diff --git a/Untitled.ipynb b/Untitled.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..14c4f123ed3e8ce2c38692cb7fbea30d09590c5b
--- /dev/null
+++ b/Untitled.ipynb
@@ -0,0 +1,481 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "96ccbf23-4a46-4bae-bef2-fdf4c2466ad3",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "3157488c-08cf-4f10-95f6-745613382000",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from cdna.cdna import cDNA_Gen"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "a6f5bc24-e454-49ad-b1e3-1f5b63c66ab2",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "ceb225a6-3a63-49e7-a0d3-a92256012261",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "INFO:root:Extracted GTF attributes: ['Accessibility_Energy', 'Hybridization_Energy', 'Interaction_Energy', 'Number_of_binding_sites', 'Binding_Probability']\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[SeqRecord(seq=Seq('ATCCATAAAAAAAAA'), id='Transcript_1', name='Transcript copy number: 8.0', description='', dbxrefs=[]), SeqRecord(seq=Seq('CATCTCAAAAAGTCT'), id='Transcript_1', name='Transcript copy number: 4.0', description='', dbxrefs=[]), SeqRecord(seq=Seq('AAAAAAAAAAAAAAA'), id='Transcript_2', name='Transcript copy number: 11.0', description='', dbxrefs=[])]\n"
+ ]
+ }
+ ],
+ "source": [
+ "test_path = \"/Users/ericboittier/Documents/github/cdna-generator/test_files/\"\n",
+ "gtf = test_path+\"Example_GTF_Input.gtf\"\n",
+ "cpn = test_path+\"copy_number_input.csv\"\n",
+ "fasta = test_path+\"yeast_example.fa\"\n",
+ "\n",
+ "G = cDNA_Gen(fasta, gtf, cpn, output_fasta=\"test_files/cDNA.fasta\", output_csv=\"test_files/cDNA.csv\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "24976988-4a28-4932-8f53-d8ac7bb018f8",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>index</th>\n",
+ " <th>ID of transcript</th>\n",
+ " <th>ID of parent transcript</th>\n",
+ " <th>Transcript copy number</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>2</td>\n",
+ " <td>1</td>\n",
+ " <td>11</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2</td>\n",
+ " <td>3</td>\n",
+ " <td>2</td>\n",
+ " <td>33</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>3</td>\n",
+ " <td>4</td>\n",
+ " <td>3</td>\n",
+ " <td>11</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>4</td>\n",
+ " <td>5</td>\n",
+ " <td>4</td>\n",
+ " <td>55</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " index ID of transcript ID of parent transcript Transcript copy number\n",
+ "0 0 1 1 12\n",
+ "1 1 2 1 11\n",
+ "2 2 3 2 33\n",
+ "3 3 4 3 11\n",
+ "4 4 5 4 55"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "G.df_input_CSV"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "f7fdfef3-58b5-45c5-bd0f-e215a3b13636",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>seqname</th>\n",
+ " <th>source</th>\n",
+ " <th>feature</th>\n",
+ " <th>start</th>\n",
+ " <th>end</th>\n",
+ " <th>score</th>\n",
+ " <th>strand</th>\n",
+ " <th>frame</th>\n",
+ " <th>Accessibility_Energy</th>\n",
+ " <th>Hybridization_Energy</th>\n",
+ " <th>Interaction_Energy</th>\n",
+ " <th>Number_of_binding_sites</th>\n",
+ " <th>Binding_Probability</th>\n",
+ " <th>Normalized_Binding_Probability</th>\n",
+ " <th>Transcript_Copy_Number</th>\n",
+ " <th>priming_site</th>\n",
+ " <th>compliment</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Transcript_1</td>\n",
+ " <td>RIBlast</td>\n",
+ " <td>Priming_site</td>\n",
+ " <td>10</td>\n",
+ " <td>25</td>\n",
+ " <td>NaN</td>\n",
+ " <td>+</td>\n",
