Fig. 3: Comparison of DeepTMP and direct training model (DT_Model).
From: Deep transfer learning for inter-chain contact predictions of transmembrane protein complexes
a The violin plots of the top 10 and L precisions for DeepTMP and the direct training model (DT_ Model) on n = 52 cases in the TMP test set. The box plot inside the violin displays the 25th and 75th percentiles of the data, and the dot indicates the median. The whiskers extend to the highest and lowest values within 1.5 times the interquartile range of the data. b The top L precisions of DeepTMP versus those of DT_Model for all 52 test cases. c The gap of top L precision between DeepTMP and DT_Model versus the percentage of transmembrane region on the test set of 52 targets. d The top L precisions of IT_Model versus those of DT_Model for all 52 transmembrane protein complexes in the test set.
