CRISPRTool / cas9on.py
supercat666's picture
fix
445015e
raw
history blame
8.36 kB
import requests
import tensorflow as tf
import pandas as pd
import numpy as np
from operator import add
from functools import reduce
from Bio import SeqIO
from Bio.SeqRecord import SeqRecord
from Bio.SeqFeature import SeqFeature, FeatureLocation
from Bio.Seq import Seq
from keras.models import load_model
import random
# configure GPUs
for gpu in tf.config.list_physical_devices('GPU'):
tf.config.experimental.set_memory_growth(gpu, enable=True)
if len(tf.config.list_physical_devices('GPU')) > 0:
tf.config.experimental.set_visible_devices(tf.config.list_physical_devices('GPU')[0], 'GPU')
ntmap = {'A': (1, 0, 0, 0),
'C': (0, 1, 0, 0),
'G': (0, 0, 1, 0),
'T': (0, 0, 0, 1)
}
def get_seqcode(seq):
return np.array(reduce(add, map(lambda c: ntmap[c], seq.upper()))).reshape(
(1, len(seq), -1))
from keras.models import load_model
class DCModelOntar:
def __init__(self, ontar_model_dir, is_reg=False):
self.model = load_model(ontar_model_dir)
def ontar_predict(self, x, channel_first=True):
if channel_first:
x = x.transpose([0, 2, 3, 1])
yp = self.model.predict(x)
return yp.ravel()
# Function to predict on-target efficiency and format output
def format_prediction_output(targets, model_path):
dcModel = DCModelOntar(model_path)
formatted_data = []
for target in targets:
# Encode the gRNA sequence
encoded_seq = get_seqcode(target[0]).reshape(-1,4,1,23)
# Predict on-target efficiency using the model
prediction = dcModel.ontar_predict(encoded_seq)
# Format output
sgRNA = target[1]
chr = target[2]
start = target[3]
end = target[4]
strand = target[5]
transcript_id = target[6]
formatted_data.append([chr, start, end, strand, transcript_id, target[0], sgRNA, prediction[0]])
return formatted_data
def fetch_ensembl_transcripts(gene_symbol):
headers = {"Content-Type": "application/json"}
url = f"https://rest.ensembl.org/lookup/symbol/homo_sapiens/{gene_symbol}?expand=1"
response = requests.get(url, headers=headers)
if response.status_code == 200:
gene_data = response.json()
return gene_data.get('Transcript', [])
else:
print(f"Error fetching gene data from Ensembl: {response.text}")
return None
def fetch_ensembl_sequence(transcript_id):
headers = {"Content-Type": "application/json"}
url = f"https://rest.ensembl.org/sequence/id/{transcript_id}"
response = requests.get(url, headers=headers)
if response.status_code == 200:
sequence_data = response.json()
return sequence_data.get('seq', '')
else:
print(f"Error fetching sequence data from Ensembl for transcript {transcript_id}: {response.text}")
return None
def fetch_ensembl_exons(transcript_id):
headers = {"Content-Type": "application/json"}
url = f"https://rest.ensembl.org/overlap/id/{transcript_id}?feature=exon"
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.json()
else:
print(f"Error fetching exon data from Ensembl for transcript {transcript_id}: {response.text}")
return None
def fetch_ensembl_cds(transcript_id):
headers = {"Content-Type": "application/json"}
url = f"https://rest.ensembl.org/overlap/id/{transcript_id}?feature=cds"
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.json()
else:
print(f"Error fetching CDS data from Ensembl for transcript {transcript_id}: {response.text}")
return None
def find_crispr_targets(sequence, chr, start, strand, transcript_id, pam="NGG", target_length=20):
targets = []
len_sequence = len(sequence)
complement = {'A': 'T', 'T': 'A', 'C': 'G', 'G': 'C'}
if strand == -1:
sequence = ''.join([complement[base] for base in reversed(sequence)])
for i in range(len_sequence - len(pam) + 1):
if sequence[i + 1:i + 3] == pam[1:]:
if i >= target_length:
target_seq = sequence[i - target_length:i + 3]
tar_start = start + i - target_length
tar_end = start + i + 3
sgRNA = sequence[i - target_length:i]
targets.append([target_seq, sgRNA, chr, str(tar_start), str(tar_end), str(strand), transcript_id])
return targets
def process_gene(gene_symbol, model_path):
transcripts = fetch_ensembl_transcripts(gene_symbol)
all_data = []
if transcripts:
cdslist = fetch_ensembl_cds(transcripts[0].get('id'))
for transcript in transcripts:
transcript_id = transcript.get('id')
chr = transcript.get('seq_region_name', 'unknown')
start = transcript.get('start', 0)
strand = transcript.get('strand', 'unknown')
# Fetch the gene sequence for each transcript
gene_sequence = fetch_ensembl_sequence(transcript_id) or ''
# Fetch exon and CDS information is not directly used here but you may need it elsewhere
exons = fetch_ensembl_exons(transcript_id)
if gene_sequence:
# Now correctly passing transcript_id as an argument
gRNA_sites = find_crispr_targets(gene_sequence, chr, start, strand, transcript_id)
if gRNA_sites:
formatted_data = format_prediction_output(gRNA_sites, model_path)
all_data.extend(formatted_data)
# Return the data and potentially any other information as needed
return all_data, gene_sequence, exons, cdslist
def create_genbank_features(formatted_data):
features = []
for data in formatted_data:
# Strand conversion to Biopython's convention
strand = 1 if data[3] == '+' else -1
location = FeatureLocation(start=int(data[1]), end=int(data[2]), strand=strand)
feature = SeqFeature(location=location, type="misc_feature", qualifiers={
'label': data[5], # Use gRNA as the label
'target': data[4], # Include the target sequence
'note': f"Prediction: {data[6]}" # Include the prediction score
})
features.append(feature)
return features
def generate_genbank_file_from_df(df, gene_sequence, gene_symbol, output_path):
features = []
for index, row in df.iterrows():
# Use 'Transcript ID' if it exists, otherwise use a default value like 'Unknown'
transcript_id = row.get("Transcript ID", "Unknown")
# Make sure to use the correct column names for Start Pos, End Pos, and Strand
location = FeatureLocation(start=int(row["Start Pos"]),
end=int(row["End Pos"]),
strand=1 if row["Strand"] == '+' else -1)
feature = SeqFeature(location=location, type="gene", qualifiers={
'locus_tag': transcript_id, # Now using the variable that holds the safe value
'note': f"gRNA: {row['gRNA']}, Prediction: {row['Prediction']}"
})
features.append(feature)
# The rest of the function remains unchanged
record = SeqRecord(Seq(gene_sequence), id=gene_symbol, name=gene_symbol,
description=f'CRISPR Cas9 predicted targets for {gene_symbol}', features=features)
record.annotations["molecule_type"] = "DNA"
SeqIO.write(record, output_path, "genbank")
def create_bed_file_from_df(df, output_path):
with open(output_path, 'w') as bed_file:
for index, row in df.iterrows():
# Adjust field names based on your actual formatted data
chrom = row["Chr"]
start = int(row["Start Pos"])
end = int(row["End Pos"])
strand = '+' if row["Strand"] == '+' else '-' # Ensure strand is correctly interpreted
gRNA = row["gRNA"]
score = str(row["Prediction"]) # Ensure score is converted to string if not already
transcript_id = row["Transcript ID"] # Extract transcript ID
bed_file.write(f"{chrom}\t{start}\t{end}\t{gRNA}\t{score}\t{strand}\t{transcript_id}\n") # Include transcript ID in BED output
def create_csv_from_df(df, output_path):
df.to_csv(output_path, index=False)