gencodegenes 1.0.10__tar.gz → 1.1.1__tar.gz

{gencodegenes-1.0.10/src/gencodegenes.egg-info → gencodegenes-1.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gencodegenes
-Version: 1.0.10
+Version: 1.1.1
 Summary: Package to load genes from GENCODE GTF files
 Home-page: https://github.com/jeremymcrae/gencodegenes
 Author: Jeremy McRae
@@ -29,7 +29,10 @@ pip install gencodegenes
 ```py
 from gencodegenes import Gencode
 
-gencode = Gencode(GTF_PATH)  # or Gencode(GTF, FASTA_PATH) to give transcripts DNA sequence
+gencode = Gencode(GTF_PATH)
+# full function arguments are Gencode(gtf_path, fasta_path=None, coding_only=True)
+#  - fasta_path: pass in path to fasta file to get gene transcripts with sequence
+#  - coding_only: pass in False to include all transcripts, not just protein coding
 
 # get gene by HGNC symbol
 gene = gencode['OR5A1']

{gencodegenes-1.0.10 → gencodegenes-1.1.1}/README.md

@@ -14,7 +14,10 @@ pip install gencodegenes
 ```py
 from gencodegenes import Gencode
 
-gencode = Gencode(GTF_PATH)  # or Gencode(GTF, FASTA_PATH) to give transcripts DNA sequence
+gencode = Gencode(GTF_PATH)
+# full function arguments are Gencode(gtf_path, fasta_path=None, coding_only=True)
+#  - fasta_path: pass in path to fasta file to get gene transcripts with sequence
+#  - coding_only: pass in False to include all transcripts, not just protein coding
 
 # get gene by HGNC symbol
 gene = gencode['OR5A1']

{gencodegenes-1.0.10 → gencodegenes-1.1.1}/setup.py

@@ -112,7 +112,7 @@ setup(name="gencodegenes",
     description='Package to load genes from GENCODE GTF files',
     long_description=io.open('README.md', encoding='utf-8').read(),
     long_description_content_type='text/markdown',
-    version="1.0.10",
+    version="1.1.1",
     author="Jeremy McRae",
     author_email="jeremy.mcrae@gmail.com",
     license="MIT",

{gencodegenes-1.0.10 → gencodegenes-1.1.1}/src/gencodegenes/gencode.cpp

@@ -5755,11 +5755,12 @@ static PyObject *__pyx_f_12gencodegenes_7gencode__open_gencode(PyObject *__pyx_v
   int __pyx_t_4;
   std::string __pyx_t_5;
   bool __pyx_t_6;
-  std::vector<struct gencode::NamedTx> ::iterator __pyx_t_7;
-  struct gencode::NamedTx __pyx_t_8;
-  gencode::Tx __pyx_t_9;
-  PyObject *__pyx_t_10 = NULL;
-  int __pyx_t_11;
+  std::vector<struct gencode::NamedTx>  __pyx_t_7;
+  std::vector<struct gencode::NamedTx> ::iterator __pyx_t_8;
+  struct gencode::NamedTx __pyx_t_9;
+  gencode::Tx __pyx_t_10;
+  PyObject *__pyx_t_11 = NULL;
+  int __pyx_t_12;
   int __pyx_lineno = 0;
   const char *__pyx_filename = NULL;
   int __pyx_clineno = 0;
@@ -5804,7 +5805,13 @@ static PyObject *__pyx_f_12gencodegenes_7gencode__open_gencode(PyObject *__pyx_v
   __pyx_t_5 = __pyx_convert_string_from_py_6libcpp_6string_std__in_string(__pyx_t_1); if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 66, __pyx_L1_error)
   __Pyx_DECREF(__pyx_t_1); __pyx_t_1 = 0;
   __pyx_t_6 = __Pyx_PyObject_IsTrue(__pyx_v_coding_only); if (unlikely((__pyx_t_6 == ((bool)-1)) && PyErr_Occurred())) __PYX_ERR(0, 66, __pyx_L1_error)
-  __pyx_v__transcripts = gencode::open_gencode(__PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_5), __pyx_t_6);
+  try {
+    __pyx_t_7 = gencode::open_gencode(__PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_5), __pyx_t_6);
+  } catch(...) {
+    __Pyx_CppExn2PyErr();
+    __PYX_ERR(0, 66, __pyx_L1_error)
+  }
+  __pyx_v__transcripts = __PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_7);
 
   /* "gencodegenes/gencode.pyx":68
  *     cdef vector[NamedTx] _transcripts = open_gencode(gtf_path.encode('utf8'), coding_only)
@@ -5825,12 +5832,12 @@ static PyObject *__pyx_f_12gencodegenes_7gencode__open_gencode(PyObject *__pyx_v
  *         tx = x.tx
  *         chrom = tx.get_chrom().decode('utf8')
  */
-  __pyx_t_7 = __pyx_v__transcripts.begin();
+  __pyx_t_8 = __pyx_v__transcripts.begin();
   for (;;) {
-    if (!(__pyx_t_7 != __pyx_v__transcripts.end())) break;
-    __pyx_t_8 = *__pyx_t_7;
-    ++__pyx_t_7;
-    __pyx_v_x = __pyx_t_8;
+    if (!(__pyx_t_8 != __pyx_v__transcripts.end())) break;
+    __pyx_t_9 = *__pyx_t_8;
+    ++__pyx_t_8;
+    __pyx_v_x = __pyx_t_9;
 
