Protein structure and folding pathway prediction based on remote homologs recognition using PAthreader

BINDTI: A Bi-Directional Intention Network for Drug-Target Interaction Identification Based on Attention Mechanisms

The identification of drug-target interactions (DTIs) is an essential step in drug discovery. In vitro experimental methods are expensive, laborious, and time-consuming. Deep learning has witnessed promising progress in DTI prediction. However, how to precisely represent drug and protein features is a major challenge for DTI prediction. Here, we developed an end-to-end DTI identification framework called BINDTI based on bi-directional Intention network. First, drug features are encoded with graph convolutional networks based on its 2D molecular graph obtained by its SMILES string. Next, protein features are encoded based on its amino acid sequence through a mixed model called ACmix, which integrates self-attention mechanism and convolution. Third, drug and target features are fused through bi-directional Intention network, which combines Intention and multi-head attention. Finally, unknown drug-target (DT) pairs are classified through multilayer perceptron based on the fused DT features. The results demonstrate that BINDTI greatly outperformed four baseline methods (i.e., CPI-GNN, TransfomerCPI, MolTrans, and IIFDTI) on the BindingDB, BioSNAP, DrugBank, and Human datasets. More importantly, it was more appropriate to predict new DTIs than the four baseline methods on imbalanced datasets. Ablation experimental results elucidated that both bi-directional Intention and ACmix could greatly advance DTI prediction. The fused feature visualization and case studies manifested that the predicted results by BINDTI were basically consistent with the true ones. We anticipate that the proposed BINDTI framework can find new low-cost drug candidates, improve drugs' virtual screening, and further facilitate drug repositioning as well as drug discovery.

Recent advances and challenges in protein complex model accuracy estimation

Estimation of model accuracy plays a crucial role in protein structure prediction, aiming to evaluate the quality of predicted protein structure models accurately and objectively. This process is not only key to screening candidate models that are close to the real structure, but also provides guidance for further optimization of protein structures. With the significant advancements made by AlphaFold2 in monomer structure, the problem of single-domain protein structure prediction has been widely solved. Correspondingly, the importance of assessing the quality of single-domain protein models decreased, and the research focus has shifted to estimation of model accuracy of protein complexes. In this review, our goal is to provide a comprehensive overview of the reference and statistical metrics, as well as representative methods, and the current challenges within four distinct facets (Topology Global Score, Interface Total Score, Interface Residue-Wise Score, and Tertiary Residue-Wise Score) in the field of complex EMA.

Keeping it in the family: using protein family templates to rescue low confidence AlphaFold2 models

Motivation

High confidence structure prediction models have become available for nearly all protein sequences. More than 200 million AlphaFold2 models are now publicly available. We observe that there can be significant variability in the prediction confidence as judged by plDDT scores across a protein family. We have explored whether the predictions with lower plDDT in a family can be improved by the use of higher plDDT templates from the family as template structures in AlphaFold2.

Results

Our work shows that about one-third of the time structures with a low plDDT can be "rescued," moved from low to reasonable confidence. We also find that surprisingly in many cases we get a higher plDDT model when we switch off the multiple sequence alignment (MSA) option in AlphaFold2 and solely rely on a high-quality template. However, we find the best overall strategy is to make predictions both with and without the MSA information and select the model with the highest average plDDT. We also find that using high plDDT models as templates can increase the speed of AlphaFold2 as implemented in ColabFold. Additionally, we try to demonstrate that as well as having increased overall plDDT, the models are likely to have higher quality structures as judged by two metrics.

Availability and implementation

We have implemented our pipeline in NextFlow and it is available in GitHub: https://github.com/FranceCosta/AF2Fix.

Prediction of Inter-Residue Multiple Distances and Exploration of Protein Multiple Conformations by Deep Learning

AlphaFold2 has achieved a major breakthrough in end-to-end prediction for static protein structures. However, protein conformational change is considered to be a key factor in protein biological function. Inter-residue multiple distances prediction is of great significance for research on protein multiple conformations exploration. In this study, we proposed an inter-residue multiple distances prediction method, DeepMDisPre, based on an improved network which integrates triangle update, axial attention and ResNet to predict multiple distances of residue pairs. We built a dataset which contains proteins with a single structure and proteins with multiple conformations to train the network. We tested DeepMDisPre on 114 proteins with multiple conformations. The results show that the inter-residue distance distribution predicted by DeepMDisPre tends to have multiple peaks for flexible residue pairs than for rigid residue pairs. On two cases of proteins with multiple conformations, we modeled the multiple conformations relatively accurately by using the predicted inter-residue multiple distances. In addition, we also tested the performance of DeepMDisPre on 279 proteins with a single structure. Experimental results demonstrate that the average contact accuracy of DeepMDisPre is higher than that of the comparative method. In terms of static protein modeling, the average TM-score of the 3D models built by DeepMDisPre is also improved compared with the comparative method.

