fix

app.py

@@ -181,7 +181,7 @@ if selected_model == 'Cas9':
                 # Include "Target" in the DataFrame's columns
                 try:
                     df = pd.DataFrame(st.session_state['on_target_results'],
-                                      columns=["Chr", "Start", "End", "Strand", "Transcript ID", "Target Sequence",
+                                      columns=["Chr", "Start", "End", "Strand", "Target Sequence",
                                                "sgRNA", "Prediction"])
                     st.dataframe(df)
                 except ValueError as e:
@@ -229,7 +229,7 @@ if selected_model == 'Cas9':
 
                 # Iterate over the sorted predictions to create the plot
                 for i, prediction in enumerate(st.session_state['on_target_results'], start=1):
-                    chrom, start, end, strand,transcript_id, target, gRNA, pred_score = prediction
+                    chrom, start, end, strand, target, gRNA, pred_score = prediction
 
                     midpoint = (int(start) + int(end)) / 2
                     y_value = i * 0.1 if strand == '1' else -i * 0.1  # Adjust multiplier for spacing
@@ -241,7 +241,7 @@ if selected_model == 'Cas9':
                         marker=dict(symbol='triangle-up' if strand == '1' else 'triangle-down', size=12),
                         text=f"Rank: {i}",  # Adjust based on your data
                         hoverinfo='text',
-                        hovertext=f"Rank: {i}<br>Chromosome: {chrom}<br>Target Sequence: {target}<br>gRNA: {gRNA}<br>Start: {start}<br>End: {end}<br>Strand: {'+' if strand == '1' else '-'}<br>Transcript_id: {transcript_id}<br>Prediction Score: {pred_score:.4f}",
+                        hovertext=f"Rank: {i}<br>Chromosome: {chrom}<br>Target Sequence: {target}<br>gRNA: {gRNA}<br>Start: {start}<br>End: {end}<br>Strand: {'+' if strand == '1' else '-'}<br>Prediction Score: {pred_score:.4f}",
                     ))
 
                 # Update the layout of the plot for better clarity and interactivity

cas9on.py

@@ -39,6 +39,27 @@ class DCModelOntar:
         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
+        gRNA = target[1]
+        chr = target[2]
+        start = target[3]
+        end = target[4]
+        strand = target[5]
+        formatted_data.append([chr, start, end, strand, target[0], gRNA, prediction[0]])
+
+    return formatted_data
 
 def fetch_ensembl_transcripts(gene_symbol):
     url = f"https://rest.ensembl.org/lookup/symbol/homo_sapiens/{gene_symbol}?expand=1;content-type=application/json"
@@ -68,87 +89,71 @@ def fetch_ensembl_sequence(transcript_id):
         print(f"Error fetching sequence data from Ensembl: {response.text}")
         return None
 
-def fetch_ensembl_cds(transcript_id):
-    url = f"https://rest.ensembl.org/overlap/id/{transcript_id}?feature=cds;content-type=application/json"
-    response = requests.get(url)
-    if response.status_code == 200:
-        cds_data = response.json()
-        return cds_data
-    else:
-        print(f"Error fetching CDS data from Ensembl: {response.text}")
-        return []
-def find_crispr_targets(sequence, chr, start, strand, transcript_id, pam="NGG", target_length=20):
+def find_crispr_targets(sequence, chr, start, strand, 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])
+                gRNA = sequence[i - target_length:i]
+                targets.append([target_seq, gRNA, chr, str(tar_start), str(tar_end), str(strand)])
 
     return targets
 
-# 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 process_gene(gene_symbol, model_path):
     transcripts = fetch_ensembl_transcripts(gene_symbol)
-    results = []
+    all_data = []
+    gene_sequence = ''  # Initialize an empty string for the gene sequence
+
     if transcripts:
-        for i in range(len(transcripts)):
-            transcript_id = transcripts[i]['display_name']
-            Exons = transcripts[i]['Exon']
+        for transcript in transcripts:
+            transcript_id = transcript['id']
+            chr = transcript.get('seq_region_name', 'unknown')
+            start = transcript.get('start', 0)
+            strand = transcript.get('strand', 'unknown')
+            # Fetch the sequence here and concatenate if multiple transcripts
+            gene_sequence += fetch_ensembl_sequence(transcript_id) or ''
+
+            # Fetch exon and CDS information
+            exons = fetch_ensembl_exons(transcript_id)
             cds_list = fetch_ensembl_cds(transcript_id)
-            for j in range(len(Exons)):
-                exon_id = Exons[j]['id']
-                gene_sequence = fetch_ensembl_sequence(exon_id)
-                if gene_sequence:
-                    start = Exons[j]['start']
-                    strand = Exons[j]['strand']
-                    chr = Exons[j]['seq_region_name']
-                    targets = find_crispr_targets(gene_sequence, chr, start, strand, transcript_id)
-                    if not targets:
-                        print("No gRNA sites found in the gene sequence.")
-                    else:
-                        # Predict on-target efficiency for each gRNA site
-                        formatted_data = format_prediction_output(targets,model_path)
-                        results.append(formatted_data)
-                        print(f"Appended formatted data: {formatted_data[-1]}")  # Check the last appended item
-                        print(f"Current results length: {len(results)}")
-                else:
-                    print("Failed to retrieve gene sequence.")
+
+            # You might want to do something specific with exons and CDS information here
+            # For example, store them, print them, or include them in your analysis
+
+            if gene_sequence:
+                gRNA_sites = find_crispr_targets(gene_sequence, chr, start, strand)
+                if gRNA_sites:
+                    formatted_data = format_prediction_output(gRNA_sites, model_path)
+                    all_data.extend(formatted_data)
+
+    # Return the data, fetched sequence, and possibly exon/CDS data
+    return all_data, gene_sequence, exons, cds_list
+
+def fetch_ensembl_exons(transcript_id):
+    """Fetch exon information for a given transcript from Ensembl."""
+    url = f"https://rest.ensembl.org/overlap/id/{transcript_id}?feature=exon;content-type=application/json"
+    response = requests.get(url)
+    if response.status_code == 200:
+        return response.json()  # Returns a list of exons for the transcript
     else:
-        print("Failed to retrieve transcripts.")
+        print(f"Error fetching exon data from Ensembl for transcript {transcript_id}: {response.text}")
+        return None
 
-    # Note: Returning last exon's sequence, might need adjustment based on use-case
-    return results, gene_sequence, Exons, cds_list
+def fetch_ensembl_cds(transcript_id):
+    """Fetch coding sequence (CDS) information for a given transcript from Ensembl."""
+    url = f"https://rest.ensembl.org/overlap/id/{transcript_id}?feature=cds;content-type=application/json"
+    response = requests.get(url)
+    if response.status_code == 200:
+        return response.json()  # Returns a list of CDS regions for the transcript
+    else:
+        print(f"Error fetching CDS data from Ensembl for transcript {transcript_id}: {response.text}")
+        return None
 
 def create_genbank_features(formatted_data):
     features = []