better describe model
Browse files- folding_studio_demo/app.py +2 -27
- folding_studio_demo/correlate.py +40 -14
folding_studio_demo/app.py
CHANGED
@@ -13,7 +13,8 @@ from folding_studio_demo.correlate import (
|
|
13 |
fake_predict_and_correlate,
|
14 |
make_regression_plot,
|
15 |
compute_correlation_data,
|
16 |
-
plot_correlation_ranking
|
|
|
17 |
)
|
18 |
from folding_studio_demo.predict import predict, predict_comparison
|
19 |
|
@@ -235,32 +236,6 @@ def create_correlation_tab():
|
|
235 |
with gr.Row():
|
236 |
log_scale = gr.Checkbox(label="Display x-axis on logarithmic scale", value=False)
|
237 |
with gr.Row():
|
238 |
-
def get_score_description(score: str) -> str:
|
239 |
-
descriptions = {
|
240 |
-
"Boltz Confidence Score": "The Boltz confidence score provides an overall assessment of prediction quality (0-1, higher is better).",
|
241 |
-
"Boltz pTM Score": "The Boltz predicted TM-score (pTM) assesses the overall fold accuracy of the predicted structure (0-1, higher is better).",
|
242 |
-
"Boltz ipTM Score": "The Boltz interface pTM score (ipTM) specifically evaluates the accuracy of interface regions (0-1, higher is better).",
|
243 |
-
"Boltz Complex pLDDT": "The Boltz Complex pLDDT measures confidence in local structure predictions across the entire complex (0-100, higher is better).",
|
244 |
-
"Boltz Complex ipLDDT": "The Boltz Complex interface pLDDT (ipLDDT) focuses on confidence in interface region predictions (0-100, higher is better).",
|
245 |
-
"Boltz Complex pDE": "The Boltz Complex predicted distance error (pDE) estimates the confidence in predicted distances between residues (0-1, higher is better).",
|
246 |
-
"Boltz Complex ipDE": "The Boltz Complex interface pDE (ipDE) estimates confidence in predicted distances specifically at interfaces (0-1, higher is better).",
|
247 |
-
"Monomer Interchain PAE": "The monomer interchain predicted aligned error (PAE) estimates position errors between chains in monomeric predictions (lower is better).",
|
248 |
-
"Monomer Interface PAE": "The monomer interface PAE estimates position errors specifically at interfaces in monomeric predictions (lower is better).",
|
249 |
-
"Monomer Overall PAE": "The monomer overall PAE estimates position errors across the entire structure in monomeric predictions (lower is better).",
|
250 |
-
"Monomer Interface pLDDT": "The monomer interface pLDDT measures confidence in interface region predictions for monomeric models (0-100, higher is better).",
|
251 |
-
"Monomer Average pLDDT": "The monomer average pLDDT provides the mean confidence across all residues in monomeric predictions (0-100, higher is better).",
|
252 |
-
"Monomer pTM Score": "The monomer pTM score assesses overall fold accuracy in monomeric predictions (0-1, higher is better).",
|
253 |
-
"Monomer Interface pTM": "The monomer interface pTM specifically evaluates accuracy of interface regions in monomeric predictions (0-1, higher is better).",
|
254 |
-
"Multimer Interchain PAE": "The multimer interchain PAE estimates position errors between chains in multimeric predictions (lower is better).",
|
255 |
-
"Multimer Interface PAE": "The multimer interface PAE estimates position errors specifically at interfaces in multimeric predictions (lower is better).",
|
256 |
-
"Multimer Overall PAE": "The multimer overall PAE estimates position errors across the entire structure in multimeric predictions (lower is better).",
|
257 |
-
"Multimer Interface pLDDT": "The multimer interface pLDDT measures confidence in interface region predictions for multimeric models (0-100, higher is better).",
|
258 |
-
"Multimer Average pLDDT": "The multimer average pLDDT provides the mean confidence across all residues in multimeric predictions (0-100, higher is better).",
|
259 |
-
"Multimer pTM Score": "The multimer pTM score assesses overall fold accuracy in multimeric predictions (0-1, higher is better).",
|
260 |
-
"Multimer Interface pTM": "The multimer interface pTM specifically evaluates accuracy of interface regions in multimeric predictions (0-1, higher is better)."
|
261 |
-
}
|
262 |
-
return descriptions.get(score, "No description available for this score.")
