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)