Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: CysPresso: a classification model utilizing deep learning protein representations to predict recombinant expression of cysteine-dense peptides

Fig. 1

Random forest classifiers trained on SeqVec, proteInfer, and AlphaFold2 protein representations predict recombinant CDP expressibility. Random forest classifiers were trained using protein representations generated by primary sequences of CDPs and performance was estimated by tenfold cross validation. AUC was used as the performance metric. A An example showing receiver operating characteristic curves generated using the single representation from AlphaFold2 neural embeddings. B The performance of protein representations generated by SeqVec, proteInfer, and AlphaFold2. AlphaFold2 protein representations had the highest predictive performance. C The predictive performance of neural embeddings from the four representations generated by AlphaFold2 and a concatenated combined representation. The combined representation produced classifiers with the best performance at predicting recombinant CDP expressibility. Error bars represent standard deviation of the mean value

Back to article page