better describe model

folding_studio_demo/app.py

@@ -13,7 +13,8 @@ from folding_studio_demo.correlate import (
     fake_predict_and_correlate,
     make_regression_plot,
     compute_correlation_data,
-    plot_correlation_ranking
+    plot_correlation_ranking,
+    get_score_description
 )
 from folding_studio_demo.predict import predict, predict_comparison
 
@@ -235,32 +236,6 @@ def create_correlation_tab():
             with gr.Row():
                 log_scale = gr.Checkbox(label="Display x-axis on logarithmic scale", value=False)
             with gr.Row():
-                def get_score_description(score: str) -> str:
-                    descriptions = {
-                        "Boltz Confidence Score": "The Boltz confidence score provides an overall assessment of prediction quality (0-1, higher is better).",
-                        "Boltz pTM Score": "The Boltz predicted TM-score (pTM) assesses the overall fold accuracy of the predicted structure (0-1, higher is better).",
-                        "Boltz ipTM Score": "The Boltz interface pTM score (ipTM) specifically evaluates the accuracy of interface regions (0-1, higher is better).",
-                        "Boltz Complex pLDDT": "The Boltz Complex pLDDT measures confidence in local structure predictions across the entire complex (0-100, higher is better).",
-                        "Boltz Complex ipLDDT": "The Boltz Complex interface pLDDT (ipLDDT) focuses on confidence in interface region predictions (0-100, higher is better).",
-                        "Boltz Complex pDE": "The Boltz Complex predicted distance error (pDE) estimates the confidence in predicted distances between residues (0-1, higher is better).",
-                        "Boltz Complex ipDE": "The Boltz Complex interface pDE (ipDE) estimates confidence in predicted distances specifically at interfaces (0-1, higher is better).",
-                        "Monomer Interchain PAE": "The monomer interchain predicted aligned error (PAE) estimates position errors between chains in monomeric predictions (lower is better).",
-                        "Monomer Interface PAE": "The monomer interface PAE estimates position errors specifically at interfaces in monomeric predictions (lower is better).",
-                        "Monomer Overall PAE": "The monomer overall PAE estimates position errors across the entire structure in monomeric predictions (lower is better).",
-                        "Monomer Interface pLDDT": "The monomer interface pLDDT measures confidence in interface region predictions for monomeric models (0-100, higher is better).",
-                        "Monomer Average pLDDT": "The monomer average pLDDT provides the mean confidence across all residues in monomeric predictions (0-100, higher is better).",
-                        "Monomer pTM Score": "The monomer pTM score assesses overall fold accuracy in monomeric predictions (0-1, higher is better).",
-                        "Monomer Interface pTM": "The monomer interface pTM specifically evaluates accuracy of interface regions in monomeric predictions (0-1, higher is better).",
-                        "Multimer Interchain PAE": "The multimer interchain PAE estimates position errors between chains in multimeric predictions (lower is better).",
-                        "Multimer Interface PAE": "The multimer interface PAE estimates position errors specifically at interfaces in multimeric predictions (lower is better).", 
-                        "Multimer Overall PAE": "The multimer overall PAE estimates position errors across the entire structure in multimeric predictions (lower is better).",
-                        "Multimer Interface pLDDT": "The multimer interface pLDDT measures confidence in interface region predictions for multimeric models (0-100, higher is better).",
-                        "Multimer Average pLDDT": "The multimer average pLDDT provides the mean confidence across all residues in multimeric predictions (0-100, higher is better).",
-                        "Multimer pTM Score": "The multimer pTM score assesses overall fold accuracy in multimeric predictions (0-1, higher is better).",
-                        "Multimer Interface pTM": "The multimer interface pTM specifically evaluates accuracy of interface regions in multimeric predictions (0-1, higher is better)."
-                    }
-                    return descriptions.get(score, "No description available for this score.")
-
                 score_description = gr.Markdown(get_score_description(correlation_column.value))
                 correlation_column.change(
                     fn=lambda x: get_score_description(x),

