File size: 5,741 Bytes
692c464 |
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 |
from Bio.Blast import NCBIWWW, NCBIXML
from Bio.Seq import Seq
from Bio import SeqIO
from Bio.SeqUtils import GC
import time
import warnings
import streamlit as st
from PIL import Image
from io import StringIO
img = Image.open("image.png")
st.image(img, use_column_width=True)
st.write(""" ## **Your results will display here :**
""")
def set_button_style():
button_style = """
<style>
.stButton button {
background-color: #FF6F61;
color: white;
border-radius: 100px;
border: 2px solid #FFFFFF;
box-shadow: 2px 2px 5px #000000;
width: 160px;
}
</style>
"""
st.markdown(button_style, unsafe_allow_html=True)
st.sidebar.title('Protein alignment with BLAST')
up = st.sidebar.file_uploader("Choose an existing fasta file", accept_multiple_files=False)
if up :
fasta = up.read()
seq = st.sidebar.text_area('Or enter a sequence to analyze : ')
b1 = st.sidebar.button("Calculate GC")
b2 = st.sidebar.button("Replicate")
b3 = st.sidebar.button("Transcribe")
b4 = st.sidebar.button("Back-Transcribe")
b5 = st.sidebar.button("Translate")
type = st.sidebar.text_input('Enter BLAST type : ',placeholder='exemple : blastp, blastn ...')
data = st.sidebar.text_input('Enter the database : ', placeholder='exemple : nt, nr ...')
detailed = st.sidebar.text_input('Enter detailed search : ', placeholder='Homo sapiens')
set_button_style()
b = st.sidebar.button("Run BLAST")
s = st.sidebar.button("Run detailed search")
def blast(seq, type, data):
st.write("""Starting BLAST search...""")
start_time = time.time()
result_handle2 = NCBIWWW.qblast(type, data, seq)
end_time = time.time()
st.write("""BLAST search completed.""")
st.write(f"Time taken: {end_time - start_time:.2f} seconds.")
with open("output.xml", "w") as out_handle:
out_handle.write(result_handle2.read())
st.write("Results saved to output.xml")
st.write("===================================")
result_handle = open("output.xml")
blast_record = NCBIXML.read(result_handle)
st.write(""" **Results :** """)
count = 0
for alignment in blast_record.alignments:
st.write("**"+str(alignment.title)+"**")
for hsp in alignment.hsps:
st.write(str(hsp.query[0:50]))
st.write(str(hsp.query[0:50]))
st.write(str(hsp.query[0:50]))
percentage_result = (hsp.query_end - hsp.query_start + 1) / hsp.align_length * 100
st.write(str(hsp))
if percentage_result >= 50:
st.write(f'<p style="color:green;">{percentage_result:.2f}</p>', unsafe_allow_html=True)
else:
st.write(f'<p style="color:red;">{percentage_result:.2f}</p>', unsafe_allow_html=True)
count += 1
if count == 10:
break
def detailed_search(detailed):
result_handle = open("output.xml")
blast_record = NCBIXML.read(result_handle)
st.write(" Detailed search on : " + "**" + str(detailed) + "**")
for alignment in blast_record.alignments:
if detailed in alignment.title:
st.write(str(alignment.title))
for hsp in alignment.hsps:
st.write(str(hsp.query[0:50]))
st.write(str(hsp.match[0:50]))
st.write(str(hsp.sbjct[0:50]))
st.write(str(hsp.positives) + str(hsp.score) + str(hsp.expect) + str(hsp.bits) + str(hsp.gaps))
def save_seq(seq):
with open("sequenceinput.fsa", "w") as file:
file.write(str(seq))
st.write("sequence saved to sequenceinput.fsa")
if seq :
save_seq(seq)
if (seq and type and data and b) :
blast(seq, type, data)
elif (up and type and data and b) :
blast(fasta, type, data)
if detailed and s :
detailed_search(detailed)
def calculate(seq):
with warnings.catch_warnings():
warnings.simplefilter("ignore") # Ignore all warnings
gc_content = GC(seq)
st.write(f"### **GC :** {gc_content}")
if seq and b1 :
calculate(seq)
elif up and b1 :
calculate(fasta.decode())
def reverse(seq):
sequence = Seq(seq)
r_seq = sequence.reverse_complement()
chunked_r_seq = [r_seq[i:i+50] for i in range(0, len(r_seq), 50)]
st.write("### **Reversed sequence :**")
for chunk in chunked_r_seq:
st.write("#### " + str(chunk))
if seq and b2 :
reverse(seq)
elif up and b2 :
reverse(fasta)
def transcribe_seq(seq):
sequence = Seq(seq)
r_seq = sequence.transcribe()
chunked_r_seq = [r_seq[i:i+50] for i in range(0, len(r_seq), 50)]
st.write("### **Transcribed sequence :** ")
for chunk in chunked_r_seq:
st.write("#### " + str(chunk))
if seq and b3 :
transcribe_seq(seq)
elif up and b3 :
transcribe_seq(fasta)
def back_transcribe_seq(seq):
sequence = Seq(seq)
r_seq = sequence.back_transcribe()
chunked_r_seq = [r_seq[i:i+50] for i in range(0, len(r_seq), 50)]
st.write("### **Back-Transcribed sequence :** ")
for chunk in chunked_r_seq:
st.write("#### " + str(chunk))
if seq and b4 :
back_transcribe_seq(seq)
elif up and b4 :
back_transcribe_seq(fasta)
def translate_seq(seq):
try :
sequence = Seq(seq)
r_seq = sequence.translate()
chunked_r_seq = [r_seq[i:i+50] for i in range(0, len(r_seq), 50)]
st.write("### **Translated sequence :** ")
for chunk in chunked_r_seq:
st.write("#### " + str(chunk))
except Exception as e:
st.write(f"#### Unable to translate this sequence! {e}")
if seq and b5 :
translate_seq(seq)
elif up and b5 :
transcribe_seq(fasta)
|