Create app.py

app.py

@@ -0,0 +1,138 @@
+import gradio as gr
+
+base_pairing = {'A':'U', 'U':'A', 'C':'G','G':'C'}
+
+#def transcribe(seq): 
+  #RNA_seq = seq.replace('T', 'U')
+  ### Define location of start codon (AUG)
+  #start_codon = RNA_seq.find('AUG')
+  #codons = []
+
+  #for i in range(start_codon, len(RNA_seq), 3): 
+    #codon = RNA_seq[i:i + 3]
+    #if len(codon)==3:
+        #codons.append(codon)
+  #return codons
+
+####################################################################################### 
+# define dictionary to translate three-letter mRNA to three-letter amino acid here 
+#######################################################################################
+
+translate = { 
+  'UUU':'Phe','UCU':'Ser','UAU':'Tyr','UGU':'Cys',
+  'UUC':'Phe','UCC':'Ser','UAC':'Tyr','UGC':'Cys',
+  'UUA':'Leu','UCA':'Ser','UAA':'Stop','UGA':'Stop',
+  'UUG':'Leu','UCG':'Ser','UAG':'Stop','UGG':'Trp',
+  'CUU':'Leu','CCU':'Pro','CAU':'His','CGU':'Arg',
+  'CUC':'Leu','CCC':'Pro','CAC':'His','CGC':'Arg',
+  'CUA':'Leu','CCA':'Pro','CAA':'Gln','CGA':'Arg',
+  'CUG':'Leu','CCG':'Pro','CAG':'Gln','CGG':'Arg',
+  'AUU':'Ile','ACU':'Thr','AAU':'Asn','AGU':'Ser',
+  'AUC':'Ile','ACC':'Thr','AAC':'Asn','AGC':'Ser',
+  'AUA':'Ile','ACA':'Thr','AAA':'Lys','AGA':'Arg',
+  'AUG':'Met','ACG':'Thr','AAG':'Lys','AGG':'Arg',
+  'GUU':'Val','GCU':'Ala','GAU':'Asp','GGU':'Gly',
+  'GUC':'Val','GCC':'Ala','GAC':'Asp','GGC':'Gly',
+  'GUA':'Val','GCA':'Ala','GAA':'Glu','GGA':'Gly',
+  'GUG':'Val','GCG':'Ala','GAG':'Glu','GGG':'Gly'
+}
+
+#######################################################################################
+# define dictionary to map three-letter amino acid to one-letter amino acid here
+#######################################################################################
+
+AA_mapping = {
+    'Ala':'A', 'Arg':'R','Asn':'N',
+    'Asp':'D', 'Cys':'C','Gln':'Q',
+    'Glu':'E', 'Gly':'G','His':'H',
+    'Ile':'I', 'Leu':'L','Lys':'K',
+    'Met':'M', 'Phe':'F','Pro':'P',
+    'Ser':'S', 'Thr':'T','Trp':'W',
+    'Tyr':'Y','Val':'V'
+}
+
+def transcribe(seq): 
+  RNA_seq = seq.replace('T', 'U')
+  reading_frames = []
+  # forward strand
+
+  for pos in range(0,3):
+    codons = []
+    for i in range(pos, len(RNA_seq), 3): 
+      codon = RNA_seq[i:i + 3]
+      if len(codon)==3:
+          codons.append(codon)
+    reading_frames.append(codons)
+
+  # reverse strand
+  RNA_seq_rev = RNA_seq[::-1]
+  cDNA = ''
+  for i in range(0, len(RNA_seq_rev)):
+    cDNA += base_pairing[RNA_seq_rev[i]]
+
+  for pos in range(0,3):
+    codons = []
+    for i in range(pos, len(cDNA), 3): 
+      codon = cDNA[i:i + 3]
+      if len(codon)==3:
+          codons.append(codon)
+    reading_frames.append(codons)
+
+  return reading_frames
+
+def get_protein_from_DNA(DNA):
+  reading_frames =transcribe(DNA)
+  orf_list = []
+
+  for i in range(len(reading_frames)):
+      mRNA = reading_frames[i]
+      one_letter=''
+      found_start = False
+      for codon in mRNA:
+          if codon =='AUG' and not found_start:
+            one_letter +=  '<'
+            found_start = True
+          if codon =='UAA' or codon=='UGA'or codon =='UAG':
+            if found_start:
+              one_letter +=  '>'
+              found_start = False
+            continue
+          one_letter +=  AA_mapping[translate[codon]]
+
+      # mark the valid orf found
+      if one_letter.find('M') != -1:
+        one_letter = '*' + one_letter + '>'
+      orf_list.append(one_letter)
+
+  r = " * means the ORF sequence exists and highlighted in as <>; \n5'to 3' Frame 1:"+ orf_list[0] +"\n5'to 3' Frame 2:" + orf_list[1] + "\n5'to 3' Frame 3:" + orf_list[2] + "\n3'to 5' Frame 1:" + orf_list[3] + "\n3'to 5' Frame 2:" + orf_list[4] + "\n3'to 5' Frame 3:"+orf_list[5] 
+  return r
+
+
+results = get_protein_from_DNA(DNA)
+
+def highlight_text(string_in):
+  string_in=string_in.replace('<','\033[1m\033[94m')
+  string_in=string_in.replace('>','\033[0m')
+  print(string_in)
+
+highlight_text(results)
+
+
+##configure inputs/outputs
+
+input_module = gr.inputs.Textbox(label = "Enter your DNA sequence in the box:")
+output_module = gr.outputs.Textbox(label = 'Protein sequence')
+
+### configure gradio, detailed can be found at https://www.gradio.app/docs/#i_slider
+interface = gr.Interface(fn=get_protein_from_DNA, 
+                         inputs=input_module, 
+                         outputs=output_module,
+                         title="CSCI1020 Demo 2: Web Application for DNA Transcrioption & RNA Translation", 
+                         description= "Click examples below for a quick demo",
+                         theme = 'huggingface',
+                         layout = 'vertical'
+                         )
+interface.launch()
+
+
+