From 4edd965fa21550381ef710b9bd45e6ecd35b2d94 Mon Sep 17 00:00:00 2001
From: baer0006 <max.baer@unibas.ch>
Date: Wed, 16 Nov 2022 23:39:50 +0100
Subject: [PATCH] First attempt on postprocess
---
primingsitepredictor/createtranscript.py | 64 +++++++++++++++++-------
1 file changed, 47 insertions(+), 17 deletions(-)
diff --git a/primingsitepredictor/createtranscript.py b/primingsitepredictor/createtranscript.py
index 9b114cc..4466d92 100644
--- a/primingsitepredictor/createtranscript.py
+++ b/primingsitepredictor/createtranscript.py
@@ -12,27 +12,57 @@ Created on Wed Nov 16 17:48:04 2022
# print(len(content[3:]))
# print((content[3:]))
+import pandas as pd
+import math
+
class CreateTranscript():
def __init__(self):
with open("RIBlast output example.txt", 'r') as file:
- self.list_of_interactions = file.readlines()[3:]
+ self.raw_interactions = file.readlines()[3:]
- def generate_interaction_list(self):
- interaction_list = []
- for i in range(0, (len(self.list_of_interactions)-1)):
- current_interaction = self.list_of_interactions[i].strip(' \n').split(',')
- #print(self.list_of_interactions[i].strip(' \n').split(','))
- interaction_list.append(current_interaction)
- return interaction_list
-
-
-
-transcriptlist = CreateTranscript()
-print(transcriptlist.generate_interaction_list())
-
-#go from interaction list to transcript list? -no we will serve them a interaction list.
-
- # print(content[3:][0].strip(' \n').split(',')[-1].strip('()').split(':'))
+ def generate_interaction_df(self):
+
+ self.interaction_list = []
+
+ #clean up the original list so that we have a neet list
+ for i in range(0, (len(self.raw_interactions)-1)):
+ current_interaction = self.raw_interactions[i].strip(' \n').replace('(', '').replace(')','').replace('-',',').replace(':',',').split(',')
+ self.interaction_list.append(current_interaction)
+
+ #identify if the interaction is the same as the previous one, just shifted by 1 bp (if we have 20 A in the transcript the 15 T primer has 5 matching possibilities although it is only 1 bindingsite)
+ previous_interaction_base = int
+ for i in range(0, len(self.interaction_list)):
+ previous_interaction_base = int(self.interaction_list[i-1][13])
+ if int(self.interaction_list[i][13]) in range(previous_interaction_base-1,previous_interaction_base-15,-1):
+ self.interaction_list[i].append('Repeat')
+ else :
+ self.interaction_list[i].append('Not_repeat')
+
+ #exclude all interactions which are a repeat and belong to the same bindingsite
+ self.cleaned_interaction_list = [item for item in self.interaction_list if item[-1]=='Not_repeat']
+
+
+ #add total number of interactions per transcript and calculate energy
+ self.df = pd.DataFrame(self.cleaned_interaction_list)
+ self.df['Number of interactions'] = int
+ self.df['Interaction Energy'] = float
+
+ energy_constant = 1.380649*10**(-23)*298
+ kcalmol_joul = 6.9477*10**-21
+
+
+ for ind in self.df.index:
+ self.df['Number of interactions'][ind]=self.df[3].value_counts()[self.df[3][ind]]
+ self.df['Interaction Energy'][ind]=math.exp(-float(self.df[5][ind])*kcalmol_joul/energy_constant)
+ print(self.df['Interaction Energy'])
+ print(self.df)
+
+
+ return self.df
+
+transcripts = CreateTranscript()
+interaction_df = transcripts.generate_interaction_df()
+
--
GitLab