unit-interval tiger model with web tool output transformation

model/fingerprint.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d2b657d4a87fe128786cd8435a2f4c8d4e5d08571b12ff8911f100c0ee043b
-size 54
+oid sha256:50863a0916cffccddcaf74e2fd7ce7103ed14ccdd8ab99d668afd4f82c7bddd4
+size 55

model/keras_metadata.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e89af418a7cbb78442c6a65f20f2817352361b826189c4aad0de8a531aa5a8d
-size 13629
+oid sha256:3d0f11e71ac2a87c7492ffcffb4952fa20be69acdf5ae4a0892087fe0534518e
+size 13631

model/saved_model.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f91692a0db6169ce09c321d292a7622468ea1b46c2f2293d97e43aa7c9cb9719
-size 241848
+oid sha256:5c1e3ad2ce93d6b789ac232e88e3504244f5c82ce81266fa698944d75046a79b
+size 242327

model/variables/variables.data-00000-of-00001

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff1487ef1c93444ea6eeb6b023a0f4095aa0af473d98022d8c6e8b9e339d0add
+oid sha256:414d4a3165687fac6ef187601e84b95dbecec6e73a5779ac7f46e099186bdeaa
 size 948103

model/variables/variables.index

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00477f5d3801ba7e566cfcb16d16970ee88a94b716db4232e30ac27115bbfbd
+oid sha256:9443a94e79ea78e84271801274ba69b826c4b1fd2190a9eff9e7406423eb13a3
 size 877

tiger.py

@@ -1,6 +1,7 @@
 import argparse
 import os
 import gzip
+import numpy as np
 import pandas as pd
 import tensorflow as tf
 from Bio import SeqIO
@@ -98,6 +99,19 @@ def process_data(transcript_seq: str):
     return target_seq, guide_seq, model_inputs
 
 
+def prediction_transform(predictions: np.array, cutoff_path: str = 'cutoff.npy'):
+    """
+    :param predictions: in [0,1] where 0 represents most active guides
+    :param cutoff_path: full path to cutoff.npy (a float in [0,1] above which guides are inactive)
+    :return: predictions in [0,1] where 1 represents most active guides
+    """
+    cutoff = np.load(cutoff_path)
+    predictions[predictions > cutoff] = cutoff + (predictions[predictions > cutoff] - cutoff) * 0.01
+    predictions = predictions.max() - predictions
+    predictions = predictions / predictions.max()
+    return predictions
+
+
 def predict_on_target(transcript_seq: str, model: tf.keras.Model):
 
     # parse transcript sequence