+ " <td>0</td>\n",
+ " <td>1.49</td>\n",
+ " <td>-9.76</td>\n",
+ " <td>-8.74</td>\n",
+ " <td>2</td>\n",
+ " <td>0.12</td>\n",
+ " <td>0.705882</td>\n",
+ " <td>8.0</td>\n",
+ " <td>(T, T, T, T, T, T, T, T, T, A, T, G, G, A, T)</td>\n",
+ " <td>ATCCATAAAAAAAAA</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Transcript_1</td>\n",
+ " <td>RIBlast</td>\n",
+ " <td>Priming_site</td>\n",
+ " <td>640</td>\n",
+ " <td>655</td>\n",
+ " <td>NaN</td>\n",
+ " <td>+</td>\n",
+ " <td>0</td>\n",
+ " <td>1.71</td>\n",
+ " <td>-9.12</td>\n",
+ " <td>-8.34</td>\n",
+ " <td>2</td>\n",
+ " <td>0.05</td>\n",
+ " <td>0.294118</td>\n",
+ " <td>4.0</td>\n",
+ " <td>(A, G, A, C, T, T, T, T, T, G, A, G, A, T, G)</td>\n",
+ " <td>CATCTCAAAAAGTCT</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Transcript_2</td>\n",
+ " <td>RIBlast</td>\n",
+ " <td>Priming_site</td>\n",
+ " <td>3</td>\n",
+ " <td>18</td>\n",
+ " <td>NaN</td>\n",
+ " <td>+</td>\n",
+ " <td>0</td>\n",
+ " <td>1.21</td>\n",
+ " <td>-5.12</td>\n",
+ " <td>-2.34</td>\n",
+ " <td>1</td>\n",
+ " <td>0.15</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>11.0</td>\n",
+ " <td>(T, T, T, T, T, T, T, T, T, T, T, T, T, T, T)</td>\n",
+ " <td>AAAAAAAAAAAAAAA</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Transcript_3</td>\n",
+ " <td>RIBlast</td>\n",
+ " <td>Priming_site</td>\n",
+ " <td>5</td>\n",
+ " <td>35</td>\n",
+ " <td>NaN</td>\n",
+ " <td>+</td>\n",
+ " <td>0</td>\n",
+ " <td>1.21</td>\n",
+ " <td>-5.12</td>\n",
+ " <td>-2.34</td>\n",
+ " <td>1</td>\n",
+ " <td>0.25</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>33.0</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Transcript_4</td>\n",
+ " <td>RIBlast</td>\n",
+ " <td>Priming_site</td>\n",
+ " <td>5</td>\n",
+ " <td>35</td>\n",
+ " <td>NaN</td>\n",
+ " <td>+</td>\n",
+ " <td>0</td>\n",
+ " <td>1.21</td>\n",
+ " <td>-5.12</td>\n",
+ " <td>-2.34</td>\n",
+ " <td>1</td>\n",
+ " <td>0.15</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>11.0</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>Transcript_5</td>\n",
+ " <td>RIBlast</td>\n",
+ " <td>Priming_site</td>\n",
+ " <td>5</td>\n",
+ " <td>35</td>\n",
+ " <td>NaN</td>\n",
+ " <td>+</td>\n",
+ " <td>0</td>\n",
+ " <td>1.21</td>\n",
+ " <td>-5.12</td>\n",
+ " <td>-2.34</td>\n",
+ " <td>1</td>\n",
+ " <td>0.15</td>\n",
+ " <td>1.000000</td>\n",
+ " <td>55.0</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " seqname source feature start end score strand frame \\\n",
+ "0 Transcript_1 RIBlast Priming_site 10 25 NaN + 0 \n",
+ "1 Transcript_1 RIBlast Priming_site 640 655 NaN + 0 \n",
+ "2 Transcript_2 RIBlast Priming_site 3 18 NaN + 0 \n",
+ "3 Transcript_3 RIBlast Priming_site 5 35 NaN + 0 \n",
+ "4 Transcript_4 RIBlast Priming_site 5 35 NaN + 0 \n",
+ "5 Transcript_5 RIBlast Priming_site 5 35 NaN + 0 \n",
+ "\n",
+ " Accessibility_Energy Hybridization_Energy Interaction_Energy \\\n",
+ "0 1.49 -9.76 -8.74 \n",
+ "1 1.71 -9.12 -8.34 \n",
+ "2 1.21 -5.12 -2.34 \n",
+ "3 1.21 -5.12 -2.34 \n",
+ "4 1.21 -5.12 -2.34 \n",
+ "5 1.21 -5.12 -2.34 \n",
+ "\n",
+ " Number_of_binding_sites Binding_Probability \\\n",
+ "0 2 0.12 \n",
+ "1 2 0.05 \n",
+ "2 1 0.15 \n",
+ "3 1 0.25 \n",
+ "4 1 0.15 \n",
+ "5 1 0.15 \n",
+ "\n",
+ " Normalized_Binding_Probability Transcript_Copy_Number \\\n",
+ "0 0.705882 8.0 \n",
+ "1 0.294118 4.0 \n",
+ "2 1.000000 11.0 \n",
+ "3 1.000000 33.0 \n",
+ "4 1.000000 11.0 \n",
+ "5 1.000000 55.0 \n",
+ "\n",
+ " priming_site compliment \n",
