Skip to main content
. 2023 Feb 17;51(7):3017–3029. doi: 10.1093/nar/gkad055

Figure 2.

Figure 2.

The statistical analysis on the protein toxicity dataset. (A) Sequence compositions of positive and negative samples in the training and testing sets. (B) Sequence length distribution of positive and negative samples in the training and testing sets. (C) Motifs of sequence statistics from the training and testing sets.