Prediction of inter-chain distance maps of protein complexes with 2D attention-based deep neural networks

A variational expectation-maximization framework for balanced multi-scale learning of protein and drug interactions

Protein functions are characterized by interactions with proteins, drugs, and other biomolecules. Understanding these interactions is essential for deciphering the molecular mechanisms underlying biological processes and developing new therapeutic strategies. Current computational methods mostly predict interactions based on either molecular network or structural information, without integrating them within a unified multi-scale framework. While a few multi-view learning methods are devoted to fusing the multi-scale information, these methods tend to rely intensively on a single scale and under-fitting the others, likely attributed to the imbalanced nature and inherent greediness of multi-scale learning. To alleviate the optimization imbalance, we present MUSE, a multi-scale representation learning framework based on a variant expectation maximization to optimize different scales in an alternating procedure over multiple iterations. This strategy efficiently fuses multi-scale information between atomic structure and molecular network scale through mutual supervision and iterative optimization. MUSE outperforms the current state-of-the-art models not only in molecular interaction (protein-protein, drug-protein, and drug-drug) tasks but also in protein interface prediction at the atomic structure scale. More importantly, the multi-scale learning framework shows potential for extension to other scales of computational drug discovery.

Protein language model-embedded geometric graphs power inter-protein contact prediction

Accurate prediction of contacting residue pairs between interacting proteins is very useful for structural characterization of protein-protein interactions. Although significant improvement has been made in inter-protein contact prediction recently, there is still a large room for improving the prediction accuracy. Here we present a new deep learning method referred to as PLMGraph-Inter for inter-protein contact prediction. Specifically, we employ rotationally and translationally invariant geometric graphs obtained from structures of interacting proteins to integrate multiple protein language models, which are successively transformed by graph encoders formed by geometric vector perceptrons and residual networks formed by dimensional hybrid residual blocks to predict inter-protein contacts. Extensive evaluation on multiple test sets illustrates that PLMGraph-Inter outperforms five top inter-protein contact prediction methods, including DeepHomo, GLINTER, CDPred, DeepHomo2, and DRN-1D2D_Inter, by large margins. In addition, we also show that the prediction of PLMGraph-Inter can complement the result of AlphaFold-Multimer. Finally, we show leveraging the contacts predicted by PLMGraph-Inter as constraints for protein-protein docking can dramatically improve its performance for protein complex structure prediction.

Deep learning in modeling protein complex structures: From contact prediction to end-to-end approaches

Protein-protein interactions play crucial roles in many biological processes. Traditionally, protein complex structures are normally built by protein-protein docking. With the rapid development of artificial intelligence and its great success in monomer protein structure prediction, deep learning has widely been applied to modeling protein-protein complex structures through inter-protein contact prediction and end-to-end approaches in the past few years. This article reviews the recent advances of deep-learning-based approaches in modeling protein-protein complex structures as well as their advantages and limitations. Challenges and possible future directions are also briefly discussed in applying deep learning for the prediction of protein complex structures.

MoDAFold: a strategy for predicting the structure of missense mutant protein based on AlphaFold2 and molecular dynamics

Protein structure prediction is a longstanding issue crucial for identifying new drug targets and providing a mechanistic understanding of protein functions. To enhance the progress in this field, a spectrum of computational methodologies has been cultivated. AlphaFold2 has exhibited exceptional precision in predicting wild-type protein structures, with performance exceeding that of other methods. However, predicting the structures of missense mutant proteins using AlphaFold2 remains challenging due to the intricate and substantial structural alterations caused by minor sequence variations in the mutant proteins. Molecular dynamics (MD) has been validated for precisely capturing changes in amino acid interactions attributed to protein mutations. Therefore, for the first time, a strategy entitled 'MoDAFold' was proposed to improve the accuracy and reliability of missense mutant protein structure prediction by combining AlphaFold2 with MD. Multiple case studies have confirmed the superior performance of MoDAFold compared to other methods, particularly AlphaFold2.

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.

ConPep: Prediction of peptide contact maps with pre-trained biological language model and multi-view feature extracting strategy

The accurate prediction of peptide contact maps remains a challenging task due to the difficulty in obtaining the interactive information between residues on short sequences. To address this challenge, we propose ConPep, a deep learning framework designed for predicting the contact map of peptides based on sequences only. To sufficiently incorporate the sequential semantic information between residues in peptide sequences, we use a pre-trained biological language model and transfer prior knowledge from large scale databases. Additionally, to extract and integrate sequential local information and residue-based global correlations, our model incorporates Bidirectional Gated Recurrent Unit and attention mechanisms. They can obtain multi-view features and thus enhance the accuracy and robustness of our prediction. Comparative results on independent tests demonstrate that our proposed method significantly outperforms state-of-the-art methods even with short peptides. Notably, our method exhibits superior performance at the sequence level, suggesting the robust ability of our model compared with the multiple sequence alignment (MSA) analysis-based methods. We expect it can be meaningful research for facilitating the wide use of our method.

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.