+ "0 (T, T, T, T, T, T, T, T, T, A, T, G, G, A, T) ATCCATAAAAAAAAA \n",
+ "1 (A, G, A, C, T, T, T, T, T, G, A, G, A, T, G) CATCTCAAAAAGTCT \n",
+ "2 (T, T, T, T, T, T, T, T, T, T, T, T, T, T, T) AAAAAAAAAAAAAAA \n",
+ "3 None None \n",
+ "4 None None \n",
+ "5 None None "
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "G.df_input_GTF"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "9e7fe7be-d134-4c1e-8eea-55273c79e39d",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "G.add_sequences()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "2eb8f224-0292-4bb0-9e27-ef3bc3676f1d",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "NameError",
+ "evalue": "name 'G' is not defined",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "Input \u001b[0;32mIn [3]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mG\u001b[49m\u001b[38;5;241m.\u001b[39mdf_input_GTF\n",
+ "\u001b[0;31mNameError\u001b[0m: name 'G' is not defined"
+ ]
+ }
+ ],
+ "source": [
+ "G.df_input_GTF"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "4a482960-0e05-4355-b91c-fc7f51c138c2",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "NameError",
+ "evalue": "name 'G' is not defined",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "Input \u001b[0;32mIn [4]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m G\u001b[38;5;241m.\u001b[39mdf_input_GTF[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mA\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[43mG\u001b[49m\u001b[38;5;241m.\u001b[39mdf_input_GTF\u001b[38;5;241m.\u001b[39mapply(\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28;01mlambda\u001b[39;00m row: foo(row[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mseqname\u001b[39m\u001b[38;5;124m\"\u001b[39m], \n\u001b[1;32m 3\u001b[0m row[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstart\u001b[39m\u001b[38;5;124m\"\u001b[39m], \n\u001b[1;32m 4\u001b[0m row[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mend\u001b[39m\u001b[38;5;124m\"\u001b[39m]), \n\u001b[1;32m 5\u001b[0m axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1\u001b[39m\n\u001b[1;32m 6\u001b[0m )\n",
+ "\u001b[0;31mNameError\u001b[0m: name 'G' is not defined"
+ ]
+ }
+ ],
+ "source": [
+ "G.df_input_GTF[\"A\"] = G.df_input_GTF.apply(\n",
+ " lambda row: foo(row[\"seqname\"], \n",
+ " row[\"start\"], \n",
+ " row[\"end\"]), \n",
+ " axis=1\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "304fd031-524a-4fc3-9322-9b3dd55268fb",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# G.df_input_GTF[\"A\"] = G.df_input_GTF.apply(lambda row: foo(row), axis=1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "a8f7a36d-d768-4daf-8705-4cab5e06b562",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "G.df_input_GTF[G.df_input_GTF[\"seqname\"]==\"Transcript_1\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b0d7f2e4-c590-49a9-89eb-b53144dba9e8",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.9.13"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/cdna/cdna.py b/cdna/cdna.py
index 1aaa2262b5cadfde403169af50ca6c47a97143e2..edd15c4432d0f1c1dae902715126c4b3d95376dd 100644
--- a/cdna/cdna.py
+++ b/cdna/cdna.py
@@ -1,44 +1,28 @@
import sys
-import pandas as pd
+import warnings
+import pandas as pd
+from Bio import SeqIO
+from Bio.Seq import Seq
+from Bio.SeqRecord import SeqRecord
from gtfparse import read_gtf
+# ignore warnings from read_gtf
+warnings.filterwarnings(action='ignore', category=FutureWarning)
