Skip to main content
Fig. 1 | BMC Medical Genomics

Fig. 1

From: Clinical feature-related single-base substitution sequence signatures identified with an unsupervised machine learning approach

Fig. 1

Training process of the LSTM-SOM model. a Sketch map of LSTM-SOM. b The clustering process. Two classifications were used for each training period. Ten classes of mutant sequences were obtained after 3 rounds and an extra round of training. Three of the eight dimensions in LSTM output vectors are shown in the space rectangular coordinate system

Back to article page

BMC Medical Genomics

ISSN: 1755-8794

Contact us