def gdraw0(graphs, plotname = 'default_name', measure = 'cosine'):
pos = nx.graphviz_layout(graphs['kg'])
adjs = [ array(nx.adj_matrix(g)) for g in graphs.values() ]
nrms = []
for a in adjs:
n = sqrt(sum(a**2))
nrms.append(a / n)
kgelt = graphs.keys().index('kg')
if measure == 'cosine':
sims = array([round(nfu.cosine_adj(a1,nrms[kgelt]),8) for a1 in nrms])
else:
raise Exception()
kg = graphs['kg']
srto = argsort(graphs.keys())
#XVALs give ranks of each key index.
xvals = argsort(srto)
cols = map(lambda x:
('flt' in x and x.count('thr') > 1) and 'orange' or
('flt' in x) and 'red' or
('thr' in x) and 'yellow' or
('fg' in x) and 'green' or
('su' in x) and 'blue' or
'black', graphs.keys())
yvals = sims
f = plt.gcf()
f = myplots.fignum(3, (.25 * len(sims),10))
f.clear()
ax = f.add_subplot(111)
myplots.padded_limits(ax,xvals,yvals + [0.], margin = [.02,.02])
ax.scatter(xvals,yvals,100, color = cols)
ax.set_ylabel('red fly similarity ({0})'.format(measure))
ax.set_xlabel('networks')
ax.set_xticklabels([])
ax.set_xticks([])
mark_ys = [0, median(sims), mean(sims), sort(sims)[::-1][1],1]
ax.hlines(mark_ys, *ax.get_xlim(), linestyle = ':',alpha = .2)
f.savefig(cfg.dataPath('figs/meAWG/filter_{0}_meth_{1}_nolabels.pdf'.\
format(plotname,measure)))
ax.set_xticks(range(len(srto)))
ax.annotate('\n'.join(' '.join(z) for z in zip(graphs.keys(),cols)),
[0,1],xycoords = 'axes fraction', va = 'top')
ax.set_xticklabels([graphs.keys()[i] for i in srto],
rotation = 45, size = 'xx-small',ha = 'right')
f.savefig(cfg.dataPath('figs/meAWG/filter_{0}_meth_{1}_labels.pdf'.\
format(plotname,measure)))
def setFetchAliNames(**kwargs):
fa_file = cfg.dataPath('pvt1/pvt1.fa')
ali = aio.parse(open(fa_file), 'fasta')
a0 = ali.next()
return [a.id for a in a0]
def run_batch(geometry):
muts = [.0005, .001, .002, .003, .004]
delta_multiplier = .125
geometries = [geometry]
dims = [20, 40, 80]
iters = 400
import compbio.config as cfg
root = cfg.dataPath('avida_runs')
if not os.path.isdir(root):
os.mkdir(root)
os.chdir(root)
exec_subdirs = [
'big_{0}_{1}_{2}_{3}'.format(i, j, k, l) for l in range(iters)
for k in dims for j in muts[::-1] for i in geometries
]
for e in exec_subdirs:
if not os.path.isdir(os.path.join(root, e)):
os.mkdir(os.path.join(root, e))
os.chdir(os.path.join(root, e))
p = get_params(psets['lots'])
make_cfg(p,
geo=e.split('_')[1],
mut=float(e.split('_')[2]),
delta=delta_multiplier * float(e.split('_')[2]),
dim=int(e.split('_')[3]))
d = os.path.join(root, e)
os.chdir(d)
prc = subprocess.Popen(
'bsub -o bsub_log -q compbio-week "avida -v0 -c proj0/autogen/avida.cfg.auto"',
shell=True,
stdout=subprocess.PIPE)
print prc.stdout.read()
def cr_locii(chrname = 'CHR_I', **kwargs):
ng =20;
root = cfg.dataPath('/data/genomes/Caenorhabditis_elegans')
fdir = os.path.join(root,chrname)
for r, d, files in os.walk(fdir):
for f in files:
if '.gb' in f:
fopen = open(os.path.join(r,f))
break
gb = list(sio.parse(fopen, 'genbank'))[0]