     /* "gencodegenes/gencode.pyx":70
  *     transcripts = []
@@ -5839,8 +5846,8 @@ static PyObject *__pyx_f_12gencodegenes_7gencode__open_gencode(PyObject *__pyx_v
  *         chrom = tx.get_chrom().decode('utf8')
  *         start = tx.get_start()
  */
-    __pyx_t_9 = __pyx_v_x.tx;
-    __pyx_v_tx = __PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_9);
+    __pyx_t_10 = __pyx_v_x.tx;
+    __pyx_v_tx = __PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_10);
 
     /* "gencodegenes/gencode.pyx":71
  *     for x in _transcripts:
@@ -5948,39 +5955,39 @@ static PyObject *__pyx_f_12gencodegenes_7gencode__open_gencode(PyObject *__pyx_v
     __Pyx_GOTREF(__pyx_t_1);
     __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_end); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 79, __pyx_L1_error)
     __Pyx_GOTREF(__pyx_t_3);
-    __pyx_t_10 = PyTuple_New(8); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 79, __pyx_L1_error)
-    __Pyx_GOTREF(__pyx_t_10);
+    __pyx_t_11 = PyTuple_New(8); if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 79, __pyx_L1_error)
+    __Pyx_GOTREF(__pyx_t_11);
     __Pyx_INCREF(__pyx_v_tx_id);
     __Pyx_GIVEREF(__pyx_v_tx_id);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 0, __pyx_v_tx_id)) __PYX_ERR(0, 79, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 0, __pyx_v_tx_id)) __PYX_ERR(0, 79, __pyx_L1_error);
     __Pyx_INCREF(__pyx_v_chrom);
     __Pyx_GIVEREF(__pyx_v_chrom);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 1, __pyx_v_chrom)) __PYX_ERR(0, 79, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 1, __pyx_v_chrom)) __PYX_ERR(0, 79, __pyx_L1_error);
     __Pyx_GIVEREF(__pyx_t_1);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 2, __pyx_t_1)) __PYX_ERR(0, 79, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 2, __pyx_t_1)) __PYX_ERR(0, 79, __pyx_L1_error);
     __Pyx_GIVEREF(__pyx_t_3);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 3, __pyx_t_3)) __PYX_ERR(0, 79, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 3, __pyx_t_3)) __PYX_ERR(0, 79, __pyx_L1_error);
     __Pyx_INCREF(__pyx_v_strand);
     __Pyx_GIVEREF(__pyx_v_strand);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 4, __pyx_v_strand)) __PYX_ERR(0, 79, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 4, __pyx_v_strand)) __PYX_ERR(0, 79, __pyx_L1_error);
     __Pyx_INCREF(__pyx_v_transcript_type);
     __Pyx_GIVEREF(__pyx_v_transcript_type);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 5, __pyx_v_transcript_type)) __PYX_ERR(0, 79, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 5, __pyx_v_transcript_type)) __PYX_ERR(0, 79, __pyx_L1_error);
     __Pyx_INCREF(__pyx_v_exons);
     __Pyx_GIVEREF(__pyx_v_exons);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 6, __pyx_v_exons)) __PYX_ERR(0, 79, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 6, __pyx_v_exons)) __PYX_ERR(0, 79, __pyx_L1_error);
     __Pyx_INCREF(__pyx_v_cds);
     __Pyx_GIVEREF(__pyx_v_cds);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 7, __pyx_v_cds)) __PYX_ERR(0, 79, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 7, __pyx_v_cds)) __PYX_ERR(0, 79, __pyx_L1_error);
     __pyx_t_1 = 0;
     __pyx_t_3 = 0;
     __pyx_t_3 = __Pyx_PyDict_NewPresized(1); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 79, __pyx_L1_error)
     __Pyx_GOTREF(__pyx_t_3);
     if (PyDict_SetItem(__pyx_t_3, __pyx_n_s_offset, __pyx_int_0) < 0) __PYX_ERR(0, 79, __pyx_L1_error)
-    __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_t_10, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 79, __pyx_L1_error)
+    __pyx_t_1 = __Pyx_PyObject_Call(__pyx_t_2, __pyx_t_11, __pyx_t_3); if (unlikely(!__pyx_t_1)) __PYX_ERR(0, 79, __pyx_L1_error)
     __Pyx_GOTREF(__pyx_t_1);
     __Pyx_DECREF(__pyx_t_2); __pyx_t_2 = 0;
-    __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0;
+    __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0;
     __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
     __Pyx_XDECREF_SET(__pyx_v_transcript, __pyx_t_1);
     __pyx_t_1 = 0;
@@ -5996,19 +6003,19 @@ static PyObject *__pyx_f_12gencodegenes_7gencode__open_gencode(PyObject *__pyx_v
     __Pyx_GOTREF(__pyx_t_1);
     __pyx_t_3 = __Pyx_PyInt_From_int(__pyx_v_x.is_canonical); if (unlikely(!__pyx_t_3)) __PYX_ERR(0, 80, __pyx_L1_error)
     __Pyx_GOTREF(__pyx_t_3);
-    __pyx_t_10 = PyTuple_New(3); if (unlikely(!__pyx_t_10)) __PYX_ERR(0, 80, __pyx_L1_error)
-    __Pyx_GOTREF(__pyx_t_10);
+    __pyx_t_11 = PyTuple_New(3); if (unlikely(!__pyx_t_11)) __PYX_ERR(0, 80, __pyx_L1_error)
+    __Pyx_GOTREF(__pyx_t_11);
     __Pyx_GIVEREF(__pyx_t_1);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 0, __pyx_t_1)) __PYX_ERR(0, 80, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 0, __pyx_t_1)) __PYX_ERR(0, 80, __pyx_L1_error);
     __Pyx_INCREF(__pyx_v_transcript);
     __Pyx_GIVEREF(__pyx_v_transcript);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 1, __pyx_v_transcript)) __PYX_ERR(0, 80, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 1, __pyx_v_transcript)) __PYX_ERR(0, 80, __pyx_L1_error);
     __Pyx_GIVEREF(__pyx_t_3);
-    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_10, 2, __pyx_t_3)) __PYX_ERR(0, 80, __pyx_L1_error);
+    if (__Pyx_PyTuple_SET_ITEM(__pyx_t_11, 2, __pyx_t_3)) __PYX_ERR(0, 80, __pyx_L1_error);
     __pyx_t_1 = 0;
     __pyx_t_3 = 0;
-    __pyx_t_11 = __Pyx_PyList_Append(__pyx_v_transcripts, __pyx_t_10); if (unlikely(__pyx_t_11 == ((int)-1))) __PYX_ERR(0, 80, __pyx_L1_error)
-    __Pyx_DECREF(__pyx_t_10); __pyx_t_10 = 0;
+    __pyx_t_12 = __Pyx_PyList_Append(__pyx_v_transcripts, __pyx_t_11); if (unlikely(__pyx_t_12 == ((int)-1))) __PYX_ERR(0, 80, __pyx_L1_error)
+    __Pyx_DECREF(__pyx_t_11); __pyx_t_11 = 0;
 
