Spaces:
No application file
No application file
Update app.py
Browse files
app.py
CHANGED
|
@@ -7,7 +7,7 @@ import os
|
|
| 7 |
import re
|
| 8 |
import logging
|
| 9 |
import numpy as np
|
| 10 |
-
from
|
| 11 |
from tensorflow.keras.models import load_model
|
| 12 |
import ml_simplified_tree
|
| 13 |
import tempfile
|
|
@@ -24,7 +24,7 @@ logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(
|
|
| 24 |
|
| 25 |
# --- Paths ---
|
| 26 |
model_repo = "GGproject10/best_boundary_aware_model"
|
| 27 |
-
csv_path = "
|
| 28 |
classifier_model_dir = "model"
|
| 29 |
|
| 30 |
# Get HF token from environment
|
|
@@ -94,8 +94,268 @@ except Exception as e:
|
|
| 94 |
logging.error(f"Failed to initialize tree analyzer: {e}")
|
| 95 |
analyzer = None
|
| 96 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 97 |
# --- Tool Detection and Helper Functions ---
|
| 98 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
|
| 100 |
def read_fasta_file(file_obj):
|
| 101 |
try:
|
|
@@ -119,8 +379,8 @@ def run_pipeline_from_file(fasta_file_obj, similarity_score, build_ml_tree):
|
|
| 119 |
if not dna_input:
|
| 120 |
return "Failed to read FASTA file", "", "", "", "", "", "", "", "", None, None, None, "No input sequence"
|
| 121 |
return enhanced_run_pipeline(
|
| 122 |
-
dna_input, keras_model, kmer_to_index, classifier_model,
|
| 123 |
-
classifier_kmer_to_index, classifier_maxlen, LABELS,
|
| 124 |
similarity_score, build_ml_tree
|
| 125 |
)
|
| 126 |
except Exception as e:
|
|
@@ -192,8 +452,8 @@ def create_interface():
|
|
| 192 |
return run_pipeline_from_file(file_obj, sim_score, build_tree)
|
| 193 |
else:
|
| 194 |
return enhanced_run_pipeline(
|
| 195 |
-
dna_seq, keras_model, kmer_to_index, classifier_model,
|
| 196 |
-
classifier_kmer_to_index, classifier_maxlen, LABELS,
|
| 197 |
sim_score, build_tree
|
| 198 |
)
|
| 199 |
def clear_inputs():
|
|
|
|
| 7 |
import re
|
| 8 |
import logging
|
| 9 |
import numpy as np
|
| 10 |
+
from tensorflow.keras.preprocessing.sequence import pad_sequences
|
| 11 |
from tensorflow.keras.models import load_model
|
| 12 |
import ml_simplified_tree
|
| 13 |
import tempfile
|
|
|
|
| 24 |
|
| 25 |
# --- Paths ---
|
| 26 |
model_repo = "GGproject10/best_boundary_aware_model"
|
| 27 |
+
csv_path = "f_cleaned.csv"
|
| 28 |
classifier_model_dir = "model"
|
| 29 |
|
| 30 |
# Get HF token from environment
|
|
|
|
| 94 |
logging.error(f"Failed to initialize tree analyzer: {e}")
|
| 95 |
analyzer = None
|
| 96 |
|
| 97 |
+
# --- Predictor Functions (from predictor.py) ---
|
| 98 |
+
class GenePredictor:
|
| 99 |
+
"""Minimal implementation to load and use the boundary-aware model"""
|
| 100 |
+
def __init__(self, model_path):
|
| 101 |
+
try:
|
| 102 |
+
self.model = torch.load(model_path, map_location=torch.device('cpu'))
|
| 103 |
+
logging.info(f"Loaded boundary model from {model_path}")
|
| 104 |
+
except Exception as e:
|
| 105 |
+
logging.error(f"Failed to load boundary model: {e}")
|
| 106 |
+
self.model = None
|
| 107 |
+
|
| 108 |
+