chrinfos= parse_genes();
for i in range(ng):
g = chrinfos[chrname][i]
gid = g.qualifiers['db_xref'][1][9:]
print gid
neighbor_range =[max(0, g.location.start.position-5000),
min(len(gb.seq)-1, g.location.end.position+5000)]
feats_matching =[f for f in gb.features
if f.location.start.position > neighbor_range[0]
and f.location.end.position < neighbor_range[1]]
seq = gb.seq[neighbor_range[0]:neighbor_range[1]]
import Bio.SeqRecord as sr
import Bio.Seq as sq
rec = sr.SeqRecord(sq.Seq(seq.tostring(),seq.alphabet),
name = '{0}_g{1}'.format(chrname,i),
description='genomic neighborhood of {0}'\
.format(gid),
annotations = {'organism':'worm'})
import Bio.SeqFeature as sf
import copy
for f in feats_matching:
fnew = copy.deepcopy(f)
fnew.location.start.position -= neighbor_range[0]
fnew.location.end.position -= neighbor_range[0]
rec.features.append(fnew)
root = cfg.dataPath('modencode/worm_gene_extracts/{0}'.format(chrname))
if not os.path.isdir(root): os.mkdir(root)
fname = os.path.join(root,'{0}.gbk'.format(gid))
fopen = open(fname, 'w')
sio.write(rec, fopen, 'genbank')
fopen.close()
def set_map_rows(**kwargs):
mapfile = cfg.dataPath("wormbase/loci_all.txt")
fopen = open(mapfile)
lines = fopen.readlines()
cols = [e.strip() for e in lines[0].strip().split(",")]
rows = [dict(zip(cols, [e.strip() for e in l.strip().split(",")])) for l in lines[1:-1]]
return rows
def set_rows(**kwargs):
root = cfg.dataPath('wormbrain/2006')
connect_file = os.path.join(root, 'NeuronConnect.xls')
fp_file = os.path.join(root,'NeuronFixedPoints.xls')
cwb = xlrd.open_workbook(connect_file)
sh = cwb.sheets()[0]
rows = [[e.value for e in sh.row(i)] for i in range(1,sh.nrows) ]
return rows
def figpath(filename = 'plot.pdf', delete = False):
called_name = inspect.stack()[1][3]
stack = inspect.stack()[1]
call_path = os.path.abspath(stack[1])
path = cfg.relPath(call_path)
figpath = cfg.dataPath(os.path.join('figs',path,called_name,filename))
if delete:
if os.path.isfile(figpath):
os.remove(figpath)
return figpath
def setFetchNumAli(**kwargs):
fa_file = cfg.dataPath('pvt1/pvt1.fa')
ali = aio.parse(open(fa_file), 'fasta')
a_ali = ali.next()
a0 = [[nt_dict[elt] for elt in a.seq.upper()] for a in a_ali]
a0_num = array(a0, byte)
return a0_num
def load_pdbfiles(nbs = False):
bfiles = dict([(rvd, cfg.dataPath('structs/3ugm/3UGM_{0}_{1}_NOFIX.pdb'\
.format(rvd,'NBS' if nbs else 'NONBS')))
for rvd in ['NN', 'NH', 'NK']])
structs = {}
for rvd, fname in bfiles.iteritems():
fopen = open(fname)
pparse = PDB.PDBParser(PERMISSIVE = 0)
struct = pparse.get_structure('tmp', fopen)
fopen.close()
structs[rvd] = struct
return structs
def fetch_cluster_results(keys):
cells = []
for k in keys:
try:
res = sio.loadmat(cfg.dataPath('soheil/ben_results/cluster_results/results/'+\
'expression_c4d_n4_t{0}.mat'.format(k)))
cells.append((k, [ dict(gene = int(squeeze(r[0][0])),
sign = r[1][0],
module = tuple(sorted(r[2][0])),
score = r[4][0])
for r in res['network_cell']]))
