Framework of the proposed predictor. Constructed a dataset based on the existing datasets and also our own collections. The resulting sequences are encoded with the eight individual feature representation algorithms, respectively. Then the resulting features are submitted to our proposed iterative feature representation scheme, generating the probabilistic feature vector. Afterwards, each sequence is assigned a score ranging from 0 to 1 by the SVM model. If the score >0.5, it indicates that the sequence is predicted to be ORIs; otherwise, it is non-ORIs. (See reference for more detailed information).
Reference
yORIpred: accurate prediction of DNA replication origin from yeast species using an iterative feature representation (Submitted). [Please cite this paper if you find yORIpred is useful in your research]
