Fig. 2
From: Meta-learning-based Inductive logistic matrix completion for prediction of kinase inhibitors
The overall framework of MetaILMC. MetaILMC consists of two phases: meta-training and meta-test (few-shot samples adaptation). In the meta-training phase, multiple kinases with sufficient samples are adopted as meta-training tasks to obtain a well-initialized model which could be fast adapted to a new kinase with limited data. In the adaptation phase, a few (e.g., less than 5) known active and inactive samples from a new target kinase are used to fine-tune the model on this kinase to capture its specific model