except Exception, e:
cells.append((k,[]))
def load_bonds(nbs = False):
bfiles = dict([(rvd,cfg.dataPath('structs/bonds/3UGM/3UGM_{0}_{1}_NOFIX.bonds'\
.format(rvd, 'NBS' if nbs else 'NONBS')))
for rvd in ['NN', 'NH', 'NK']])
all_bonds = {}
for k,bf in bfiles.iteritems():
fopen = open(bf)
data = fopen.readlines()
bonds = []
for line in data:
split = line.index('))') + 2
bonds.append(dict(zip( ['atoms','dist'],
[json.loads(line[0:split].replace('(','[').replace(')',']').replace("'", '"')),json.loads(line[split:])]
)))
all_bonds[k.upper()] = bonds
return all_bonds
def set_genes(**kwargs):
lens =[]
all_genes = {}
names = chromosome_names()
for name in names:
root = cfg.dataPath('/data/genomes/Caenorhabditis_elegans')
fdir = os.path.join(root,name)
for r, d, files in os.walk(fdir):
for f in files:
if '.gb' in f:
fopen = open(os.path.join(r,f))
break
gb = list(sio.parse(fopen, 'genbank'))[0]
genes = [f for f in gb.features if f.type== 'gene']
all_genes[name] = genes
fopen.close()
return all_genes
def mod_list():
path = cfg.dataPath("soheil/results_new/to ben-july 21/modules/denovo.mat")
mods_d = sio.loadmat(path)['denovo']
gene_mods = {}
tf_mods = {}
for m in mods_d:
m = [tuple(list(elt[0])) for elt in m]
gm = gene_mods.get(m[1], [])
tm = tf_mods.get(m[0], [])
gm.append(m[0])
tm.append(m[1])
gene_mods[m[1]] = gm
tf_mods[m[0]] = tm
return(tf_mods, gene_mods)
def set_tiling_peaks(**kwargs):
root = cfg.dataPath('modencode/wormtile/computed-peaks_gff3')
files = [os.path.join(root, f) for f in os.listdir(root)]
out = {}
for f in files:
if f[-2:] != 'gz': continue
fopen= gzip.open(f)
data = [l for l in fopen.readlines() if not l[0] == '#']
out[os.path.basename(f)] = \
[dict(zip(['chr', 'meth', 'type',
'start','end','score',
'blank','blank2','annotations' ],
l.strip().split('\t')))
for l in data]
for k,v in out.iteritems():
for d in v:
d['start'] = int(d['start'])
d['end'] = int(d['end'])
d['score'] = float(d['score'])
return out
def set_chromosome_offsets(**kwargs):
lens =[]
names = chromosome_names()
for name in names:
root = cfg.dataPath('/data/genomes/Caenorhabditis_elegans')
fdir = os.path.join(root,name)
for r, d, files in os.walk(fdir):
for f in files:
if '.gb' in f:
fopen = open(os.path.join(r,f))
break
gb = list(sio.parse(fopen, 'genbank'))[0]
fopen.close()
lens.append( gb.features[0].location.end.position)
offsets = {}
cur_ofs = 0
for i, l in enumerate(lens):
offsets[names[i]] = cur_ofs
cur_ofs += l
return offsets
def setTf_Chip_Peaks(**kwargs):
root = cfg.dataPath('wormchip')
files = [os.path.join(root, f) for f in os.listdir(root)]
out = {}
for f in files:
fopen= open(f)
data = [l for l in fopen.readlines() if not l[0] == '#']
out[os.path.basename(f)] = \
[dict(zip(['chr', 'meth', 'type',
'start','end','score',
'blank','blank2','qValue' ],
l.strip().split('\t')))
for l in data]
vlens = [len(e) for e in out[os.path.basename(f)]]
for k,v in out.iteritems():
for d in v:
d['start'] = int(d['start'])
