Protein Tertiary Structure Prediction Research Articles

Using protein language models for protein interaction hot spot prediction with limited data.

Protein language models, inspired by the success of large language models in deciphering human language, have emerged as powerful tools for unraveling the intricate code of life inscribed within protein sequences. They have gained significant attention for their promising applications across various areas, including the sequence-based prediction of secondary and tertiary protein structure, the discovery of new functional protein sequences/folds, and the assessment of mutational impact on protein fitness. However, their utility in learning to predict protein residue properties based on scant datasets, such as protein-protein interaction (PPI)-hotspots whose mutations significantly impair PPIs, remained unclear. Here, we explore the feasibility of using protein language-learned representations as features for machine learning to predict PPI-hotspots using a dataset containing 414 experimentally confirmed PPI-hotspots and 504 PPI-nonhot spots. Our findings showcase the capacity of unsupervised learning with protein language models in capturing critical functional attributes of protein residues derived from the evolutionary information encoded within amino acid sequences. We show that methods relying on protein language models can compete with methods employing sequence and structure-based features to predict PPI-hotspots from the free protein structure. We observed an optimal number of features for model precision, suggesting a balance between information and overfitting. This study underscores the potential of transformer-based protein language models to extract critical knowledge from sparse datasets, exemplified here by the challenging realm of predicting PPI-hotspots. These models offer a cost-effective and time-efficient alternative to traditional experimental methods for predicting certain residue properties. However, the challenge of explaining why specific features are important for determining certain residue properties remains.

Recent Progress of Protein Tertiary Structure Prediction.

The prediction of three-dimensional (3D) protein structure from amino acid sequences has stood as a significant challenge in computational and structural bioinformatics for decades. Recently, the widespread integration of artificial intelligence (AI) algorithms has substantially expedited advancements in protein structure prediction, yielding numerous significant milestones. In particular, the end-to-end deep learning method AlphaFold2 has facilitated the rise of structure prediction performance to new heights, regularly competitive with experimental structures in the 14th Critical Assessment of Protein Structure Prediction (CASP14). To provide a comprehensive understanding and guide future research in the field of protein structure prediction for researchers, this review describes various methodologies, assessments, and databases in protein structure prediction, including traditionally used protein structure prediction methods, such as template-based modeling (TBM) and template-free modeling (FM) approaches; recently developed deep learning-based methods, such as contact/distance-guided methods, end-to-end folding methods, and protein language model (PLM)-based methods; multi-domain protein structure prediction methods; the CASP experiments and related assessments; and the recently released AlphaFold Protein Structure Database (AlphaFold DB). We discuss their advantages, disadvantages, and application scopes, aiming to provide researchers with insights through which to understand the limitations, contexts, and effective selections of protein structure prediction methods in protein-related fields.

Molecular characterization of a tetra segmented ssDNA virus infecting Botrytis cinerea worldwide

BackgroundFamily Genomoviridae was recently established, and only a few mycoviruses have been described and characterized, and almost all of them (Sclerotinia sclerotiorum hypovirulence-associated DNA virus 1, Fusarium graminearum gemyptripvirus 1 and Botrytis cinerea gemydayirivirus 1) induced hypovirulence in their host. Botrytis cinerea ssDNA virus 1 (BcssDV1), a tetrasegmented single-stranded DNA virus infecting the fungus Botrytis cinerea, has been molecularly characterized in this work.MethodsBcssDV1 was detected in Spanish and Italian B. cinerea field isolates obtained from grapevine. BcssDV1 variants genomes were molecularly characterized via NGS and Sanger sequencing. Nucleotide and amino acid sequences were used for diversity and phylogenetic analysis. Prediction of protein tertiary structures and putative associated functions were performed by AlphaFold2 and DALI.ResultsBcssDV1 is a tetrasegmented single-stranded DNA virus. The mycovirus was composed by four genomic segments of approximately 1.7 Kb each, which are DNA-A, DNA-B, and DNA-C and DNA-D, that coded, respectively, for the rolling-circle replication initiation protein (Rep), capsid protein (CP) and two hypothetical proteins. BcssDV1 was present in several Italian and Spanish regions with high incidence and low variability among the different viral variants. DNA-A and DNA-D were found to be the more conserved genomic segments among variants, while DNA-B and DNA-C segments were shown to be the most variable ones. Tertiary structures of the proteins encoded by each segment suggested specific functions associated with each of them.ConclusionsThis study presented the first complete sequencing and characterization of a tetrasegmented ssDNA mycovirus, its incidence in Spain and Italy, its presence in other countries and its high conservation among regions.

