Merge pull request #24 from YuWei-CH/use-chromosome-name

Use chromosome name

reform.py

@@ -255,7 +255,10 @@ def write_in_gff_lines(gff_out, in_gff_lines, position, split_features, sequence
 	sequence_length: length of the inserted sequence, used to determine 
 		the new end positions in the GFF file.
 	'''
-	# Handling of single-line comments
+  for l in in_gff_lines:
+		# Replace the original chromosome ID from in_gtf with chrom (seq.id)
+		l[0] = chrom
+  # Handling of single-line comments
 	if len(in_gff_lines) == 1:
 		l = in_gff_lines[0]
 		## Check length
@@ -317,7 +320,7 @@ def create_new_gff(new_gff_name, ref_gff, in_gff_lines, position, down_position,
 		columns (in gff format) associated with each new feature to insert
 	position: start position of removal of existing sequence
 	down_position: end position of removal of existing sequence
-	chrom_id: the ID of the chromosome to modify
+	chrom_id: the ID of the chromosome to modify, which is seq.id
 	new_seq_length: the length of the new sequence being added to the chromosome
 	'''
 	with open(new_gff_name, "w") as gff_out:

test_data/14/gold.gtf

@@ -1,10 +1,10 @@
-X	new	exon	5	14	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	5	14	.	+	0	gene_id "first"; transcript_id "new.1";
 X	ref	exon	15	23	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";reform_comment "5 prime side of feature cut-off by inserted sequence";reform_comment "original feature split by inserted sequence, this is the 5 prime end";
 X	ref	CDS	15	23	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";reform_comment "5 prime side of feature cut-off by inserted sequence";reform_comment "original feature split by inserted sequence, this is the 5 prime end";
-X	new	exon	24	33	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	24	33	.	+	0	gene_id "second"; transcript_id "new.2";
 X	ref	exon	34	38	.	+	0	gene _id "ref_gene_split"; transcript_id "ref_gene.1";reform_comment "5 prime side of feature cut-off by inserted sequence";reform_comment "original feature split by inserted sequence, this is the 3 prime end";reform_comment "original feature split by inserted sequence, this is the 5 prime end";
 X	ref	CDS	34	37	.	+	0	gene _id "ref_gene_split"; transcript_id "ref_gene.1";reform_comment "5 prime side of feature cut-off by inserted sequence";reform_comment "original feature split by inserted sequence, this is the 3 prime end";
 X	ref	stop_codon	38	38	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";reform_comment "original feature split by inserted sequence, this is the 5 prime end";
-X	new	exon	39	48	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	39	48	.	+	0	gene_id "third"; transcript_id "new.3";
 X	ref	exon	49	49	.	+	0	gene _id "ref_gene_split"; transcript_id "ref_gene.1";reform_comment "5 prime side of feature cut-off by inserted sequence";reform_comment "original feature split by inserted sequence, this is the 3 prime end";reform_comment "original feature split by inserted sequence, this is the 3 prime end";
 X	ref	stop_codon	49	49	.	+	0	gene _id "ref_gene_split"; transcript_id "ref_gene.1";reform_comment "original feature split by inserted sequence, this is the 3 prime end";

test_data/14/in1.gtf

@@ -1 +1 @@
-X	new	exon	1	10	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	1	10	.	+	0	gene_id "first"; transcript_id "new.1";

test_data/14/in2.gtf

@@ -1 +1 @@
-X	new	exon	1	10	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	1	10	.	+	0	gene_id "second"; transcript_id "new.2";

test_data/14/in3.gtf

@@ -1 +1 @@
-X	new	exon	1	10	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	1	10	.	+	0	gene_id "third"; transcript_id "new.3";

test_data/15/gold.gtf

@@ -1,8 +1,8 @@
-X	new	exon	1	10	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	1	10	.	+	0	gene_id "first"; transcript_id "new.1";
 X	ref	exon	15	15	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";reform_comment "original feature split by inserted sequence, this is the 5 prime end";
-X	new	exon	16	25	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	16	25	.	+	0	gene_id "second"; transcript_id "new.2";
 X	ref	exon	26	45	.	+	0	gene _id "ref_gene_split"; transcript_id "ref_gene.1";reform_comment "original feature split by inserted sequence, this is the 3 prime end";
 X	ref	CDS	28	42	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";
 X	ref	start_codon	15	15	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";reform_comment "original feature split by inserted sequence, this is the 5 prime end";
 X	ref	stop_codon	43	45	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";
-X	new	exon	51	60	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	51	60	.	+	0	gene_id "third"; transcript_id "new.3";

test_data/15/in1.gtf

@@ -1 +1 @@
-X	new	exon	1	10	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	1	10	.	+	0	gene_id "first"; transcript_id "new.1";

test_data/15/in2.gtf

@@ -1 +1 @@
-X	new	exon	1	10	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	1	10	.	+	0	gene_id "second"; transcript_id "new.2";

test_data/15/in3.gtf

@@ -1 +1 @@
-X	new	exon	1	10	.	+	0	gene_id "new"; transcript_id "new.1";
+X	new	exon	1	10	.	+	0	gene_id "third"; transcript_id "new.3";

test_data/16/gold.fa

@@ -0,0 +1,2 @@
+>X
+XZZZABBBBBDDDDDCCCCCIIIIIKKKKK----------

test_data/16/gold.gtf

@@ -0,0 +1,5 @@
+X	ref	exon	5	25	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";
+X	ref	CDS	8	22	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";
+X	ref	start_codon	5	7	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";
+X	ref	stop_codon	23	25	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";
+X	new	exon	31	40	.	+	0	gene_id "new"; transcript_id "new.1";

test_data/16/in.fa

@@ -0,0 +1,2 @@
+>test 1
+----------

test_data/16/in.gtf

@@ -0,0 +1 @@
+I	new	exon	1	10	.	+	0	gene_id "new"; transcript_id "new.1";

test_data/16/ref.fa

@@ -0,0 +1,2 @@
+>X
+XZZZABBBBBDDDDDCCCCCIIIIIKKKKK

test_data/16/ref.gtf

@@ -0,0 +1,4 @@
+X	ref	exon	5	25	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";
+X	ref	CDS	8	22	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";
+X	ref	start_codon	5	7	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";
+X	ref	stop_codon	23	25	.	+	0	gene_id "ref_gene"; transcript_id "ref_gene.1";