loodvanniekerkginkgo commited on
Commit
11e5e48
·
1 Parent(s): 57878eb

Added some more info in About section

Browse files
Files changed (1) hide show
  1. app.py +23 -4
app.py CHANGED
@@ -50,7 +50,7 @@ def get_leaderboard_object(assay: str | None = None):
50
  filter_columns = ["model"]
51
  if assay is None:
52
  filter_columns.append("property")
53
- # TODO how to sort filter columns?
54
  Leaderboard(
55
  value=df,
56
  datatype=["str", "str", "str", "number"],
@@ -67,7 +67,11 @@ def show_output_box(message):
67
  #
68
  # def gradio_interface() -> gr.Blocks:
69
  with gr.Blocks() as demo:
70
- gr.Markdown("## Welcome to the Ginkgo Antibody Developability Benchmark Leaderboard!")
 
 
 
 
71
  with gr.Tabs(elem_classes="tab-buttons"):
72
  with gr.TabItem("🚀 Leaderboard", elem_id="abdev-benchmark-tab-table"):
73
  gr.Markdown("# Antibody Developability Benchmark Leaderboard")
@@ -85,8 +89,23 @@ with gr.Blocks() as demo:
85
  with gr.TabItem("❔About", elem_id="abdev-benchmark-tab-table"):
86
  gr.Markdown(
87
  """
88
- ## About
89
- Some info here
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90
  """
91
  )
92
 
 
50
  filter_columns = ["model"]
51
  if assay is None:
52
  filter_columns.append("property")
53
+ # TODO how to sort filter columns alphabetically?
54
  Leaderboard(
55
  value=df,
56
  datatype=["str", "str", "str", "number"],
 
67
  #
68
  # def gradio_interface() -> gr.Blocks:
69
  with gr.Blocks() as demo:
70
+ gr.Markdown("""
71
+ ## Welcome to the Ginkgo Antibody Developability Benchmark Leaderboard!
72
+
73
+ Participants can submit their model to the leaderboard by
74
+ """)
75
  with gr.Tabs(elem_classes="tab-buttons"):
76
  with gr.TabItem("🚀 Leaderboard", elem_id="abdev-benchmark-tab-table"):
77
  gr.Markdown("# Antibody Developability Benchmark Leaderboard")
 
89
  with gr.TabItem("❔About", elem_id="abdev-benchmark-tab-table"):
90
  gr.Markdown(
91
  """
92
+ ## About this challenge
93
+
94
+ 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).
95
+
96
+ **What is antibody developability?**
97
+
98
+ Antibodies have to be manufacturable, stable in high concentrations, and have low off-target effects.
99
+ Properties such as these can often hinder the progression of an antibody to the clinic, and are collectively referred to as 'developability'.
100
+ Here we show 5 of these properties and invite the community to submit and develop better predictors, which will be tested out on a heldout private set to assess model generalization.
101
+
102
+ **How to submit?**
103
+
104
+ TODO
105
+
106
+ **How to evaluate?**
107
+
108
+ TODO
109
  """
110
  )
111