mirror of
https://github.com/Priyatham-sai-chand/compara-deep-learning.git
synced 2026-10-05 08:11:34 -07:00
86 lines
2.7 KiB
Python
86 lines
2.7 KiB
Python
|
import numpy as np
|
||
|
|
import pandas as pd
|
||
|
|
import json
|
||
|
|
import os
|
||
|
|
import sys
|
||
|
|
import pickle
|
||
|
|
from select_data import read_db_homology
|
||
|
|
from threads import Procerssrunner
|
||
|
|
from read_get_gene_seq import read_gene_sequences
|
||
|
|
from access_data_rest import update_rest
|
||
|
|
|
||
|
|
def read_data_synteny(nop,name):
|
||
|
|
smg=[]
|
||
|
|
sml=[]
|
||
|
|
indexes=[]
|
||
|
|
for i in range(nop):
|
||
|
|
try:
|
||
|
|
with open("temp_"+name+"/thread_"+str(i+1)+"_smg.temp","rb") as file:
|
||
|
|
smg=smg+pickle.load(file)
|
||
|
|
with open("temp_"+name+"/thread_"+str(i+1)+"_sml.temp","rb") as file:
|
||
|
|
sml=sml+pickle.load(file)
|
||
|
|
with open("temp_"+name+"/thread_"+str(i+1)+"_indexes.temp","rb") as file:
|
||
|
|
indexes=indexes+pickle.load(file)
|
||
|
|
except Exception as e:
|
||
|
|
print("Problem with thread",i+1,"detected for",name,e)
|
||
|
|
continue
|
||
|
|
print(len(indexes))
|
||
|
|
return smg,sml,indexes
|
||
|
|
|
||
|
|
def load_neighbor_genes():
|
||
|
|
with open("processed/neighbor_genes.json","r") as file:
|
||
|
|
lsy=dict(json.load(file))
|
||
|
|
print(len(lsy))
|
||
|
|
print("Neighbor Genes Loaded")
|
||
|
|
return lsy
|
||
|
|
|
||
|
|
def read_data_homology(dirname):
|
||
|
|
lf=os.listdir(dirname)
|
||
|
|
if len(lf)==0:
|
||
|
|
print("No Files in the Directory!!!!!!!")
|
||
|
|
sys.exit(1)
|
||
|
|
a_h=[]
|
||
|
|
d_h=[]
|
||
|
|
for x in lf:
|
||
|
|
df,n=read_db_homology(dirname,x)
|
||
|
|
n=n.split()[0]
|
||
|
|
try:
|
||
|
|
indexes=np.load("processed/"+n+"_selected_indexes.npy")
|
||
|
|
except:
|
||
|
|
print("Incomplete data for:",n)
|
||
|
|
df=df.loc[indexes]
|
||
|
|
a_h.append(df)
|
||
|
|
d_h.append(n)
|
||
|
|
return a_h,d_h
|
||
|
|
|
||
|
|
def main():
|
||
|
|
arg=sys.argv
|
||
|
|
nop=int(arg[-1])
|
||
|
|
n=3
|
||
|
|
a_h,d_h=read_data_homology("data_homology")
|
||
|
|
print("Data Read")
|
||
|
|
lsy=load_neighbor_genes()
|
||
|
|
gene_sequences=read_gene_sequences(a_h,lsy,"geneseq","gene_seq_positive")
|
||
|
|
gene_sequences=update_rest(gene_sequences,"gene_seq_positive")
|
||
|
|
print("Gene Sequences Loaded.")
|
||
|
|
if not os.path.isdir("processed/synteny_matrices"):
|
||
|
|
os.mkdir("processed/synteny_matrices")
|
||
|
|
ndir="processed/synteny_matrices/"
|
||
|
|
nf1="synteny_matrices_global"
|
||
|
|
nf2="synteny_matrices_local"
|
||
|
|
nf3="indexes"
|
||
|
|
for i in range(len(a_h)):
|
||
|
|
df=a_h[i]
|
||
|
|
part=len(df)//nop
|
||
|
|
pr=Procerssrunner()
|
||
|
|
pr.start_processes(nop,df,gene_sequences,lsy,part,n,d_h[i])
|
||
|
|
smg,sml,indexes=read_data_synteny(nop,d_h[i])
|
||
|
|
print(len(indexes))
|
||
|
|
np.save(ndir+str(d_h[i])+"_"+nf1,smg)
|
||
|
|
np.save(ndir+str(d_h[i])+"_"+nf2,sml)
|
||
|
|
np.save(ndir+str(d_h[i])+"_"+nf3,indexes)
|
||
|
|
print("Synteny Matrices Created Successfully :)")
|
||
|
|
|
||
|
|
if __name__=="__main__":
|
||
|
|
main()
|