d['end'] = int(d['end'])
d['score'] = float(d['score'])
d['qValue'] = float(d['qValue'].split('=')[1])
return out
def run_batch(geometry):
muts = [.0005,.001,.002,.003,.004]
delta_multiplier = .125
geometries = [geometry]
dims = [20,40,80]
iters = 400
import compbio.config as cfg
root = cfg.dataPath('avida_runs')
if not os.path.isdir(root):
os.mkdir(root)
os.chdir( root)
exec_subdirs = ['big_{0}_{1}_{2}_{3}'.format(i,j,k,l)
for l in range(iters)
for k in dims
for j in muts[::-1]
for i in geometries
]
for e in exec_subdirs:
if not os.path.isdir(os.path.join(root,e)):
os.mkdir(os.path.join(root,e))
os.chdir(os.path.join(root,e))
p = get_params(psets['lots'])
make_cfg(p,
geo = e.split('_')[1],
mut = float(e.split('_')[2]),
delta = delta_multiplier * float(e.split('_')[2]),
dim = int(e.split('_')[3])
)
d = os.path.join(root,e)
os.chdir(d)
prc = subprocess.Popen('bsub -o bsub_log -q compbio-week "avida -v0 -c proj0/autogen/avida.cfg.auto"',
shell = True,
stdout = subprocess.PIPE)
print prc.stdout.read()
import Bio.SeqIO as SeqIO
import Bio.Seq as seq
import Bio.Alphabet as Alphabet
import Bio.Align as al
import Bio.AlignIO as aio
import Bio.SeqRecord as sr
from numpy import *
import os, re
import cb.config as cfg
temp_dir = cfg.dataPath('alg')
if not os.path.isdir(temp_dir):
os.mkdir(temp_dir)
import subprocess as spc
def writelines(lines,gid):
ali = al.MultipleSeqAlignment([sr.SeqRecord(seq.Seq(''.join(line)),
'{1}{0}i'.format(i,gid),
description = '{1}{0}d'.format(i,gid)
)
for i, line in enumerate(lines[::50])])
return ali
def write_fa(lines, gid):
fpath = os.path.join(temp_dir, '{0}_seqlines.fa'.format(gid))
fopen = open(fpath,'w')
alignment = writelines(lines,gid)
SeqIO.write(alignment,fopen,'fasta')
fopen.close()
return fpath
import cb.projects.network.io as nio
import numpy as np
from numpy import *
import cb.utils.plots as myplots
import cb.config as cfg
import cb.utils.colors as mycolors
import cb.utils.graphs.utils as gutils
import networkx as nx
import matplotlib.pyplot as plt
from scipy.stats import linregress
ecount = 200000
run_name = 'bn_edges'
figtemplate = cfg.dataPath('figs/filtering/comparator-{0}-{{0}}.pdf'.\
format(run_name))
net_types = 'all'
pctype = 'bn'
def get_graphs(selector = 'just_nets',
net_choice = net_types,
pctype = pctype,
fixed_ecount = ecount,
restriction = 'none'):
'''Get a list of graphs.
net_choices:
'all': fetch all available nets and build graphs according to
def make_cfg(plot_params,
name =default_name,
geo = 'square',
mut = .002,
delta = .0005,
dim = 20):
if not os.path.isdir(name):
os.mkdir(name)
import shutil
flist = os.listdir(name)
cfg_start = cfg.dataPath('avida_default_cfgfiles')
for r,d,files in os.walk(cfg_start):
for f in files:
if f in flist:
continue
shutil.copyfile(os.path.join(r,f),
os.path.join(name, f))
#default_file = open(os.path.join(name,'avida.cfg'))
outfile = open(os.path.join(name,'avida.cfg.auto'),'w')
outfile.write('#avida.cfg generated by python.')
