diff --git a/Untitled.ipynb b/Untitled.ipynb
index 14c4f123ed3e8ce2c38692cb7fbea30d09590c5b..f05859bb38cbefb0db8b6a4a7ae94d302ee60aa1 100644
--- a/Untitled.ipynb
+++ b/Untitled.ipynb
@@ -43,7 +43,7 @@
"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"
+ "[SeqRecord(seq=Seq('ATCCATAAAAAAAAA'), id='Transcript_1_0', name='Transcript copy number: 8.0', description='', dbxrefs=[]), SeqRecord(seq=Seq('CATCTCAAAAAGTCT'), id='Transcript_1_1', name='Transcript copy number: 4.0', description='', dbxrefs=[]), SeqRecord(seq=Seq('AAAAAAAAAAAAAAA'), id='Transcript_2_0', name='Transcript copy number: 11.0', description='', dbxrefs=[])]\n"
]
}
],
@@ -189,6 +189,7 @@
" <th>Binding_Probability</th>\n",
" <th>Normalized_Binding_Probability</th>\n",
" <th>Transcript_Copy_Number</th>\n",
+ " <th>cdna_ID</th>\n",
" <th>priming_site</th>\n",
" <th>compliment</th>\n",
" </tr>\n",
@@ -211,6 +212,7 @@
" <td>0.12</td>\n",
" <td>0.705882</td>\n",
" <td>8.0</td>\n",
+ " <td>Transcript_1_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",
@@ -231,6 +233,7 @@
" <td>0.05</td>\n",
" <td>0.294118</td>\n",
" <td>4.0</td>\n",
+ " <td>Transcript_1_1</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",
@@ -251,6 +254,7 @@
" <td>0.15</td>\n",
" <td>1.000000</td>\n",
" <td>11.0</td>\n",
+ " <td>Transcript_2_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",
@@ -271,6 +275,7 @@
" <td>0.25</td>\n",
" <td>1.000000</td>\n",
" <td>33.0</td>\n",
+ " <td>Transcript_3_0</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
@@ -291,6 +296,7 @@
" <td>0.15</td>\n",
" <td>1.000000</td>\n",
" <td>11.0</td>\n",
+ " <td>Transcript_4_0</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
@@ -311,6 +317,7 @@
" <td>0.15</td>\n",
" <td>1.000000</td>\n",
" <td>55.0</td>\n",
+ " <td>Transcript_5_0</td>\n",
" <td>None</td>\n",
" <td>None</td>\n",
" </tr>\n",
@@ -343,13 +350,13 @@
"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",
+ " Normalized_Binding_Probability Transcript_Copy_Number cdna_ID \\\n",
+ "0 0.705882 8.0 Transcript_1_0 \n",
+ "1 0.294118 4.0 Transcript_1_1 \n",
+ "2 1.000000 11.0 Transcript_2_0 \n",
+ "3 1.000000 33.0 Transcript_3_0 \n",
+ "4 1.000000 11.0 Transcript_4_0 \n",
+ "5 1.000000 55.0 Transcript_5_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",
@@ -371,7 +378,17 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 5,
+ "id": "0511af5c-780e-41ba-9fb2-17e6640c5822",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "G.write_csv()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
"id": "9e7fe7be-d134-4c1e-8eea-55273c79e39d",
"metadata": {},
"outputs": [],
diff --git a/cdna/cdna.py b/cdna/cdna.py
index edd15c4432d0f1c1dae902715126c4b3d95376dd..5615eb5f7887c9a3ab7303842c867d40ac567635 100644
--- a/cdna/cdna.py
+++ b/cdna/cdna.py
@@ -28,6 +28,15 @@ class cDNA_Gen:
def __init__(
self, fasta, gtf, cpn, output_fasta="cDNA.fasta", output_csv="cDNA.csv"
):
+ """_summary_
+
+ Args:
+ fasta (_type_): _description_
+ gtf (_type_): _description_
+ cpn (_type_): _description_
+ output_fasta (str, optional): _description_. Defaults to "cDNA.fasta".
+ output_csv (str, optional): _description_. Defaults to "cDNA.csv".
+ """
# inputs
self.fasta = fasta
self.gtf = gtf
@@ -49,6 +58,7 @@ class cDNA_Gen:
self.add_compliment()
self.add_records()
self.write_fasta()
+ self.write_csv()
def add_records(self):
self.fasta_records = []
@@ -57,7 +67,7 @@ class cDNA_Gen:
copy_number = row["Transcript_Copy_Number"]
record = SeqRecord(
Seq(row["compliment"]),
- row["seqname"],
+ row["cdna_ID"],
f"Transcript copy number: {copy_number}",
"")
self.fasta_records.append(record)
@@ -96,15 +106,17 @@ class cDNA_Gen:
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"] = ''
-
+ count = 0
+ prev_id = None
# 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'])
+ id_GTF = str(row['seqname'])
+ if id_GTF == prev_id:
+ count += 1
+ else:
+ prev_id = None
+ count = 0
# CVS transcript ID
id_CSV = str(row['seqname']).split('_')[1]
# Calculate Normalized_Binding_Probability and add to GTF dataframe
@@ -112,7 +124,9 @@ class cDNA_Gen:
# 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'])
-
+ df_input_GTF.loc[index,'cdna_ID'] = f"{id_GTF}_{count}"
+ prev_id = id_GTF
+
self.df_input_GTF = df_input_GTF
def write_fasta(self):
@@ -120,7 +134,7 @@ class cDNA_Gen:
SeqIO.write(self.fasta_records, self.output_fasta, "fasta")
def write_csv(self):
- pass
+ self.df_input_GTF[["cdna_ID", "Transcript_Copy_Number"]].to_csv(self.output_csv, index=False)
def return_output(self):
return self.output_fasta, self.output_csv
diff --git a/requirements.txt b/requirements.txt
index cd291123f6021cb082303d6be191fc008d64026f..3abd0040d0dc49c74b00ed3979faa68cb8b5c07d 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1 +1,2 @@
gtfparse
+biopython
\ No newline at end of file
diff --git a/requirements_dev.txt b/requirements_dev.txt
index 3135aba351690e706d8e7721ce014ebcf645fec7..5c28b616b49842bc376717e7a65ece2468a760c0 100644
--- a/requirements_dev.txt
+++ b/requirements_dev.txt
@@ -1,4 +1,5 @@
gtfparse
+biopython
black
flake8
flake8-docstrings
diff --git a/test_files/cDNA.csv b/test_files/cDNA.csv
new file mode 100644
index 0000000000000000000000000000000000000000..d88da423c611025b828e53eb4de0409f8f7d4cbe
--- /dev/null
+++ b/test_files/cDNA.csv
@@ -0,0 +1,7 @@
+cdna_ID,Transcript_Copy_Number
+Transcript_1_0,8.0
+Transcript_1_1,4.0
+Transcript_2_0,11.0
+Transcript_3_0,33.0
+Transcript_4_0,11.0
+Transcript_5_0,55.0
diff --git a/test_files/cDNA.fasta b/test_files/cDNA.fasta
index 1b8d3989aede7948effa7afb4c43a10eac63ebb1..18bd991775a765df6bad34d73d75e47e94aedf4b 100644
--- a/test_files/cDNA.fasta
+++ b/test_files/cDNA.fasta
@@ -1,6 +1,6 @@
->Transcript_1
+>Transcript_1_0
ATCCATAAAAAAAAA
->Transcript_1
+>Transcript_1_1
CATCTCAAAAAGTCT
->Transcript_2
+>Transcript_2_0
AAAAAAAAAAAAAAA