|
263 |
-
|
264 |
score_description = gr.Markdown(get_score_description(correlation_column.value))
|
265 |
correlation_column.change(
|
266 |
fn=lambda x: get_score_description(x),
|
|
|
13 |
fake_predict_and_correlate,
|
14 |
make_regression_plot,
|
15 |
compute_correlation_data,
|
16 |
+
plot_correlation_ranking,
|
17 |
+
get_score_description
|
18 |
)
|
19 |
from folding_studio_demo.predict import predict, predict_comparison
|
20 |
|
|
|
236 |
with gr.Row():
|
237 |
log_scale = gr.Checkbox(label="Display x-axis on logarithmic scale", value=False)
|
238 |
with gr.Row():
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
239 |
score_description = gr.Markdown(get_score_description(correlation_column.value))
|
240 |
correlation_column.change(
|
241 |
fn=lambda x: get_score_description(x),
|
folding_studio_demo/correlate.py
CHANGED
@@ -15,24 +15,50 @@ SCORE_COLUMN_NAMES = {
|
|
15 |
"complex_iplddt_boltz": "Boltz Complex ipLDDT",
|
16 |
"complex_pde_boltz": "Boltz Complex pDE",
|
17 |
"complex_ipde_boltz": "Boltz Complex ipDE",
|
18 |
-
"interchain_pae_monomer": "
|
19 |
-
"interface_pae_monomer": "
|
20 |
-
"overall_pae_monomer": "
|
21 |
-
"interface_plddt_monomer": "
|
22 |
-
"average_plddt_monomer": "
|
23 |
-
"ptm_monomer": "
|
24 |
-
"interface_ptm_monomer": "
|
25 |
-
"interchain_pae_multimer": "Multimer Interchain PAE",
|
26 |
-
"interface_pae_multimer": "Multimer Interface PAE",
|
27 |
-
"overall_pae_multimer": "Multimer Overall PAE",
|
28 |
-
"interface_plddt_multimer": "Multimer Interface pLDDT",
|
29 |
-
"average_plddt_multimer": "Multimer Average pLDDT",
|
30 |
-
"ptm_multimer": "Multimer pTM Score",
|
31 |
-
"interface_ptm_multimer": "Multimer Interface pTM"
|
32 |
}
|
33 |
|
34 |
SCORE_COLUMNS = list(SCORE_COLUMN_NAMES.values())
|
35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
def compute_correlation_data(spr_data_with_scores: pd.DataFrame, score_cols: list[str]) -> pd.DataFrame:
|
37 |
corr_data_file = Path("corr_data.csv")
|
38 |
if corr_data_file.exists():
|
|
|
15 |
"complex_iplddt_boltz": "Boltz Complex ipLDDT",
|
16 |
"complex_pde_boltz": "Boltz Complex pDE",
|
17 |
"complex_ipde_boltz": "Boltz Complex ipDE",
|
18 |
+
"interchain_pae_monomer": "AlphaFold2 GapTrick Interchain PAE",
|
19 |
+
"interface_pae_monomer": "AlphaFold2 GapTrick Interface PAE",
|
20 |
+
"overall_pae_monomer": "AlphaFold2 GapTrick Overall PAE",
|
21 |
+
"interface_plddt_monomer": "AlphaFold2 GapTrick Interface pLDDT",
|
22 |
+
"average_plddt_monomer": "AlphaFold2 GapTrick Average pLDDT",
|
23 |
+
"ptm_monomer": "AlphaFold2 GapTrick pTM Score",
|
24 |
+
"interface_ptm_monomer": "AlphaFold2 GapTrick Interface pTM",
|
25 |
+
"interchain_pae_multimer": "AlphaFold2 Multimer Interchain PAE",
|
26 |
+
"interface_pae_multimer": "AlphaFold2 Multimer Interface PAE",
|
27 |
+
"overall_pae_multimer": "AlphaFold2 Multimer Overall PAE",
|
28 |
+
"interface_plddt_multimer": "AlphaFold2 Multimer Interface pLDDT",
|
29 |
+
"average_plddt_multimer": "AlphaFold2 Multimer Average pLDDT",
|
30 |
+
"ptm_multimer": "AlphaFold2 Multimer pTM Score",
|
31 |
+
"interface_ptm_multimer": "AlphaFold2 Multimer Interface pTM"
|
32 |
}
|
33 |
|
34 |
SCORE_COLUMNS = list(SCORE_COLUMN_NAMES.values())
|
35 |
|
36 |
+
def get_score_description(score: str) -> str:
|
37 |
+
descriptions = {
|
38 |
+
"Boltz Confidence Score": "The Boltz model confidence score provides an overall assessment of prediction quality (0-1, higher is better).",
|
39 |
+
"Boltz pTM Score": "The Boltz model predicted TM-score (pTM) assesses the overall fold accuracy of the predicted structure (0-1, higher is better).",
|
40 |
+
"Boltz ipTM Score": "The Boltz model interface pTM score (ipTM) specifically evaluates the accuracy of interface regions (0-1, higher is better).",
