Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: CancerSiamese: one-shot learning for predicting primary and metastatic tumor types unseen during model training

Fig. 1

Illustration of a 6-way one-shot prediction of cancer types for a query tumor sample. A query sample is compared with each sample in a support set, which includes 6 samples, each from a cancer type. A machine learning algorithm computes the probability of similarity between the query and every support sample. The final predicted type (HCC) is the sample type in the support set that has the highest probability of being similar to the query sample

Back to article page