iMPT-FDNPL: Identification of Membrane Protein Types with Functional Domains and a Natural Language Processing Approach

<div>Boxplot to show the performance of classifiers with different feature types using tenfold cross-validation for 20 times. (a) Accuracy; (b) exact match; (c) hamming loss; (d) integrated score. Features derived from functional domain via word2vector are most efficient to identify membrane protein types.</div>

Computational and Mathematical Methods in Medicine

fig4

Figure 4

Figure 4: iMPT-FDNPL: Identification of Membrane Protein Types with Functional Domains and a Natural Language Processing Approach 