Journal
BRIEFINGS IN BIOINFORMATICS
Volume 24, Issue 1, Pages -Publisher
OXFORD UNIV PRESS
DOI: 10.1093/bib/bbac507
Keywords
model quality assessment; multiple sequence alignment; homologous template; deep learning
Ask authors/readers for more resources
In this study, an improved protein model quality assessment method, DeepUMQA2, is proposed, which plays a crucial role in protein structure prediction, protein design, and drug discovery. The method extracts sequence features with protein co-evolution information and structural features reflecting family information to complement model-dependent features. A novel backbone network based on triangular multiplication update and axial attention mechanism is designed to enhance information exchange between inter-residue pairs. Experimental results demonstrate that DeepUMQA2 outperforms state-of-the-art model quality assessment methods and can select more suitable best models than state-of-the-art protein structure methods.
Protein model quality assessment plays an important role in protein structure prediction, protein design and drug discovery. In this work, DeepUMQA2, a substantially improved version of DeepUMQA for protein model quality assessment, is proposed. First, sequence features containing protein co -evolution information and structural features reflecting family information are extracted to complement model -dependent features. Second, a novel backbone network based on triangular multiplication update and axial attention mechanism is designed to enhance information exchange between inter-residue pairs. On CASP13 and CASP14 datasets, the performance of DeepUMQA2 increases by 20.5 and 20.4% compared with DeepUMQA, respectively (measured by top 1 loss). Moreover, on the three-month CAMEO dataset (11 March to 04 June 2022), DeepUMQA2 outperforms DeepUMQA by 15.5% (measured by local AUC0,0.2) and ranks first among all competing server methods in CAMEO blind test. Experimental results show that DeepUMQA2 outperforms state-of-the-art model quality assessment methods, such as ProQ3D-LDDT, ModFOLD8, and DeepAccNet and DeepUMQA2 can select more suitable best models than state-of-the-art protein structure methods, such as AlphaFold2, RoseTTAFold and I-TASSER, provided themselves.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available