Parameters
If you want to test the sample, you just need to upload the file and click the bottom start button.
( the example file click here)

SubLocEP

Tips:We recommend that users upload mRNA sequences. SubLocEP is a multi-label classification model. The EP1 and EP2 models are identical, and the user is free to choose.

SubLocEP is proposed as a two-layer integrated prediction model, whose purpose is to accurately predict the location of sequence samples. Compared with the existing models based on limited features, SubLocEP comprehensively considers more feature attributes and combines with lightGBM to generated single feature classifiers. Next, the first integration model (single-layer models) is generated according to categories of the feature. Subsequently, the two single-layer integration models are weighted (sequence-based: physicochemical property = 2:1) to produce the final two-layer model.

  • Sequence-based features:

       PseEIIP, TNC, DNC, and CKSNAP.

  • Physicochemical properties:

       PCPseDNC, PCPseTNC, SCPseDNC, SCPseTNC and DACC.

  • If you have any problems,please contact me.

    lijingtju@foxmail.com