def predict(self, sequence):
|
| 109 |
+
if self.model is None:
|
| 110 |
+
return None, None, 0.0
|
| 111 |
+
# Placeholder: Implement actual prediction logic
|
| 112 |
+
return [0] * len(sequence), [0.5] * len(sequence), 0.5
|
| 113 |
+
|
| 114 |
+
def extract_gene_regions(self, predictions, sequence):
|
| 115 |
+
if predictions is None:
|
| 116 |
+
return []
|
| 117 |
+
return [{"sequence": sequence, "start": 0, "end": len(sequence), "confidence": 0.5}]
|
| 118 |
+
|
| 119 |
+
def preprocess_sequence_for_ndv_f_gene(sequence):
|
| 120 |
+
"""Enhanced preprocessing specifically for NDV F gene sequences"""
|
| 121 |
+
try:
|
| 122 |
+
sequence = sequence.upper().strip()
|
| 123 |
+
sequence = re.sub(r'[^ATCGN]', '', sequence)
|
| 124 |
+
if len(sequence) < 1000:
|
| 125 |
+
logging.warning(f"Sequence length ({len(sequence)}) shorter than typical NDV F gene (1662-1800 nt)")
|
| 126 |
+
if not sequence.startswith('ATG'):
|
| 127 |
+
logging.warning("Sequence doesn't start with ATG start codon")
|
| 128 |
+
atg_pos = sequence.find('ATG')
|
| 129 |
+
if atg_pos != -1:
|
| 130 |
+
sequence = sequence[atg_pos:]
|
| 131 |
+
logging.info(f"Found ATG at position {atg_pos}, using sequence from there")
|
| 132 |
+
if len(sequence) % 3 != 0:
|
| 133 |
+
sequence = sequence[:len(sequence) - (len(sequence) % 3)]
|
| 134 |
+
logging.info(f"Trimmed sequence to maintain reading frame: {len(sequence)} nt")
|
| 135 |
+
return sequence
|
| 136 |
+
except Exception as e:
|
| 137 |
+
logging.error(f"Sequence preprocessing failed: {e}")
|
| 138 |
+
return sequence
|
| 139 |
+
|
| 140 |
+
def enhanced_keras_prediction(sequence, keras_model, kmer_to_index, kmer_size=6):
|
| 141 |
+
"""Enhanced Keras prediction with better handling for NDV F gene"""
|
| 142 |
+
try:
|
| 143 |
+
if not keras_model or not kmer_to_index:
|
| 144 |
+
return "Keras model not available"
|
| 145 |
+
processed_seq = preprocess_sequence_for_ndv_f_gene(sequence)
|
| 146 |
+
if len(processed_seq) < kmer_size:
|
| 147 |
+
return f"Sequence too short for k-mer prediction (minimum {kmer_size} nucleotides required)"
|
| 148 |
+
kmers = [processed_seq[i:i+kmer_size] for i in range(len(processed_seq)-kmer_size+1)]
|
| 149 |
+
indices = []
|
| 150 |
+
unknown_kmers = 0
|
| 151 |
+
for kmer in kmers:
|
| 152 |
+
if kmer in kmer_to_index:
|
| 153 |
+
indices.append(kmer_to_index[kmer])
|
| 154 |
+
else:
|
| 155 |
+
indices.append(0)
|
| 156 |
+
unknown_kmers += 1
|
| 157 |
+
logging.info(f"Generated {len(kmers)} k-mers, {unknown_kmers} unknown k-mers")
|
| 158 |
+
input_arr = np.array([indices])
|
| 159 |
+
prediction = keras_model.predict(input_arr, verbose=0)[0]
|
| 160 |
+
max_prob = np.max(prediction)
|
| 161 |
+
mean_prob = np.mean(prediction)
|
| 162 |
+
confidence_score = max_prob
|
| 163 |
+
consistency_score = 1.0 - np.std(prediction)
|
| 164 |
+
result = {
|
| 165 |
+
'raw_prediction': prediction.tolist(),
|
| 166 |
+
'max_probability': float(max_prob),
|
| 167 |
+
'mean_probability': float(mean_prob),
|
| 168 |
+
