debase 0.4.4__tar.gz → 0.5.0__tar.gz

{debase-0.4.4/src/debase.egg-info → debase-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: debase
-Version: 0.4.4
+Version: 0.5.0
 Summary: Enzyme lineage analysis and sequence extraction package
 Home-page: https://github.com/YuemingLong/DEBase
 Author: DEBase Team

{debase-0.4.4 → debase-0.5.0}/src/debase/_version.py

@@ -1,3 +1,3 @@
 """Version information."""
 
-__version__ = "0.4.4"
+__version__ = "0.5.0"

{debase-0.4.4 → debase-0.5.0}/src/debase/cleanup_sequence.py

@@ -30,6 +30,27 @@ except ImportError:  # pragma: no cover
 # === 1. CONFIGURATION & CONSTANTS === ----------------------------------------
 
 VALID_AMINO_ACIDS = set("ACDEFGHIKLMNPQRSTVWY*")  # Include * for stop codons
+VALID_DNA_BASES = set("ACGT")
+
+# Genetic code table for DNA to amino acid translation
+GENETIC_CODE = {
+    'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+    'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+    'TAT': 'Y', 'TAC': 'Y', 'TAA': '*', 'TAG': '*',
+    'TGT': 'C', 'TGC': 'C', 'TGA': '*', 'TGG': 'W',
+    'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+    'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+    'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+    'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+    'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+    'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+    'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+    'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+    'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+    'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+    'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+    'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'
+}
 
 # Gemini API configuration
 GEMINI_API_KEY: str = os.environ.get("GEMINI_API_KEY", "")
@@ -182,6 +203,44 @@ class SequenceManipulator:
         """Validate that a sequence contains only valid amino acids."""
         return all(aa in VALID_AMINO_ACIDS for aa in seq.upper())
     
+    @staticmethod
+    def is_dna_sequence(seq: str) -> bool:
+        """Check if a sequence is DNA (contains only ACGT)."""
+        seq_upper = seq.upper().replace(" ", "").replace("\n", "")
+        return all(base in VALID_DNA_BASES for base in seq_upper) and len(seq_upper) > 0
+    
+    @staticmethod
+    def translate_dna_to_protein(dna_seq: str) -> str:
+        """Translate DNA sequence to protein sequence.
+        
+        Args:
+            dna_seq: DNA sequence string
+            
+        Returns:
+            Protein sequence string
+        """
+        # Clean the DNA sequence
+        dna_seq = dna_seq.upper().replace(" ", "").replace("\n", "")
+        
+        # Check if sequence length is multiple of 3
+        if len(dna_seq) % 3 != 0:
+            log.warning(f"DNA sequence length ({len(dna_seq)}) is not a multiple of 3. Truncating to nearest codon.")
+            dna_seq = dna_seq[:-(len(dna_seq) % 3)]
+        
+        protein_seq = []
+        for i in range(0, len(dna_seq), 3):
+            codon = dna_seq[i:i+3]
+            if len(codon) == 3:
+                # Handle unknown codons (with N or other non-standard bases)
+                if codon in GENETIC_CODE:
+                    protein_seq.append(GENETIC_CODE[codon])
+                else:
+                    # If codon contains non-standard bases, add 'X' for unknown amino acid
+                    protein_seq.append('X')
+                    log.debug(f"Unknown codon '{codon}' at position {i}, using 'X' for unknown amino acid")
+        
+        return ''.join(protein_seq)
+    
     @staticmethod
     def determine_indexing(parent_seq: str, mutations: List[Mutation]) -> int:
         """Determine whether mutations use 0-based or 1-based indexing."""
@@ -1141,6 +1200,9 @@ class SequenceProcessor:
         # Detect and handle column format automatically
         self._normalize_columns()
         
+        # Translate DNA sequences to protein sequences if needed
+        self._translate_dna_sequences()
+        
         log.info(
             f"Loaded {len(self.df)} rows, "
             f"{sum(self.df['protein_sequence'].str.strip() == '')} empty sequences"
@@ -1153,6 +1215,67 @@ class SequenceProcessor:
         # Initialize generator
         self.generator = SequenceGenerator(self.df, strict_mutation_validation=self.strict_mutation_validation)
     
+    def _translate_dna_sequences(self) -> None:
+        """Translate DNA sequences to protein sequences if no amino acid sequences exist."""
+        manipulator = SequenceManipulator()
+        
+        # First check if ANY sequences are amino acid sequences
+        has_amino_acid = False
+        for idx, row in self.df.iterrows():
+            seq = str(row.get("protein_sequence", "")).strip()
+            if seq and seq.lower() not in ["nan", "none", ""]:
+                if not manipulator.is_dna_sequence(seq):
+                    has_amino_acid = True
+                    break
+        
+        # If we found amino acid sequences, don't translate anything
+        if has_amino_acid:
+            log.info("Found amino acid sequences in data, skipping DNA translation")
+            return
+        
+        # No amino acid sequences found, check for DNA sequences in dna_seq column
+        if "dna_seq" in self.df.columns:
+            dna_count = 0
+            for idx, row in self.df.iterrows():
+                protein_seq = str(row.get("protein_sequence", "")).strip()
+                dna_seq = str(row.get("dna_seq", "")).strip()
+                
+                # If protein_sequence is empty but dna_seq has content, translate it
+                if (not protein_seq or protein_seq.lower() in ["nan", "none", ""]) and \
+                   (dna_seq and dna_seq.lower() not in ["nan", "none", ""]):
+                    if manipulator.is_dna_sequence(dna_seq):
+                        # Translate DNA to protein
+                        translated_seq = manipulator.translate_dna_to_protein(dna_seq)
+                        self.df.at[idx, "protein_sequence"] = translated_seq
+                        
+                        # Add flag to indicate this was translated from DNA
+                        if "flag" not in self.df.columns:
+                            self.df["flag"] = ""
+                        existing_flag = str(self.df.at[idx, "flag"]).strip()
+                        self.df.at[idx, "flag"] = f"{existing_flag} dna_translated".strip()
+                        dna_count += 1
+            
+            if dna_count > 0:
+                log.info(f"Translated {dna_count} DNA sequences from dna_seq column to protein sequences")
+        
+        # Also check if DNA sequences are mistakenly in protein_sequence column
+        dna_count = 0
+        for idx, row in self.df.iterrows():
+            seq = str(row.get("protein_sequence", "")).strip()
+            if seq and seq.lower() not in ["nan", "none", ""]:
+                if manipulator.is_dna_sequence(seq):
+                    # Translate DNA to protein
+                    protein_seq = manipulator.translate_dna_to_protein(seq)
+                    self.df.at[idx, "protein_sequence"] = protein_seq
+                    
+                    # Add flag to indicate this was translated from DNA
+                    existing_flag = str(self.df.at[idx, "flag"]).strip()
+                    self.df.at[idx, "flag"] = f"{existing_flag} dna_translated".strip()
+                    dna_count += 1
+        
+        if dna_count > 0:
+            log.info(f"Translated {dna_count} DNA sequences to protein sequences")
+    
     def _normalize_columns(self) -> None:
         """Automatically detect and normalize column names from different formats."""
         # Check if this is enzyme_lineage_extractor format