remove bad score

.gitignore

@@ -1,3 +1,5 @@
 .envrc
 
-boltz_results/
+boltz_results/
+
+**/__pycache__/

app.py

@@ -191,12 +191,18 @@ def add_plddt_plot(plddt_vals: list[float]) -> str:
 def fake_predict_and_correlate(spr_data_with_scores: pd.DataFrame, score_cols: list[str]) -> tuple[pd.DataFrame, go.Figure]:
     """Fake predict structures of all complexes and correlate the results."""
     corr_data = []
+    spr_data_with_scores["log_kd"] = np.log10(spr_data_with_scores["KD (nM)"])
+    kd_col = "KD (nM)"
     for score_col in score_cols:
-        logging.info("Computing correlation between %s and KD (nM)", score_col)
-        res = spearmanr(spr_data_with_scores["KD (nM)"], spr_data_with_scores[score_col])
+        logger.info(f"Computing correlation between {score_col} and KD (nM)")
+        res = spearmanr(spr_data_with_scores[kd_col], spr_data_with_scores[score_col])
         corr_data.append({"score": score_col, "correlation": res.statistic, "p-value": res.pvalue})
+        logger.info(f"Correlation between {score_col} and KD (nM): {res.statistic}")
 
     corr_data = pd.DataFrame(corr_data)
+    # Find the lines in corr_data with NaN values and remove them
+    corr_data = corr_data[corr_data["correlation"].notna()]
+    logger.info("Correlation data: %s", corr_data)
     # Sort correlation data by correlation value
     corr_data = corr_data.sort_values('correlation', ascending=True)
     
@@ -223,16 +229,16 @@ def fake_predict_and_correlate(spr_data_with_scores: pd.DataFrame, score_cols: l
     for score_col in score_cols:
         scatters.append(
             go.Scatter(
-                x=spr_data_with_scores["KD (nM)"],
+                x=spr_data_with_scores[kd_col],
                 y=spr_data_with_scores[score_col],
-                name=f"KD (nM) vs {score_col}",
+                name=f"{kd_col} vs {score_col}",
                 mode='markers',  # Only show markers/dots, no lines
-                hovertemplate="<i>Score:</i> %{y}<br><i>KD (nM):</i> %{x:.2f}<br>"
+                hovertemplate="<i>Score:</i> %{y}<br><i>KD:</i> %{x:.2f}<br>"
             )   
         )
     corr_plot = go.Figure(data=scatters)
     
-    cols_to_show = ["KD (nM)"]
+    cols_to_show = [kd_col]
     cols_to_show.extend(score_cols)
 
     return spr_data_with_scores[cols_to_show], corr_ranking_plot, corr_plot