-# returns GTF with essential columns such as "feature", "seqname", "start", "end"
-# alongside the names of any optional keys which appeared in the attribute column
-df_input_GTF = read_gtf("Example_GTF_Input.gtf")
-df_input_CSV = pd.read_csv("copy_number_input.csv")
-
-df_input_CSV = df_input_CSV.reset_index() # make sure indexes pair with number of rows
-
-df_input_GTF['Binding_Probability'] = pd.to_numeric(df_input_GTF['Binding_Probability']) # convert to numeric
-df_normalization_bind_probablility = df_input_GTF.groupby('seqname')['Binding_Probability'].sum() # extract binding probablility
-
-# Add New columns to the existing DataFrame
-df_input_GTF["Normalized_Binding_Probability"] = ''
-df_input_GTF["Transcript_Copy_Number"] = ''
-
-
-# Adds Normalized_Binding_Probability and Transcript_Copy_Number to each transcript in the dataframe
-for index, row in df_input_GTF.iterrows():
- # GTF transcript ID
- id_GTF = str(row['seqname'])
- # CVS transcript ID
- id_CSV = str(row['seqname']).split('_')[1]
- # Calculate Normalized_Binding_Probability and add to GTF dataframe
- df_input_GTF.loc[index, 'Normalized_Binding_Probability'] = row['Binding_Probability'] / df_normalization_bind_probablility[id_GTF]
- # Calculate Normalized_Binding_Probability and add to GTF dataframe
- csv_transcript_copy_number = df_input_CSV.loc[df_input_CSV['ID of transcript'] == int(id_CSV), 'Transcript copy number'].iloc[0]
- df_input_GTF.loc[index,'Transcript_Copy_Number'] = round(csv_transcript_copy_number * df_input_GTF.loc[index,'Normalized_Binding_Probability'])
-
-
-def translate(res):
- translate_dict = {"A": "T", "U": "A", "G": "C", "C": "G"}
+def compliment(res):
+ translate_dict = {"A": "T", "T": "A", "U": "A", "G": "C", "C": "G"}
if res not in translate_dict.keys():
- print("cDNA residue not A,T,U or G ")
- sys.exit(1)
+ print(f"Unknown character, {res}")
+ sys.exit(1)
return translate_dict[res]
+def seq_compliment(sequence):
+ if sequence is None:
+ return None
+ _ = "".join([compliment(char) for char in str(sequence)])[::-1] # reverse string
+ return _
+
class cDNA_Gen:
def __init__(
@@ -50,52 +34,93 @@ class cDNA_Gen:
self.cpn = cpn
self.output_fasta = output_fasta
self.output_csv = output_csv
+
# variables
- self.prime_sites = []
- self.fasta_seq = ""
- self.fasta_id = ""
- self.copy_numbers = {}
+ self.fasta_dict = None
+ self.fasta_records = None
self.run()
def run(self):
+ self.read_csv()
self.read_fasta()
self.read_gtf()
+ self.add_sequences()
+ self.add_compliment()
+ self.add_records()
+ self.write_fasta()
+
+ def add_records(self):
+ self.fasta_records = []
+ for index, row in self.df_input_GTF.iterrows():
+ if row["compliment"] is not None:
+ copy_number = row["Transcript_Copy_Number"]
+ record = SeqRecord(
+ Seq(row["compliment"]),
+ row["seqname"],
+ f"Transcript copy number: {copy_number}",
+ "")
+ self.fasta_records.append(record)
+
+ def add_sequences(self):
+ self.df_input_GTF["priming_site"] = self.df_input_GTF.apply(
+ lambda row: self.read_primingsite(row["seqname"],
+ row["start"],
+ row["end"]),
+ axis=1)
+
+ def add_compliment(self):
+ self.df_input_GTF["compliment"] = self.df_input_GTF["priming_site"].apply(
+ lambda x: seq_compliment(x))
+
+ def read_primingsite(self, sequence, start, end):
+ if sequence not in self.fasta_dict.keys():
+ return None
+ _ = self.fasta_dict[sequence].seq[start:end]
+ return _
- def order_priming_sites(self):
- pass
+ def read_fasta(self):
+ record = SeqIO.parse(self.fasta, "fasta")
+ records = list(record)
