feat: adds transcript structure generator

tests/resources/test_transcript_structure/RP1_RIK.gtf

+1	ensembl_havana	gene	3999557	4409241	.	-	.	gene_id "ENSMUSG00000025900"; gene_version "12"; gene_name "Rp1"; gene_source "ensembl_havana"; gene_biotype "protein_coding";
+1	havana	transcript	4290846	4409241	.	-	.	gene_id "ENSMUSG00000025900"; gene_version "12"; transcript_id "ENSMUST00000208793"; transcript_version "1"; gene_name "Rp1"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "Rp1-204"; transcript_source "havana"; transcript_biotype "retained_intron"; transcript_support_level "1";
+1	havana	exon	4409170	4409241	.	-	.	gene_id "ENSMUSG00000025900"; gene_version "12"; transcript_id "ENSMUST00000208793"; transcript_version "1"; exon_number "1"; gene_name "Rp1"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "Rp1-204"; transcript_source "havana"; transcript_biotype "retained_intron"; exon_id "ENSMUSE00001379779"; exon_version "1"; transcript_support_level "1";
+1	havana	exon	4352202	4352837	.	-	.	gene_id "ENSMUSG00000025900"; gene_version "12"; transcript_id "ENSMUST00000208793"; transcript_version "1"; exon_number "2"; gene_name "Rp1"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "Rp1-204"; transcript_source "havana"; transcript_biotype "retained_intron"; exon_id "ENSMUSE00001377400"; exon_version "1"; transcript_support_level "1";
+1	havana	exon	4351910	4352081	.	-	.	gene_id "ENSMUSG00000025900"; gene_version "12"; transcript_id "ENSMUST00000208793"; transcript_version "1"; exon_number "3"; gene_name "Rp1"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "Rp1-204"; transcript_source "havana"; transcript_biotype "retained_intron"; exon_id "ENSMUSE00001380148"; exon_version "1"; transcript_support_level "1";
+1	havana	exon	4290846	4293012	.	-	.	gene_id "ENSMUSG00000025900"; gene_version "12"; transcript_id "ENSMUST00000208793"; transcript_version "1"; exon_number "4"; gene_name "Rp1"; gene_source "ensembl_havana"; gene_biotype "protein_coding"; transcript_name "Rp1-204"; transcript_source "havana"; transcript_biotype "retained_intron"; exon_id "ENSMUSE00001345123"; exon_version "1"; transcript_support_level "1";
+1	havana	gene	9747648	9791924	.	+	.	gene_id "ENSMUSG00000097893"; gene_version "8"; gene_name "1700034P13Rik"; gene_source "havana"; gene_biotype "lncRNA";
+1	havana	transcript	9747648	9791922	.	+	.	gene_id "ENSMUSG00000097893"; gene_version "8"; transcript_id "ENSMUST00000181821"; transcript_version "7"; gene_name "1700034P13Rik"; gene_source "havana"; gene_biotype "lncRNA"; transcript_name "1700034P13Rik-202"; transcript_source "havana"; transcript_biotype "lncRNA"; transcript_support_level "1";
+1	havana	exon	9747648	9748604	.	+	.	gene_id "ENSMUSG00000097893"; gene_version "8"; transcript_id "ENSMUST00000181821"; transcript_version "7"; exon_number "1"; gene_name "1700034P13Rik"; gene_source "havana"; gene_biotype "lncRNA"; transcript_name "1700034P13Rik-202"; transcript_source "havana"; transcript_biotype "lncRNA"; exon_id "ENSMUSE00001104564"; exon_version "1"; transcript_support_level "1";
+1	havana	exon	9752449	9752564	.	+	.	gene_id "ENSMUSG00000097893"; gene_version "8"; transcript_id "ENSMUST00000181821"; transcript_version "7"; exon_number "2"; gene_name "1700034P13Rik"; gene_source "havana"; gene_biotype "lncRNA"; transcript_name "1700034P13Rik-202"; transcript_source "havana"; transcript_biotype "lncRNA"; exon_id "ENSMUSE00001144804"; exon_version "1"; transcript_support_level "1";
+1	havana	exon	9789656	9789780	.	+	.	gene_id "ENSMUSG00000097893"; gene_version "8"; transcript_id "ENSMUST00000181821"; transcript_version "7"; exon_number "3"; gene_name "1700034P13Rik"; gene_source "havana"; gene_biotype "lncRNA"; transcript_name "1700034P13Rik-202"; transcript_source "havana"; transcript_biotype "lncRNA"; exon_id "ENSMUSE00001175967"; exon_version "1"; transcript_support_level "1";
+1	havana	exon	9791125	9791922	.	+	.	gene_id "ENSMUSG00000097893"; gene_version "8"; transcript_id "ENSMUST00000181821"; transcript_version "7"; exon_number "4"; gene_name "1700034P13Rik"; gene_source "havana"; gene_biotype "lncRNA"; transcript_name "1700034P13Rik-202"; transcript_source "havana"; transcript_biotype "lncRNA"; exon_id "ENSMUSE00001174858"; exon_version "1"; transcript_support_level "1";
\ No newline at end of file