     /* "gencodegenes/gencode.pyx":69
  * 
@@ -6044,7 +6051,7 @@ static PyObject *__pyx_f_12gencodegenes_7gencode__open_gencode(PyObject *__pyx_v
   __Pyx_XDECREF(__pyx_t_1);
   __Pyx_XDECREF(__pyx_t_2);
   __Pyx_XDECREF(__pyx_t_3);
-  __Pyx_XDECREF(__pyx_t_10);
+  __Pyx_XDECREF(__pyx_t_11);
   __Pyx_AddTraceback("gencodegenes.gencode._open_gencode", __pyx_clineno, __pyx_lineno, __pyx_filename);
   __pyx_r = 0;
   __pyx_L0:;
@@ -11146,8 +11153,9 @@ static int __pyx_pf_12gencodegenes_7gencode_7Gencode___cinit__(struct __pyx_obj_
   int __pyx_t_8;
   std::string __pyx_t_9;
   bool __pyx_t_10;
-  std::vector<struct gencode::NamedTx> ::iterator __pyx_t_11;
-  struct gencode::NamedTx __pyx_t_12;
+  std::vector<struct gencode::NamedTx>  __pyx_t_11;
+  std::vector<struct gencode::NamedTx> ::iterator __pyx_t_12;
+  struct gencode::NamedTx __pyx_t_13;
   int __pyx_lineno = 0;
   const char *__pyx_filename = NULL;
   int __pyx_clineno = 0;
@@ -11549,7 +11557,13 @@ static int __pyx_pf_12gencodegenes_7gencode_7Gencode___cinit__(struct __pyx_obj_
     __pyx_t_9 = __pyx_convert_string_from_py_6libcpp_6string_std__in_string(__pyx_t_3); if (unlikely(PyErr_Occurred())) __PYX_ERR(0, 349, __pyx_L1_error)
     __Pyx_DECREF(__pyx_t_3); __pyx_t_3 = 0;
     __pyx_t_10 = __Pyx_PyObject_IsTrue(__pyx_v_coding_only); if (unlikely((__pyx_t_10 == ((bool)-1)) && PyErr_Occurred())) __PYX_ERR(0, 349, __pyx_L1_error)
-    __pyx_v_transcripts = gencode::open_gencode(__PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_9), __pyx_t_10);
+    try {
+      __pyx_t_11 = gencode::open_gencode(__PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_9), __pyx_t_10);
+    } catch(...) {
+      __Pyx_CppExn2PyErr();
+      __PYX_ERR(0, 349, __pyx_L1_error)
+    }
+    __pyx_v_transcripts = __PYX_STD_MOVE_IF_SUPPORTED(__pyx_t_11);
 
     /* "gencodegenes/gencode.pyx":350
  *         if gencode is not None:
@@ -11558,12 +11572,12 @@ static int __pyx_pf_12gencodegenes_7gencode_7Gencode___cinit__(struct __pyx_obj_
  *                 symbol = x.symbol.decode('utf8')
  *                 if symbol not in self.genes:
  */
-    __pyx_t_11 = __pyx_v_transcripts.begin();
+    __pyx_t_12 = __pyx_v_transcripts.begin();
     for (;;) {
-      if (!(__pyx_t_11 != __pyx_v_transcripts.end())) break;
-      __pyx_t_12 = *__pyx_t_11;
-      ++__pyx_t_11;
-      __pyx_v_x = __pyx_t_12;
+      if (!(__pyx_t_12 != __pyx_v_transcripts.end())) break;
+      __pyx_t_13 = *__pyx_t_12;
+      ++__pyx_t_12;
+      __pyx_v_x = __pyx_t_13;
 
