cursor unhinged

folding_studio_demo/app.py

@@ -269,25 +269,24 @@ def model_comparison(api_key: str) -> None:
 def create_antibody_discovery_tab():
     gr.Markdown("# Accelerating Antibody Discovery: In-Silico and Experimental Insights")
     gr.Markdown("""
-        This analysis explores the relationship between protein folding model confidence scores and experimental binding affinity data, with the goal of accelerating antibody drug discovery.
-        
-        The experimental dataset contains binding affinity measurements (KD in nM) between different antibodies and a fixed antigen target. 
-        Each data point includes:
-        - The antibody's light and heavy chain sequences
-        - The antigen sequence
-        - The experimental KD value (binding strength)
+        Hey there! 👋 Let's dive into how we're using AI to speed up antibody drug discovery by looking at how protein folding models stack up against real lab data.
+
+        We've got this cool dataset that shows how well different antibodies stick to a specific target (we measure this as KD in nM). 🧪
+        For each antibody-target pair, we've recorded:
+        - The antibody's light and heavy chain sequences (think of them as the antibody's building blocks) 🧬
+        - The target (antigen) sequence 🎯
+        - How strongly they bind together in the lab (the KD value, lower means stronger binding) 💪
         
-        The analysis involves submitting these sequences to protein folding models for 3D structure prediction.
-        The models generate various confidence scores for each prediction. By correlating these scores
-        with the experimental binding affinity measurements, we can identify which confidence metrics
-        are the best predictors of actual binding strength.
+        Here's where it gets interesting! We take these sequences and feed them into protein folding models
+        that predict their 3D structures. The models tell us how confident they are about their predictions.
+        By comparing these confidence scores with our lab results, we can figure out which model scores
+        are actually good at predicting real binding strength! 🎯
         
-        This correlation study has important implications for drug discovery: once we identify a reliable
-        computational predictor of binding affinity, we can use it to rapidly screen thousands of candidate
-        antibody sequences in-silico. This computational approach is much faster than experimental testing,
-        allowing us to efficiently identify promising antibody candidates that are likely to bind strongly
-        to the target antigen. The best candidates can then be validated experimentally, significantly
-        accelerating the drug discovery process.
+        Why is this super exciting for drug discovery? 🚀 Once we know which computational scores to trust,
+        we can use them to quickly check thousands of potential antibodies without having to test each one
+        in the lab. It's like having a super-fast screening tool! We can then focus our lab work on testing
+        just the most promising candidates. This means we can find effective antibody drugs way faster than
+        before! 🔬✨
     """)
     spr_data_with_scores = pd.read_csv("spr_af_scores_mapped.csv")
     spr_data_with_scores = spr_data_with_scores.rename(columns=SCORE_COLUMN_NAMES)