tests/resources/test_transcript_structure/Rik_5_Rp1_5_no_title.csv

+1700034P13Rik,5
+Rp1,5
\ No newline at end of file

tests/resources/test_transcript_structure/Rik_5_Rp1_5_title.csv

+GeneID,count
+1700034P13Rik,5
+Rp1,5
\ No newline at end of file

tests/test_transcript_structure.py

+import pytest
+from transcript_structure import Generate_transcript_structure as Gts
+
+TEST_CSV_TITLE = './tests/resources/test_transcript_structure/Rik_5_Rp1_5_title.csv'
+TEST_CSV_NO_TITLE = './tests/resources/test_transcript_structure/Rik_5_Rp1_5_no_title.csv'
+
+GENE_COORDS = './tests/resources/RP1_RIK.gtf'
+GENE_KEYS = ['Rp1', '1700034P13Rik']
+
+P_INTRON_0: float = 0
+P_INTRON_0_2 = 0.2
+P_INTRON_1: float = 1
+
+
+@pytest.mark.parametrize(
+        "test_input",
+        [(TEST_CSV_TITLE, GENE_COORDS, P_INTRON_0),
+         (TEST_CSV_NO_TITLE, GENE_COORDS, P_INTRON_0)
+         ],
+)
+def test_csv_2_dict(test_input):
+    builder = Gts.BuildTranscriptStructure(test_input[0], test_input[1], test_input[2])
+    builder.csv_2_dict()
+    with open(TEST_CSV_TITLE) as csv:
+        csv_lines = csv.readlines()
+    first_line = csv_lines[0].split(',')
+    if not first_line[1].isnumeric():
+        del(csv_lines[0])  # Removes title.
+    csv_lines[-1] = ''.join([csv_lines[-1], '\n'])  # Adds \n to last line of csv.
+
+    keys = list(builder.gene_count_dict.keys())
+    for index, line in enumerate(csv_lines):
+        dic_line = ''.join([keys[index], ',', str(builder.gene_count_dict[keys[index]]), '\n'])
+        assert line == dic_line
+
+
+def test_gtf_2_dict():
+    builder = Gts.BuildTranscriptStructure(TEST_CSV_TITLE, GENE_COORDS, P_INTRON_0)
+    builder.gtf_2_dict()
+    assert len(builder.gene_sequences_dict) == 2  # Two genes read in the dictionary.
+    assert len(builder.gene_sequences_dict[GENE_KEYS[0]]) == 5
+    assert len(builder.gene_sequences_dict[GENE_KEYS[1]]) == 5
+    gene_line_rik = ('1\thavana\tgene\t9747648\t9791924\t.\t+\t.\tgene_id "ENSMUSG00000097893"; gene_version "8"; '
+                     'gene_name "1700034P13Rik"; gene_source "havana"; gene_biotype "lncRNA";\n')
+    assert gene_line_rik == builder.gene_sequences_dict[GENE_KEYS[1]]['gene_line']
+
+    with open(GENE_COORDS) as gtf:
+        lines = gtf.readlines()
+        numb_exons_gtf = len(lines) - 4  # 2x exon + transcript line
+    numb_exons_dict = 0
+    for gene_key in GENE_KEYS:
+        numb_exons_dict += len(builder.gene_sequences_dict[gene_key]['exon_seq'])
+    assert numb_exons_gtf == numb_exons_dict
+
+
+@pytest.mark.parametrize(
+        "test_input",
+        [(TEST_CSV_TITLE, GENE_COORDS, P_INTRON_0),
+         (TEST_CSV_TITLE, GENE_COORDS, P_INTRON_1)
+         ],
+)
+def test_make_new_transcripts(test_input):