       /* "gencodegenes/gencode.pyx":351
  *             transcripts = open_gencode(str(gencode).encode('utf8'), coding_only)

{gencodegenes-1.0.10 → gencodegenes-1.1.1}/src/gencodegenes/gencode.pyx

@@ -41,7 +41,7 @@ cdef extern from "gencode.h" namespace "gencode":
         int pos
         string symbol
     
-    vector[NamedTx] open_gencode(string, bool)
+    vector[NamedTx] open_gencode(string, bool) except +
     bool CompFunc(const GenePoint &l, const GenePoint &r)
     vector[string] _in_region(string chrom, int start, int end, 
         map[string, vector[GenePoint]] & starts, map[string, vector[GenePoint]] & ends,

{gencodegenes-1.0.10 → gencodegenes-1.1.1}/src/gencodegenes/tx.cpp

@@ -66,6 +66,10 @@ void Tx::set_exons(std::vector<std::vector<int>> exon_ranges) {
 void Tx::set_cds(std::vector<std::vector<int>> cds_ranges) {
    cds.clear();
    
+   if (cds_ranges.size() == 0) {
+    return;
+   }
+   
    // If the transcript lacks exon coordinates and only has a single CDS
     // region, then if the CDS region fits within the gene range, make a
     // single exon, using the transcript start and end. This prevents issues
@@ -247,6 +251,9 @@ int Tx::closest_exon_num(int pos, std::vector<Region> & group) {
 //
 // @param position integer chromosome position e.g. 10000000
 Region Tx::get_closest_exon(int pos) {
+    if (exons.size() == 0) {
+        throw std::invalid_argument("no exons assigned to this transcript");
+    }
     int idx = closest_exon_num(pos);
     return exons[idx];
 }
@@ -255,6 +262,9 @@ Region Tx::get_closest_exon(int pos) {
 //
 // @param position integer chromosome position e.g. 10000000
 bool Tx::in_coding_region(int pos) {
+    if (cds.size() == 0) {
+        return false;
+    }
     int idx = closest_exon_num(pos, cds);
     Region region = cds[idx];
     return (pos >= region.start) && (pos <= region.end);

