High-accuracy protein model quality assessment using attention graph neural networks.

Great improvement has been brought to protein tertiary structure prediction through deep learning. It is important but very challenging to accurately rank and score decoy structures predicted by different models. CASP14 results show that existing quality assessment (QA) approaches lag behind the development of protein structure prediction methods, where almost all existing QA models degrade in accuracy when the target is a decoy of high quality. How to give an accurate assessment to high-accuracy decoys is particularly useful with the available of accurate structure prediction methods. Here we propose a fast and effective single-model QA method, QATEN, which can evaluate decoys only by their topological characteristics and atomic types. Our model uses graph neural networks and attention mechanisms to evaluate global and amino acid level scores, and uses specific loss functions to constrain the network to focus more on high-precision decoys and protein domains. On the CASP14 evaluation decoys, QATEN performs better than other QA models under all correlation coefficients when targeting average LDDT. QATEN shows promising performance when considering only high-accuracy decoys. Compared to the embedded evaluation modules of predicted ${C}_{\alpha^{-}} RMSD$ (pRMSD) in RosettaFold and predicted LDDT (pLDDT) in AlphaFold2, QATEN is complementary and capable of achieving better evaluation on some decoy structures generated by AlphaFold2 and RosettaFold. These results suggest that the new QATEN approach can be used as a reliable independent assessment algorithm for high-accuracy protein structure decoys.

Accurate disulfide-bonding network predictions improve ab initio structure prediction of cysteine-rich proteins.

MOTIVATION: Cysteine-rich proteins cover many important families in nature but there are currently no methods specifically designed for modeling the structure of these proteins. The accuracy of disulfide connectivity pattern prediction, particularly for the proteins of higher-order connections, e.g., >3 bonds, is too low to effectively assist structure assembly simulations. RESULTS: We propose a new hierarchical order reduction protocol called Cyscon for disulfide-bonding prediction. The most confident disulfide bonds are first identified and bonding prediction is then focused on the remaining cysteine residues based on SVR training. Compared with purely machine learning-based approaches, Cyscon improved the average accuracy of connectivity pattern prediction by 21.9%. For proteins with more than 5 disulfide bonds, Cyscon improved the accuracy by 585% on the benchmark set of PDBCYS. When applied to 158 non-redundant cysteine-rich proteins, Cyscon predictions helped increase (or decrease) the TM-score (or RMSD) of the ab initio QUARK modeling by 12.1% (or 14.4%). This result demonstrates a new avenue to improve the ab initio structure modeling for cysteine-rich proteins. AVAILABILITY AND IMPLEMENTATION: http://www.csbio.sjtu.edu.cn/bioinf/Cyscon/ CONTACT: zhng@umich.edu or hbshen@sjtu.edu.cn. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

TargetFreeze: Identifying Antifreeze Proteins via a Combination of Weights using Sequence Evolutionary Information and Pseudo Amino Acid Composition.

Antifreeze proteins (AFPs) are indispensable for living organisms to survive in an extremely cold environment and have a variety of potential biotechnological applications. The accurate prediction of antifreeze proteins has become an important issue and is urgently needed. Although considerable progress has been made, AFP prediction is still a challenging problem due to the diversity of species. In this study, we proposed a new sequence-based AFP predictor, called TargetFreeze. TargetFreeze utilizes an enhanced feature representation method that weightedly combines multiple protein features and takes the powerful support vector machine as the prediction engine. Computer experiments on benchmark datasets demonstrate the superiority of the proposed TargetFreeze over most recently released AFP predictors. We also implemented a user-friendly web server, which is openly accessible for academic use and is available at http://csbio.njust.edu.cn/bioinf/TargetFreeze. TargetFreeze supplements existing AFP predictors and will have potential applications in AFP-related biotechnology fields.

Predicting protein-ATP binding sites from primary sequence through fusing bi-profile sampling of multi-view features.

BACKGROUND: Adenosine-5'-triphosphate (ATP) is one of multifunctional nucleotides and plays an important role in cell biology as a coenzyme interacting with proteins. Revealing the binding sites between protein and ATP is significantly important to understand the functionality of the proteins and the mechanisms of protein-ATP complex. RESULTS: In this paper, we propose a novel framework for predicting the proteins' functional residues, through which they can bind with ATP molecules. The new prediction protocol is achieved by combination of sequence evolutional information and bi-profile sampling of multi-view sequential features and the sequence derived structural features. The hypothesis for this strategy is single-view feature can only represent partial target's knowledge and multiple sources of descriptors can be complementary. CONCLUSIONS: Prediction performances evaluated by both 5-fold and leave-one-out jackknife cross-validation tests on two benchmark datasets consisting of 168 and 227 non-homologous ATP binding proteins respectively demonstrate the efficacy of the proposed protocol. Our experimental results also reveal that the residue structural characteristics of real protein-ATP binding sites are significant different from those normal ones, for example the binding residues do not show high solvent accessibility propensities, and the bindings prefer to occur at the conjoint points between different secondary structure segments. Furthermore, results also show that performance is affected by the imbalanced training datasets by testing multiple ratios between positive and negative samples in the experiments. Increasing the dataset scale is also demonstrated useful for improving the prediction performances.

Fuzzy KNN for predicting membrane protein types from pseudo-amino acid composition.

Cell membranes are vitally important to the life of a cell. Although the basic structure of biological membrane is provided by the lipid bilayer, membrane proteins perform most of the specific functions. Membrane proteins are putatively classified into five different types. Identification of their types is currently an important topic in bioinformatics and proteomics. In this paper, based on the concept of representing protein samples in terms of their pseudo-amino acid composition, the fuzzy K-nearest neighbors (KNN) algorithm has been introduced to predict membrane protein types, and high success rates were observed. It is anticipated that, the current approach, which is based on a branch of fuzzy mathematics and represents a new strategy, may play an important complementary role to the existing methods in this area. The novel approach may also have notable impact on prediction of the other attributes, such as protein structural class, protein subcellular localization, and enzyme family class, among many others.