Enhancing alphafold-multimer-based protein complex structure prediction with MULTICOM in CASP15

To enhance the AlphaFold-Multimer-based protein complex structure prediction, we developed a quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and refine its outputs. MULTICOM samples diverse multiple sequence alignments (MSAs) and templates for AlphaFold-Multimer to generate structural predictions by using both traditional sequence alignments and Foldseek-based structure alignments, ranks structural predictions through multiple complementary metrics, and refines the structural predictions via a Foldseek structure alignment-based refinement method. The MULTICOM system with different implementations was blindly tested in the assembly structure prediction in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 as both server and human predictors. MULTICOM_qa ranked 3rd among 26 CASP15 server predictors and MULTICOM_human ranked 7th among 87 CASP15 server and human predictors. The average TM-score of the first predictions submitted by MULTICOM_qa for CASP15 assembly targets is ~0.76, 5.3% higher than ~0.72 of the standard AlphaFold-Multimer. The average TM-score of the best of top 5 predictions submitted by MULTICOM_qa is ~0.80, about 8% higher than ~0.74 of the standard AlphaFold-Multimer. Moreover, the Foldseek Structure Alignment-based Multimer structure Generation (FSAMG) method outperforms the widely used sequence alignment-based multimer structure generation.

Accurate prediction of protein tertiary structural changes induced by single-site mutations with equivariant graph neural networks

Predicting the change of protein tertiary structure caused by singlesite mutations is important for studying protein structure, function, and interaction. Even though computational protein structure prediction methods such as AlphaFold can predict the overall tertiary structures of most proteins rather accurately, they are not sensitive enough to accurately predict the structural changes induced by single-site amino acid mutations on proteins. Specialized mutation prediction methods mostly focus on predicting the overall stability or function changes caused by mutations without attempting to predict the exact mutation-induced structural changes, limiting their use in protein mutation study. In this work, we develop the first deep learning method based on equivariant graph neural networks (EGNN) to directly predict the tertiary structural changes caused by single-site mutations and the tertiary structure of any protein mutant from the structure of its wild-type counterpart. The results show that it performs substantially better in predicting the tertiary structures of protein mutants than the widely used protein structure prediction method AlphaFold.

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.

Deep transfer learning for inter-chain contact predictions of transmembrane protein complexes

Membrane proteins are encoded by approximately a quarter of human genes. Inter-chain residue-residue contact information is important for structure prediction of membrane protein complexes and valuable for understanding their molecular mechanism. Although many deep learning methods have been proposed to predict the intra-protein contacts or helix-helix interactions in membrane proteins, it is still challenging to accurately predict their inter-chain contacts due to the limited number of transmembrane proteins. Addressing the challenge, here we develop a deep transfer learning method for predicting inter-chain contacts of transmembrane protein complexes, named DeepTMP, by taking advantage of the knowledge pre-trained from a large data set of non-transmembrane proteins. DeepTMP utilizes a geometric triangle-aware module to capture the correct inter-chain interaction from the coevolution information generated by protein language models. DeepTMP is extensively evaluated on a test set of 52 self-associated transmembrane protein complexes, and compared with state-of-the-art methods including DeepHomo2.0, CDPred, GLINTER, DeepHomo, and DNCON2_Inter. It is shown that DeepTMP considerably improves the precision of inter-chain contact prediction and outperforms the existing approaches in both accuracy and robustness.

Thermoresponsive Polypeptide Fused L-Asparaginase with Mitigated Immunogenicity and Enhanced Efficacy in Treating Hematologic Malignancies

L-Asparaginase (ASP) is well-known for its excellent efficacy in treating hematological malignancies. Unfortunately, the intrinsic shortcomings of ASP, namely high immunogenicity, severe toxicity, short half-life, and poor stability, restrict its clinical usage. Poly(ethylene glycol) conjugation (PEGylation) of ASP is an effective strategy to address these issues, but it is not ideal in clinical applications due to complex chemical synthesis procedures, reduced ASP activity after conjugation, and pre-existing anti-PEG antibodies in humans. Herein, the authors genetically engineered an elastin-like polypeptide (ELP)-fused ASP (ASP-ELP), a core-shell structured tetramer predicted by AlphaFold2, to overcome the limitations of ASP and PEG-ASP. Notably, the unique thermosensitivity of ASP-ELP enables the in situ formation of a sustained-release depot post-injection with zero-order release kinetics over a long time. The in vitro and in vivo studies reveal that ASP-ELP possesses increased activity retention, improved stability, extended half-life, mitigated immunogenicity, reduced toxicity, and enhanced efficacy compared to ASP and PEG-ASP. Indeed, ASP-ELP treatment in leukemia or lymphoma mouse models of cell line-derived xenograft (CDX) shows potent anti-cancer effects with significantly prolonged survival. The findings also indicate that artificial intelligence (AI)-assisted genetic engineering is instructive in designing protein-polypeptide conjugates and may pave the way to develop next-generation biologics to enhance cancer treatment.

