progress

app.py

@@ -40,16 +40,14 @@ def entry_method_change_callback():
 def process_input():
 
     # initialize transcript DataFrame
-    st.session_state.transcripts = pd.DataFrame()
+    st.session_state.transcripts = pd.DataFrame(columns=[tiger.ID_COL, tiger.SEQ_COL])
 
     # manual entry
     if st.session_state.entry_method == ENTRY_METHODS['manual']:
-        sequence = st.session_state.manual_entry
-        if len(sequence) < tiger.TARGET_LEN:
-            with TRANSCRIPT_ENTRY:
-                st.write('Transcript must be at least {:d} bases.'.format(tiger.TARGET_LEN))
-        else:
-            st.session_state.transcripts = pd.DataFrame({tiger.ID_COL: ['ManualEntry'], tiger.SEQ_COL: [sequence]})
+        st.session_state.transcripts = pd.DataFrame({
+            tiger.ID_COL: ['ManualEntry'],
+            tiger.SEQ_COL: [st.session_state.manual_entry]
+        })
 
     # fasta file upload
     elif st.session_state.entry_method == ENTRY_METHODS['fasta']:
@@ -64,15 +62,23 @@ def process_input():
             else:
                 st.session_state.transcripts = df
 
-    # convert ot upper case as used by tokenizer
+    # 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())
 
+    # make sure all transcripts satisfy length requirements
+    too_short = st.session_state.transcripts[tiger.SEQ_COL].apply(lambda s: len(s)) < tiger.TARGET_LEN
+    if any(too_short):
+        with TRANSCRIPT_ENTRY:
+            st.write('Transcript(s) must be at least {:d} bases.'.format(tiger.TARGET_LEN))
 
     # 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!')
     print(st.session_state.transcripts)
 
+    # everything looks good to run the model
+    st.session_state.run = True
+
 
 if __name__ == '__main__':