Computational tools to predict context-specific protein complexes

Interactions between thousands of proteins define cells' protein-protein interaction (PPI) network. Some of these interactions lead to the formation of protein complexes. It is challenging to identify a protein complex in a haystack of protein-protein interactions, and it is even more difficult to predict all protein complexes of the complexome. Simulations and machine learning approaches try to crack these problems by looking at the PPI network or predicted protein structures. Clustering of PPI networks led to the first protein complex predictions, while most recently, atomistic models of protein complexes and deep-learning-based structure prediction methods have also emerged. The simulation of PPI level interactions even enables the quantitative prediction of protein complexes. These methods, the required data sources, and their potential future developments are discussed in this review.

Protein Multiple Conformation Prediction Using Multi-Objective Evolution Algorithm

The breakthrough of AlphaFold2 and the publication of AlphaFold DB represent a significant advance in the field of predicting static protein structures. However, AlphaFold2 models tend to represent a single static structure, and multiple-conformation prediction remains a challenge. In this work, we proposed a method named MultiSFold, which uses a distance-based multi-objective evolutionary algorithm to predict multiple conformations. To begin, multiple energy landscapes are constructed using different competing constraints generated by deep learning. Subsequently, an iterative modal exploration and exploitation strategy is designed to sample conformations, incorporating multi-objective optimization, geometric optimization and structural similarity clustering. Finally, the final population is generated using a loop-specific sampling strategy to adjust the spatial orientations. MultiSFold was evaluated against state-of-the-art methods using a benchmark set containing 80 protein targets, each characterized by two representative conformational states. Based on the proposed metric, MultiSFold achieves a remarkable success ratio of 56.25% in predicting multiple conformations, while AlphaFold2 only achieves 10.00%, which may indicate that conformational sampling combined with knowledge gained through deep learning has the potential to generate conformations spanning the range between different conformational states. In addition, MultiSFold was tested on 244 human proteins with low structural accuracy in AlphaFold DB to test whether it could further improve the accuracy of static structures. The experimental results demonstrate the performance of MultiSFold, with a TM-score better than that of AlphaFold2 by 2.97% and RoseTTAFold by 7.72%. The online server is at http://zhanglab-bioinf.com/MultiSFold .

DSSGNN-PPI: A Protein-Protein Interactions prediction model based on Double Structure and Sequence graph neural networks

The process of experimentally confirming complex interaction networks among proteins is time-consuming and laborious. This study aims to address Protein-Protein Interactions (PPIs) prediction based on graph neural networks (GNN). A novel multilevel prediction model for PPIs named DSSGNN-PPI (Double Structure and Sequence GNN for PPIs) is designed. Initially, a distance graph between amino acid residues is constructed. Subsequently, the distance graph is fed into an underlying graph attention network module. This enables us to efficiently learn vector representations that encode the three-dimensional structure of proteins and simultaneously aggregate key local patterns and overall topological information to obtain graph embedding that adequately represent local and global structural features. In addition, the embedding representations that reflect sequence properties are obtained. Two features are fused to construct high-level protein complex networks, which are fed into the designed gated graph attention network to extract complex topological patterns. By combining heterogeneous multi-source information from downstream structure graph and upstream sequence models, the understanding of PPIs is comprehensively enhanced. A series of evaluation results validate the remarkable effectiveness of DSSGNN-PPI framework in enhancing the prediction of multi-type interactions among proteins. The multilevel representation learning and information fusion strategies provide a new effective solution paradigm for structural biology problems. The source code for DSSGNN-PPI has been hosted on GitHub and is available at https://github.com/cstudy1/DSSGNN-PPI.