Challenges in structural modeling of RNA-protein interactions

In the past few years, the number of RNA-binding proteins (RBP) and RNA-RBP interactions has increased significantly. Here, we review recent developments in the methodology for protein-RNA and protein-protein complex structure modeling with deep learning and co-evolution, as well as discuss the challenges and opportunities for building a reliable approach for protein-RNA complex structure modelling. Protein Data bank (PDB) and Cross-linking immunoprecipitation (CLIP) data could be combined together and used to infer 2D geometry of protein-RNA interactions by deep learning.

A gated graph transformer for protein complex structure quality assessment and its performance in CASP15

MOTIVATION

Proteins interact to form complexes to carry out essential biological functions. Computational methods such as AlphaFold-multimer have been developed to predict the quaternary structures of protein complexes. An important yet largely unsolved challenge in protein complex structure prediction is to accurately estimate the quality of predicted protein complex structures without any knowledge of the corresponding native structures. Such estimations can then be used to select high-quality predicted complex structures to facilitate biomedical research such as protein function analysis and drug discovery.

RESULTS

In this work, we introduce a new gated neighborhood-modulating graph transformer to predict the quality of 3D protein complex structures. It incorporates node and edge gates within a graph transformer framework to control information flow during graph message passing. We trained, evaluated and tested the method (called DProQA) on newly-curated protein complex datasets before the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) and then blindly tested it in the 2022 CASP15 experiment. The method was ranked 3rd among the single-model quality assessment methods in CASP15 in terms of the ranking loss of TM-score on 36 complex targets. The rigorous internal and external experiments demonstrate that DProQA is effective in ranking protein complex structures.

AVAILABILITY AND IMPLEMENTATION

The source code, data, and pre-trained models are available at https://github.com/jianlin-cheng/DProQA.

Enhancing AlphaFold-Multimer-based Protein Complex Structure Prediction with MULTICOM in CASP15

AlphaFold-Multimer has emerged as the state-of-the-art tool for predicting the quaternary structure of protein complexes (assemblies or multimers) since its release in 2021. To further enhance the AlphaFold-Multimer-based complex structure prediction, we developed a new quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and refine the outputs generated by AlphaFold2-Multimer. Specifically, MULTICOM samples diverse multiple sequence alignments (MSAs) and templates for AlphaFold-Multimer to generate structural models by using both traditional sequence alignments and new Foldseek-based structure alignments, ranks structural models through multiple complementary metrics, and refines the structural models via a Foldseek structure alignment-based refinement method. The MULTICOM system with different implementations was blindly tested in the assembly structure prediction in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 as both server and human predictors. Our server (MULTICOM_qa) ranked 3rd among 26 CASP15 server predictors and our human predictor (MULTICOM_human) ranked 7th among 87 CASP15 server and human predictors. The average TM-score of the first models predicted by MULTICOM_qa for CASP15 assembly targets is ~0.76, 5.3% higher than ~0.72 of the standard AlphaFold-Multimer. The average TM-score of the best of top 5 models predicted by MULTICOM_qa is ~0.80, about 8% higher than ~0.74 of the standard AlphaFold-Multimer. Moreover, the novel Foldseek Structure Alignment-based Model Generation (FSAMG) method based on AlphaFold-Multimer outperforms the widely used sequence alignment-based model generation. The source code of MULTICOM is available at: https://github.com/BioinfoMachineLearning/MULTICOM3.

Reconciling membrane protein simulations with experimental DEER spectroscopy data

Spectroscopy experiments are crucial to study membrane proteins for which traditional structure determination methods still prove challenging. Double electron-electron resonance (DEER) spectroscopy experiments provide protein residue-pair distance distributions that are indicative of their conformational heterogeneity. Atomistic molecular dynamics (MD) simulations are another tool that have been proven to be vital to study the structural dynamics of membrane proteins such as to identify inward-open, occluded, and outward-open conformations of transporter membrane proteins, among other partially open or closed states of the protein. Yet, studies have reported that there is no direct consensus between the distributional data from DEER experiments and MD simulations, which has challenged validation of structures obtained from long-timescale simulations and using simulations to design experiments. Current coping strategies for comparisons rely on heuristics, such as mapping the nearest matching peaks between two ensembles or biased simulations. Here we examine the differences in residue-pair distance distributions arising due to the choice of membranes around the protein and covalent modification of a pair of residues to nitroxide spin labels in DEER experiments. Through comparing MD simulations of two proteins, PepT_So and LeuT-both of which have been characterized using DEER experiments previously-we show that the proteins' dynamics are similar despite the choice of the detergent micelle as a membrane mimetic in DEER experiments. On the other hand, covalently modified residues show slight local differences in their dynamics and a huge divergence when the oxygen atom pair distances between spin labeled residues are measured rather than protein backbone distances. Given the computational expense associated with pairwise MTSSL labeled MD simulations, we examine the use of biased simulations to explore the conformational dynamics of the spin labels only to reveal that such simulations alter the underlying protein dynamics. Our study identifies the main cause for the mismatch between DEER experiments and MD simulations and will accelerate the development of potential mitigation strategies to improve the match.