'confidence_score': float(confidence_score),
|
| 169 |
+
'consistency_score': float(consistency_score),
|
| 170 |
+
'sequence_length': len(processed_seq),
|
| 171 |
+
'kmers_generated': len(kmers),
|
| 172 |
+
'unknown_kmers': unknown_kmers,
|
| 173 |
+
'kmer_coverage': 1.0 - (unknown_kmers / len(kmers)) if kmers else 0.0
|
| 174 |
+
}
|
| 175 |
+
return result
|
| 176 |
+
except Exception as e:
|
| 177 |
+
logging.error(f"Enhanced Keras prediction failed: {e}")
|
| 178 |
+
return f"Enhanced Keras prediction failed: {str(e)}"
|
| 179 |
+
|
| 180 |
+
def enhanced_classify_sequence(sequence, classifier_model, classifier_kmer_to_index, classifier_maxlen, labels):
|
| 181 |
+
"""Enhanced classification with NDV F gene specific improvements"""
|
| 182 |
+
try:
|
| 183 |
+
if not classifier_model or not classifier_kmer_to_index or classifier_maxlen is None:
|
| 184 |
+
return {
|
| 185 |
+
"status": "error",
|
| 186 |
+
"message": "Classification model not available",
|
| 187 |
+
"confidence": None,
|
| 188 |
+
"predicted_label": None,
|
| 189 |
+
"details": {}
|
| 190 |
+
}
|
| 191 |
+
processed_seq = preprocess_sequence_for_ndv_f_gene(sequence)
|
| 192 |
+
if len(processed_seq) < 1000:
|
| 193 |
+
return {
|
| 194 |
+
"status": "warning",
|
| 195 |
+
"message": f"Sequence shorter than typical NDV F gene ({len(processed_seq)} < 1000 nt)",
|
| 196 |
+
"confidence": None,
|
| 197 |
+
"predicted_label": None,
|
| 198 |
+
"details": {"sequence_length": len(processed_seq)}
|
| 199 |
+
}
|
| 200 |
+
kmer_size = 6
|
| 201 |
+
tokens = [processed_seq[i:i+kmer_size] for i in range(len(processed_seq)-kmer_size+1)]
|
| 202 |
+
encoded = []
|
| 203 |
+
unknown_count = 0
|
| 204 |
+
for kmer in tokens:
|
| 205 |
+
if kmer in classifier_kmer_to_index:
|
| 206 |
+
encoded.append(classifier_kmer_to_index[kmer])
|
| 207 |
+
else:
|
| 208 |
+
encoded.append(0)
|
| 209 |
+
unknown_count += 1
|
| 210 |
+
padded = pad_sequences([encoded], maxlen=classifier_maxlen, padding='post')
|
| 211 |
+
pred = classifier_model.predict(padded, verbose=0)
|
| 212 |
+
predicted_class = int(np.argmax(pred))
|
| 213 |
+
confidence = float(np.max(pred))
|
| 214 |
+
predicted_label = labels[predicted_class] if predicted_class < len(labels) else "Unknown"
|
| 215 |
+
kmer_coverage = 1.0 - (unknown_count / len(tokens)) if tokens else 0.0
|
| 216 |
+
prediction_entropy = -np.sum(pred[0] * np.log(pred[0] + 1e-10))
|
| 217 |
+
details = {
|
| 218 |
+
"sequence_length": len(processed_seq),
|
| 219 |
+
"kmers_generated": len(tokens),
|
| 220 |
+
"unknown_kmers": unknown_count,
|
| 221 |
+
"kmer_coverage": kmer_coverage,
|
| 222 |
+
"prediction_entropy": float(prediction_entropy),
|
| 223 |
+
"all_probabilities": {labels[i]: float(pred[0][i]) for i in range(len(labels)) if i < len(pred[0])},
|
| 224 |
+
"starts_with_atg": processed_seq.startswith('ATG'),
|
| 225 |
+
"length_in_frame": len(processed_seq) % 3 == 0
|
| 226 |
+
}
|
| 227 |
+
if predicted_label == "F":
|
| 228 |
+
f_gene_score = confidence
|
| 229 |
+
if kmer_coverage > 0.8: f_gene_score *= 1.1