FoldPAthreader: predicting protein folding pathway using a novel folding force field model derived from known protein universe

Protein folding has become a tractable problem with the significant advances in deep learning-driven protein structure prediction. Here we propose FoldPAthreader, a protein folding pathway prediction method that uses a novel folding force field model by exploring the intrinsic relationship between protein evolution and folding from the known protein universe. Further, the folding force field is used to guide Monte Carlo conformational sampling, driving the protein chain fold into its native state by exploring potential intermediates. On 30 example targets, FoldPAthreader successfully predicts 70% of the proteins whose folding pathway is consistent with biological experimental data.

SPDesign: protein sequence designer based on structural sequence profile using ultrafast shape recognition

Protein sequence design can provide valuable insights into biopharmaceuticals and disease treatments. Currently, most protein sequence design methods based on deep learning focus on network architecture optimization, while ignoring protein-specific physicochemical features. Inspired by the successful application of structure templates and pre-trained models in the protein structure prediction, we explored whether the representation of structural sequence profile can be used for protein sequence design. In this work, we propose SPDesign, a method for protein sequence design based on structural sequence profile using ultrafast shape recognition. Given an input backbone structure, SPDesign utilizes ultrafast shape recognition vectors to accelerate the search for similar protein structures in our in-house PAcluster80 structure database and then extracts the sequence profile through structure alignment. Combined with structural pre-trained knowledge and geometric features, they are further fed into an enhanced graph neural network for sequence prediction. The results show that SPDesign significantly outperforms the state-of-the-art methods, such as ProteinMPNN, Pifold and LM-Design, leading to 21.89%, 15.54% and 11.4% accuracy gains in sequence recovery rate on CATH 4.2 benchmark, respectively. Encouraging results also have been achieved on orphan and de novo (designed) benchmarks with few homologous sequences. Furthermore, analysis conducted by the PDBench tool suggests that SPDesign performs well in subdivided structures. More interestingly, we found that SPDesign can well reconstruct the sequences of some proteins that have similar structures but different sequences. Finally, the structural modeling verification experiment indicates that the sequences designed by SPDesign can fold into the native structures more accurately.

Understanding the heterogeneity intrinsic to protein folding

Relating the native fold of a protein to its amino acid sequence remains a fundamental problem in biology. While computer algorithms have demonstrated recently their prowess in predicting what structure a particular amino acid sequence will fold to, an understanding of how and why a specific protein fold is achieved remains elusive. A major challenge is to define the role of conformational heterogeneity during protein folding. Recent experimental studies, utilizing time-resolved FRET, hydrogen-exchange coupled to mass spectrometry, and single-molecule force spectroscopy, often in conjunction with simulation, have begun to reveal how conformational heterogeneity evolves during folding, and whether an intermediate ensemble of defined free energy consists of different sub-populations of molecules that may differ significantly in conformation, energy and entropy.

Recent Advances and Challenges in Protein Structure Prediction

Artificial intelligence has made significant advances in the field of protein structure prediction in recent years. In particular, DeepMind's end-to-end model, AlphaFold2, has demonstrated the capability to predict three-dimensional structures of numerous unknown proteins with accuracy levels comparable to those of experimental methods. This breakthrough has opened up new possibilities for understanding protein structure and function as well as accelerating drug discovery and other applications in the field of biology and medicine. Despite the remarkable achievements of artificial intelligence in the field, there are still some challenges and limitations. In this Review, we discuss the recent progress and some of the challenges in protein structure prediction. These challenges include predicting multidomain protein structures, protein complex structures, multiple conformational states of proteins, and protein folding pathways. Furthermore, we highlight directions in which further improvements can be conducted.

Multi-domain and complex protein structure prediction using inter-domain interactions from deep learning

Accurately capturing domain-domain interactions is key to understanding protein function and designing structure-based drugs. Although AlphaFold2 has made a breakthrough on single domain, it should be noted that the structure modeling for multi-domain protein and complex remains a challenge. In this study, we developed a multi-domain and complex structure assembly protocol, named DeepAssembly, based on domain segmentation and single domain modeling algorithms. Firstly, DeepAssembly uses a population-based evolutionary algorithm to assemble multi-domain proteins by inter-domain interactions inferred from a developed deep learning network. Secondly, protein complexes are assembled by means of domains rather than chains using DeepAssembly. Experimental results show that on 219 multi-domain proteins, the average inter-domain distance precision by DeepAssembly is 22.7% higher than that of AlphaFold2. Moreover, DeepAssembly improves accuracy by 13.1% for 164 multi-domain structures with low confidence deposited in AlphaFold database. We apply DeepAssembly for the prediction of 247 heterodimers. We find that DeepAssembly successfully predicts the interface (DockQ ≥ 0.23) for 32.4% of the dimers, suggesting a lighter way to assemble complex structures by treating domains as assembly units and using inter-domain interactions learned from monomer structures.