#lines = default_file.readlines()
auto_dir = os.path.join(name,os.path.join('autogen'))
if not os.path.isdir(auto_dir):
os.mkdir(auto_dir)
eve_fname = ca.make_eve(name,default_evename)
org_fname = ca.make_org(name,default_orgname)
ana_fname = ca.make_ana(name,default_ananame)
env_fname = ca.make_env(name,default_envname)
ins_fname = ca.make_ins(name,default_insname)
computed = presets.differential_mut(name,
mut = mut,
geo_name = geo,
delta = delta,
dim = dim,
eve_fname = eve_fname,
org_fname = org_fname,
ana_fname = ana_fname,
env_fname = env_fname,
ins_fname = ins_fname,
gen_name = default_genname)
for pp in plot_params:
pp['computed'] = computed
print
print 'setting print params: '
print
for p in plot_params:
if p['type'] == 'ts':
colstr = ''
for col in p.get('command_params',[]):
colstr += col + ' '
printstr = p['update']+' '+p['command'] +' '+p['fname'] + ' '+colstr
ca.alter_eve(eve_fname, printstr)
elif p['type'] == 'grid':
printstr = p['update'] + ' ' + p['command'] + ' ' + p['fname']
ca.alter_eve(eve_fname, printstr)
f = open(eve_fname).read()
print f
#!/usr/bin/env python
import cb.config as cfg
import os
import cb.utils.bsub_utils as bsu
import cb.utils.bsub as bsub
import subprocess
import pipes
sdp = cfg.dataPath('soheil')
matfiles = [os.path.join(sdp,f) for f in os.listdir(sdp) if '.mat' in f]
for control in [0,2,3]:
for f in matfiles:
args = \
f, \
os.path.join(*( os.path.split(f)[:-1]+('mat_out_{0}'.format(control),)+os.path.split(f)[-1:])),\
os.path.join(*( os.path.split(f)[:-1]+('mat_all_out_{0}'.format(control),)+os.path.split(f)[-1:]))
for a in args:
if not os.path.isdir(os.path.dirname(a)):
os.makedirs(os.path.dirname(a))
print 'made directory: {0}'.format(os.path.dirname(a))
script = 'test_mine'
mat_cmd ='''\\"{3}('{0}', '{1}', '{2}', '{4}' ); exit\\"'''.format(\
*(args + (script,)+(control,)))
#print mat_cmd
cstr = '''echo {0} | matlab -nojvm -nodisplay -nosplash '''.\
def run(num = 2):
dfile = sio.loadmat(cfg.dataPath('soheil/expression_c4d_n4_intercluster.mat'))
trgs, tfs = nio.getNet()
bdgenes = nio.getBDTNP()
bdset = set(bdgenes.keys())
xs, ys, colors, corrs,lcorrs = [[] for i in range(5)]
count = 0
for k, v in bdgenes.iteritems():
count += 1
if count < num:
continue
if not trgs.has_key(k): continue
trg = trgs[k]
fsub = set(tfs.keys()).intersection(bdset)
gexpr = bdgenes[k]['vals'][::50,4].flatten() #squeeze(dfile[k])
fexpr = [bdgenes[fname]['vals'][::50,4].flatten() for fname in fsub]#[squeeze(dfile[fname]) for fname in fsub]
print shape(fexpr)
if len(fexpr )< 3: continue
ct = mycolors.getct(len(fexpr))
for idx, f in enumerate(fexpr):
c = corrcoef(f, gexpr)[0,1]
if not isfinite(c): c = 0
lc = corrcoef(log(f), log(gexpr))[0,1]
if not isfinite(lc): lc = 0
corrs.append(c)
lcorrs.append(lc)
ys.append(gexpr)
xs.append(f)
colors.append([ct[idx]]* len(f))
break
if len(xs) > 10000:
break
cbest = argsort(-1 * abs(array(corrs)))
f = plt.figure(1)
f.clear()
ax = f.add_subplot(111)
inds = argsort(gexpr)
for idx in cbest[:3]:
import scipy.signal as ss
import cb.utils.sigsmooth as sgs
