Text changes

about.py

@@ -3,7 +3,7 @@ ABOUT_TEXT = """
 
 We're inviting the ML/bio community to predict developability properties for 244 antibodies from the [GDPa1 dataset](https://huggingface.co/datasets/ginkgo-datapoints/GDPa1).
 
-**What is antibody developability?**
+**What is antibody developability and why is it important?**
 
 Antibodies have to be manufacturable, stable in high concentrations, and have low off-target effects.
 Properties such as these can often hinder the progression of an antibody to the clinic, and are collectively referred to as 'developability'.
@@ -13,12 +13,12 @@ Here we show 5 of these properties and invite the community to submit and develo
 
 1. Download the [GDPa1 dataset](https://huggingface.co/datasets/ginkgo-datapoints/GDPa1)
 2. Make predictions for all the antibody sequences for your property of interest. 
-3. Submit a CSV file containing the `"antibody_name"` column and a column matching the property name you are predicting (e.g. `"antibody_name,Titer"` if you are predicting Titer). 
+3. Submit a CSV file containing the `"antibody_name"` column and a column from GDPa1 matching the property name you are predicting (e.g. `"antibody_name,Titer"` if you are predicting Titer). 
 There is an example submission file on the "✉️ Submit" tab.
 
 For the cross-validation metrics (if training only on the GDPa1 dataset), use the `"hierarchical_cluster_IgG_isotype_stratified_fold"` column to split the dataset into folds and make predictions for each of the folds. 
 Submit a CSV file in the same format but also containing the `"hierarchical_cluster_IgG_isotype_stratified_fold"` column. 
-There is also an example cross-validation submission file on the "✉️ Submit" tab, and we will be releasing a full code tutorial shortly.
+There is also an example cross-validation submission file on the "✉️ Submit" tab, and we will be releasing a full cross-validation code tutorial shortly.
 
 **How to evaluate?**
 

app.py

@@ -116,9 +116,10 @@ with gr.Blocks() as demo:
 
         with gr.TabItem("✉️ Submit", elem_id="boundary-benchmark-tab-table"):
             gr.Markdown(
-                """
+            f"""
             # Antibody Developability Submission
             Upload a CSV to get a score!
+            List of valid property names: `{', '.join(ASSAY_LIST)}`.
 
             Please use your Hugging Face account name to submit your model - we use this to track separate submissions, and if you would like to remain anonymous please set up an anonymous huggingface account.
             Your submission will be evaluated and added to the leaderboard.

constants.py

@@ -16,7 +16,7 @@ ASSAY_RENAME = {
 }
 ASSAY_DESCRIPTION = {
     "AC-SINS_pH7.4": "Self association by AC-SINS at pH 7.4",
-    "PR_CHO": "Polyreactivity by bead-based method against CHO SMP and ovalbumin",
+    "PR_CHO": "Polyreactivity by bead-based method against CHO SMP",
     "HIC": "Hydrophobicity by HIC",
     "Tm2": "Thermostability by nanoDSF",
     "Titer": "Titer by Valita",

submit.py

@@ -71,7 +71,8 @@ def make_submission(
     if not model_name:
         raise gr.Error("Please provide a model name.")
     if not model_description:
-        raise gr.Error("Please provide a model description.")
+        model_description = ""
+        # raise gr.Error("Please provide a model description.")
     if submitted_file is None:
         raise gr.Error("Please upload a CSV file before submitting.")
 

utils.py

@@ -22,6 +22,6 @@ def fetch_hf_results():
     )["train"].to_pandas()
     assert all(col in df.columns for col in LEADERBOARD_RESULTS_COLUMNS), f"Expected columns {LEADERBOARD_RESULTS_COLUMNS} not found in {df.columns}. Missing columns: {set(LEADERBOARD_COLUMNS) - set(df.columns)}"
     # Show latest submission only
-    df = df.sort_values("submission_time", ascending=False).drop_duplicates(subset=["model", "assay"], keep="first")
+    df = df.sort_values("submission_time", ascending=False).drop_duplicates(subset=["model", "assay", "user"], keep="first")
     df["property"] = df["assay"].map(ASSAY_RENAME)
     return df

validation.py

@@ -49,7 +49,7 @@ def validate_username(username: str) -> bool:
                 )
         elif response.status_code == 404:
             raise gr.Error(
-                f"❌ Hugging Face user '{username}' does not exist. Please check the username or create an account at https://huggingface.co"
+                f"❌ Hugging Face user '{username}' does not exist. Please check the username or create an account at https://huggingface.co. This is used to track unique submissions."
             )
         else:
             raise gr.Error(