+    builder = Gts.BuildTranscriptStructure(test_input[0], test_input[1], test_input[2])
+    builder.csv_2_dict()  # Generates dictionary from gene count csv file.
+    builder.gtf_2_dict()  # Generates dictionary from gtf file.
+    builder.make_new_transcripts()  # Generates the differently spliced transcripts.
+
+    numb_trans_dict = 0
+    numb_trans_csv = 10
+    for gene_key in GENE_KEYS:
+        for trans_id in builder.gene_transcript_dict[gene_key]:
+            numb_trans_dict += builder.gene_transcript_dict[gene_key][trans_id]
+    assert numb_trans_csv == numb_trans_csv
+
+    for gene_key in GENE_KEYS:
+        assert len(builder.gene_transcript_dict[gene_key]) == 1  # All have identical transcript IDs.
+
+
+@pytest.mark.parametrize(
+        "test_input",
+        [(TEST_CSV_TITLE, GENE_COORDS, P_INTRON_0),
+         (TEST_CSV_TITLE, GENE_COORDS, P_INTRON_1)
+         ],
+)
+def test_make_gtf_lines(test_input):
+    builder = Gts.BuildTranscriptStructure(test_input[0], test_input[1], test_input[2])
+    builder.csv_2_dict()  # Generates dictionary from gene count csv file.
+    builder.gtf_2_dict()  # Generates dictionary from gtf file.
+    builder.make_new_transcripts()  # Generates the differently spliced transcripts.
+    builder.make_gtf_info()
+    for line in builder.gtf_lines:
+        columns = line.split('\t')
+        assert columns[3] < columns[4]  # Tests that the coordinates are increasing.
+    pass
+
+
+@pytest.mark.parametrize(
+        "test_input",
+        [(TEST_CSV_TITLE, GENE_COORDS, P_INTRON_0),
+         (TEST_CSV_TITLE, GENE_COORDS, P_INTRON_1)
+         ],
+)
+def test_sort_gtf_lines(test_input):
+    builder = Gts.BuildTranscriptStructure(test_input[0], test_input[1], test_input[2])
+    builder.csv_2_dict()  # Generates dictionary from gene count csv file.
+    builder.gtf_2_dict()  # Generates dictionary from gtf file.
+    builder.make_new_transcripts()  # Generates the differently spliced transcripts.
+    builder.make_gtf_info()
+
+    starts_before = []  # Verifies that the function actually has to sort.
+    for line in builder.gtf_lines:
+        columns = line.split('\t')
+        if columns[2] == 'gene':
+            starts_before.append(columns[3])
+    for ii in range(len(starts_before)-1):
+        assert starts_before[ii] > starts_before[ii+1]
+    builder.sort_gtf_lines()
+
+    builder.sort_gtf_lines()
+    starts_after = []  # Verifies that the function sorted.
+    for line in builder.gtf_lines:
+        columns = line.split('\t')
+        if columns[2] == 'gene':
+            starts_after.append(columns[3])
+    for ii in range(len(starts_before)-1):
+        assert starts_after[ii] < starts_after[ii+1]
+    builder.sort_gtf_lines()
+
+
+def test_write_gtf():
+    pass
+
+
+def test_write_csv():
+    pass