Improving AlphaFold2-based protein tertiary structure prediction with MULTICOM in CASP15

Since the 14th Critical Assessment of Techniques for Protein Structure Prediction (CASP14), AlphaFold2 has become the standard method for protein tertiary structure prediction. One remaining challenge is to further improve its prediction. We developed a new version of the MULTICOM system to sample diverse multiple sequence alignments (MSAs) and structural templates to improve the input for AlphaFold2 to generate structural models. The models are then ranked by both the pairwise model similarity and AlphaFold2 self-reported model quality score. The top ranked models are refined by a novel structure alignment-based refinement method powered by Foldseek. Moreover, for a monomer target that is a subunit of a protein assembly (complex), MULTICOM integrates tertiary and quaternary structure predictions to account for tertiary structural changes induced by protein-protein interaction. The system participated in the tertiary structure prediction in 2022 CASP15 experiment. Our server predictor MULTICOM_refine ranked 3rd among 47 CASP15 server predictors and our human predictor MULTICOM ranked 7th among all 132 human and server predictors. The average GDT-TS score and TM-score of the first structural models that MULTICOM_refine predicted for 94 CASP15 domains are ~0.80 and ~0.92, 9.6% and 8.2% higher than ~0.73 and 0.85 of the standard AlphaFold2 predictor respectively.

Resolving Confusion Surrounding d-Ala-d-Ala Ligase Catalysis in Cyanobacterial Mycosporine-Like Amino Acid (MAA) Biosynthesis.

Mycosporine-like amino acids (MAAs) are natural UV-absorbing sunscreens that evolved in cyanobacteria and algae to palliate harmful effects from obligatory exposure to solar radiation. Multiple lines of evidence prove that in cyanobacteria all MAAs are derived from mycosporine-glycine, which is typically modified by an ATP-dependent ligase encoded by the gene mysD. The function of the mysD ligase has been experimentally described but haphazardly named based solely upon sequence similarity to the d-alanine-d-alanine ligase of bacterial peptidoglycan biosynthesis. Combining phylogeny and alpha-fold tertiary protein structure prediction unambiguously distinguished mysD from d-alanine-d-alanine ligase. The renaming of mysD to mycosporine-glycine-amine ligase (MG-amine ligase) using recognised enzymology rules of nomenclature is, therefore, proposed, and considers relaxed specificity for several different amino acid substrates. The evolutionary and ecological context of MG-amine ligase catalysis merits wider appreciation especially when considering exploiting cyanobacteria for biotechnology, for example, producing mixtures of MAAs with enhanced optical or antioxidant properties.

Investigating Native Metal Ion Binding Sites in Mammalian Histidine-Rich Glycoprotein.

Mammalian histidine-rich glycoprotein (HRG) is a highly versatile and abundant blood plasma glycoprotein with a diverse range of ligands that is involved in regulating many essential biological processes, including coagulation, cell adhesion, and angiogenesis. Despite its biomedical importance, structural information on the multi-domain protein is sparse, not least due to intrinsically disordered regions that elude high-resolution structural characterization. Binding of divalent metal ions, particularly ZnII, to multiple sites within the HRG protein is of critical functional importance and exerts a regulatory role. However, characterization of the ZnII binding sites of HRG is a challenge; their number and composition as well as their affinities and stoichiometries of binding are currently not fully understood. In this study, we explored modern electron paramagnetic resonance (EPR) spectroscopy methods supported by protein secondary and tertiary structure prediction to assemble a holistic picture of native HRG and its interaction with metal ions. To the best of our knowledge, this is the first time that this suite of EPR techniques has been applied to count and characterize endogenous metal ion binding sites in a native mammalian protein of unknown structure.

