Spaces:
Sleeping
Sleeping
File size: 10,304 Bytes
2dc56c6 45ecc7a 2dc56c6 45ecc7a 2dc56c6 45ecc7a 8514d6e 45ecc7a 8514d6e 45ecc7a 6c3a9a2 8514d6e 6c3a9a2 8514d6e 6c3a9a2 8514d6e 6c3a9a2 8514d6e 6c3a9a2 8514d6e 6c3a9a2 8514d6e 6c3a9a2 8514d6e 45ecc7a 2dc56c6 45ecc7a 76d2043 d304bc6 45ecc7a d54796c 8bd3df4 ea9c8bb 8bd3df4 45ecc7a d54796c 76d2043 a115539 76d2043 2db3f30 a115539 76d2043 4b9653e 76d2043 d457ef4 478cf26 76d2043 45ecc7a 3c73739 76d2043 a115539 2db3f30 a115539 2319b33 0b0c338 2215c31 527e309 d457ef4 45ecc7a 478cf26 45ecc7a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 |
import streamlit as st
import zipfile
import urllib.request
import glob
import SigProfilerMatrixGenerator
from SigProfilerMatrixGenerator import install as genInstall
import shutil
import os
from SigProfilerExtractor import sigpro as sig
import sys
import numpy as np
import base64
import streamlit.components.v1 as components
curdir= os.getcwd()
def remove_old_vcf():
vcfrem=glob.glob('input/*.vcf')
for filepath in vcfrem:
os.remove(filepath)
vcfrem=glob.glob('input/input/*.vcf')
for filepath in vcfrem:
os.remove(filepath)
def show_pdf(file_path):
with open(file_path,"rb") as f:
base64_pdf = base64.b64encode(f.read()).decode('utf-8')
pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="1500" height="1000" type="application/pdf"></iframe>'
st.markdown(pdf_display, unsafe_allow_html=True)
#@st.cache_data(experimental_allow_widgets=True)
def showdl(file_to_lookat,to_dl_sbs,to_dl_indel,to_dl_dbs,to_dl_sbs_text,to_dl_indel_text,to_dl_dbs_text):
for j in np.arange(0,len(to_dl_sbs)):
if to_dl_sbs[j] != []:
download_link1 = f'<a href="data:application/octet-stream;base64, \
{base64.b64encode(to_dl_sbs[j]).decode()}" download=" \
{file_to_lookat[j].name}SBS.pdf">Download {file_to_lookat[j].name} Single Base Substition pdf</a>'
download_link2 = f'<a href="data:application/octet-stream;base64, \
{base64.b64encode(to_dl_sbs_text[j]).decode()}" download=" \
{file_to_lookat[j].name}SBS.txt">Download {file_to_lookat[j].name} Single Base Substition table</a>'
st.markdown(download_link1, unsafe_allow_html=True)
st.markdown(download_link2, unsafe_allow_html=True)
for j in np.arange(0,len(to_dl_indel)):
if to_dl_indel[j] != []:
download_link3 = f'<a href="data:application/octet-stream;base64, \
{base64.b64encode(to_dl_indel[j]).decode()}" download=" \
{file_to_lookat[j].name}Indel.pdf">Download {file_to_lookat[j].name} indel pdf</a>'
download_link4 = f'<a href="data:application/octet-stream;base64, \
{base64.b64encode(to_dl_indel_text[j]).decode()}" download=" \
{file_to_lookat[j].name}Indel.txt">Download {file_to_lookat[j].name} indel table</a>'
st.markdown(download_link3, unsafe_allow_html=True)
st.markdown(download_link4, unsafe_allow_html=True)
for j in np.arange(0,len(to_dl_dbs)):
if to_dl_dbs[j] !=[]:
download_link5 = f'<a href="data:application/octet-stream;base64, \
{base64.b64encode(to_dl_dbs[j]).decode()}" download=" \
{file_to_lookat[j].name}DBS.pdf">Download {file_to_lookat[j].name} Double Base Substitution pdf</a>'