transcript_structure/Generate_transcript_structure.py

+import random
+import csv
+import copy
+
+
+class BuildTranscriptStructure:
+
+    """Creates differently spliced transcripts.
+
+    Args:
+        input_gene_count(str): Path to csv file of type "geneID", number to sample.
+        input_coordinates(str): Path to gtf file of relevant genes.
+        p_intron(float): Probability to include each intron in the mRNA sequence.
+
+    Attributes:
+        gene_count_dict(dict): Dictionary of format {"gene_ID": number_of_samplings}
+        gene_sequences_dict(dict): Nested dictionary with information about each gene.
+            Format: {"gene_ID": {"gene_line": gene_gtf_line,
+                                 "transcript_line": transcript_gtf_line,
+                                 "exon_line": exemplary_exon_line,
+                                 "exon_seq": [[start_exon1, end_exon1],[start_exon2, end_exon2],...]
+                                 }
+                    }
+        gene_transcript_dict(dict): Nested dictionary with amount of each differently spliced transcript.
+            Format: {"gene_ID": {"transcript_ID": n_copies}}
+            The transcript ID is a binary code, signifying whether a certain intron is included or not.
+            E.g. gene with 4 exons:
+                transcript code 001: The 1. and 2. introns are not included (spliced away), the 3. is included.
+                The transcript will therefore have 3 exons (exon 3 and 4 are combined).
+            For sequences with negative strand senses, the exon numbering is determining the direction the transcript
+            code is to be applied, and not the occurrence in the gene sequence (inverted by convention).
+            E.g. '01' means the intron between original (fully spliced) exon 1 and exon 2 was spliced away,
+                        but the intron between exon 2 and exon 3 is included in the transcript.
+        gtf_lines(list): List with all newly created gtf lines.
+    """
+
+    def __init__(self,
+                 input_gene_count: str,
+                 input_coordinates: str,
+                 p_intron: float,
+                 ) -> None:
+        """Class constructor."""
+        self.gene_count = input_gene_count
+        self.input_coords = input_coordinates
+        self.p_intron = p_intron
+        self.gene_count_dict = {}
+        self.gene_sequences_dict = {}
+        self.gene_transcript_dict = {}
+        self.gtf_lines = []
+
+    def generate_transcript_structure(self):
+        """Computes distribution and gene coordinates of differently spliced mRNA."""
+        self.csv_2_dict()  # Generates dictionary from gene count csv file.
+        self.gtf_2_dict()  # Generates dictionary from gtf file.
+        self.make_new_transcripts()  # Generates the differently spliced transcripts.
+        self.make_gtf_info()  # Builds the gtf file of all newly created transcripts.
+        self.sort_gtf_lines()  # Sorts the gtf file by gene occurrence in sequence.
+
+    def csv_2_dict(self) -> None:
+        """Converts the csv file with gene count into a dictionary."""
+        with open(self.gene_count) as g_c:
+            lines = g_c.readlines()
+
+        first_line = lines[0].split(',')  # Removes the first line if it is a title.
+        if not first_line[1][0].isnumeric():
+            del lines[0]
+
+        for line in lines:
+            line_entries = line.split(',')
+            self.gene_count_dict[line_entries[0]] = int(line_entries[1])
+
+    def gtf_2_dict(self) -> None:
+        """Converts the gtf file into a nested dictionary."""
+        with open(self.input_coords) as c_g:  # Reads coordinates from .gtf file.
+            lines = c_g.readlines()
+        lines = [i for i in lines if i[0] != '#']  # Exclude comments
+
+        for gene_line in range(len(lines)):
+            gene_info = {}  # Dictionary with information of a single gene.
+            line_entries = lines[gene_line].split('\t')
+            if line_entries[2] == 'gene':  # The line indeed describes a gene.
+                attribute = line_entries[8].split(';')
+                gene_name = attribute[2][12:-1]  # Extracts the gene name from the attributes.
+                gene_info['gene_line'] = lines[gene_line]
+                gene_info['transcript_line'] = lines[gene_line + 1]
+                gene_info['exon_line'] = lines[gene_line + 2]  # Exemplary line of an exon.
+                gene_info['strand_sense'] = line_entries[6] == '+'  # Strand sense.
+
+                coordinates = []