GPCNDTA: Prediction of drug-target binding affinity through cross-attention networks augmented with graph features and pharmacophores

Drug-target affinity prediction is a challenging task in drug discovery. The latest computational models have limitations in mining edge information in molecule graphs, accessing to knowledge in pharmacophores, integrating multimodal data of the same biomolecule and realizing effective interactions between two different biomolecules. To solve these problems, we proposed a method called Graph features and Pharmacophores augmented Cross-attention Networks based Drug-Target binding Affinity prediction (GPCNDTA). First, we utilized the GNN module, the linear projection unit and self-attention layer to correspondingly extract features of drugs and proteins. Second, we devised intramolecular and intermolecular cross-attention to respectively fuse and interact features of drugs and proteins. Finally, the linear projection unit was applied to gain final features of drugs and proteins, and the Multi-Layer Perceptron was employed to predict drug-target binding affinity. Three major innovations of GPCNDTA are as follows: (i) developing the residual CensNet and the residual EW-GCN to correspondingly extract features of drug and protein graphs, (ii) regarding pharmacophores as a new type of priors to heighten drug-target affinity prediction performance, and (iii) devising intramolecular and intermolecular cross-attention, in which the intramolecular cross-attention realizes the effective fusion of different modal data related to the same biomolecule, and the intermolecular cross-attention fulfills the information interaction between two different biomolecules in attention space. The test results on five benchmark datasets imply that GPCNDTA achieves the best performance compared with state-of-the-art computational models. Besides, relying on ablation experiments, we proved effectiveness of GNN modules, pharmacophores and two cross-attention strategies in improving the prediction accuracy, stability and reliability of GPCNDA. In case studies, we applied GPCNDTA to predict binding affinities between 3C-like proteinase and 185 drugs, and observed that most binding affinities predicted by GPCNDTA are close to corresponding experimental measurements.

E2EDA: Protein Domain Assembly Based on End-to-End Deep Learning

With the development of deep learning, almost all single-domain proteins can be predicted at experimental resolution. However, the structure prediction of multi-domain proteins remains a challenge. Achieving end-to-end protein domain assembly and further improving the accuracy of the full-chain modeling by accurately predicting inter-domain orientation while improving the assembly efficiency will provide significant insights into structure-based drug discovery. In this work, we propose an End-to-End Domain Assembly method based on deep learning, named E2EDA. We first develop RMNet, an EfficientNetV2-based deep learning model that fuses multiple features using an attention mechanism to predict inter-domain rigid motion. Then, the predicted rigid motions are transformed into inter-domain spatial transformations to directly assemble the full-chain model. Finally, the scoring strategy RMscore is designed to select the best model from multiple assembled models. The experimental results show that the average TM-score of the model assembled by E2EDA on the benchmark set (282) is 0.827, which is better than those of other domain assembly methods SADA (0.792) and DEMO (0.730). Meanwhile, on our constructed multi-domain data set from AlphaFold DB, the model reassembled by E2EDA is 7.0% higher in TM-score compared to the full-chain model predicted by AlphaFold2, indicating that E2EDA can capture more accurate inter-domain orientations to improve the quality of the model predicted by AlphaFold2. Furthermore, compared to SADA and AlphaFold2, E2EDA reduced the average runtime on the benchmark by 64.7% and 19.2%, respectively, indicating that E2EDA can significantly improve assembly efficiency through an end-to-end approach. The online server is available at http://zhanglab-bioinf.com/E2EDA.

SeqPredNN: a neural network that generates protein sequences that fold into specified tertiary structures

BACKGROUND

The relationship between the sequence of a protein, its structure, and the resulting connection between its structure and function, is a foundational principle in biological science. Only recently has the computational prediction of protein structure based only on protein sequence been addressed effectively by AlphaFold, a neural network approach that can predict the majority of protein structures with X-ray crystallographic accuracy. A question that is now of acute relevance is the "inverse protein folding problem": predicting the sequence of a protein that folds into a specified structure. This will be of immense value in protein engineering and biotechnology, and will allow the design and expression of recombinant proteins that can, for instance, fold into specified structures as a scaffold for the attachment of recombinant antigens, or enzymes with modified or novel catalytic activities. Here we describe the development of SeqPredNN, a feed-forward neural network trained with X-ray crystallographic structures from the RCSB Protein Data Bank to predict the identity of amino acids in a protein structure using only the relative positions, orientations, and backbone dihedral angles of nearby residues.