download_link6 = f'<a href="data:application/octet-stream;base64, \
{base64.b64encode(to_dl_dbs_text[j]).decode()}" download=" \
{file_to_lookat[j].name}DBS.txt">Download {file_to_lookat[j].name} Double Base Substitution table</a>'
st.markdown(download_link5, unsafe_allow_html=True)
st.markdown(download_link6, unsafe_allow_html=True)
#st.download_button(label="Download image with single base substitution profiles", key=j,
# data=to_dl_sbs[j],
# file_name="SBS.pdf",
# mime='application/octet-stream')
#st.download_button(label="Download image with indel profiles", key=0.5+j,
# data=to_dl_indel[j],
# file_name="idel.pdf",
# mime='application/octet-stream')
def dl(valforkey):
#breakpoint()
seev=glob.glob('output/SBS96/Suggested_Solution/COSMIC_SBS96_Decomposed_Solution/*pdf')
for i in seev:
st.write('pdf file with sbs96 output is here: '+i)
with open("output/SBS96/Suggested_Solution/COSMIC_SBS96_Decomposed_Solution/SBS96_Decomposition_Plots.pdf", "rb") as pdf_file:
PDFbyte1 = pdf_file.read()
with open("output/SBS96/Samples.txt","rb") as txt_file:
Txtbyte1 = txt_file.read()
#st.download_button(label="Download image with single base substitution profiles", key=valforkey,
# data=PDFbyte1,
# file_name="SBS.pdf",
# mime='application/octet-stream')
if glob.glob('output/ID83/Suggested_Solution/COSMIC_ID83_Decomposed_Solution/ID83_Decomposition_Plots.pdf') != []:
with open("output/ID83/Suggested_Solution/COSMIC_ID83_Decomposed_Solution/ID83_Decomposition_Plots.pdf", "rb") as pdf_file:
PDFbyte2 = pdf_file.read()
with open("output/ID83/Samples.txt","rb") as txt_file:
Txtbyte2 = txt_file.read()
else:
PDFbyte2 = []
Txtbyte2 = []
if glob.glob("output/DBS78/Suggested_Solution/COSMIC_DBS78_Decomposed_Solution/DBS78_Decomposition_Plots.pdf") != []:
with open("output/DBS78/Suggested_Solution/COSMIC_DBS78_Decomposed_Solution/DBS78_Decomposition_Plots.pdf", "rb") as pdf_file:
PDFbyte3 = pdf_file.read()
with open("output/DBS78/Samples.txt","rb") as txt_file:
Txtbyte3 = txt_file.read()
else:
PDFbyte3 = []
Txtbyte3=[]
os.system('rm -r output')
os.system('rm -r input')
#os.remove("output/SBS96/Suggested_Solution/COSMIC_SBS96_Decomposed_Solution/SBS96_Decomposition_Plots.pdf")
#os.remove("output/SBS96/Suggested_Solution/COSMIC_SBS96_Decomposed_Solution/*")
#os.remove("output/SBS96/Samples.txt")
#os.remove("output/ID83/Suggested_Solution/COSMIC_ID83_Decomposed_Solution/ID83_Decomposition_Plots.pdf")
#os.remove("output/ID83/Samples.txt")
#os.remove("output/DBS78/Suggested_Solution/COSMIC_DBS78_Decomposed_Solution/DBS78_Decomposition_Plots.pdf")
#os.remove("output/DBS78/Samples.txt")
#st.download_button(label="Download image with indel profiles", key=0.5+valforkey,
# data=PDFbyte2,
# file_name="idel.pdf",
# mime='application/octet-stream')
return PDFbyte1,PDFbyte2,PDFbyte3,Txtbyte1,Txtbyte2,Txtbyte3
#st.write(glob.glob(os.path.join(os.path.dirname(SigProfilerMatrixGenerator.__file__),'references/*txt')))
with st.form('get signature'):