|
| 230 |
+
if processed_seq.startswith('ATG'): f_gene_score *= 1.05
|
| 231 |
+
if len(processed_seq) % 3 == 0: f_gene_score *= 1.05
|
| 232 |
+
if 1500 <= len(processed_seq) <= 2000: f_gene_score *= 1.1
|
| 233 |
+
details["enhanced_f_score"] = min(f_gene_score, 1.0)
|
| 234 |
+
if f_gene_score > 0.7:
|
| 235 |
+
return {"status": "success", "message": "NDV F gene detected with high confidence", "confidence": confidence, "predicted_label": predicted_label, "details": details}
|
| 236 |
+
elif f_gene_score > 0.5:
|
| 237 |
+
return {"status": "success", "message": "NDV F gene detected with moderate confidence", "confidence": confidence, "predicted_label": predicted_label, "details": details}
|
| 238 |
+
else:
|
| 239 |
+
return {"status": "warning", "message": "Possible F gene but low confidence - check sequence quality", "confidence": confidence, "predicted_label": predicted_label, "details": details}
|
| 240 |
+
elif predicted_label == "Random":
|
| 241 |
+
if kmer_coverage < 0.5:
|
| 242 |
+
return {"status": "error", "message": f"Poor sequence quality detected (coverage: {kmer_coverage:.1%}). Check for sequencing errors.", "confidence": confidence, "predicted_label": predicted_label, "details": details}
|
| 243 |
+
else:
|
| 244 |
+
return {"status": "error", "message": "Sequence does not appear to be NDV F gene. Verify input sequence.", "confidence": confidence, "predicted_label": predicted_label, "details": details}
|
| 245 |
+
else:
|
| 246 |
+
return {"status": "error", "message": f"Detected as {predicted_label} gene, not F gene. Please provide NDV F gene sequence.", "confidence": confidence, "predicted_label": predicted_label, "details": details}
|
| 247 |
+
except Exception as e:
|
| 248 |
+
logging.error(f"Enhanced classification failed: {e}")
|
| 249 |
+
return {"status": "error", "message": f"Classification failed: {str(e)}", "confidence": None, "predicted_label": None, "details": {"error": str(e)}}
|
| 250 |
+
|
| 251 |
+
def validate_ndv_f_gene_sequence(sequence):
|
| 252 |
+
"""Additional validation specific to NDV F gene characteristics"""
|
| 253 |
+
issues = []
|
| 254 |
+
suggestions = []
|
| 255 |
+
if len(sequence) < 1500:
|
| 256 |
+
issues.append(f"Sequence length ({len(sequence)}) shorter than typical NDV F gene (1662-1800 nt)")
|
| 257 |
+
suggestions.append("Verify complete F gene sequence was provided")
|
| 258 |
+
elif len(sequence) > 2000:
|
| 259 |
+
issues.append(f"Sequence length ({len(sequence)}) longer than typical NDV F gene")
|
| 260 |
+
suggestions.append("Check if sequence contains additional regions beyond F gene")
|
| 261 |
+
if not sequence.startswith('ATG'):
|
| 262 |
+
issues.append("Sequence doesn't start with ATG start codon")
|
| 263 |
+
suggestions.append("Ensure sequence starts from the translation start site")
|
| 264 |
+
if len(sequence) % 3 != 0:
|
| 265 |
+
issues.append("Sequence length not divisible by 3 (reading frame issue)")
|
| 266 |
+
suggestions.append("Check for insertions/deletions or trim to proper reading frame")
