update description to give warning about tt3d behavior
Browse files
app.py
CHANGED
@@ -22,29 +22,36 @@ title = "D-SCRIPT: Predicting Protein-Protein Interactions"
|
|
22 |
description = """
|
23 |
"""
|
24 |
|
25 |
-
article = """
|
|
|
|
|
|
|
|
|
26 |
|
27 |
-
<hr>
|
28 |
|
29 |
-
|
|
|
|
|
|
|
|
|
30 |
|
31 |
-
<hr>
|
32 |
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
|
|
38 |
|
39 |
-
<hr>
|
40 |
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
multi-scale, deep-learning model for PPI prediction. While Topsy-Turvy makes predictions using only sequence data, during the training phase it takes a transfer-learning approach by
|
45 |
-
incorporating patterns from both global and molecular-level views of protein interaction. In a cross-species context, we show it achieves state-of-the-art performance, offering the
|
46 |
-
ability to perform genome-scale, interpretable PPI prediction for non-model organisms with no existing experimental PPI data.
|
47 |
|
|
|
|
|
48 |
|
49 |
"""
|
50 |
|
@@ -168,7 +175,7 @@ demo = gr.Interface(
|
|
168 |
],
|
169 |
# title = title,
|
170 |
# description = description,
|
171 |
-
|
172 |
theme = theme,
|
173 |
)
|
174 |
|
|
|
22 |
description = """
|
23 |
"""
|
24 |
|
25 |
+
# article = """
|
26 |
+
|
27 |
+
# <hr>
|
28 |
+
|
29 |
+
# <img style="margin-left:auto; margin-right:auto" src="https://raw.githubusercontent.com/samsledje/D-SCRIPT/main/docs/source/img/dscript_architecture.png" alt="D-SCRIPT architecture" width="70%"/>
|
30 |
|
31 |
+
# <hr>
|
32 |
|
33 |
+
# D-SCRIPT is a deep learning method for predicting a physical interaction between two proteins given just their sequences.
|
34 |
+
# It generalizes well to new species and is robust to limitations in training data size. Its design reflects the intuition that for two proteins to physically interact,
|
35 |
+
# a subset of amino acids from each protein should be in contact with the other. The intermediate stages of D-SCRIPT directly implement this intuition, with the penultimate stage
|
36 |
+
# in D-SCRIPT being a rough estimate of the inter-protein contact map of the protein dimer. This structurally-motivated design enhances the interpretability of the results and,
|
37 |
+
# since structure is more conserved evolutionarily than sequence, improves generalizability across species.
|
38 |
|
39 |
+
# <hr>
|
40 |
|
41 |
+
# Computational methods to predict protein-protein interaction (PPI) typically segregate into sequence-based "bottom-up" methods that infer properties from the characteristics of the
|
42 |
+
# individual protein sequences, or global "top-down" methods that infer properties from the pattern of already known PPIs in the species of interest. However, a way to incorporate
|
43 |
+
# top-down insights into sequence-based bottom-up PPI prediction methods has been elusive. Topsy-Turvy builds upon D-SCRIPT by synthesizing both views in a sequence-based,
|
44 |
+
# multi-scale, deep-learning model for PPI prediction. While Topsy-Turvy makes predictions using only sequence data, during the training phase it takes a transfer-learning approach by
|
45 |
+
# incorporating patterns from both global and molecular-level views of protein interaction. In a cross-species context, we show it achieves state-of-the-art performance, offering the
|
46 |
+
# ability to perform genome-scale, interpretable PPI prediction for non-model organisms with no existing experimental PPI data.
|
47 |
|
|
|
48 |
|
49 |
+
# """
|
50 |
+
|
51 |
+
article = """
|
|
|
|
|
|
|
52 |
|
53 |
+
Note that running here with the "TT3D" model does not run structure prediction on the sequences, but rather uses the [ProstT5](https://github.com/mheinzinger/ProstT5) language model to
|
54 |
+
translate amino acid to 3di sequences. This is much faster than running structure prediction, but the results may not be as accurate.
|
55 |
|
56 |
"""
|
57 |
|
|
|
175 |
],
|
176 |
# title = title,
|
177 |
# description = description,
|
178 |
+
article = article,
|
179 |
theme = theme,
|
180 |
)
|
181 |
|