+                exon_line = []
+                line_offset = 2  # Lines after the gene line (+1 is transcript description).
+                while True:
+                    try:  # Avoids error at end of list.
+                        exon_line = lines[gene_line + line_offset].split('\t')
+                    except IndexError:  # End of gtf file reached: The job is finished.
+                        break
+                    if exon_line[2] != 'exon':  # End of exon list of this gene is reached.
+                        break
+                    else:  # The line is an exon.
+                        coordinates.append([int(exon_line[3]), int(exon_line[4])])
+                    line_offset += 1  # Move to next line.
+
+                if exon_line[6] == '-':  # Strands with sense (-)
+                    coordinates.reverse()
+
+                gene_info['exon_seq'] = coordinates
+                self.gene_sequences_dict[gene_name] = gene_info
+
+    def make_new_transcripts(self) -> None:
+        """ Generates the differently spliced transcripts."""
+        for gene in self.gene_count_dict:
+
+            # Computes the intron splicing for each transcript.
+            transcript_ids = []
+            for _ in range(self.gene_count_dict[gene]):
+                i_d = []
+                for __ in range(len(self.gene_sequences_dict[gene]['exon_seq']) - 1):
+                    if random.random() > self.p_intron:  # Intron spliced away.
+                        i_d.append('0')
+                    else:  # Intron not spliced away.
+                        i_d.append('1')
+                transcript_ids.append(''.join(i_d))  # Combine all transcript IDs in one list.
+
+            # Counts how often each transcript is is the list.
+            transcript_numbers = {}
+            while True:
+                i_d = transcript_ids.pop()
+                transcript_numbers['-'.join([gene, i_d])] = 1 + transcript_ids.count(i_d)
+                transcript_ids = [not_current_iD for not_current_iD in transcript_ids if not_current_iD != i_d]
+                if not transcript_ids:  # Leaves loop once all codes were scanned for.
+                    break
+
+            self.gene_transcript_dict[gene] = transcript_numbers
+
+    def write_csv(self,
+                  output_transcript_count: str
+                  ) -> None:
+
+        """ Writes a csv file containing the number of differently spliced transcripts.
+
+        Args:
+             output_transcript_count(str): Path and name of the output cvs file: "transcript_ID", "gene_ID", count.
+        """
+
+        with open(output_transcript_count, 'w', newline='') as file:
+            writer = csv.writer(file)
+            writer.writerow(['Transcript_ID', 'Gene_ID', 'count'])
+            for gene in self.gene_transcript_dict:
+                for transcript_ID in self.gene_transcript_dict[gene]:
+                    writer.writerow([transcript_ID, gene, self.gene_transcript_dict[gene][transcript_ID]])
+
+    def make_gtf_info(self) -> None:
+        """ Writes the lines of the new gtf file for the differently spliced transcripts."""
+        for gene in self.gene_transcript_dict:  # Iterates over all genes required.
+            self.gtf_lines.append(self.gene_sequences_dict[gene]['gene_line'])  # Add gene line to list.
+            sense = self.gene_sequences_dict[gene]['strand_sense']
+
+            for transcript_ID in self.gene_transcript_dict[gene]:  # Iterates over all occurring types of splicings.
+                # Modifies the transcript line according to the splicing.
+                transcript_line = self.gene_sequences_dict[gene]['transcript_line'].split('\t')
+                attribute = transcript_line[8].split(';')
+                attribute[7] = ''.join(['transcript_name "', transcript_ID, '"'])
+                transcript_line[8] = '; '.join(attribute)
+                self.gtf_lines.append('\t'.join(transcript_line))
+
+                start_id = len(gene)
+                i_d = list(map(int, transcript_ID[start_id + 1:]))  # Extract the splicing coding as int.
+                i_d_pop = copy.copy(i_d)
+                if sense:
+                    i_d_pop.reverse()
+                numb_introns = sum(i_d)  # Adds up the transcription ID as int.
+                numb_exons = len(self.gene_sequences_dict[gene]['exon_seq']) - numb_introns
+
+                n_unspliced = 0  # Count of number of unspliced introns.
+                exon_lines = []
+                for exon in range(numb_exons):