|
| 267 |
+
if len(sequence) >= 3:
|
| 268 |
+
last_codon = sequence[-3:]
|
| 269 |
+
stop_codons = ['TAA', 'TAG', 'TGA']
|
| 270 |
+
if last_codon not in stop_codons:
|
| 271 |
+
issues.append(f"Sequence doesn't end with stop codon (ends with {last_codon})")
|
| 272 |
+
suggestions.append("Verify complete F gene sequence including stop codon")
|
| 273 |
+
gc_content = (sequence.count('G') + sequence.count('C')) / len(sequence) * 100
|
| 274 |
+
if gc_content < 30 or gc_content > 70:
|
| 275 |
+
issues.append(f"Unusual GC content: {gc_content:.1f}% (typical range: 35-65%)")
|
| 276 |
+
suggestions.append("Verify sequence quality and correct nucleotide composition")
|
| 277 |
+
n_content = sequence.count('N') / len(sequence) * 100
|
| 278 |
+
if n_content > 5:
|
| 279 |
+
issues.append(f"High ambiguous nucleotide content: {n_content:.1f}% N's")
|
| 280 |
+
suggestions.append("Consider resequencing regions with ambiguous nucleotides")
|
| 281 |
+
return issues, suggestions
|
| 282 |
+
|
| 283 |
+
def enhanced_run_pipeline(dna_input, keras_model, kmer_to_index, classifier_model,
|
| 284 |
+
classifier_kmer_to_index, classifier_maxlen, labels,
|
| 285 |
+
similarity_score=95.0, build_ml_tree=False):
|
| 286 |
+
"""Enhanced pipeline with improved F gene prediction"""
|
| 287 |
+
try:
|
| 288 |
+
dna_input = dna_input.upper().strip()
|
| 289 |
+
if not dna_input:
|
| 290 |
+
return "Empty input", "", "", "", "", "", "", "", "", None, None, None, "No input provided"
|
| 291 |
+
if not re.match('^[ACTGN]+$', dna_input):
|
| 292 |
+
dna_input = ''.join(c if c in 'ACTGN' else 'N' for c in dna_input)
|
| 293 |
+
logging.info("DNA sequence sanitized")
|
| 294 |
+
validation_issues, validation_suggestions = validate_ndv_f_gene_sequence(dna_input)
|
| 295 |
+
keras_result = enhanced_keras_prediction(dna_input, keras_model, kmer_to_index)
|
| 296 |
+
if isinstance(keras_result, dict):
|
| 297 |
+
keras_output = f"Prediction confidence: {keras_result['confidence_score']:.3f}\n"
|
| 298 |
+
keras_output += f"K-mer coverage: {keras_result['kmer_coverage']:.1%}\n"
|
| 299 |
+
keras_output += f"Sequence length: {keras_result['sequence_length']} nt"
|
| 300 |
+
if keras_result['kmer_coverage'] < 0.8:
|
| 301 |
+
keras_output += "\n⚠️ Low k-mer coverage - may affect accuracy"
|
| 302 |
+
else:
|
| 303 |
+
keras_output = str(keras_result)
|
| 304 |
+
classifier_result = enhanced_classify_sequence(
|
| 305 |
+
dna_input, classifier_model, classifier_kmer_to_index, classifier_maxlen, labels
|
| 306 |
+
)
|
| 307 |
+
classifier_status = classifier_result["status"]
|
| 308 |
+
classifier_message = classifier_result["message"]
|
| 309 |
+
classifier_label = classifier_result["predicted_label"]
|
| 310 |
+
classifier_confidence = classifier_result["confidence"]
|
| 311 |
+
if validation_issues:
|
| 312 |
+
classifier_message += f"\n\n⚠️ Sequence validation issues:\n" + "\n".join(f"• {issue}" for issue in validation_issues[:3])
|
| 313 |
+
if validation_suggestions:
|
| 314 |
+
