def pretty(value):
if isinstance(value, dict):
page = markup.page()
page.ul(_class='dict')
for k, v in value.items():
if isinstance(v, list) and v:
pretty_value = Markup.escape(', '.join(v))
elif isinstance(v, dict) and v:
subul = markup.page()
subul.ul(_class='subdict')
for subk, subv in v.items():
subul.li()
subul.span('%s: ' % subk)
subul.span(Markup.escape(subv))
subul.li.close()
subul.ul.close()
pretty_value = subul()
elif v:
pretty_value = Markup.escape(v)
else:
continue
page.li()
page.span('%s:' % k.capitalize().replace('_', ' '))
page.span(pretty_value)
page.li.close()
page.ul.close()
return page()
elif isinstance(value, list):
return Markup.escape(', '.join(value))
else:
page = markup.page()
page.span(Markup.escape(value), _class='simple')
return page()
def __call__(self, form_field, **kwargs):
fields = [f for f in form_field if 'csrf_token' not in f.id ]
data_keys = [i[0] for i in self.data]
data_keys = self.update_keys(form_field, data_keys)
self.data = self.update_data(form_field, self.data)
page = markup.page()
page.label(self.label)
page.table(id=self.id, class_='matrix')
page.thead()
page.tr()
page.th(self.title, class_='category-left')
for i, f in enumerate(fields):
page.th(f.label.text.capitalize(), class_=i%2 and 'odd' or 'even',
id="%s-%d" % (self.id, i))
page.tr.close()
page.thead.close()
page.tbody()
page.tr()
page.td(e.div(data_keys), class_='category-left')
for i, field in enumerate(fields):
field.choices = [(k, v) for k, v in self.data]
odd_even = i % 2 and 'odd' or 'even'
page.td(field(**kwargs), class_=('check-column %s' % odd_even))
page.tr.close()
page.tbody.close()
page.table.close()
return page
def __call__(self, form_field, **kwargs):
fields = [f for f in form_field if 'csrf_token' not in f.id ]
data_keys = [i[0] for i in self.data]
data_keys = self.update_keys(form_field, data_keys)
self.data = self.update_data(form_field, self.data)
page = markup.page()
page.label(self.label)
page.table(id='ecosystem-service-types', class_='ecosystem-service-types ecosystem')
page.thead()
page.tr()
page.th('', class_='category-left')
for i, f in enumerate(fields):
page.th(f.label.text, class_=i%2 and 'odd' or 'even')
page.tr.close()
page.thead.close()
page.tbody()
page.tr(e.th('Type of ecosystems', colspan=form_field.COLSPAN, class_='category'))
page.tr()
page.td(e.div(data_keys), class_='category-left')
for i, field in enumerate(fields):
field.choices = [(k, v) for k, v in self.data]
odd_even = i%2 and 'odd' or 'even'
page.td(field(**kwargs), class_=('check-column %s' % odd_even))
page.tr.close()
page.tbody.close()
page.table.close()
return page
def __call__(self, form_field, **kwargs):
fields = [f for f in form_field if 'csrf_token' not in f.id]
data_keys = [i[0] for i in self.data]
data_keys = self.update_keys(form_field, data_keys)
self.data = self.update_data(form_field, self.data)
page = markup.page()
page.label(self.label)
page.table(id=self.id, class_='matrix')
page.thead()
page.tr()
page.th(self.title, class_='category-left')
for i, f in enumerate(fields):
page.th(f.label.text.capitalize(),
class_=i % 2 and 'odd' or 'even',
id="%s-%d" % (self.id, i))
page.tr.close()
page.thead.close()
page.tbody()
page.tr()
page.td(e.div(data_keys), class_='category-left')
for i, field in enumerate(fields):
field.choices = [(k, v) for k, v in self.data]
odd_even = i % 2 and 'odd' or 'even'
page.td(field(**kwargs), class_=('check-column %s' % odd_even))
page.tr.close()
page.tbody.close()
page.table.close()
return page
def __call__(self, field, **kwargs):
page = markup.page()
page.ul(id=field.id)
for subfield in field:
page.li()
value = field.data.get(subfield.data, '') if field.data else ''
page.input(name=subfield.name, id=subfield.id, value=value)
page.li.close()
page.ul.close()
return page()
def __call__(self, field, **kwargs):
page = markup.page()
page.ul(id=field.id)
for subfield in field:
page.li()
value = field.data.get(subfield.data, '') if field.data else ''
