add text to explain the correlation tab purpose
Browse files- folding_studio_demo/app.py +14 -0
folding_studio_demo/app.py
CHANGED
@@ -154,6 +154,20 @@ def model_comparison(api_key: str) -> None:
|
|
154 |
|
155 |
def create_correlation_tab():
|
156 |
gr.Markdown("# Correlation with experimental binding affinity data")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
spr_data_with_scores = pd.read_csv("spr_af_scores_mapped.csv")
|
158 |
prettified_columns = {
|
159 |
"antibody_name": "Antibody Name",
|
|
|
154 |
|
155 |
def create_correlation_tab():
|
156 |
gr.Markdown("# Correlation with experimental binding affinity data")
|
157 |
+
gr.Markdown("""
|
158 |
+
This analysis explores the relationship between protein folding model confidence scores and experimental binding affinity data.
|
159 |
+
|
160 |
+
The experimental dataset contains binding affinity measurements (KD in nM) between antibody-antigen pairs.
|
161 |
+
Each data point includes:
|
162 |
+
- The antibody's light and heavy chain sequences
|
163 |
+
- The antigen sequence
|
164 |
+
- The experimental KD value
|
165 |
+
|
166 |
+
The analysis involves submitting these sequences to protein folding models for 3D structure prediction.
|
167 |
+
The models generate various confidence scores for each prediction. These scores are then correlated
|
168 |
+
with the experimental binding affinity measurements to evaluate their effectiveness as predictors
|
169 |
+
of binding strength.
|
170 |
+
""")
|
171 |
spr_data_with_scores = pd.read_csv("spr_af_scores_mapped.csv")
|
172 |
prettified_columns = {
|
173 |
"antibody_name": "Antibody Name",
|