List your company
ResearchFormerly WizWand

Protein fitness regression on avGFP low-N setting (192 train, 48 val)

0.596Spearman CorrelationMutaPLM
0.286080.366540.4470.52746Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
MutaPLMtraining_setting=low-N (192 training / 48 validation samples), head=2-layer MLP, backbone=frozen, epochs=50, batch_size=16, learning_rate=0.001, loss=MSE2024.100.596
Tranception_Ltraining_setting=low-N (192 training / 48 validation samples), head=2-layer MLP, backbone=frozen, epochs=50, batch_size=16, learning_rate=0.001, loss=MSE2024.100.594
ConFittraining_setting=low-N (192 training / 48 validation samples), head=2-layer MLP, backbone=frozen, epochs=50, batch_size=16, learning_rate=0.001, loss=MSE2024.100.564
ESM-2training_setting=low-N (192 training / 48 validation samples), head=2-layer MLP, backbone=frozen, epochs=50, batch_size=16, learning_rate=0.001, loss=MSE2024.100.554
Augmented EVmutationtraining_setting=low-N (192 training / 48 validation samples), head=2-layer MLP, backbone=frozen, epochs=50, batch_size=16, learning_rate=0.001, loss=MSE2024.100.512
Augmented ESMtraining_setting=low-N (192 training / 48 validation samples), head=2-layer MLP, backbone=frozen, epochs=50, batch_size=16, learning_rate=0.001, loss=MSE2024.100.497
Ridge Regressiontraining_setting=low-N (192 training / 48 validation samples), epochs=50, batch_size=16, learning_rate=0.001, loss=MSE2024.100.298