Protein tertiary structure prediction by integrating ant colony optimization with path relinking and structure knowledge

Protein tertiary structure prediction by integrating ant colony optimization with path relinking and structure knowledge

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.

Information entropy-based differential evolution with extremely randomized trees and LightGBM for protein structural class prediction

The discovery of protein tertiary structure is the basis of current genetic engineering, medicinal design, and other biological applications. Protein structural class plays a significant role in the tertiary structure folding and function analysis of protein. However, the growth rate of new amino acid sequence far exceeds the tertiary structure. Existing research methods of confirming protein folding cannot satisfy massive sequences and protein engineering. A high-accuracy prediction result of low-similarity protein dataset is particularly critical to generate the corresponding tertiary structure from the primary structure. In this paper, we construct a novel super-large-scale feature of the primary structure based on secondary structure, evolutionary information, chemical properties, and global descriptors. The diversified and massive features are utilized to predict the protein class based on a novel feature selection algorithm and a gradient boosting decision tree model. To testify the effectiveness and robustness of our proposed method, namely IDEGBM, we choose the 10-fold cross-validation for evaluating four benchmark datasets 25PDB, FC699, D1189 and D640. Experimental results exhibit that our method improves the accuracy in comparison with other state-of-the-art prediction models in terms of both accuracy and efficiency. Furthermore, a representative protein is used to validate that our proposed IDEGBM can be applied to improve the conformation prediction of protein tertiary structure.

Illuminating the "Twilight Zone": Advances in Difficult Protein Modeling.

Homology modeling was long considered a method of choice in tertiary protein structure prediction. However, it used to provide models of acceptable quality only when templates with appreciable sequence identity with a target could be found. The threshold value was long assumed to be around 20-30%. Below this level, obtained sequence identity was getting dangerously close to values that can be obtained by chance, after aligning any random, unrelated sequences. In these cases, other approaches, including ab initio folding simulations or fragment assembly, were usually employed. The most recent editions of the CASP and CAMEO community-wide modeling methods assessment have brought some surprising outcomes, proving that much more clues can be inferred from protein sequence analyses than previously thought. In this chapter, we focus on recent advances in the field of difficult protein modeling, pushing the threshold deep into the "twilight zone", with particular attention devoted to improvements in applications of machine learning and model evaluation.

Computational Methods for Protein Tertiary Structure Analysis.

Protein folding accuracy is fundamental to all cells. In spite of this, it is difficult to maintain the fidelity of protein synthesis and folding due to the fact that the implicit genetic and biochemical systems are inherently prone to error, which leads to the constant production of a certain amount of misfolded proteins. This problem is further compounded by genetic variation and the effects of environmental stress. To that end, the prediction of protein structures for tertiary protein structure analysis and prediction might be an ideal approach for the study of mutation effects in macromolecules and their complexes. With the development and accessibility to increasingly powerful computational systems, this type of study will enable a wide variety of opportunities for the creation of better-targeted peptide-based pharmacotherapy and prospects for precision medicine in future.