page.input(name=subfield.name, id=subfield.id, value=value)
page.li.close()
page.ul.close()
return page()
def __call__(self, field, **kwargs):
page = markup.page()
page.ul(id=field.id)
for subfield in field:
page.li()
value = field.data.get(subfield.data, '') if field.data else ''
page.textarea(value, name=subfield.name, id=subfield.id,
class_='cell visible')
#page.textarea.close()
page.li.close()
page.ul.close()
return page()
def __call__(self, field, **kwargs):
page = markup.page()
page.ul(id=field.id)
for subfield in field:
page.li()
value = field.data.get(subfield.data, '') if field.data else ''
page.textarea(value,
name=subfield.name,
id=subfield.id,
class_='cell visible')
#page.textarea.close()
page.li.close()
page.ul.close()
return page()
def __call__(self, field, **kwargs):
result = super(CustomFileInput, self).__call__(field, **kwargs)
values = field.data
if values and isinstance(values, list):
page = markup.page()
page.p('Currently uploaded files', class_="file-storage")
page.ul(_class='file-list')
for value in values:
page.li()
page.a(value,
href=url_for('static', filename='files/%s' % value),
target='_blank')
page.li.close()
page.ul.close()
result += page()
return wtf.widgets.core.HTMLString(result)
def __call__(self, field, **kwargs):
result = super(CustomFileInput, self).__call__(field, **kwargs)
values = field.data
if values and isinstance(values, list):
page = markup.page()
page.p('Currently uploaded files', class_="file-storage")
page.ul(_class='file-list')
for value in values:
page.li()
page.a(value,
href=url_for('static', filename='files/%s' % value),
target='_blank')
page.li.close()
page.ul.close()
result += page()
return wtf.widgets.core.HTMLString(result)
def main():
# do Loading
db = create_engine('sqlite:///data/' + DBFILE, echo=False)
Session = sessionmaker(bind=db)
session = Session()
prot_fams_objs = session.query(Prot_Fams).all()
UNP_rec_obj = session.query(Proteins).all()
histrec = session.query(History).all()
UNP_to_seqrecord = pickle.load(
open("data/" + DBFILEINIT.replace('.db', '_') + "UNP_seqrecords.dat",
"rb"))
print """#############################################
# Let's do the analysis #
#############################################
"""
gen_info = """********************General*******************
###There are %d unique seq strucutres
""" % (len(UNP_rec_obj))
p = re.compile('Full=(.+);', re.IGNORECASE)
print '#####Summary table'
summary_data = [[
'Histone Family', 'Protein name', 'Organisms', 'UniProt IDs'
]]
for k in prot_fams_objs:
UNP_rec_objs = session.query(Proteins).filter(
Proteins.family == k).order_by(Proteins.descr).all()
summary_data.append(['######### Family: %s' % k.name])
for i in UNP_rec_objs:
m = p.search(i.descr)
href = '<a href="http://www.uniprot.org/uniprot/%s">%s</a>' % (
i.unp_id, i.unp_id)
if (SHORT_NAMES):
prot_data = [k.name, m.group(1), i.organism, href]
else:
prot_data = [k.name, i.descr, i.organism, href]
summary_data.append(prot_data)
print gen_info, summary_data #,oligo_distr,organism_distr,prot_distr
htmlfile = open('data/' + DBFILE.replace('.db', '.html'), 'wt')
title = "Seqs from %s" % DBFILE
header = "Seqs from %s" % DBFILE
header += '''<script type="text/javascript" src="https://dl.dropboxusercontent.com/u/201202/js/tooltip.js"></script>
<script type="text/javascript" src="https://dl.dropboxusercontent.com/u/201202/js/ajax.js"></script>
<link rel="stylesheet" href="http://code.jquery.com/ui/1.10.3/themes/smoothness/jquery-ui.css" />
<script src="http://code.jquery.com/jquery-1.9.1.js"></script>
<script src="http://code.jquery.com/ui/1.10.3/jquery-ui.js"></script>
<link rel="stylesheet" href="/resources/demos/style.css" />
<script>
$(function() {
$( document ).tooltip();
});
</script>
<style>
label {
display: inline-block;
width: 5em;
}
</style>'''
footer = ""
styles = ('layout.css', 'alt.css', 'images.css')
page = markup.page()
page.init(css=styles, title=title, header=header, footer=footer)
page.p("<h1> %s </h1>" % histrec[-1].dbdescr)