#k = sgs.gauss_kern(15)[8,:].flatten()
#xconv = ss.convolve(xs[idx][inds],k)
xv = ss.medfilt(xs[idx][inds],1)
yv = ys[idx][inds]
print corrcoef(xv,yv)[0,1]
print corrs[idx]
ax.plot(ss.medfilt(xs[idx][inds],1), linewidth = 10, color = colors[idx][0])
ax.plot(ys[idx][inds], linewidth = 10)
def gdraw(bgraph,cgraphs, plotname = 'default_name', measure = 'cosine'):
#pos = nx.graphviz_layout(cgraphs['kg'])
nodelist = bgraph.nodes()
adjs = [ array(nx.adj_matrix(g, nodelist = nodelist)) for g in cgraphs.values() ]
badj = array(nx.adj_matrix(bgraph, nodelist = nodelist))
bnrm = badj / sqrt(sum(badj**2))
if measure == 'cosine':
nrms = []
bnrm = badj / sqrt(sum(badj**2))
for a in adjs:
n = sqrt(sum(a**2))
nrms.append(a / n)
sims = array([round(nfu.cosine_adj(a1,bnrm),8) for a1 in nrms])
elif measure =='jaccard':
sims = array([round(nfu.dotprod(a1,badj),8)/ (sum(a1) + sum(badj))
for a1 in adjs])
elif measure =='specificity':
sims = array([round(nfu.dotprod(a1,badj),8)/sum(a1) for a1 in adjs])
elif measure =='sensitivity':
sims = array([round(nfu.dotprod(a1,badj),8)/sum(badj) for a1 in adjs])
else:
raise Exception()
srto = argsort(cgraphs.keys())
#XVALs give ranks of each key index.
xvals = argsort(srto)
cols = map(lambda x:
('flt' in x and x.count('thr') > 1) and 'orange' or
('flt' in x) and 'red' or
('thr' in x) and 'yellow' or
('fg' in x) and 'green' or
('su' in x) and 'blue' or
'black', cgraphs.keys())
yvals = sims
f = plt.gcf()
f = myplots.fignum(3, (.25 * len(sims),10))
f.clear()
ax = f.add_subplot(111)
myplots.padded_limits(ax,xvals,yvals + [0.], margin = [.02,.02])
ax.scatter(xvals,yvals,100, color = cols)
ax.set_ylabel('red fly similarity ({0})'.format(measure))
ax.set_xlabel('networks')
ax.set_xticklabels([])
ax.set_xticks([])
mark_ys = [0, median(sims), mean(sims), sort(sims)[::-1][1],1]
ax.hlines(mark_ys, *ax.get_xlim(), linestyle = ':',alpha = .2)
f.savefig(cfg.dataPath('figs/meAWG/filter_{0}_meth_{1}_nolabels.pdf'.\
format(plotname,measure)))
ax.set_xticks(range(len(srto)))
cols_added = []
annotes = []
for z in zip(cgraphs.keys(),cols):
if not z[1] in cols_added:
annotes.append( ' '.join(z))
cols_added.append(z[1])
ax.annotate('\n'.join(annotes),
[1,1],xycoords = 'axes fraction', va = 'top', ha = 'right')
ax.set_xticklabels([cgraphs.keys()[i] for i in srto],
rotation = 90, va = 'bottom', size = 'xx-small')
f.savefig(cfg.dataPath('figs/meAWG/filter_{0}_meth_{1}_labels.pdf'.\
format(plotname,measure)))
import cb.p.network.io as nio
import plots as nfplots
import utils as nfu
import cb.utils.colors as mycolors
import cb.utils.plots as myplots
import matplotlib.pyplot as plt
import networkx as nx
import cb.config as cfg
import itertools as it
from numpy import *
import numpy as np
figtemplate = cfg.dataPath('figs/filter/run_{0}.pdf')
def run( reset = False,
base_net = 'kn',
comp_net = 'fn',
demand_bdtnp = False):
tgs,tfs = nio.getNet()
ktgs,ktfs = nio.getKNet()
bd = nio.getBDTNP()
#btgs,btfs = nio.getBDTNP()
sush = nio.getSush(on_fail = 'compute')
tfset = set(ktfs.keys())
tgset = set(ktgs.keys())
def fetch_cluster_mapping():
