def triple_venn_consv():
hints = co.load_havug_ints()
ppi_cxs, clean_cxs, corconsv = ppi.load_training_complexes("Hs", "Dm")
cints = co.pairs_from_complexes(ut.i1(ppi_cxs)) # exclude huge ones
ints23 = ut.loadpy(ut.bigd("../23_collapsenodes/Hs_filtorth025_withsc_2sp_refilt2sp_cxs_cxppis_clust27_532cxs"))[1]
ints3 = [cp.consv_pairs(i, h2d) for i in ints23, hints, cints]
cp.triple_venn(ints3, ["map23", "havug", "corum"])
def predict_clust(name, sp, nsp, obs=None, exs=None, savef=None, pres=None,
pd_spcounts=None, cl_kwargs={}, clusts=None, runid=None,
count_ext=False, cutoff=0.5, n_cvs=7, accept_clust=False,
obs_fnames=None, base_splits=None, obs_kwargs={}, kfold=3,
gold_nspecies=2, do_cluster=True, do_2stage_cluster=True,
cxs_cxppis=None, do_rescue=True, n_rescue=20000, rescue_fracs=20,
rescue_score=0.9, clstruct=None, **predict_kwargs):
"""
- obs/test_kwargs: note obs_kwargs is combined with predict_kwargs to enforce
consistency.
- pd_spcounts: supply from ppi.predict_all if nsp > 1.
- base_splits: supply exs.splits to generate examples from existing
division of complexes.
- cxs_cxppis: provide if you want to export, or do the ppi rescue
clustering--also must set accept_clust=True, do_rescue=True
"""
savef = savef if savef else ut.bigd(name)+'.pyd'
print "Will save output to", savef
runid = runid or random.randrange(0,1000)
if clusts is None:
if pres is None:
if obs is None:
obs, pd_spcounts = ppi.predict_all(sp, obs_fnames,
save_fname=savef.replace('.pyd',''), nsp=nsp,
**obs_kwargs)
if exs is None:
cvtest_kwargs = ut.dict_quick_merge(obs_kwargs, predict_kwargs)
n_cvs = 1 if base_splits is not None else n_cvs
cvs, cvstd = cvstd_via_median(name, sp, nsp, obs_fnames, kfold,
base_splits, n_cvs, **cvtest_kwargs)
if n_cvs > 1:
ut.savepy(cvs, ut.pre_ext(savef, '_cvs_%s' % n_cvs))
ut.savepy(cvstd, ut.pre_ext(savef, '_cvstd'))
exs=cvstd.exs
pres = predict(name, sp, obs, exs.arrfeats, nsp, **predict_kwargs)
pres.exs = exs
ut.savepy(pres, ut.pre_ext(savef, '_pres'), check_exists=True)
else:
pres=ut.struct_copy(pres)
if do_rescue:
assert obs is not None, "Must supply obs for rescue step"
merged_splits = pres.exs.splits[1] # splits is (lp_splits, clean_splits)
if do_cluster:
if cxs_cxppis is None and clstruct is None:
if clusts is None and cxs_cxppis is None:
#if calc_fracs:
#cl_kwargs['fracs'] = [cp.find_inflection(pres.ppis, merged_splits,
#pres.species, gold_nspecies)]
clusts, runid = multi_clust(pres.ppis, savef=savef, runid=runid,
pres=pres, gold_splits=merged_splits,
gold_nspecies=gold_nspecies, **cl_kwargs)
ut.savepy(clusts, ut.pre_ext(savef, '_clusts_id%s' % runid))
if do_2stage_cluster:
clusts2 = multi_stage2_clust(clusts, pres.ppis, runid=runid,
**cl_kwargs)
clstruct = cp.result_stats(sp, merged_splits, clusts2,
gold_nspecies)
ut.savepy(clstruct, ut.pre_ext(savef, '_clstruct2_id%s' % runid))
else:
clstruct = cp.result_stats(sp, merged_splits, clusts, nsp)
ut.savepy(clstruct, ut.pre_ext(savef, '_clstruct_id%s' % runid))
if accept_clust:
if cxs_cxppis is None:
pres.cxs, pres.cxppis, pres.ind = cp.select_best(clstruct)
ut.savepy([pres.cxs,pres.cxppis],
ut.pre_ext(savef,'_cxs_cxppis_id%s_ind%s_%scxs'
% (runid, pres.ind, len(pres.cxs))))
else:
pres.cxs, pres.cxppis = cxs_cxppis
pres.ind = 0
if do_rescue:
# note cl_kwargs aren't passed--would be messy
pres.cxs, pres.cxppis, pres.ppis_rescue = rescue_ppis(pres,
obs, n_rescue, cutoff_fracs=rescue_fracs,
cutoff_score=rescue_score)
cyto_export(pres, merged_splits, name_ext='_clust%s_%scxs' % (pres.ind,
len(pres.cxs)), pd_spcounts=pd_spcounts, arrdata=obs,
cutoff=cutoff, count_ext=False, arrdata_ppis=None)
return pres
else:
return pres, clstruct
else:
return pres