|
41 |
+
"Boltz Complex pLDDT": "The Boltz model Complex pLDDT measures confidence in local structure predictions across the entire complex (0-100, higher is better).",
|
42 |
+
"Boltz Complex ipLDDT": "The Boltz model Complex interface pLDDT (ipLDDT) focuses on confidence in interface region predictions (0-100, higher is better).",
|
43 |
+
"Boltz Complex pDE": "The Boltz model Complex predicted distance error (pDE) estimates the confidence in predicted distances between residues (0-1, higher is better).",
|
44 |
+
"Boltz Complex ipDE": "The Boltz model Complex interface pDE (ipDE) estimates confidence in predicted distances specifically at interfaces (0-1, higher is better).",
|
45 |
+
"AlphaFold2 GapTrick Interchain PAE": "The AlphaFold2 GapTrick model interchain predicted aligned error (PAE) estimates position errors between chains in monomeric predictions (lower is better).",
|
46 |
+
"AlphaFold2 GapTrick Interface PAE": "The AlphaFold2 GapTrick model interface PAE estimates position errors specifically at interfaces in monomeric predictions (lower is better).",
|
47 |
+
"AlphaFold2 GapTrick Overall PAE": "The AlphaFold2 GapTrick model overall PAE estimates position errors across the entire structure in monomeric predictions (lower is better).",
|
48 |
+
"AlphaFold2 GapTrick Interface pLDDT": "The AlphaFold2 GapTrick model interface pLDDT measures confidence in interface region predictions for monomeric models (0-100, higher is better).",
|
49 |
+
"AlphaFold2 GapTrick Average pLDDT": "The AlphaFold2 GapTrick model average pLDDT provides the mean confidence across all residues in monomeric predictions (0-100, higher is better).",
|
50 |
+
"AlphaFold2 GapTrick pTM Score": "The AlphaFold2 GapTrick model pTM score assesses overall fold accuracy in monomeric predictions (0-1, higher is better).",
|
51 |
+
"AlphaFold2 GapTrick Interface pTM": "The AlphaFold2 GapTrick model interface pTM specifically evaluates accuracy of interface regions in monomeric predictions (0-1, higher is better).",
|
52 |
+
"AlphaFold2 GapTrick Interchain PAE": "The AlphaFold2 GapTrick model interchain PAE estimates position errors between chains in multimeric predictions (lower is better).",
|
53 |
+
"AlphaFold2 Multimer Interface PAE": "The AlphaFold2 Multimer model interface PAE estimates position errors specifically at interfaces in multimeric predictions (lower is better).",
|
54 |
+
"AlphaFold2 Multimer Overall PAE": "The AlphaFold2 Multimer model overall PAE estimates position errors across the entire structure in multimeric predictions (lower is better).",
|
55 |
+
"AlphaFold2 Multimer Interface pLDDT": "The AlphaFold2 Multimer model interface pLDDT measures confidence in interface region predictions for multimeric models (0-100, higher is better).",
|
56 |
+
"AlphaFold2 Multimer Average pLDDT": "The AlphaFold2 Multimer model average pLDDT provides the mean confidence across all residues in multimeric predictions (0-100, higher is better).",
|
57 |
+
"AlphaFold2 Multimer pTM Score": "The AlphaFold2 Multimer model pTM score assesses overall fold accuracy in multimeric predictions (0-1, higher is better).",
|
58 |
+
"AlphaFold2 Multimer Interface pTM": "The AlphaFold2 Multimer model interface pTM specifically evaluates accuracy of interface regions in multimeric predictions (0-1, higher is better)."
|
59 |
+
}
|
60 |
+
return descriptions.get(score, "No description available for this score.")
|
61 |
+
|
62 |
def compute_correlation_data(spr_data_with_scores: pd.DataFrame, score_cols: list[str]) -> pd.DataFrame:
|
63 |
corr_data_file = Path("corr_data.csv")
|
64 |
if corr_data_file.exists():
|