res = sio.loadmat(cfg.dataPath('soheil/ben_results/cluster_results/all/'+\
'expression_c4d_n4_t{0}.mat'.format('t_4')))
tfnames = [e[0][0] for e in res['tf_names']]
tgnames = [e[0][0] for e in res['gene_names']]
return tfnames, tgnames
import Bio.SeqIO as SeqIO
import Bio.Seq as seq
import Bio.Alphabet as Alphabet
import Bio.Align as al
import Bio.AlignIO as aio
import Bio.SeqRecord as sr
from numpy import *
import os, re
import cb.config as cfg
temp_dir = cfg.dataPath('alg')
if not os.path.isdir(temp_dir):
os.mkdir(temp_dir)
import subprocess as spc
def writelines(lines, gid):
ali = al.MultipleSeqAlignment([
sr.SeqRecord(seq.Seq(''.join(line)),
'{1}{0}i'.format(i, gid),
description='{1}{0}d'.format(i, gid))
for i, line in enumerate(lines[::50])
])
return ali
def write_fa(lines, gid):
fpath = os.path.join(temp_dir, '{0}_seqlines.fa'.format(gid))
fopen = open(fpath, 'w')
alignment = writelines(lines, gid)
SeqIO.write(alignment, fopen, 'fasta')
import cb.config as cfg
import track
import cb.utils.memo as mem
from numpy import *
import os
import numpy as np
mousefile = cfg.dataPath('silvana/mouse_genes.bed')
peakfile = cfg.dataPath('silvana/dhs.narrowPeak')
def getTrackChrPromoters(**kwargs):
'''
Get all of the forward promoter from a bed file
on a given chromosome>
kwargs
num: chromosome number
fname: bedfile path
returns
a list of the coordinates of each forward promoter.
'''
def setTrackChrPromoters(**kwargs):
fname = kwargs.get('fname', mousefile)
num = kwargs.get('num', 1)
t = track.load(fname);
chromosome_data = t.read('chr{0}'.format(num))
rows = [dict(zip(r.keys(),r.data)) for r in iter(chromosome_data)]
fwd_genes = [e for e in rows if e['strand'] == 1]
fwd_starts =dict([(e['name'],e['start']) for e in fwd_genes])
fwd_promoters= dict([(k, [v - 2000, v - 100])
import networkx as nx
from numpy import *
import numpy as np
import cb.p.network.io as nio
import cb.utils.plots as myplots
import cb.utils.graphs.draw as gd
import cb.config as cfg
import itertools as it
figtemplate = cfg.dataPath('figs/soheil/module_signs_{0}.pdf')
def view0(modules,
data_src = 'bdtnp',
net_src = 'fRN',
max_rank = 4,
module_type = 'doubles'):
'''
A routine to view the sign of interaction coefficients for
a given transcription factor split per-cluster and per-module
size.
Designed to be run on the output of view_output.modules()
'''
#COMPUTE BULK STATISTICS FOR EACH TF
bd_data = nio.getBDTNP()
genes = bd_data.keys()
tfs =sorted(set(it.chain(*[k for k in modules.keys()])))
tf_net = nx.Graph()
tf_net.add_nodes_from(tfs)
def make_cfg(plot_params,
name=default_name,
geo='square',
mut=.002,
delta=.0005,
dim=20):
if not os.path.isdir(name):
os.mkdir(name)
import shutil
flist = os.listdir(name)
cfg_start = cfg.dataPath('avida_default_cfgfiles')
for r, d, files in os.walk(cfg_start):
for f in files:
if f in flist:
continue
shutil.copyfile(os.path.join(r, f), os.path.join(name, f))
#default_file = open(os.path.join(name,'avida.cfg'))
outfile = open(os.path.join(name, 'avida.cfg.auto'), 'w')
outfile.write('#avida.cfg generated by python.')