Protein Residue Contact Prediction Based on Deep Learning and Massive Statistical Features from Multi-Sequence Alignment

Sequence-based protein tertiary structure prediction is of fundamental importance because the function of a protein ultimately depends on its 3D structure. An accurate residue-residue contact map is one of the essential elements for current ab initio prediction protocols of 3D structure prediction. Recently, with the combination of deep learning and direct coupling techniques, the performance of residue contact prediction has achieved significant progress. However, a considerable number of current Deep-Learning (DL)-based prediction methods are usually time-consuming, mainly because they rely on different categories of data types and third-party programs. In this research, we transformed the complex biological problem into a pure computational problem through statistics and artificial intelligence. We have accordingly proposed a feature extraction method to obtain various categories of statistical information from only the multi-sequence alignment, followed by training a DL model for residue-residue contact prediction based on the massive statistical information. The proposed method is robust in terms of different test sets, showed high reliability on model confidence score, could obtain high computational efficiency and achieve comparable prediction precisions with DL methods that relying on multi-source inputs.

Characterization of B-box family genes and their expression profiles under abiotic stresses in the Melilotus albus.

B-box (BBX) proteins are one of the zinc-finger transcription factor that plays a critical role in plant development, growth, and multiple stress responses. Although BBX genes have been reported in many model organisms, no comprehensive study has yet been conducted on the BBX genes in Melilotus albus, and the biological functions of this family remain unknown. In this study, a total of 20 BBX (MaBBX) genes were identified in M. albus and were phylogenetically divided into five clades. BBX members within the same clade showed similar conserved domain, suggesting similarity of potential biological function. Analysis of MaBBX conserved motifs showed that every subfamily contained two common motifs. Distribution mapping shows that BBX proteins are nonrandomly localized in eight chromosomes. The synteny showed that most homologous gene pairs of the MaBBX gene family were amplified by segmental replication, which meant segmental replication was the main way for the MaBBX gene family to evolve. Additionally, the cis-element analysis predicted light-responsive, various hormone and stress-related elements in the promoter regions of MaBBXs. Furthermore, the expression levels of all 20 MaBBX genes were detected by qRT-PCR under salt, cold, and dark stresses in M. albus. Moreover, it was observed that 16 genes had higher expression levels after 3 h of salt treatment, 10 genes were significantly upregulated after 3 h of cold treatment, and all genes were up regulated after 3 h of dark treatment, and then appeared to decline. In addition, it was also noticed that MaBBX13 may be an important candidate for improving tolerance to abiotic stress. The prediction of protein tertiary structure showed that the tertiary structures of members of the same subfamily of MaBBX proteins were highly similar. The hypothesis exhibited that most of the MaBBX proteins were predicted to be localized to the nucleus and cytoplasm and was validated by transient expression assays of MaBBX15 in tobacco leaf epidermal cells. This study provides useful information for further investigating and researching the regulatory mechanisms of BBX family genes in response to abiotic stresses in M. albus.

A deep dilated convolutional residual network for predicting interchain contacts of protein homodimers.

MotivationDeep learning has revolutionized protein tertiary structure prediction recently. The cutting-edge deep learning methods such as AlphaFold can predict high-accuracy tertiary structures for most individual protein chains. However, the accuracy of predicting quaternary structures of protein complexes consisting of multiple chains is still relatively low due to lack of advanced deep learning methods in the field. Because interchain residue–residue contacts can be used as distance restraints to guide quaternary structure modeling, here we develop a deep dilated convolutional residual network method (DRCon) to predict interchain residue–residue contacts in homodimers from residue–residue co-evolutionary signals derived from multiple sequence alignments of monomers, intrachain residue–residue contacts of monomers extracted from true/predicted tertiary structures or predicted by deep learning, and other sequence and structural features.ResultsTested on three homodimer test datasets (Homo_std dataset, DeepHomo dataset and CASP-CAPRI dataset), the precision of DRCon for top L/5 interchain contact predictions (L: length of monomer in a homodimer) is 43.46%, 47.10% and 33.50% respectively at 6 Å contact threshold, which is substantially better than DeepHomo and DNCON2_inter and similar to Glinter. Moreover, our experiments demonstrate that using predicted tertiary structure or intrachain contacts of monomers in the unbound state as input, DRCon still performs well, even though its accuracy is lower than using true tertiary structures in the bound state are used as input. Finally, our case study shows that good interchain contact predictions can be used to build high-accuracy quaternary structure models of homodimers.Availability and implementationThe source code of DRCon is available at https://github.com/jianlin-cheng/DRCon. The datasets are available at https://zenodo.org/record/5998532#.YgF70vXMKsB.Supplementary information Supplementary data are available at Bioinformatics online.