folding_studio_demo/correlate.py

@@ -15,24 +15,50 @@ SCORE_COLUMN_NAMES = {
     "complex_iplddt_boltz": "Boltz Complex ipLDDT",
     "complex_pde_boltz": "Boltz Complex pDE",
     "complex_ipde_boltz": "Boltz Complex ipDE",
-    "interchain_pae_monomer": "Monomer Interchain PAE",
-    "interface_pae_monomer": "Monomer Interface PAE", 
-    "overall_pae_monomer": "Monomer Overall PAE",
-    "interface_plddt_monomer": "Monomer Interface pLDDT",
-    "average_plddt_monomer": "Monomer Average pLDDT",
-    "ptm_monomer": "Monomer pTM Score",
-    "interface_ptm_monomer": "Monomer Interface pTM",
-    "interchain_pae_multimer": "Multimer Interchain PAE",
-    "interface_pae_multimer": "Multimer Interface PAE",
-    "overall_pae_multimer": "Multimer Overall PAE", 
-    "interface_plddt_multimer": "Multimer Interface pLDDT",
-    "average_plddt_multimer": "Multimer Average pLDDT",
-    "ptm_multimer": "Multimer pTM Score",
-    "interface_ptm_multimer": "Multimer Interface pTM"
+    "interchain_pae_monomer": "AlphaFold2 GapTrick Interchain PAE",
+    "interface_pae_monomer": "AlphaFold2 GapTrick Interface PAE", 
+    "overall_pae_monomer": "AlphaFold2 GapTrick Overall PAE",
+    "interface_plddt_monomer": "AlphaFold2 GapTrick Interface pLDDT",
+    "average_plddt_monomer": "AlphaFold2 GapTrick Average pLDDT",
+    "ptm_monomer": "AlphaFold2 GapTrick pTM Score",
+    "interface_ptm_monomer": "AlphaFold2 GapTrick Interface pTM",
+    "interchain_pae_multimer": "AlphaFold2 Multimer Interchain PAE",
+    "interface_pae_multimer": "AlphaFold2 Multimer Interface PAE",
+    "overall_pae_multimer": "AlphaFold2 Multimer Overall PAE", 
+    "interface_plddt_multimer": "AlphaFold2 Multimer Interface pLDDT",
+    "average_plddt_multimer": "AlphaFold2 Multimer Average pLDDT",
+    "ptm_multimer": "AlphaFold2 Multimer pTM Score",
+    "interface_ptm_multimer": "AlphaFold2 Multimer Interface pTM"
 }
 
 SCORE_COLUMNS = list(SCORE_COLUMN_NAMES.values())
 
+def get_score_description(score: str) -> str:
+    descriptions = {
+        "Boltz Confidence Score": "The Boltz model confidence score provides an overall assessment of prediction quality (0-1, higher is better).",
+        "Boltz pTM Score": "The Boltz model predicted TM-score (pTM) assesses the overall fold accuracy of the predicted structure (0-1, higher is better).",
+        "Boltz ipTM Score": "The Boltz model interface pTM score (ipTM) specifically evaluates the accuracy of interface regions (0-1, higher is better).",
+        "Boltz Complex pLDDT": "The Boltz model Complex pLDDT measures confidence in local structure predictions across the entire complex (0-100, higher is better).",
+        "Boltz Complex ipLDDT": "The Boltz model Complex interface pLDDT (ipLDDT) focuses on confidence in interface region predictions (0-100, higher is better).",
+        "Boltz Complex pDE": "The Boltz model Complex predicted distance error (pDE) estimates the confidence in predicted distances between residues (0-1, higher is better).",
+        "Boltz Complex ipDE": "The Boltz model Complex interface pDE (ipDE) estimates confidence in predicted distances specifically at interfaces (0-1, higher is better).",
+        "AlphaFold2 GapTrick Interchain PAE": "The AlphaFold2 GapTrick model interchain predicted aligned error (PAE) estimates position errors between chains in monomeric predictions (lower is better).",
+        "AlphaFold2 GapTrick Interface PAE": "The AlphaFold2 GapTrick model interface PAE estimates position errors specifically at interfaces in monomeric predictions (lower is better).",
+        "AlphaFold2 GapTrick Overall PAE": "The AlphaFold2 GapTrick model overall PAE estimates position errors across the entire structure in monomeric predictions (lower is better).",
+        "AlphaFold2 GapTrick Interface pLDDT": "The AlphaFold2 GapTrick model interface pLDDT measures confidence in interface region predictions for monomeric models (0-100, higher is better).",
+        "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).",
+        "AlphaFold2 GapTrick pTM Score": "The AlphaFold2 GapTrick model pTM score assesses overall fold accuracy in monomeric predictions (0-1, higher is better).",
+        "AlphaFold2 GapTrick Interface pTM": "The AlphaFold2 GapTrick model interface pTM specifically evaluates accuracy of interface regions in monomeric predictions (0-1, higher is better).",
+        "AlphaFold2 GapTrick Interchain PAE": "The AlphaFold2 GapTrick model interchain PAE estimates position errors between chains in multimeric predictions (lower is better).",
+        "AlphaFold2 Multimer Interface PAE": "The AlphaFold2 Multimer model interface PAE estimates position errors specifically at interfaces in multimeric predictions (lower is better).", 
+        "AlphaFold2 Multimer Overall PAE": "The AlphaFold2 Multimer model overall PAE estimates position errors across the entire structure in multimeric predictions (lower is better).",
+        "AlphaFold2 Multimer Interface pLDDT": "The AlphaFold2 Multimer model interface pLDDT measures confidence in interface region predictions for multimeric models (0-100, higher is better).",
+        "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).",
+        "AlphaFold2 Multimer pTM Score": "The AlphaFold2 Multimer model pTM score assesses overall fold accuracy in multimeric predictions (0-1, higher is better).",
+        "AlphaFold2 Multimer Interface pTM": "The AlphaFold2 Multimer model interface pTM specifically evaluates accuracy of interface regions in multimeric predictions (0-1, higher is better)."
+    }
+    return descriptions.get(score, "No description available for this score.")
+
 def compute_correlation_data(spr_data_with_scores: pd.DataFrame, score_cols: list[str]) -> pd.DataFrame:
     corr_data_file = Path("corr_data.csv")
     if corr_data_file.exists():