if glob.glob(os.path.join(os.path.dirname(SigProfilerMatrixGenerator.__file__),'references/chromosomes/tsb/GRCh3[78]/')+'*txt') == []:
st.write('There is no reference genome, we need to download this')
refdownload=True
else:
st.write('using reference from here:'+glob.glob(os.path.join(os.path.dirname(SigProfilerMatrixGenerator.__file__),'references/chromosomes/tsb/GRCh3[78]/'))[0])
refdownload=False
referencegenome =st.radio('reference',['hg19','GRCh38'])
file_to_lookat=st.file_uploader('VCF upload here',type=[".vcf"],accept_multiple_files=True)
remove_old_vcf()
sub=st.form_submit_button('submit input')
if file_to_lookat !=[] and sub:
#if st.button('get reference genome'):
#st.write(os.path.dirname(SigProfilerMatrixGenerator.__file__))
dirtest=os.path.dirname(SigProfilerMatrixGenerator.__file__)
#st.write(sys.path)
if refdownload==True and referencegenome=='hg19':
with st.spinner('downloading hg19 reference'):
urllib.request.urlretrieve('https://dl.dropboxusercontent.com/s/et97ewsct862x7m/references.zip?dl=0','references.zip')
with zipfile.ZipFile('references.zip', 'r') as zip_ref:
zip_ref.extractall(dirtest)
elif refdownload==True and referencegenome=='GRCh38':
with st.spinner('downloading GRCh38 reference'):
genInstall.install('GRCh38')
#seev=glob.glob(dirtest+'/references/chromosomes/tsb/GRCh37/*txt')
#for i in seev:
# st.write(i)
##genInstall.install('GRCh37')
to_dl_sbs=[]
to_dl_indel=[]
to_dl_dbs=[]
to_dl_sbs_text=[]
to_dl_indel_text=[]
to_dl_dbs_text=[]
for j in np.arange(0,len(file_to_lookat)):
if not os.path.exists('input'):
os.mkdir('input')
if not os.path.exists('input/input'):
os.mkdir('input/input')
remove_old_vcf()
bytes_data=file_to_lookat[j].read()
with open(os.path.join("input",file_to_lookat[j].name),"wb") as f:
f.write(bytes_data)
f.close()
seev=glob.glob('input/*')
#for i in seev:
# st.write(i)
#vcfuse=glob.glob('file_to_lookat[0].name')[0]
#shutil.copy2(vcfuse,'input/'+vcfuse)
#pdb.set_trace()
with st.spinner('computing signatures'):
sig.sigProfilerExtractor("vcf", "output", "input", minimum_signatures=1, maximum_signatures=3,nmf_test_conv= 1000,nmf_tolerance= 1e-10,max_nmf_iterations=100000,min_nmf_iterations= 1000)
if file_to_lookat !=[] and glob.glob('output/SBS96/Suggested_Solution/COSMIC_SBS96_Decomposed_Solution/*pdf'):
sbs_result,indel_result,dbs_result,sbs_text,indel_text,dbs_text=dl(j)
to_dl_sbs.append(sbs_result)
to_dl_sbs_text.append(sbs_text)
to_dl_indel.append(indel_result)
to_dl_indel_text.append(indel_text)
to_dl_dbs.append(dbs_result)
to_dl_dbs_text.append(dbs_text)
#show_pdf('output/SBS96/Suggested_Solution/COSMIC_SBS96_Decomposed_Solution/SBS96_Decomposition_Plots.pdf')
remove_old_vcf()
showdl(file_to_lookat,to_dl_sbs,to_dl_indel,to_dl_dbs,to_dl_sbs_text,to_dl_indel_text,to_dl_dbs_text)
components.iframe("https://cancer.sanger.ac.uk/signatures/sbs/", height=3000,width=800)
#show_pdf('output/ID83/Suggested_Solution/COSMIC_ID83_Decomposed_Solution/ID83_Decomposition_Plots.pdf')
#components.iframe("https://cancer.sanger.ac.uk/signatures/id/",height=1000,width=800) |