{gencodegenes-1.0.10 → gencodegenes-1.1.1/src/gencodegenes.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gencodegenes
-Version: 1.0.10
+Version: 1.1.1
 Summary: Package to load genes from GENCODE GTF files
 Home-page: https://github.com/jeremymcrae/gencodegenes
 Author: Jeremy McRae
@@ -29,7 +29,10 @@ pip install gencodegenes
 ```py
 from gencodegenes import Gencode
 
-gencode = Gencode(GTF_PATH)  # or Gencode(GTF, FASTA_PATH) to give transcripts DNA sequence
+gencode = Gencode(GTF_PATH)
+# full function arguments are Gencode(gtf_path, fasta_path=None, coding_only=True)
+#  - fasta_path: pass in path to fasta file to get gene transcripts with sequence
+#  - coding_only: pass in False to include all transcripts, not just protein coding
 
 # get gene by HGNC symbol
 gene = gencode['OR5A1']

{gencodegenes-1.0.10 → gencodegenes-1.1.1}/src/gtf.cpp

@@ -14,70 +14,91 @@
 
 namespace gencode {
 
-// parse the required firleds from the attributes field
+std::string trim(const std::string &s, const std::string &vals) {
+    size_t start = s.find_first_not_of(vals);
+    if (start == std::string::npos) {
+        return "";
+    }
+    size_t end = s.find_last_not_of(vals);
+    return s.substr(start, (end + 1) - start);
+}
+
+// parse the required fields from the attributes field
 static void get_attributes_fields(GTFLine &info, std::string &line, int offset) {
-    // we could check for each field individually, but since we know the order
-    // of the fields, it's much quicker to just search the remaining substring
-    size_t tx_start = line.find("transcript_id", offset) + 15;
-    size_t tx_end = line.find("\"", tx_start);
+    const std::string tx_id_key = "transcript_id ";
+    const std::string gene_id_key = "gene_id ";
+    const std::string gene_name_key = "gene_name ";
+    std::string type_key = "transcript_type ";
+    const std::string hgnc_id_key = "hgnc_id ";
+
+    size_t tx_start = line.find(tx_id_key, offset) + tx_id_key.size();
+    size_t tx_end = line.find(";", tx_start);
 
-    if (tx_start - 15 == std::string::npos) {
+    if (tx_start - tx_id_key.size() == std::string::npos) {
         // handle if the string was not found
         tx_start = offset;
         tx_end = offset;
     }
 
-    size_t gene_id_start = line.find("gene_id", offset) + 9;
-    size_t gene_id_end = line.find("\"", gene_id_start);
-    if (gene_id_start - 9 == std::string::npos) {
+    size_t gene_id_start = line.find(gene_id_key, offset) + gene_id_key.size();
+    size_t gene_id_end = line.find(";", gene_id_start);
+    if (gene_id_start - gene_id_key.size() == std::string::npos) {
         // handle if the string was not found
         gene_id_start = offset;
         gene_id_end = offset;
     }
     
+    size_t gene_start = line.find(gene_name_key, offset) + gene_name_key.size();
+    size_t gene_end = line.find(";", gene_start);
 
-    size_t gene_start = line.find("gene_name", tx_end) + 11;
-    size_t gene_end = line.find("\"", gene_start);
-
-    if (gene_start - 11 == std::string::npos) {
+    if (gene_start - gene_name_key.size() == std::string::npos) {
         // handle if the string was not found
         gene_start = tx_end;
         gene_end = tx_end;
     }
 
-    size_t type_start = line.find("transcript_type", gene_end) + 17;
-    size_t type_end = line.find("\"", type_start);
+    size_t type_start = line.find(type_key, offset) + type_key.size();
+    if (type_start - type_key.size() == std::string::npos) {
+        // allow for alternate transcript_type key, as found in non-gencode GTF files 
+        type_key = "transcript_biotype ";
+        type_start = line.find(type_key, offset) + type_key.size();
+    }
+    size_t type_end = line.find(";", type_start);
 
-    if (type_start - 17 == std::string::npos) {
+    if (type_start - type_key.size() == std::string::npos) {
         // handle if the string was not found
         type_start = gene_end;
         type_end = gene_end;
     }
 
-    size_t hgnc_id_start = line.find("hgnc_id", type_end) + 9;
-    size_t hgnc_id_end = line.find("\"", hgnc_id_start);
-    if (hgnc_id_start - 9 == std::string::npos) {
+    size_t hgnc_id_start = line.find(hgnc_id_key, offset) + hgnc_id_key.size();
+    size_t hgnc_id_end = line.find(";", hgnc_id_start);
+    if (hgnc_id_start - hgnc_id_key.size() == std::string::npos) {
         // handle if the string was not found
         hgnc_id_start = offset;
         hgnc_id_end = offset;
     }
     
-    info.symbol = line.substr(gene_start, gene_end - gene_start);
-    info.tx_id = line.substr(tx_start, tx_end - tx_start);
-    info.transcript_type = line.substr(type_start, type_end - type_start);
+    info.symbol = trim(line.substr(gene_start, gene_end - gene_start), " \"");
+    info.tx_id = trim(line.substr(tx_start, tx_end - tx_start), " \"");
+    info.transcript_type = trim(line.substr(type_start, type_end - type_start), " \"");
     
     if (gene_id_start != gene_id_end) {
-        info.alternate_ids.push_back(line.substr(gene_id_start, gene_id_end - gene_id_start));
+        std::string gene_id = trim(line.substr(gene_id_start, gene_id_end - gene_id_start), " \"");
+        if (info.symbol.size() == 0) {
+            info.symbol = gene_id;
+        } else {
+            info.alternate_ids.push_back(gene_id);
+        }
     }
     if (hgnc_id_start != hgnc_id_end) {
-        info.alternate_ids.push_back(line.substr(hgnc_id_start, hgnc_id_end - hgnc_id_start));
+        info.alternate_ids.push_back(trim(line.substr(hgnc_id_start, hgnc_id_end - hgnc_id_start), " \""));
     }
     
-    info.is_canonical = 0;
     if (info.feature == "transcript") {
