TDC.DrugComb_CSS Leaderboard

Dataset Summary

Label Size Task Metric Dataset Split
TDC.DrugComb_CSS 297,098 Regression MAE Combination

Leaderboard

Rank Model Contact Link #Params MAE
1 MLP Yusuf Roohani GitHub, Paper 7,141,297 16.858 ± 0.005

Performance Across Tissues

For this leaderboard, an automatic stratified evaluation on performance across various tissue types on the test set is generated. These scores are intended to examine if a model favors towards certain tissue types. An ideal model should perform equally well across all tissue types.

Tissue Label # of Cell Lines Test Set Size Metric
Kidney CSS 8 8,096 MAE
Lung CSS 9 9,108 MAE
Breast CSS 5 20,551 MAE
Hema CSS 6 6,072 MAE
Prostate CSS 2 2,024 MAE
Ovary CSS 7 7,084 MAE
Skin CSS 9 9,108 MAE
Brain CSS 6 6,072 MAE
Colon CSS 7 7,084 MAE

Leaderboard on Performances Across Tissues

Rank Model Contact Link #Params Kidney Lung Breast Hema
1 MLP Yusuf Roohani GitHub, Paper 7,141,297 14.570 ± 0.003 15.653 ± 0.017 13.432 ± 0.049 28.764 ± 0.201
Rank Model Contact Link #Params Prost. Ovary Skin Brain Colon
1 MLP Yusuf Roohani GitHub, Paper 7,141,297 15.692 ± 0.005 15.263 ± 0.041 15.663 ± 0.065 15.694 ± 0.006 17.729 ± 0.042

: Click to sort models for specific benchmark column.