RESULTS

We predict the sequence of a protein expected to fold into a specified structure and assess the accuracy of the prediction using both AlphaFold and RoseTTAFold to computationally generate the fold of the derived sequence. We show that the sequences predicted by SeqPredNN fold into a structure with a median TM-score of 0.638 when compared to the crystal structure according to AlphaFold predictions, yet these sequences are unique and only 28.4% identical to the sequence of the crystallized protein.

CONCLUSIONS

We propose that SeqPredNN will be a valuable tool to generate proteins of defined structure for the design of novel biomaterials, pharmaceuticals, catalysts, and reporter systems. The low sequence identity of its predictions compared to the native sequence could prove useful for developing proteins with modified physical properties, such as water solubility and thermal stability. The speed and ease of use of SeqPredNN offers a significant advantage over physics-based protein design methods.

Pathfinder: Protein folding pathway prediction based on conformational sampling

The study of protein folding mechanism is a challenge in molecular biology, which is of great significance for revealing the movement rules of biological macromolecules, understanding the pathogenic mechanism of folding diseases, and designing protein engineering materials. Based on the hypothesis that the conformational sampling trajectory contain the information of folding pathway, we propose a protein folding pathway prediction algorithm named Pathfinder. Firstly, Pathfinder performs large-scale sampling of the conformational space and clusters the decoys obtained in the sampling. The heterogeneous conformations obtained by clustering are named seed states. Then, a resampling algorithm that is not constrained by the local energy basin is designed to obtain the transition probabilities of seed states. Finally, protein folding pathways are inferred from the maximum transition probabilities of seed states. The proposed Pathfinder is tested on our developed test set (34 proteins). For 11 widely studied proteins, we correctly predicted their folding pathways and specifically analyzed 5 of them. For 13 proteins, we predicted their folding pathways to be further verified by biological experiments. For 6 proteins, we analyzed the reasons for the low prediction accuracy. For the other 4 proteins without biological experiment results, potential folding pathways were predicted to provide new insights into protein folding mechanism. The results reveal that structural analogs may have different folding pathways to express different biological functions, homologous proteins may contain common folding pathways, and α-helices may be more prone to early protein folding than β-strands.

Identifying potential drug-target interactions based on ensemble deep learning

Introduction

Drug-target interaction prediction is one important step in drug research and development. Experimental methods are time consuming and laborious.

Methods

In this study, we developed a novel DTI prediction method called EnGDD by combining initial feature acquisition, dimensional reduction, and DTI classification based on Gradient boosting neural network, Deep neural network, and Deep Forest.

Results

EnGDD was compared with seven stat-of-the-art DTI prediction methods (BLM-NII, NRLMF, WNNGIP, NEDTP, DTi2Vec, RoFDT, and MolTrans) on the nuclear receptor, GPCR, ion channel, and enzyme datasets under cross validations on drugs, targets, and drug-target pairs, respectively. EnGDD computed the best recall, accuracy, F1-score, AUC, and AUPR under the majority of conditions, demonstrating its powerful DTI identification performance. EnGDD predicted that D00182 and hsa2099, D07871 and hsa1813, DB00599 and hsa2562, D00002 and hsa10935 have a higher interaction probabilities among unknown drug-target pairs and may be potential DTIs on the four datasets, respectively. In particular, D00002 (Nadide) was identified to interact with hsa10935 (Mitochondrial peroxiredoxin3) whose up-regulation might be used to treat neurodegenerative diseases. Finally, EnGDD was used to find possible drug targets for Parkinson's disease and Alzheimer's disease after confirming its DTI identification performance. The results show that D01277, D04641, and D08969 may be applied to the treatment of Parkinson's disease through targeting hsa1813 (dopamine receptor D2) and D02173, D02558, and D03822 may be the clues of treatment for patients with Alzheimer's disease through targeting hsa5743 (prostaglandinendoperoxide synthase 2). The above prediction results need further biomedical validation.

Discussion

We anticipate that our proposed EnGDD model can help discover potential therapeutic clues for various diseases including neurodegenerative diseases.