-        if (line.find("appris_principal", type_end) != std::string::npos) {
+        if (line.find("appris_principal", offset) != std::string::npos) {
             info.is_canonical = 5;
-        } else if (line.find("Ensembl_canonical", type_end) != std::string::npos) {
+        } else if (line.find("Ensembl_canonical", offset) != std::string::npos) {
             info.is_canonical = 10;
         }
     }
@@ -96,7 +117,7 @@ GTFLine parse_gtfline(std::string & line) {
     // tab along the line, then extract the substring to get the required fields.
     // getline() with tab delimiter was 2X slower.
     int chr_idx = 0;
-    int source_idx = line.find("\t", chr_idx + 4);
+    int source_idx = line.find("\t", chr_idx);
     int feature_idx = line.find("\t", source_idx + 6);
     int start_idx = line.find("\t", feature_idx + 3);
     int end_idx = line.find("\t", start_idx + 2);

{gencodegenes-1.0.10 → gencodegenes-1.1.1}/src/gtf.h

@@ -21,7 +21,7 @@ struct GTFLine {
     std::vector<std::string> alternate_ids;
     std::string tx_id;
     std::string transcript_type;
-    int is_canonical;
+    int is_canonical = 0;
 };
 
 GTFLine parse_gtfline(std::string &line);

{gencodegenes-1.0.10 → gencodegenes-1.1.1}/src/tx.cpp

@@ -66,6 +66,10 @@ void Tx::set_exons(std::vector<std::vector<int>> exon_ranges) {
 void Tx::set_cds(std::vector<std::vector<int>> cds_ranges) {
    cds.clear();
    
+   if (cds_ranges.size() == 0) {
+    return;
+   }
+   
    // If the transcript lacks exon coordinates and only has a single CDS
     // region, then if the CDS region fits within the gene range, make a
     // single exon, using the transcript start and end. This prevents issues
@@ -247,6 +251,9 @@ int Tx::closest_exon_num(int pos, std::vector<Region> & group) {
 //
 // @param position integer chromosome position e.g. 10000000
 Region Tx::get_closest_exon(int pos) {
+    if (exons.size() == 0) {
+        throw std::invalid_argument("no exons assigned to this transcript");
+    }
     int idx = closest_exon_num(pos);
     return exons[idx];
 }
@@ -255,6 +262,9 @@ Region Tx::get_closest_exon(int pos) {
 //
 // @param position integer chromosome position e.g. 10000000
 bool Tx::in_coding_region(int pos) {
+    if (cds.size() == 0) {
+        return false;
+    }
     int idx = closest_exon_num(pos, cds);
     Region region = cds[idx];
     return (pos >= region.start) && (pos <= region.end);

{gencodegenes-1.0.10 → gencodegenes-1.1.1}/tests/test_gencode.py

@@ -55,12 +55,12 @@ class TestGencode(unittest.TestCase):
         lines = '##format: gtf\n' \
                 'chr1\tHAVANA\tgene\t10\t20\t.\t-\t.\tgene_name "TEST1";\n' \
                 'chr1\tHAVANA\ttranscript\t10\t20\t.\t-\t.\ttranscript_id "ENST_A";gene_name "TEST1"; transcript_type "protein_coding"; tag "appris_principal_1";\n' \
-                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST1"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST1"; transcript_type "protein_coding"\n' \
+                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST1"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST1"; transcript_type "protein_coding;"\n' \
                 'chr1\tHAVANA\tgene\t100\t110\t.\t-\t.\tgene_name "TEST2";\n' \
                 'chr1\tHAVANA\ttranscript\t100\t110\t.\t-\t.\ttranscript_id "ENST_B";gene_name "TEST2"; transcript_type "protein_coding"; tag "appris_principal_1";\n' \
-                'chr1\tHAVANA\texon\t100\t110\t.\t-\t.\ttranscript_id "ENST_B" gene_name "TEST2"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\tCDS\t105\t110\t.\t-\t.\ttranscript_id "ENST_B" gene_name "TEST2"; transcript_type "protein_coding"\n'\
+                'chr1\tHAVANA\texon\t100\t110\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST2"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\tCDS\t105\t110\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST2"; transcript_type "protein_coding;"\n'\
                 'chr2\tHAVANA\tgene\t100\t110\t.\t-\t.\tgene_name "TEST3";\n' \
                 'chr2\tHAVANA\ttranscript\t100\t110\t.\t-\t.\ttranscript_id "ENST_C";gene_name "TEST3"; transcript_type "protein_coding"; tag "appris_principal_1";\n' \
                 'chr2\tHAVANA\texon\t100\t110\t.\t-\t.\ttranscript_id "ENST_C" gene_name "TEST3"; transcript_type "protein_coding"\n' \
@@ -112,16 +112,16 @@ class TestGencode(unittest.TestCase):
         lines = ['##format: gtf\n',
                 'chr1\tHAVANA\tgene\t10\t20\t.\t-\t.\tgene_name "TEST1";\n',
                 'chr1\tHAVANA\ttranscript\t10\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST1"; transcript_type "protein_coding"; tag "appris_principal_1";\n',
-                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST1"; transcript_type "protein_coding"\n',
-                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST1"; transcript_type "protein_coding"\n',
+                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST1"; transcript_type "protein_coding;"\n',
+                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST1"; transcript_type "protein_coding;"\n',
                 'chr1\tHAVANA\tgene\t100\t110\t.\t-\t.\tgene_name "TEST2";\n',
                 'chr1\tHAVANA\ttranscript\t100\t110\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST2"; transcript_type "protein_coding"; tag "appris_principal_1";\n',
-                'chr1\tHAVANA\texon\t100\t110\t.\t-\t.\ttranscript_id "ENST_B" gene_name "TEST2"; transcript_type "protein_coding"\n',
-                'chr1\tHAVANA\tCDS\t105\t110\t.\t-\t.\ttranscript_id "ENST_B" gene_name "TEST2"; transcript_type "protein_coding"\n',
