Introduction
DeepUMQA-X is a fully automated server for accurate protein single-chain and complex model quality assessment. It evaluates the local residue accuracy (lDDT), overall interface accuracy (QS-score, only complex), and overall folding accuracy (TM-score) of protein structures, based on our-house improved single-model methods with lightweight structure align. DeepUMQA-X is one of the best performing methods, which performs well in CASP16 EMA blind test. In addition, in the CAMEO-QE blind test, the key component of the DeepUMQA-X server, GraphCPLMQA2L, ranked first in the 1-year (2023-06-09 to 2024-06-01) model quality assessment. (More about DeepUMQA-X...)
News
References