+ self.fasta_dict = {x.name: x for x in records}
- def generate_cdna(self):
- pass
+ def read_csv(self):
+ df_input_CSV = pd.read_csv(self.cpn, index_col=False)
+ df_input_CSV = df_input_CSV.reset_index() # make sure indexes pair with number of rows
+ self.df_input_CSV = df_input_CSV
- def read_fasta(self):
- fasta = open(self.fasta).readlines()
- self.fasta_id = fasta[0]
- print(fasta[0])
- self.fasta_seq = "".join([_.rstrip() for _ in fasta[1:]])
def read_gtf(self):
- with open(self.gtf) as gtf_file:
- gtf_lines = gtf_file.readlines()
- for line in gtf_lines[:1000]:
- if not line.startswith("#"):
- temp_gtf = GTF_entry(line)
- temp_gtf.set_sequence(self.fasta_seq)
- self.prime_sites.append(temp_gtf)
+ # returns GTF with essential columns such as "feature", "seqname", "start", "end"
+ # alongside the names of any optional keys which appeared in the attribute column
+ df_input_GTF = read_gtf(self.gtf)
+ df_input_GTF['Binding_Probability'] = pd.to_numeric(df_input_GTF['Binding_Probability']) # convert to numeric
+ df_normalization_bind_probablility = df_input_GTF.groupby('seqname')['Binding_Probability'].sum() # extract binding probablility
+
+ # # Add New columns to the existing DataFrame
+ # df_input_GTF["Normalized_Binding_Probability"] = ''
+ # df_input_GTF["Transcript_Copy_Number"] = ''
+
+ # Adds Normalized_Binding_Probability and Transcript_Copy_Number to each transcript in the dataframe
+ for index, row in df_input_GTF.iterrows():
+ # GTF transcript ID
+ id_GTF = str(row['seqname'])
+ # CVS transcript ID
+ id_CSV = str(row['seqname']).split('_')[1]
+ # Calculate Normalized_Binding_Probability and add to GTF dataframe
+ df_input_GTF.loc[index, 'Normalized_Binding_Probability'] = row['Binding_Probability'] / df_normalization_bind_probablility[id_GTF]
+ # Calculate Normalized_Binding_Probability and add to GTF dataframe
+ csv_transcript_copy_number = self.df_input_CSV.loc[self.df_input_CSV['ID of transcript'] == int(id_CSV), 'Transcript copy number'].iloc[0]
+ df_input_GTF.loc[index,'Transcript_Copy_Number'] = round(csv_transcript_copy_number * df_input_GTF.loc[index,'Normalized_Binding_Probability'])
+
+ self.df_input_GTF = df_input_GTF
def write_fasta(self):
- pass
+ print(self.fasta_records)
+ SeqIO.write(self.fasta_records, self.output_fasta, "fasta")
- def read_copy_numbers(self):
- with open(self.cpn) as cpn_file:
- cpn_lines = cpn_file.readlines()
- for line in cpn_lines:
- csv = line.split(",")
- trans_id = csv[0]
- if trans_id:
- gene_id = csv[1]
- count = csv[2]
- self.copy_numbers[gene_id] = count
+ def write_csv(self):
+ pass
def return_output(self):
return self.output_fasta, self.output_csv
@@ -104,5 +129,4 @@ class cDNA_Gen:
if __name__ == "__main__":
import argparse
-
pass
diff --git a/setup.py b/setup.py
index eca847b3176505320c62244c884b1c4878234d3b..96ecc09a8223aebbcef30db4096998562b1f0976 100644
--- a/setup.py
+++ b/setup.py
@@ -10,4 +10,4 @@ setup(
version='1.0.0',
packages=find_packages(), # this will autodetect Python packages from the directory tree, e.g., in `code/`
install_requires=[], # add here packages that are required for your package to run, including version or range of versions
-
+)
diff --git a/test_files/cDNA.fasta b/test_files/cDNA.fasta
new file mode 100644
index 0000000000000000000000000000000000000000..1b8d3989aede7948effa7afb4c43a10eac63ebb1
--- /dev/null
+++ b/test_files/cDNA.fasta
@@ -0,0 +1,6 @@
+>Transcript_1
+ATCCATAAAAAAAAA
+>Transcript_1
+CATCTCAAAAAGTCT
+>Transcript_2
+AAAAAAAAAAAAAAA