Ensemble Machine Learning to Enhance Q8 Protein Secondary Structure燩rediction

Protein structure prediction is one of the most essential objectives practiced by theoretical chemistry and bioinformatics as it is of a vital importance in medicine, biotechnology and more. Protein secondary structure prediction (PSSP) has a significant role in the prediction of protein tertiary structure, as it bridges the gap between the protein primary sequences and tertiary structure prediction. Protein secondary structures are classified into two categories: 3-state category and 8-state category. Predicting the 3 states and the 8 states of secondary structures from protein sequences are called the Q3 prediction and the Q8 prediction problems, respectively. The 8 classes of secondary structures reveal more precise structural information for a variety of applications than the 3 classes of secondary structures, however, Q8 prediction has been found to be very challenging, that is why all previous work done in PSSP have focused on Q3 prediction. In this paper, we develop an ensemble Machine Learning (ML) approach for Q8 PSSP to explore the performance of ensemble learning algorithms compared to that of individual ML algorithms in Q8 PSSP. The ensemble members considered for constructing the ensemble models are well known classifiers, namely SVM (Support Vector Machines), KNN (K-Nearest Neighbor), DT (Decision Tree), RF (Random Forest), and NB (Naïve Bayes), with two feature extraction techniques, namely LDA (Linear Discriminate Analysis) and PCA (Principal Component Analysis). Experiments have been conducted for evaluating the performance of single models and ensemble models, with PCA and LDA, in Q8 PSSP. The novelty of this paper lies in the introduction of ensemble learning in Q8 PSSP problem. The experimental results confirmed that ensemble ML models are more accurate than individual ML models. They also indicated that features extracted by LDA are more effective than those extracted by PCA.

Protein secondary structure prediction based on Wasserstein generative adversarial networks and temporal convolutional networks with convolutional block attention modules.

As an important task in bioinformatics, protein secondary structure prediction (PSSP) is not only beneficial to protein function research and tertiary structure prediction, but also to promote the design and development of new drugs. However, current PSSP methods cannot sufficiently extract effective features. In this study, we propose a novel deep learning model WGACSTCN, which combines Wasserstein generative adversarial network with gradient penalty (WGAN-GP), convolutional block attention module (CBAM) and temporal convolutional network (TCN) for 3-state and 8-state PSSP. In the proposed model, the mutual game of generator and discriminator in WGAN-GP module can effectively extract protein features, and our CBAM-TCN local extraction module can capture key deep local interactions in protein sequences segmented by sliding window technique, and the CBAM-TCN long-range extraction module can further capture the key deep long-range interactions in sequences. We evaluate the performance of the proposed model on seven benchmark datasets. Experimental results show that our model exhibits better prediction performance compared to the four state-of-the-art models. The proposed model has strong feature extraction ability, which can extract important information more comprehensively.

In Silico Study of Secondary Structure of Hemoglobin Protein

Protein structure prediction is one of the important goals in the area of bioinformatics and biotechnology. Prediction methods include structure prediction of both secondary and tertiary structures of protein. Protein secondary structure prediction infers knowledge related to presence of helixes, sheets and coils in a polypeptide chain whereas protein tertiary structure prediction infers knowledge related to three dimensional structures of proteins. Protein secondary structures represent the possible motifs or regular expressions represented as patterns that are predicted from primary protein sequence in the form of alpha helix, betastr and and coils. The secondary structure prediction is useful as it infers information related to the structure and function of unknown protein sequence. There are various secondary structure prediction methods used to predict about helixes, sheets and coils. Based on these methods there are various prediction tools under study. This study includes prediction of hemoglobin using various tools. The results produced inferred knowledge with reference to percentage of amino acids participating to produce helices, sheets and coils. PHD and DSC produced the best of the results out of all the tools used.