+                    exon_line = self.gene_sequences_dict[gene]['exon_line'].split('\t')  # Initializes exon line.
+                    exon_line[2] = 'exon'
+                    attribute = exon_line[8].split(';')
+                    if sense:
+                        attribute[4] = ''.join(['exon_number "', str(exon + 1), '"'])
+                    else:
+                        attribute[4] = ''.join(['exon_number "', str(numb_exons - exon), '"'])
+                    attribute[8] = ''.join(['transcript_name "', transcript_ID, '"'])
+                    exon_line[8] = '; '.join(attribute)
+                    exon_line[3] = str(self.gene_sequences_dict[gene]['exon_seq'][exon + n_unspliced][0])
+                    exon_line[4] = str(self.gene_sequences_dict[gene]['exon_seq'][exon + n_unspliced][1])
+
+                    try:
+                        while i_d_pop.pop():
+                            n_unspliced += 1
+                            if sense:
+                                exon_line[4] = str(self.gene_sequences_dict[gene]['exon_seq'][exon + n_unspliced][1])
+                            else:
+                                exon_line[3] = str(self.gene_sequences_dict[gene]['exon_seq'][exon + n_unspliced][0])
+                    except IndexError:  # End of ID reached
+                        pass
+
+                    exon_lines.append('\t'.join(exon_line))
+
+                if not self.gene_sequences_dict[gene]['strand_sense']:  # Negative strand sense need reversed order.
+                    exon_lines.reverse()
+                self.gtf_lines.extend(exon_lines)
+
+    def sort_gtf_lines(self) -> None:
+
+        """ Sorts the gtf lines by the position of the genes (increasing) and returns it."""
+
+        # Builds and uses a dictionary with the start of the gene as key, and all lines related to this gene as value:
+        # {start_gene(int): [[gene_line],[transcript_line],[exon_line1],[exon_line2],...]}
+
+        gene_lines_dict = {}
+        gene_start = 0  # Validation: This key should remain unused, as every gtf file starts with a gene.
+        for index, line in enumerate(self.gtf_lines):
+            line_content = line.split('\t')
+            if line_content[2] == 'gene':  # This is the next gene line. Initializes dictionary entry.
+                gene_start = line_content[3]  # Extract the  key = start of gene.
+                gene_lines_dict[gene_start] = []
+            gene_lines_dict[gene_start].append(line)  # Append all lines related to this gene.
+
+        sorted_keys = sorted(gene_lines_dict)  # Sorts the keys by their values.
+        sorted_gtf_lines = []
+        for key in sorted_keys:
+            sorted_gtf_lines.extend(gene_lines_dict[key])  # Creates a new list of the gtf lines in the correct order.
+
+        self.gtf_lines = sorted_gtf_lines
+
+    def write_gtf(self,
+                  output_coords: str
+                  ) -> None:
+
+        """ Writes a gtf file with the information about the differently spliced transcripts.
+
+        Args:
+            output_coords(str): Path and name of the output gtf file with the information of all relevant transcripts.
+        """
+        with open(output_coords, 'w') as gtf_file:
+            gtf_file.writelines(self.gtf_lines)
+
+
+def main():
+    """ Main Function."""
+    # Inputs
+    # gene_count = 'gene_count/Rik_5.csv'  # Strand with + sense
+    # gene_count = 'gene_count/Rp1_5.csv'  # Strand with - sense.
+    gene_count = 'gene_count/Rik_5_Rp1_5.csv'  # Both strand senses combined
+    coordinates_genes = 'gtf/coordinates.gtf'
+    p_intron = 0.3
+
+    # Output paths and names.
+    name_csv_output = 'Outputs/csv_new.csv'
+    name_gtf_output = 'Outputs/gtf_new.gtf'
+
+    random.seed(10)  # Initializes seed for random functions for reproducibility.
+
+    bts = BuildTranscriptStructure(gene_count, coordinates_genes, p_intron)
+    bts.csv_2_dict()  # Generates dictionary from gene count csv file.
+    bts.gtf_2_dict()  # Generates dictionary from gtf file.
+    bts.make_new_transcripts()  # Generates the differently spliced transcripts.
+    bts.make_gtf_info()  # Builds the gtf file of all newly created transcripts.
+    bts.sort_gtf_lines()  # Sorts the gtf file by gene occurrence in sequence.
+    bts.write_gtf(name_gtf_output)  # Writes the new gtf file.
+    bts.write_csv(name_csv_output)  # Writes the new csv file with the count of the transcripts.
+
+
+if __name__ == '__main__':
+    main()
+    print('process completed')

