Make Genes.write_gff use the sequence ID as the ID of each gene (#18)

pyrodigal/_pyrodigal.pxd

@@ -247,6 +247,9 @@ cdef class Gene:
     cdef Genes  owner
     cdef _gene* gene
 
+    cpdef str _gene_data(self, object sequence_id)
+    cpdef str _score_data(self)
+
     cpdef double confidence(self)
     cpdef str sequence(self)
     cpdef str translate(

pyrodigal/_pyrodigal.pyx

@@ -2501,32 +2501,6 @@ cdef class Gene:
 
     # --- Properties ---------------------------------------------------------
 
-    @property
-    def _gene_data(self):
-        cdef size_t node_index = <size_t> (self.gene - &self.owner.genes[0])
-        return "ID={}_{};partial={}{};start_type={};rbs_motif={};rbs_spacer={};gc_cont={:.3f}".format(
-            self.owner._num_seq,
-            node_index + 1,
-            int(self.partial_begin),
-            int(self.partial_end),
-            self.start_type,
-            self.rbs_motif,
-            self.rbs_spacer,
-            self.owner.nodes.nodes[self.gene.start_ndx].gc_cont
-        )
-
-    @property
-    def _score_data(self):
-        return "conf={:.2f};score={:.2f};cscore={:.2f};sscore={:.2f};rscore={:.2f};uscore={:.2f};tscore={:.2f};".format(
-            self.confidence(),
-            self.score,
-            self.cscore,
-            self.sscore,
-            self.rscore,
-            self.uscore,
-            self.tscore,
-        )
-
     @property
     def begin(self):
         """`int`: The coordinate at which the gene begins.
@@ -2715,6 +2689,33 @@ cdef class Gene:
         """
         return self.owner.nodes[self.gene.stop_ndx]
 
+
+    # --- Utils --------------------------------------------------------------
+
+    cpdef str _gene_data(self, object sequence_id):
+        cdef size_t node_index = <size_t> (self.gene - &self.owner.genes[0])
+        return "ID={}_{};partial={}{};start_type={};rbs_motif={};rbs_spacer={};gc_cont={:.3f}".format(
+            sequence_id,
+            node_index + 1,
+            int(self.partial_begin),
+            int(self.partial_end),
+            self.start_type,
+            self.rbs_motif,
+            self.rbs_spacer,
+            self.owner.nodes.nodes[self.gene.start_ndx].gc_cont
+        )
+
+    cpdef str _score_data(self):
+        return "conf={:.2f};score={:.2f};cscore={:.2f};sscore={:.2f};rscore={:.2f};uscore={:.2f};tscore={:.2f};".format(
+            self.confidence(),
+            self.score,
+            self.cscore,
+            self.sscore,
+            self.rscore,
+            self.uscore,
+            self.tscore,
+        )
+
     # --- Python interface ---------------------------------------------------
 
     cpdef double confidence(self):
@@ -3262,9 +3263,9 @@ cdef class Genes:
             n += file.write("\t")
             n += file.write("0")
             n += file.write("\t")
-            n += file.write(gene._gene_data)
+            n += file.write(gene._gene_data(sequence_id))
             n += file.write(";")
-            n += file.write(gene._score_data)
+            n += file.write(gene._score_data())
             n += file.write("\n")
 
         return n
@@ -3305,7 +3306,7 @@ cdef class Genes:
             n += file.write(" # ")
             n += file.write(str(gene.strand))
             n += file.write(" # ")
-            n += file.write(gene._gene_data)
+            n += file.write(gene._gene_data(self._num_seq))
             n += file.write("\n")
             for line in textwrap.wrap(gene.sequence(), width=width):
                 n += file.write(line)
@@ -3355,7 +3356,7 @@ cdef class Genes:
             n += file.write(" # ")
             n += file.write(str(gene.strand))
             n += file.write(" # ")
-            n += file.write(gene._gene_data)
+            n += file.write(gene._gene_data(self._num_seq))
             n += file.write("\n")
             for line in textwrap.wrap(gene.translate(translation_table), width=width):
                 n += file.write(line)

pyrodigal/tests/test_genes.py

@@ -27,19 +27,19 @@ def setUpClass(cls):
 
     def test_indexing(self):
         length = len(self.genes)
-        self.assertEqual(self.genes[0]._gene_data, self.genes[-length]._gene_data)
+        self.assertEqual(self.genes[0]._gene_data(1), self.genes[-length]._gene_data(1))
         with self.assertRaises(IndexError):
             self.genes[length]
         with self.assertRaises(IndexError):
             self.genes[-length - 1]
 
     def test_iter(self):
         for i, gene in zip(range(len(self.genes)), self.genes):
-            self.assertEqual(gene._gene_data, self.genes[i]._gene_data)
+            self.assertEqual(gene._gene_data(1), self.genes[i]._gene_data(1))
 
     def test_reversed(self):
         for i, gene in zip(range(1, len(self.genes) + 1), reversed(self.genes)):
-            self.assertEqual(gene._gene_data, self.genes[-i]._gene_data)
+            self.assertEqual(gene._gene_data(1), self.genes[-i]._gene_data(1))
 
     def test_bool(self):
         self.assertTrue(bool(self.genes))
@@ -94,7 +94,7 @@ def test_write_scores(self):
     def test_pickle(self):
         genes = pickle.loads(pickle.dumps(self.genes))
         for gene1, gene2 in zip(self.genes, genes):
-            self.assertEqual(gene1._gene_data, gene2._gene_data)
+            self.assertEqual(gene1._gene_data(1), gene2._gene_data(1))
 
     def test_write_gff(self):
         buffer = io.StringIO()

pyrodigal/tests/test_orf_finder.py

@@ -86,7 +86,7 @@ def assertGeneDataEqual(self, predictions, proteins):
         self.assertEqual(len(predictions), len(proteins))
         for gene, protein in zip(predictions, proteins):
             *_, gene_data = protein.description.split(" # ")
-            self.assertEqual(gene._gene_data, gene_data.strip())
+            self.assertEqual(gene._gene_data(1), gene_data.strip())
 
     def assertPredictionsEqual(self, predictions, proteins):
         self.assertTranslationsEqual(predictions, proteins)