progress

app.py

@@ -73,13 +73,16 @@ def process_input():
     # convert to upper case as used by tokenizer
     st.session_state.transcripts[tiger.SEQ_COL] = st.session_state.transcripts[tiger.SEQ_COL].apply(lambda s: s.upper())
 
-    # if src_seq and all([True if nt.upper() in NUCLEOTIDE_TOKENS.keys() else False for nt in src_seq]):
-    # elif src_seq is not None:
-    #     st.write('Invalid input!')
+    # make sure all transcripts only contain nucleotides A, C, G, T, and wildcard N
+    valid = st.session_state.transcripts[tiger.SEQ_COL].apply(lambda s: set(s).issubset(tiger.NUCLEOTIDE_TOKENS.keys()))
+    if not all(valid):
+        with TRANSCRIPT_ENTRY:
+            st.write('Transcript(s) must only contain upper or lower case A, C, G, and Ts')
+        return
 
     print(st.session_state.transcripts)
 
-    # everything looks good to run the model
+    # everything looks good, so run the model
     st.session_state.run = True