Cleaning up previous fasta files

app.py

@@ -1,6 +1,6 @@
 import pandas as pd
 import streamlit as st
-import os
+import os, shutil
 from tiger import tiger_exhibit, load_transcripts, TARGET_LEN, NUCLEOTIDE_TOKENS
 
 
@@ -38,11 +38,15 @@ status_bar_textform = text_form.progress(0)
 fasta_form = st.form("fasta")
 fasta = fasta_form.file_uploader(label="upload fasta file") 
 if fasta:
+    if os.path.exists("temp"):
+        shutil.rmtree("temp")
+    os.makedirs("temp")
     fname = fasta.name 
     st.write(fname)
-    with open(fname,"w") as f:
+    fpath = os.path.join("temp", fname)
+    with open(fpath, "w") as f:
         f.write(fasta.getvalue().decode("utf-8"))
-    transcript_tbl = load_transcripts([fname])
+    transcript_tbl = load_transcripts([fpath])
     fasta_form.text("fasta file contents")
     fasta_form.write(transcript_tbl)
     seq = transcript_tbl['seq'][0]

tiger.py

@@ -24,7 +24,6 @@ for gpu in tf.config.list_physical_devices('GPU'):
 if len(tf.config.list_physical_devices('GPU')) > 0:
     tf.config.experimental.set_visible_devices(tf.config.list_physical_devices('GPU')[0], 'GPU')
 
-
 def load_transcripts(fasta_files):
 
     # load all transcripts from fasta files into a DataFrame
@@ -95,7 +94,7 @@ def process_data(transcript_seq: str):
         tf.reshape(one_hot_encode_sequence(target_seq, add_context_padding=False), [len(target_seq), -1]),
         tf.reshape(one_hot_encode_sequence(guide_seq, add_context_padding=True), [len(guide_seq), -1]),
         ], axis=-1)
-
+    print(model_inputs)
     return target_seq, guide_seq, model_inputs
 
 
@@ -166,8 +165,9 @@ def find_off_targets(top_guides: pd.DataFrame, status_bar, status_text):
             off_targets = pd.concat([off_targets, pd.DataFrame(dict_off_targets)])
 
         # progress update
-        status_text.text("Scanning for off-targets Percent complete: {:.2f}%".format(int(100 * min(i / len(reference_transcripts), 1))))
-        status_bar.progress(int(100 * min(i / len(reference_transcripts), 1)))
+        if status_bar:
+            status_text.text("Scanning for off-targets Percent complete: {:.2f}%".format(int(100 * min(i / len(reference_transcripts), 1))))
+            status_bar.progress(int(100 * min(i / len(reference_transcripts), 1)))
         print('\rPercent complete: {:.2f}%'.format(100 * min(i / len(reference_transcripts), 1)), end='')
     print('')
 
@@ -188,7 +188,7 @@ def predict_off_target(off_targets: pd.DataFrame, model: tf.keras.Model):
     return off_targets.sort_values('Normalized LFC')
 
 
-def tiger_exhibit(transcripts: pd.DataFrame, status_bar, status_text):
+def tiger_exhibit(transcripts: pd.DataFrame, status_bar=None, status_text=None):
 
     # load model
     if os.path.exists('model'):
@@ -206,8 +206,9 @@ def tiger_exhibit(transcripts: pd.DataFrame, status_bar, status_text):
         on_target_predictions = pd.concat([on_target_predictions, df.iloc[:NUM_TOP_GUIDES]])
 
         # progress update
-        status_text.text("Scanning for on-targets Percent complete: {:.2f}%".format(100 * min((i + 1) / len(transcripts), 1)))
-        status_bar.progress(int(100 * min((i + 1) / len(transcripts), 1)))
+        if status_bar:
+            status_text.text("Scanning for on-targets Percent complete: {:.2f}%".format(100 * min((i + 1) / len(transcripts), 1)))
+            status_bar.progress(int(100 * min((i + 1) / len(transcripts), 1)))
         print('\rPercent complete: {:.2f}%'.format(100 * min((i + 1) / len(transcripts), 1)), end='')
     print('')