+                'chr1\tHAVANA\texon\t100\t110\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST2"; transcript_type "protein_coding;"\n',
+                'chr1\tHAVANA\tCDS\t105\t110\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST2"; transcript_type "protein_coding;"\n',
                 'chr2\tHAVANA\tgene\t100\t110\t.\t-\t.\tgene_name "TEST3";\n',
                 'chr2\tHAVANA\ttranscript\t100\t110\t.\t-\t.\ttranscript_id "ENST_C"; gene_name "TEST3"; transcript_type "protein_coding"; tag "appris_principal_1";\n',
-                'chr2\tHAVANA\texon\t100\t110\t.\t-\t.\ttranscript_id "ENST_C" gene_name "TEST3"; transcript_type "protein_coding"\n',
-                'chr2\tHAVANA\tCDS\t105\t110\t.\t-\t.\ttranscript_id "ENST_C" gene_name "TEST3"; transcript_type "protein_coding"\n']
+                'chr2\tHAVANA\texon\t100\t110\t.\t-\t.\ttranscript_id "ENST_C"; gene_name "TEST3"; transcript_type "protein_coding;"\n',
+                'chr2\tHAVANA\tCDS\t105\t110\t.\t-\t.\ttranscript_id "ENST_C"; gene_name "TEST3"; transcript_type "protein_coding;"\n']
         
         write_gtf(self.temp_gtf_path, lines)
         make_fasta(self.temp_fasta_path, ['chr1', 'chr2'])
@@ -150,12 +150,12 @@ class TestGencode(unittest.TestCase):
         lines = ['##format: gtf\n',
                 'chr1\tHAVANA\tgene\t20\t30\t.\t-\t.\tgene_name "TEST1";\n',
                 'chr1\tHAVANA\ttranscript\t20\t30\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST1"; transcript_type "protein_coding"; tag "appris_principal_1";\n',
-                'chr1\tHAVANA\texon\t20\t30\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST1"; transcript_type "protein_coding"\n',
-                'chr1\tHAVANA\tCDS\t25\t30\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST1"; transcript_type "protein_coding"\n',
+                'chr1\tHAVANA\texon\t20\t30\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST1"; transcript_type "protein_coding;"\n',
+                'chr1\tHAVANA\tCDS\t25\t30\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST1"; transcript_type "protein_coding;"\n',
                 'chr1\tHAVANA\tgene\t100\t110\t.\t-\t.\tgene_name "TEST1";\n',
                 'chr1\tHAVANA\ttranscript\t100\t110\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST1"; transcript_type "protein_coding";\n',
-                'chr1\tHAVANA\texon\t100\t110\t.\t-\t.\ttranscript_id "ENST_B" gene_name "TEST1"; transcript_type "protein_coding"\n',
-                'chr1\tHAVANA\tCDS\t110\t100\t.\t-\t.\ttranscript_id "ENST_B" gene_name "TEST1"; transcript_type "protein_coding"\n',
+                'chr1\tHAVANA\texon\t100\t110\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST1"; transcript_type "protein_coding;"\n',
+                'chr1\tHAVANA\tCDS\t110\t100\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST1"; transcript_type "protein_coding;"\n',
         ]
         
         write_gtf(self.temp_gtf_path, lines)
@@ -231,7 +231,7 @@ class TestGencode(unittest.TestCase):
             'gene_status "KNOWN"; gene_name "OR4F5"; transcript_type "protein_coding"; ' \
             'transcript_status "KNOWN"; transcript_name "OR4F5-001"; level 2; ' \
             'protein_id "ENSP00000334393.3"; tag "basic"; transcript_support_level "NA"; ' \
-            'hgnc_id "HGNC:14825", tag "appris_principal_1"; tag "CCDS"; ccdsid "CCDS30547.1"; ' \
+            'hgnc_id "HGNC:14825"; tag "appris_principal_1"; tag "CCDS"; ccdsid "CCDS30547.1"; ' \
             'havana_gene "OTTHUMG00000001094.2"; havana_transcript "OTTHUMT00000003223.2";\n'
         obj = _parse_gtfline(line.encode('utf8'))
         expected = {'chrom': b'chr1', 
@@ -251,7 +251,7 @@ class TestGencode(unittest.TestCase):
         line = 'chr1\tHAVANA\ttranscript\t69091\t70008\t.\t+\t.\t '\
             'transcript_id "ENST00000335137.3"; gene_type "protein_coding"; ' \
             'gene_status "KNOWN"; gene_name "OR4F5"; transcript_type "protein_coding";' \
-            'hgnc_id "HGNC:14825", tag "appris_principal_1"; tag "CCDS"; ccdsid "CCDS30547.1"; '
+            'hgnc_id "HGNC:14825"; tag "appris_principal_1"; tag "CCDS"; ccdsid "CCDS30547.1"; '
         obj = _parse_gtfline(line.encode('utf8'))
         expected = {'chrom': b'chr1', 
             'feature': b'transcript', 
@@ -431,12 +431,12 @@ class TestGencode(unittest.TestCase):
         lines = '##format: gtf\n' \
                 'chr1\tHAVANA\tgene\t10\t20\t.\t-\t.\tgene_name "TEST1";\n' \
                 'chr1\tHAVANA\ttranscript\t10\t20\t.\t-\t.\ttranscript_id "ENST_A";gene_name "TEST1"; transcript_type "protein_coding"; tag "appris_principal_1";\n' \
-                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST1"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST1"; transcript_type "protein_coding"\n' \
+                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST1"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST1"; transcript_type "protein_coding;"\n' \
                 'chr1\tHAVANA\tgene\t10\t30\t.\t-\t.\tgene_name "TEST2";\n' \
                 'chr1\tHAVANA\ttranscript\t10\t30\t.\t-\t.\ttranscript_id "ENST_B";gene_name "TEST2"; transcript_type "protein_coding"; tag "appris_principal_1";\n' \
-                'chr1\tHAVANA\texon\t10\t30\t.\t-\t.\ttranscript_id "ENST_B" gene_name "TEST2"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\tCDS\t15\t30\t.\t-\t.\ttranscript_id "ENST_B" gene_name "TEST2"; transcript_type "protein_coding"\n'
+                'chr1\tHAVANA\texon\t10\t30\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST2"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\tCDS\t15\t30\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST2"; transcript_type "protein_coding;"\n'
         
