletion/NA excluded)} \\label{section_real_mismatch}\n'
)
diff_details_ls = self.beautify_snp_diff_details_ls(
diff_details_ls, ecotype_id2info_ls, snp_index2snp_info_ls,
alignment_id2start, snp_index2alignment_id)
table_label = 'table_dm%s' % table_no
caption = 'mismatches between pcr and sequenom data (deletion/NA excluded, sorted by accession id)'
outf.write(
outputMatrixInLatexTable(diff_details_ls,
caption,
table_label,
header_ls=[
'nativename', 'stkparent',
'ecotype_id', 'duplicate',
'accession_id', 'SNP',
'chromosome', 'position',
'alignment_id', 'alignment_start',
'pcr_call', 'sequenom_call'
]))
#Strain-wise comparison
outf.write(
'\\section{2010 PCR versus sequenom for each strain} \\label{section_strain_wise}\n'
)
accession_id_ls.sort()
for accession_id in accession_id_ls:
ecotype_id_ls = accession_id2ecotype_id_ls[accession_id]
outf.write(
'\\subsection{strain %s(accession id=%s)}\n' %
(ecotype_id2info_ls[ecotype_id_ls[0]][0], accession_id))
for ecotype_id in ecotype_id_ls:
outf.write(
'\\subsubsection{corresponding ecotype %s(stkparent=%s, ecotype id=%s, duplicate=%s)}\n'
% (ecotype_id2info_ls[ecotype_id][0],
ecotype_id2info_ls[ecotype_id][1], ecotype_id[0],
ecotype_id[1]))
e_row_index = ecotype_id2row_index[ecotype_id]
a_row_index = accession_id2row_index[accession_id]
diff_matrix_ls, diff_details_ls = self.cmp_two_lists(
accession_X_snp_matrix[a_row_index, :],
accession_X_snp_matrix_touched[a_row_index, :],
ecotype_X_snp_matrix[e_row_index, :],
ecotype_X_snp_matrix_touched[e_row_index, :],
nt_number2diff_matrix_index)
wrapped_diff_matrix = self.wrap_diff_matrix_with_row_col_names(
diff_matrix_ls[0])
table_no += 1
table_label = 'table_dm%s' % table_no
caption = 'accession id=%s vs ecotype id=%s, duplicate=%s(nativename=%s, stockparent=%s)' % (
accession_id, ecotype_id[0], ecotype_id[1],
ecotype_id2info_ls[ecotype_id][0],
ecotype_id2info_ls[ecotype_id][1])
outf.write(
outputMatrixInLatexTable(wrapped_diff_matrix, caption,
table_label))
if diff_details_ls:
diff_details_ls = self.beautify_diff_details_ls(
diff_details_ls, snp_index2snp_info_ls,
alignment_id2start, snp_index2alignment_id)
table_no += 1
table_label = 'table_dm%s' % table_no
caption = 'detailed difference for accession id=%s vs ecotype id=%s, duplicate=%s' % (
accession_id, ecotype_id[0], ecotype_id[1])
outf.write(
outputMatrixInLatexTable(
diff_details_ls,
caption,
table_label,
header_ls=[
'snp', 'chromosome', 'position',
'alignment_id', 'alignment_start',
'pcr_call', 'sequenom_call'
]))
#SNP-wise comparison
outf.write(
'\\section{2010 PCR versus sequenom for each SNP} \\label{section_snp_wise}\n'
)
for snp_column in range(accession_X_snp_matrix.shape[1]):
snp_acc, chromosome, position = snp_index2snp_info_ls[
snp_column]
alignment_id = snp_index2alignment_id[snp_column]
alignment_start = alignment_id2start[alignment_id]
outf.write(
'\\subsection{SNP %s(chrom=%s, pos=%s, alignment id=%s, alignment start=%s)}\n'
% (snp_acc, chromosome, position, alignment_id,
alignment_start))
diff_matrix_ls, diff_details_ls = self.cmp_two_matricies(
accession_X_snp_matrix,
accession_X_snp_matrix_touched,
ecotype_X_snp_matrix,
ecotype_X_snp_matrix_touched,
nt_number2diff_matrix_index,
ecotype_id2accession_id,
ecotype_id2row_index,
accession_id2row_index,
snp_column=snp_column,
diff_details_ls_type=1)
wrapped_diff_matrix = self.wrap_diff_matrix_with_row_col_names(
diff_matrix_ls[0])
table_no += 1
table_label = 'table_dm%s' % table_no
caption = 'SNP %s(chromosome=%s, position=%s, alignment id=%s, alignment start=%s)' % (
snp_acc, chromosome, position, alignment_id,
alignment_start)
outf.write(
outputMatrixInLatexTable(wrapped_diff_matrix, caption,
table_label))
if diff_details_ls:
diff_details_ls = self.beautify_snp_diff_details_ls(
diff_details_ls, ecotype_id2info_ls)
table_no += 1
table_label = 'table_dm%s' % table_no
caption = 'detailed difference for SNP %s' % (snp_acc)
header_ls = [
'nativename', 'stkparent', 'ecotype_id', 'duplicate',
'accession_id', 'pcr_call', 'sequenom_call'
]
outf.write(
outputMatrixInLatexTable(diff_details_ls, caption,
table_label, header_ls))
del outf