classifier_message += f"\n\n💡 Suggestions:\n" + "\n".join(f"• {sug}" for sug in validation_suggestions[:3])
|
| 315 |
+
if classifier_result.get("details"):
|
| 316 |
+
details = classifier_result["details"]
|
| 317 |
+
if "all_probabilities" in details:
|
| 318 |
+
probs = details["all_probabilities"]
|
| 319 |
+
classifier_message += f"\n\nPrediction probabilities:"
|
| 320 |
+
for label, prob in sorted(probs.items(), key=lambda x: x[1], reverse=True)[:3]:
|
| 321 |
+
classifier_message += f"\n• {label}: {prob:.1%}"
|
| 322 |
+
boundary_output = f"Enhanced preprocessing applied. Length: {len(dna_input)} bp"
|
| 323 |
+
if validation_issues:
|
| 324 |
+
boundary_output += f"\n{len(validation_issues)} validation issues detected"
|
| 325 |
+
return (
|
| 326 |
+
boundary_output,
|
| 327 |
+
keras_output,
|
| 328 |
+
classifier_status,
|
| 329 |
+
classifier_message,
|
| 330 |
+
classifier_label or "Unknown",
|
| 331 |
+
f"{classifier_confidence:.3f}" if classifier_confidence else "N/A",
|
| 332 |
+
"ML tree not requested" if not build_ml_tree else "ML tree processing...",
|
| 333 |
+
"Enhanced analysis completed",
|
| 334 |
+
"<p>Enhanced F gene analysis completed</p>",
|
| 335 |
+
None, None, None,
|
| 336 |
+
f"Enhanced pipeline completed. Processed {len(dna_input)} bp sequence."
|
| 337 |
+
)
|
| 338 |
+
except Exception as e:
|
| 339 |
+
error_msg = f"Enhanced pipeline failed: {str(e)}"
|
| 340 |
+
logging.error(error_msg)
|
| 341 |
+
return (
|
| 342 |
+
error_msg, "", "error", error_msg, "Error", "0.000",
|
| 343 |
+
"", "", f"<p>Error: {error_msg}</p>",
|
| 344 |
+
None, None, None, error_msg
|
| 345 |
+
)
|
| 346 |
+
|
| 347 |
# --- Tool Detection and Helper Functions ---
|
| 348 |
+
def check_tool_availability():
|
| 349 |
+
mafft_available = shutil.which(MAFFT_PATH) is not None
|
| 350 |
+
iqtree_available = shutil.which(IQTREE_PATH) is not None
|
| 351 |
+
return mafft_available, iqtree_available, MAFFT_PATH, IQTREE_PATH
|
| 352 |
+
|
| 353 |
+
def install_dependencies_guide():
|
| 354 |
+
return """
|
| 355 |
+
🔧 INSTALLATION GUIDE:
|
| 356 |
+
- MAFFT: `conda install -c bioconda mafft`
|
| 357 |
+
- IQ-TREE: `conda install -c bioconda iqtree`
|
| 358 |
+
"""
|
| 359 |
|
| 360 |
def read_fasta_file(file_obj):
|
| 361 |
try:
|
|
|
|
| 379 |
if not dna_input:
|
| 380 |
return "Failed to read FASTA file", "", "", "", "", "", "", "", "", None, None, None, "No input sequence"
|
| 381 |
return enhanced_run_pipeline(
|
| 382 |
+
dna_input, keras_model, kmer_to_index, classifier_model,
|
| 383 |
+
classifier_kmer_to_index, classifier_maxlen, LABELS,
|
| 384 |
similarity_score, build_ml_tree
|
| 385 |
)
|
| 386 |
except Exception as e:
|
|
|
|
| 452 |
return run_pipeline_from_file(file_obj, sim_score, build_tree)
|
| 453 |
else:
|
| 454 |
return enhanced_run_pipeline(
|
| 455 |
+
dna_seq, keras_model, kmer_to_index, classifier_model,
|
| 456 |
+
classifier_kmer_to_index, classifier_maxlen, LABELS,
|
| 457 |
sim_score, build_tree
|
| 458 |
)
|
| 459 |
def clear_inputs():
|