         write_gtf(self.temp_gtf_path, lines)
         data = _open_gencode(self.temp_gtf_path)
@@ -452,8 +452,8 @@ class TestGencode(unittest.TestCase):
         lines = '##format: gtf\n' \
                 'chr1\tHAVANA\tgene\t10\t20\t.\t-\t.\tgene_name "TEST";\n' \
                 'chr1\tHAVANA\ttranscript\t10\t20\t.\t-\t.\ttranscript_id "ENST_A";gene_name "TEST"; transcript_type "processed_transcript"; tag "appris_principal_1";\n' \
-                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "processed_transcript"\n' \
-                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "processed_transcript"\n' \
+                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "processed_transcript;"\n' \
+                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "processed_transcript;"\n' \
                         
         write_gtf(self.temp_gtf_path, lines)
         data = _open_gencode(self.temp_gtf_path)
@@ -472,12 +472,12 @@ class TestGencode(unittest.TestCase):
         lines = '##format: gtf\n' \
                 'chr1\tHAVANA\tgene\t10\t20\t.\t-\t.\tgene_name "TEST";\n' \
                 'chr1\tHAVANA\ttranscript\t10\t20\t.\t-\t.\ttranscript_id "ENST_A";gene_name "TEST"; transcript_type "protein_coding"; tag "appris_principal_1";\n' \
-                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "protein_coding"\n' \
+                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "protein_coding;"\n' \
                 'chr1\tHAVANA\tgene\t10\t30\t.\t-\t.\tgene_name "TEST";\n' \
                 'chr1\tHAVANA\ttranscript\t10\t30\t.\t-\t.\ttranscript_id "ENST_B";gene_name "TEST"; transcript_type "protein_coding"; tag "appris_principal_1";\n' \
-                'chr1\tHAVANA\texon\t10\t30\t.\t-\t.\ttranscript_id "ENST_B" gene_name "TEST"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\tCDS\t15\t30\t.\t-\t.\ttranscript_id "ENST_B" gene_name "TEST"; transcript_type "protein_coding"\n'
+                'chr1\tHAVANA\texon\t10\t30\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\tCDS\t15\t30\t.\t-\t.\ttranscript_id "ENST_B"; gene_name "TEST"; transcript_type "protein_coding;"\n'
         
         write_gtf(self.temp_gtf_path, lines)
         data = _open_gencode(self.temp_gtf_path)
@@ -497,13 +497,38 @@ class TestGencode(unittest.TestCase):
         lines = '##format: gtf\n' \
                 'chr1\tHAVANA\tgene\t10\t100\t.\t-\t.\tgene_name "TEST";\n' \
                 'chr1\tHAVANA\ttranscript\t10\t100\t.\t-\t.\ttranscript_id "ENST_A";gene_name "TEST"; transcript_type "protein_coding"; tag "appris_principal_1";\n' \
-                'chr1\tHAVANA\tUTR\t10\t15\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "protein_coding";\n' \
-                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\texon\t30\t40\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\tCDS\t30\t40\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\texon\t90\t100\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "protein_coding"\n' \
-                'chr1\tHAVANA\tUTR\t90\t100\t.\t-\t.\ttranscript_id "ENST_A" gene_name "TEST"; transcript_type "protein_coding"\n'
+                'chr1\tHAVANA\tUTR\t10\t15\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "protein_coding";\n' \
+                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\texon\t30\t40\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\tCDS\t30\t40\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\texon\t90\t100\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "protein_coding;"\n' \
+                'chr1\tHAVANA\tUTR\t90\t100\t.\t-\t.\ttranscript_id "ENST_A"; gene_name "TEST"; transcript_type "protein_coding;"\n'
+        
+        write_gtf(self.temp_gtf_path, lines)
+        data = _open_gencode(self.temp_gtf_path)
+        
+        self.assertEqual(len(data), 1)
+        symbol, tx, is_principal = data[0]
+        self.assertEqual(symbol, 'TEST')
+        self.assertEqual(tx.name, 'ENST_A')
+        self.assertEqual(tx.strand, '-')
+        self.assertEqual(tx.exons, [{'start': 10, 'end': 20}, {'start': 30, 'end': 40}, {'start': 90, 'end': 100}])
+        self.assertEqual(tx.cds, [{'start': 15, 'end': 20}, {'start': 30, 'end': 40}])
+    
+    def test__open_gencode_unquoted(self):
+        '''test we can parse a GTF without quoted attributes
+        '''
+        lines = '##format: gtf\n' \
+                'chr1\tHAVANA\tgene\t10\t100\t.\t-\t.\tgene_name "TEST";\n' \
+                'chr1\tHAVANA\ttranscript\t10\t100\t.\t-\t.\ttranscript_id ENST_A;gene_name TEST; transcript_type protein_coding; tag appris_principal_1;\n' \
+                'chr1\tHAVANA\tUTR\t10\t15\t.\t-\t.\ttranscript_id ENST_A; gene_name TEST; transcript_type protein_coding;\n' \
+                'chr1\tHAVANA\texon\t10\t20\t.\t-\t.\ttranscript_id ENST_A; gene_name TEST; transcript_type protein_coding;\n' \
+                'chr1\tHAVANA\tCDS\t15\t20\t.\t-\t.\ttranscript_id ENST_A; gene_name TEST; transcript_type protein_coding;\n' \
+                'chr1\tHAVANA\texon\t30\t40\t.\t-\t.\ttranscript_id ENST_A; gene_name TEST; transcript_type protein_coding;\n' \
+                'chr1\tHAVANA\tCDS\t30\t40\t.\t-\t.\ttranscript_id ENST_A; gene_name TEST; transcript_type protein_coding;\n' \
+                'chr1\tHAVANA\texon\t90\t100\t.\t-\t.\ttranscript_id ENST_A; gene_name TEST; transcript_type protein_coding;\n' \
+                'chr1\tHAVANA\tUTR\t90\t100\t.\t-\t.\ttranscript_id ENST_A; gene_name TEST; transcript_type protein_coding;\n'
         
         write_gtf(self.temp_gtf_path, lines)
         data = _open_gencode(self.temp_gtf_path)