page.p("<h1> Database analysis:</h1>")
page.br()
page.p('<h2>History of how the database was created </h2>')
for h in histrec:
page.p(
str(h.time.strftime("%Y-%m-%d %H:%M")) + ' | ' + h.dbname + ' | ' +
h.histrec)
page.br()
page.p('<h2>Now comes the analysis</h2>')
page.p(gen_info.replace('\n', '<br>'))
page.br()
page.p('<h2>Summary table </h2>')
htmlcode = HTML.table(summary_data)
page.add(htmlcode)
# page.p("********************Oligomeric state distribution*******************")
# page.p("###Olig state : Num PDBIDs : PDBIDs ")
# for key in sorted(NUMPDBs_with_NUMCHAINS.iterkeys()):
# page.p('### %s : %d' % (key, NUMPDBs_with_NUMCHAINS[key])) # , ' : ', PDBs_with_NUMCHAINS[key]
# for i in PDBs_with_NUMCHAINS[key]:
# if(OUTPUT_LINKS_TO_FILES): page.a( i, class_='internal', href='http://www.rcsb.org/pdb/download/downloadFile.do?fileFormat=pdb&compression=NO&structureId=%s' % i, title=mmdb_descr[i]['PdbDescr'], onmouseover="showtrail(1,1,'http://www.rcsb.org/pdb/images/%s_asym_r_500.jpg');" % i, onmouseout="hidetrail();" )
# else: page.a( i, class_='internal', href='http://www.rcsb.org/pdb/explore.do?structureId=%s' % i, title=mmdb_descr[i]['PdbDescr'], onmouseover="showtrail(1,1,'http://www.rcsb.org/pdb/images/%s_asym_r_500.jpg');" % i, onmouseout="hidetrail();" )
# page.br( )
# page.p(organism_distr.replace('\n','<br>').replace(' ',' '))
# page.br()
#
# prot_distr='*****************Protein distribution**************************\n'
# prot_distr+='### UniProtID | Num PDBs in database having it | Descr\n'
# page.p(prot_distr.replace('\n','<br>'))
# for key in sorted(UNPs, key=UNPs.get, reverse=True):
# number_pdbs_with_unp=len(session.query(PDB_UNP).filter(PDB_UNP.unp_id==key).all())
# pdb_ids_for_unp=""
# for i in session.query(PDB_UNP).filter(PDB_UNP.unp_id==key).all(): pdb_ids_for_unp+=i.pdb_id+' '
# page.add('### ')
# page.a('%8s' % key, href="http://www.uniprot.org/uniprot/%s" % key)
# page.add(' ')
# page.a(' %4d ' % number_pdbs_with_unp, href='#', title=pdb_ids_for_unp)
# page.add(' ')
# page.add(' %s' % UNP_to_record[key].description)
# page.br()
#
#
htmlfile.write(page.__call__())
htmlfile.close()
session.close()
def main():
# do Loading
db = create_engine('sqlite:///data/' + DBFILE, echo=False)
Session = sessionmaker(bind=db)
session = Session()
res = session.query(PDB_UNP).all()
histrec = session.query(History).all()
session.close()
UNP_to_record = pickle.load(
open("data/" + DBFILEINIT.replace('.db', '_') + "UNP_records.dat",
"rb"))
mmdb_descr = pickle.load(
open("data/" + DBFILEINIT.replace('.db', '_') + "MMDB_descr.dat",
"rb"))
UNPs = collections.Counter()
PDBs = collections.Counter()
TAXIDs = collections.Counter()
ORGNs = collections.Counter()
CHAINs_in_PDB = collections.Counter()
NUMPDBs_with_NUMCHAINS = collections.Counter()
PDBs_with_NUMCHAINS = collections.defaultdict(list)
print "Read %d lines in table" % len(res)
for rec in res:
UNPs[rec.unp_id] += 1
PDBs[rec.pdb_id] += 1
TAXIDs[UNP_to_record[rec.unp_id].taxonomy_id[0]] += 1
ORGNs[UNP_to_record[rec.unp_id].organism] += 1
CHAINs_in_PDB[rec.pdb_id] += rec.unp_num
for pdb_id in CHAINs_in_PDB:
NUMPDBs_with_NUMCHAINS[CHAINs_in_PDB[pdb_id]] += 1
PDBs_with_NUMCHAINS[CHAINs_in_PDB[pdb_id]].append(pdb_id)
# print rec.pdb_id, rec.unp_id, UNP_to_record[rec.unp_id].taxonomy_id[0]
# print vars(UNP_to_record[rec.unp_id])
print """#############################################
# Let's do the analysis #
#############################################
"""
gen_info = """********************General*******************
###There are %d unique pdb strucutres
###There are %d unique protein ids
###There are %d unique taxonomic organisms present
###Total protein chains in set %d""" % (
len(PDBs), len(UNPs), len(TAXIDs),
sum([
a * b for a, b in zip(NUMPDBs_with_NUMCHAINS.values(),
map(int, NUMPDBs_with_NUMCHAINS.keys()))
]))
oligo_distr = "********************Oligomeric state distribution*******************\n"