High-Performance Deep Learning Toolbox for Genome-Scale Prediction of Protein Structure and Function.

Computational biology is one of many scientific disciplines ripe for innovation and acceleration with the advent of high-performance computing (HPC). In recent years, the field of machine learning has also seen significant benefits from adopting HPC practices. In this work, we present a novel HPC pipeline that incorporates various machine-learning approaches for structure-based functional annotation of proteins on the scale of whole genomes. Our pipeline makes extensive use of deep learning and provides computational insights into best practices for training advanced deep-learning models for high-throughput data such as proteomics data. We showcase methodologies our pipeline currently supports and detail future tasks for our pipeline to envelop, including large-scale sequence comparison using SAdLSA and prediction of protein tertiary structures using AlphaFold2.

FALCON2: a web server for high-quality prediction of protein tertiary structures

BackgroundAccurate prediction of protein tertiary structures is highly desired as the knowledge of protein structures provides invaluable insights into protein functions. We have designed two approaches to protein structure prediction, including a template-based modeling approach (called ProALIGN) and an ab initio prediction approach (called ProFOLD). Briefly speaking, ProALIGN aligns a target protein with templates through exploiting the patterns of context-specific alignment motifs and then builds the final structure with reference to the homologous templates. In contrast, ProFOLD uses an end-to-end neural network to estimate inter-residue distances of target proteins and builds structures that satisfy these distance constraints. These two approaches emphasize different characteristics of target proteins: ProALIGN exploits structure information of homologous templates of target proteins while ProFOLD exploits the co-evolutionary information carried by homologous protein sequences. Recent progress has shown that the combination of template-based modeling and ab initio approaches is promising.ResultsIn the study, we present FALCON2, a web server that integrates ProALIGN and ProFOLD to provide high-quality protein structure prediction service. For a target protein, FALCON2 executes ProALIGN and ProFOLD simultaneously to predict possible structures and selects the most likely one as the final prediction result. We evaluated FALCON2 on widely-used benchmarks, including 104 CASP13 (the 13th Critical Assessment of protein Structure Prediction) targets and 91 CASP14 targets. In-depth examination suggests that when high-quality templates are available, ProALIGN is superior to ProFOLD and in other cases, ProFOLD shows better performance. By integrating these two approaches with different emphasis, FALCON2 server outperforms the two individual approaches and also achieves state-of-the-art performance compared with existing approaches.ConclusionsBy integrating template-based modeling and ab initio approaches, FALCON2 provides an easy-to-use and high-quality protein structure prediction service for the community and we expect it to enable insights into a deep understanding of protein functions.

Protein tertiary structure prediction and refinement using deep learning and Rosetta in CASP14.

The trRosetta structure prediction method employs deep learning to generate predicted residue‐residue distance and orientation distributions from which 3D models are built. We sought to improve the method by incorporating as inputs (in addition to sequence information) both language model embeddings and template information weighted by sequence similarity to the target. We also developed a refinement pipeline that recombines models generated by template‐free and template utilizing versions of trRosetta guided by the DeepAccNet accuracy predictor. Both benchmark tests and CASP results show that the new pipeline is a considerable improvement over the original trRosetta, and it is faster and requires less computing resources, completing the entire modeling process in a median < 3 h in CASP14. Our human group improved results with this pipeline primarily by identifying additional homologous sequences for input into the network. We also used the DeepAccNet accuracy predictor to guide Rosetta high‐resolution refinement for submissions in the regular and refinement categories; although performance was quite good on a CASP relative scale, the overall improvements were rather modest in part due to missing inter‐domain or inter‐chain contacts.