#lines = default_file.readlines()
auto_dir = os.path.join(name, os.path.join('autogen'))
if not os.path.isdir(auto_dir):
os.mkdir(auto_dir)
eve_fname = ca.make_eve(name, default_evename)
org_fname = ca.make_org(name, default_orgname)
ana_fname = ca.make_ana(name, default_ananame)
env_fname = ca.make_env(name, default_envname)
ins_fname = ca.make_ins(name, default_insname)
computed = presets.differential_mut(name,
mut=mut,
geo_name=geo,
delta=delta,
dim=dim,
eve_fname=eve_fname,
org_fname=org_fname,
ana_fname=ana_fname,
env_fname=env_fname,
ins_fname=ins_fname,
gen_name=default_genname)
for pp in plot_params:
pp['computed'] = computed
print
print 'setting print params: '
print
for p in plot_params:
if p['type'] == 'ts':
colstr = ''
for col in p.get('command_params', []):
colstr += col + ' '
printstr = p['update'] + ' ' + p['command'] + ' ' + p[
'fname'] + ' ' + colstr
ca.alter_eve(eve_fname, printstr)
elif p['type'] == 'grid':
printstr = p['update'] + ' ' + p['command'] + ' ' + p['fname']
ca.alter_eve(eve_fname, printstr)
f = open(eve_fname).read()
print f
import Bio.PDB as PDB
import Bio.PDB.PDBIO as PDBIO
from Bio.PDB.PDBIO import Select
import cb.config as cfg
import os, itertools as it, re
droot = cfg.dataPath('structs')
pdb_ann = os.path.join(droot, '3UGM.pdb')
pdb_plain = os.path.join(droot, '3UGM_.pdb')
pqr_file = os.path.join(droot, '3UGM.pqr')
def test(filename = 'g_princeps.pdb'):
st = read_struct(open(filename))
def read_struct(fopen):
pparse = PDB.PDBParser(PERMISSIVE = 0)
struct = pparse.get_structure('tmp', fopen)
return struct
def res_pos(filename = 'g_princeps.pdb'):
raise Exception()
def extract_chain(struct,fout):
io=PDBIO()
io.set_structure(struct)
io.save(fout, select = ChainSelector('A'))
return
class ChainSelector(Select):
import networkx as nx
import cb.config as cfg
import os, itertools as it
from numpy import *
import numpy as np
import cb.utils.colors as mycolors
aba_path = cfg.dataPath('brain_atlas/mouse_aba')
structures_path = os.path.join(aba_path, 'brainstructures.csv')
coords_path = os.path.join(aba_path, 'AtlasAnnotation200.sva')
def structure_voxels():
structs_open = open(structures_path)
slines = structs_open.readlines()
structs_open.close()
coords_open = open(coords_path)
clines = coords_open.readlines()
coords_open.close()
crows = [[int(e) for e in l.strip().split(',')] for l in clines[2:]]
scols = slines[0].strip().split(',')
srows = [dict( zip(scols,l.strip().split(','))) for l in slines[1:]]
cgroups =[(k,list(g)) for k, g in it.groupby(
sorted(crows, key =lambda x: x[3])
, key = lambda x: x[3])]
coords = dict([(k, array([[e[0],e[1],e[2]]
for e in v]))
def save(self):
savepath = cfg.dataPath('figs/tmp/tmp_fig_{0}.pdf').format(self.num)
self.f.savefig(savepath)