oligo_distr += "###Olig state : Num PDBIDs : PDBIDs \n"
for key in sorted(NUMPDBs_with_NUMCHAINS.iterkeys()):
oligo_distr += '### %s : %d ' % (key, NUMPDBs_with_NUMCHAINS[key])
for item in PDBs_with_NUMCHAINS[key]:
oligo_distr += ' %s ' % item
oligo_distr += '\n'
organism_distr = '*****************Organismic distribution**************************\n'
organism_distr += '### Num PDBs with at least one protein from organism | Organism name\n'
for key in sorted(ORGNs, key=ORGNs.get, reverse=True):
organism_distr += '### %8s %s\n' % (ORGNs[key], key)
prot_distr = '*****************Protein distribution**************************\n'
prot_distr += '### UniProtID | Num PDBs in database having it | Descr\n'
for key in sorted(UNPs, key=UNPs.get, reverse=True):
number_pdbs_with_unp = len(
session.query(PDB_UNP).filter(PDB_UNP.unp_id == key).all())
prot_distr += '### %8s %4d %s\n' % (key, number_pdbs_with_unp,
UNP_to_record[key].description)
print gen_info, oligo_distr, organism_distr, prot_distr
htmlfile = open('data/' + DBFILE.replace('.db', '.html'), 'wt')
title = "PDBids from %s" % DBFILE
header = "PDBids from %s" % DBFILE
header += '''<script type="text/javascript" src="https://dl.dropboxusercontent.com/u/201202/js/tooltip.js"></script>
<script type="text/javascript" src="https://dl.dropboxusercontent.com/u/201202/js/ajax.js"></script>
<link rel="stylesheet" href="http://code.jquery.com/ui/1.10.3/themes/smoothness/jquery-ui.css" />
<script src="http://code.jquery.com/jquery-1.9.1.js"></script>
<script src="http://code.jquery.com/ui/1.10.3/jquery-ui.js"></script>
<link rel="stylesheet" href="/resources/demos/style.css" />
<script>
$(function() {
$( document ).tooltip();
});
</script>
<style>
label {
display: inline-block;
width: 5em;
}
</style>'''
footer = ""
styles = ('layout.css', 'alt.css', 'images.css')
page = markup.page()
page.init(css=styles, title=title, header=header, footer=footer)
page.p("<h1> %s </h1>" % histrec[-1].dbdescr)
page.p("<h1> Database analysis:</h1>")
page.br()
page.p('<h2>History of how the database was created </h2>')
for h in histrec:
page.p(
str(h.time.strftime("%Y-%m-%d %H:%M")) + ' | ' + h.dbname + ' | ' +
h.histrec)
page.br()
page.p('<h2>Now comes the analysis</h2>')
page.p(gen_info.replace('\n', '<br>'))
page.br()
page.p(
"********************Oligomeric state distribution*******************")
page.p("###Olig state : Num PDBIDs : PDBIDs ")
for key in sorted(NUMPDBs_with_NUMCHAINS.iterkeys()):
page.p(
'### %s : %d' %
(key,
NUMPDBs_with_NUMCHAINS[key])) # , ' : ', PDBs_with_NUMCHAINS[key]
for i in PDBs_with_NUMCHAINS[key]:
if (OUTPUT_LINKS_TO_FILES):
page.a(
i,
class_='internal',
href=
'http://www.rcsb.org/pdb/download/downloadFile.do?fileFormat=pdb&compression=NO&structureId=%s'
% i,
title=mmdb_descr[i]['PdbDescr'],
onmouseover=
"showtrail(1,1,'http://www.rcsb.org/pdb/images/%s_asym_r_500.jpg');"
% i,
onmouseout="hidetrail();")
else:
page.a(
i,
class_='internal',
href='http://www.rcsb.org/pdb/explore.do?structureId=%s' %
i,
title=mmdb_descr[i]['PdbDescr'],
onmouseover=
"showtrail(1,1,'http://www.rcsb.org/pdb/images/%s_asym_r_500.jpg');"
% i,
onmouseout="hidetrail();")
page.br()
page.p(organism_distr.replace('\n', '<br>').replace(' ', ' '))
page.br()
prot_distr = '*****************Protein distribution**************************\n'
prot_distr += '### UniProtID | Num PDBs in database having it | Descr\n'
page.p(prot_distr.replace('\n', '<br>'))
for key in sorted(UNPs, key=UNPs.get, reverse=True):
number_pdbs_with_unp = len(
session.query(PDB_UNP).filter(PDB_UNP.unp_id == key).all())
pdb_ids_for_unp = ""
for i in session.query(PDB_UNP).filter(PDB_UNP.unp_id == key).all():
pdb_ids_for_unp += i.pdb_id + ' '
page.add('### ')
page.a('%8s' % key, href="http://www.uniprot.org/uniprot/%s" % key)
page.add(' ')
page.a(' %4d ' % number_pdbs_with_unp,
href='#',
title=pdb_ids_for_unp)
page.add(' ')
page.add(' %s' % UNP_to_record[key].description)
page.br()
htmlfile.write(page.__call__())
htmlfile.close()