transcript_structure/Outputs/csv_new.csv

+Transcript_ID,Gene_ID,count
+1700034P13Rik-010,1700034P13Rik,3
+1700034P13Rik-100,1700034P13Rik,1
+1700034P13Rik-000,1700034P13Rik,1
+Rp1-111,Rp1,1
+Rp1-000,Rp1,2
+Rp1-010,Rp1,1
+Rp1-001,Rp1,1

transcript_structure/Outputs/gtf_new.gtf

+1	ensembl_havana	gene	3999557	4409241	.	-	.	gene_id "ENSMUSG00000025900"; gene_version "12"; gene_name "Rp1"; gene_source "ensembl_havana"; gene_biotype "protein_coding";
+1	havana	transcript	4290846	4409241	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-111";  transcript_source "havana";  transcript_biotype "retained_intron";  transcript_support_level "1"; 
+1	havana	exon	4409170	4293012	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "1";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-111";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	transcript	4290846	4409241	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-000";  transcript_source "havana";  transcript_biotype "retained_intron";  transcript_support_level "1"; 
+1	havana	exon	4409170	4409241	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "1";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-000";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	4352202	4352837	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "2";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-000";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	4351910	4352081	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "3";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-000";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	4290846	4293012	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "4";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-000";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	transcript	4290846	4409241	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-010";  transcript_source "havana";  transcript_biotype "retained_intron";  transcript_support_level "1"; 
+1	havana	exon	4409170	4409241	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "1";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-010";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	4352202	4352081	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "2";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-010";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	4290846	4293012	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "3";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-010";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	transcript	4290846	4409241	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-001";  transcript_source "havana";  transcript_biotype "retained_intron";  transcript_support_level "1"; 
+1	havana	exon	4409170	4409241	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "1";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-001";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	4352202	4352837	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "2";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-001";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	4351910	4293012	.	-	.	gene_id "ENSMUSG00000025900";  gene_version "12";  transcript_id "ENSMUST00000208793";  transcript_version "1"; exon_number "3";  gene_name "Rp1";  gene_source "ensembl_havana";  gene_biotype "protein_coding"; transcript_name "Rp1-001";  transcript_source "havana";  transcript_biotype "retained_intron";  exon_id "ENSMUSE00001379779";  exon_version "1";  transcript_support_level "1"; 
+1	havana	gene	9747648	9791924	.	+	.	gene_id "ENSMUSG00000097893"; gene_version "8"; gene_name "1700034P13Rik"; gene_source "havana"; gene_biotype "lncRNA";
+1	havana	transcript	9747648	9791922	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-010";  transcript_source "havana";  transcript_biotype "lncRNA";  transcript_support_level "1"; 
+1	havana	exon	9747648	9748604	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7"; exon_number "1";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-010";  transcript_source "havana";  transcript_biotype "lncRNA";  exon_id "ENSMUSE00001104564";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	9752449	9789780	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7"; exon_number "2";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-010";  transcript_source "havana";  transcript_biotype "lncRNA";  exon_id "ENSMUSE00001104564";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	9791125	9791922	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7"; exon_number "3";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-010";  transcript_source "havana";  transcript_biotype "lncRNA";  exon_id "ENSMUSE00001104564";  exon_version "1";  transcript_support_level "1"; 
+1	havana	transcript	9747648	9791922	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-100";  transcript_source "havana";  transcript_biotype "lncRNA";  transcript_support_level "1"; 
+1	havana	exon	9747648	9752564	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7"; exon_number "1";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-100";  transcript_source "havana";  transcript_biotype "lncRNA";  exon_id "ENSMUSE00001104564";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	9789656	9789780	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7"; exon_number "2";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-100";  transcript_source "havana";  transcript_biotype "lncRNA";  exon_id "ENSMUSE00001104564";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	9791125	9791922	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7"; exon_number "3";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-100";  transcript_source "havana";  transcript_biotype "lncRNA";  exon_id "ENSMUSE00001104564";  exon_version "1";  transcript_support_level "1"; 
+1	havana	transcript	9747648	9791922	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-000";  transcript_source "havana";  transcript_biotype "lncRNA";  transcript_support_level "1"; 
+1	havana	exon	9747648	9748604	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7"; exon_number "1";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-000";  transcript_source "havana";  transcript_biotype "lncRNA";  exon_id "ENSMUSE00001104564";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	9752449	9752564	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7"; exon_number "2";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-000";  transcript_source "havana";  transcript_biotype "lncRNA";  exon_id "ENSMUSE00001104564";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	9789656	9789780	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7"; exon_number "3";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-000";  transcript_source "havana";  transcript_biotype "lncRNA";  exon_id "ENSMUSE00001104564";  exon_version "1";  transcript_support_level "1"; 
+1	havana	exon	9791125	9791922	.	+	.	gene_id "ENSMUSG00000097893";  gene_version "8";  transcript_id "ENSMUST00000181821";  transcript_version "7"; exon_number "4";  gene_name "1700034P13Rik";  gene_source "havana";  gene_biotype "lncRNA"; transcript_name "1700034P13Rik-000";  transcript_source "havana";  transcript_biotype "lncRNA";  exon_id "ENSMUSE00001104564";  exon_version "1";  transcript_support_level "1"; 

transcript_structure/__init__.py

+# Transcript Structure root package
+__version__ = "1.1.0"

transcript_structure/gene_count/Rik_5.csv

+GeneID,count
+1700034P13Rik,5
\ No newline at end of file

transcript_structure/gene_count/Rik_5_Rp1_5.csv

+GeneID,count
+1700034P13Rik,5
+Rp1,5
\ No newline at end of file

transcript_structure/gene_count/Rp1_5.csv

+GeneID,count
+Rp1,5
\ No newline at end of file

[Timon Baltisberger]

Working on issue #2, generating transcript structure