def evaluate_inference(result, distance_name=None, hitlist_file='/media/lalil0u/New/workspace2/Xb_screen/data/mitocheck_exp_hitlist_perPheno.pkl',
print_=False,folder='/media/lalil0u/New/projects/drug_screen/results/',
threshold=0.0001):
f=open(hitlist_file, 'r')
hitlist=pickle.load(f); f.close()
yqualdict=expSi('../data/mapping_2014/qc_export.txt')
dictSiEntrez=siEntrez('../data/mapping_2014/mitocheck_siRNAs_target_genes_Ens75.txt')
trad=EnsemblEntrezTrad('../data/mapping_2014/mitocheck_siRNAs_target_genes_Ens75.txt')
to_plot_info=defaultdict(dict)
to_GO_info=defaultdict(list)
for cond in sorted(result):
if print_:
print '-----------', cond
l=np.array([(dictSiEntrez[el[0]], el[-1]) for el in result[cond]])
to_plot_info[cond]=defaultdict(list)
for el in sorted(KNOWN_TARGETS[cond.split('--')[0]]):
if np.where(l[:,0]==el)[0].shape[0]>0:
rank_=np.where(l[:,0]==el)[0][0]
to_plot_info[cond]['genes'].append(rank_)
to_plot_info[cond]['gene_list'].append(el)
if print_:
print el, l[np.where(l[:,0]==el)], rank_
if type(threshold)==int:
gene_lim=l[:threshold][:,0]
else:
lim=np.where(np.array(l[:,1], dtype=float)==threshold)[0]
gene_lim=l[lim][:,0]
to_GO_info[cond]=[trad[el] for el in gene_lim]
res=[]
for gene in gene_lim:
res.extend(hitlist[gene])
#STEP2 here : we add writing gene list files
to_plot_info[cond]['type']= Counter(res)
multipleGeneListsToFile([to_GO_info[el] for el in to_GO_info], [el for el in to_GO_info], name=os.path.join(folder, 'GO_{}.txt'.format(distance_name)))
return to_plot_info
def condition_cluster_inference(M, clusters, who_hits, exposure_hits, who_Mitocheck, num_permutations, threshold, random_result, filename,
taking_siRNAs=True, gsea=False):
'''
- M: distance matrix of size (hits, mitocheck)
- taking_siRNAs: indicates if you want to consider different values of the same siRNAs independently (False) or as replicates of the same condition
- num_permutations: no calculation of p-values if None, else number of permutations
- filename if we want to write GSEA ranking files
- gsea : if you want to write gsea ranking files
'''
r={}
yqualdict=expSi('../data/mapping_2014/qc_export.txt')
yqualdict.update(expSi('../data/mapping_2014/qc_validation_exp.txt', primary_screen=False))
dictSiEntrez=siEntrez('../data/mapping_2014/mitocheck_siRNAs_target_genes_Ens75.txt')
trad=EnsemblEntrezTrad('../data/mapping_2014/mitocheck_siRNAs_target_genes_Ens75.txt')
siRNAs=[yqualdict[e] for e in who_Mitocheck]
genes=[dictSiEntrez[e] for e in siRNAs]
past_cluster_num=0
for cluster_num in clusters:
print cluster_num
r[cluster_num]={'conditions':clusters[cluster_num]}
where_=np.hstack((np.where(exposure_hits==el)[0] for el in clusters[cluster_num]))
batch_names = who_hits[where_]
curr_dist=np.hstack((M[j] for j in where_))
curr_who=[(batch_names[0], '') for k in range(M.shape[1])]
curr_conditions=list(who_Mitocheck) if not taking_siRNAs else list(genes)
for name in batch_names[1:]:
curr_who.extend([(name, '') for k in range(M.shape[1])])
if not taking_siRNAs:
curr_conditions.extend(who_Mitocheck)
else:
curr_conditions.extend(genes)
print curr_dist.shape
if num_permutations is not None and past_cluster_num!=len(batch_names):
#If there are only five experiments that are different between the two cluster length, then no need to redo the random rank product computation
random_result=None
curr_res=computeRPpvalues(curr_dist, np.array(curr_who),
conditions=np.array(curr_conditions),
technical_replicates_key=np.median,
xb_screen=False,
num_permutations=num_permutations, reverse=False,
batch_names=batch_names, random_result=random_result,
signed=False)
#donc curr_res est [(gene, rank value)]
if num_permutations is None and gsea:
writeGSEARankingFile(curr_res, filename.format(cluster_num))
else:
if len(curr_res)==2:
#this means that we have the p-values
curr_res, random_result=curr_res
curr_res=sorted(curr_res, key=itemgetter(-1))
pval=np.array(np.array(curr_res)[:,-1], dtype=float)
if not taking_siRNAs:
currG=[dictSiEntrez[yqualdict[e]] for e in np.array(curr_res)[np.where(pval<=threshold)][:,0]]
else:
currG=[e for e in np.array(curr_res)[np.where(pval<=threshold)][:,0]]
print sorted(currG)
else:
#this means that we're working with the rank product values
curr_res=sorted(curr_res, key=itemgetter(-1))
if not taking_siRNAs:
currG=[dictSiEntrez[yqualdict[e]] for e in np.array(curr_res)[:threshold][:,0]]
else:
currG=[e for e in np.array(curr_res)[:threshold][:,0]]
print sorted(currG)
past_cluster_num=len(batch_names)
r[cluster_num]['genes']=[trad[el] for el in currG]
r[cluster_num]['result']=[(el[0],el[-1]) for el in curr_res]
multipleGeneListsToFile([r[k]['genes'] for k in r], [k for k in r], name=filename)
return r