File size: 2,853 Bytes
7a1c35b 4d9df8e 7a1c35b 62b6599 7a1c35b 61fa714 7a1c35b 471531b 15ae508 471531b 7a1c35b 0f3e1b5 b2a1e67 bff3b9b 7ac33bb b2a1e67 bff3b9b 7ac33bb b2a1e67 7a1c35b 8f9985e 7a1c35b 8f9985e 5d5df93 10e69e7 89d69bf 61fa714 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 |
"""
Constants for the Antibody Developability Benchmark
"""
import os
from huggingface_hub import HfApi
import pandas as pd
ASSAY_LIST = ["AC-SINS_pH7.4", "PR_CHO", "HIC", "Tm2", "Titer"]
ASSAY_RENAME = {
"AC-SINS_pH7.4": "Self-association",
"PR_CHO": "Polyreactivity",
"HIC": "Hydrophobicity",
"Tm2": "Thermostability",
"Titer": "Titer",
}
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",
"HIC": "Hydrophobicity by HIC",
"Tm2": "Thermostability by nanoDSF",
"Titer": "Titer by Valita",
}
ASSAY_EMOJIS = {
"AC-SINS_pH7.4": "🧲",
"PR_CHO": "🎯",
"HIC": "💧",
"Tm2": "🌡️",
"Titer": "🧪",
}
# Tabs with emojis
ABOUT_TAB_NAME = "📖 About / Rules"
FAQ_TAB_NAME = "❓ FAQs"
SUBMIT_TAB_NAME = "✉️ Submit"
REGISTRATION_CODE = "GINKGO-ABDEV-2025"
TERMS_URL = "https://euphsfcyogalqiqsawbo.supabase.co/storage/v1/object/public/gdpweb/pdfs/2025%20Ginkgo%20Antibody%20Developability%20Prediction%20Competition%202025-08-28-v2.pdf"
# Input CSV file requirements
REQUIRED_COLUMNS: list[str] = [
"antibody_name",
"vh_protein_sequence",
"vl_protein_sequence",
]
# Cross validation
CV_COLUMN = "hierarchical_cluster_IgG_isotype_stratified_fold"
# Example files
EXAMPLE_FILE_DICT = {
"GDPa1": "data/example-predictions.csv",
"GDPa1_cross_validation": "data/example-predictions-cv.csv",
"Heldout Test Set": "data/example-predictions-heldout.csv",
}
ANTIBODY_NAMES_DICT = {
"GDPa1": pd.read_csv(EXAMPLE_FILE_DICT["GDPa1"])["antibody_name"].tolist(),
"GDPa1_cross_validation": pd.read_csv(EXAMPLE_FILE_DICT["GDPa1_cross_validation"])[
"antibody_name"
].tolist(),
"Heldout Test Set": pd.read_csv(EXAMPLE_FILE_DICT["Heldout Test Set"])["antibody_name"].tolist(),
}
# Huggingface API
TOKEN = os.environ.get("HF_TOKEN")
CACHE_PATH = os.getenv("HF_HOME", ".")
API = HfApi(token=TOKEN)
# Huggingface repos
ORGANIZATION = "ginkgo-datapoints"
SUBMISSIONS_REPO = f"{ORGANIZATION}/abdev-bench-submissions"
RESULTS_REPO = f"{ORGANIZATION}/abdev-bench-results"
# Leaderboard dataframes
LEADERBOARD_RESULTS_COLUMNS = ["model", "assay", "spearman", "dataset", "user", "submission_time"] # The columns expected from the results dataset
LEADERBOARD_DISPLAY_COLUMNS = ["model", "property", "spearman", "dataset", "user", "submission_time"] # After changing assay to property (pretty formatting)
LEADERBOARD_COLUMNS_RENAME = {
"spearman": "Spearman Correlation",
"dataset": "Dataset",
"user": "User",
"submission_time": "Submission Time",
"model": "Model Name",
"property": "Property",
}
def LEADERBOARD_COLUMNS_RENAME_LIST(columns: list[str]) -> list[str]:
return list(map(lambda x: LEADERBOARD_COLUMNS_RENAME.get(x,x), columns))
|