Protein Structural Information Research Articles

The Present State and Impact of AI-Driven Computational Tools for Predicting Plant Protein Structures.

Several key functions of plants, such as photosynthesis, nutrient transport, disease resistance, and abiotic tolerance, are manifested by several classes of proteins. Prediction of 3- dimensional (3-D) structures of proteins and their working mechanisms can have a profound impact on plant proteomics research and could help improve key agricultural traits in crop plants. This review aims to present the current status of plant protein structure determination and discuss the way forward. Most experimentally proven protein structures are available only for the model plant Arabidopsis thaliana. Most of the key crop plants have only a few hundred or fewer experimentally proven 3-D structures. Fewer than 1% of the protein sequences in the majority of plants have had their 3D structures experimentally determined, and A. thaliana is the sole plant with the highest percentage of 1.4 % of protein sequences with experimentally determined structures. AI-based protein structure prediction tool AlphaFold has predicted models of several thousand proteins for many crop plants. In AlphaFold predicted protein models, soybean has the highest percentage (65%) of its UniProt protein sequences with predicted models, and a few other crop plants have also a considerable percentage of its UniProt sequences with AlphaFold predicted models. AlphaFold might help predict models and bridge the gap in plant structure determination studies. Protein structure information might lead to engineering key residues to improve the agronomical performance of crop plants.

DIONYSUS: a database of protein-carbohydrate interfaces.

Protein-carbohydrate interactions govern a wide variety of biological processes and play an essential role in the development of different diseases. Here, we present DIONYSUS, the first database of protein-carbohydrate interfaces annotated according to structural, chemical and functional properties of both proteins and carbohydrates. We provide exhaustive information on the nature of interactions, binding site composition, biological function and specific additional information retrieved from existing databases. The user can easily search the database using protein sequence and structure information or by carbohydrate binding site properties. Moreover, for a given interaction site, the user can perform its comparison with a representative subset of non-covalent protein-carbohydrate interactions to retrieve information on its potential function or specificity. Therefore, DIONYSUS is a source of valuable information both for a deeper understanding of general protein-carbohydrate interaction patterns, for annotation of the previously unannotated proteins and for such applications as carbohydrate-based drug design. DIONYSUS is freely available at www.dsimb.inserm.fr/DIONYSUS/.

Using deep-learning predictions reveals a large number of register errors in PDB depositions.

The accuracy of the information in the Protein Data Bank (PDB) is of great importance for the myriad downstream applications that make use of protein structural information. Despite best efforts, the occasional introduction of errors is inevitable, especially where the experimental data are of limited resolution. A novel protein structure validation approach based on spotting inconsistencies between the residue contacts and distances observed in a structural model and those computationally predicted by methods such as AlphaFold2 has previously been established. It is particularly well suited to the detection of register errors. Importantly, this new approach is orthogonal to traditional methods based on stereochemistry or map-model agreement, and is resolution independent. Here, thousands of likely register errors are identified by scanning 3-5 Å resolution structures in the PDB. Unlike most methods, the application of this approach yields suggested corrections to the register of affected regions, which it is shown, even by limited implementation, lead to improved refinement statistics in the vast majority of cases. A few limitations and confounding factors such as fold-switching proteins are characterized, but this approach is expected to have broad application in spotting potential issues in current accessions and, through its implementation and distribution in CCP4, helping to ensure the accuracy of future depositions.

PDNAPred: Interpretable prediction of protein-DNA binding sites based on pre-trained protein language models

Protein-DNA interactions play critical roles in various biological processes and are essential for drug discovery. However, traditional experimental methods are labor-intensive and unable to keep pace with the increasing volume of protein sequences, leading to a substantial number of proteins lacking DNA-binding annotations. Therefore, developing an efficient computational method to identify protein-DNA binding sites is crucial. Unfortunately, most existing computational methods rely on manually selected features or protein structure information, making these methods inapplicable to large-scale prediction tasks. In this study, we introduced PDNAPred, a sequence-based method that combines two pre-trained protein language models with a designed CNN-GRU network to identify DNA-binding sites. Additionally, to tackle the issue of imbalanced dataset samples, we employed focal loss. Our comprehensive experiments demonstrated that PDNAPred significantly improved the accuracy of DNA-binding site prediction, outperforming existing state-of-the-art sequence-based methods. Remarkably, PDNAPred also achieved results comparable to advanced structure-based methods. The designed CNN-GRU network enhances its capability to detect DNA-binding sites accurately. Furthermore, we validated the versatility of PDNAPred by training it on RNA-binding site datasets, showing its potential as a general framework for amino acid binding site prediction. Finally, we conducted model interpretability analysis to elucidate the reasons behind PDNAPred's outstanding performance.

Accessing a Medicinal-Chemistry-Relevant Chemical Space with sp2–sp3 Hybrid Heterocyclic Fragments

AbstractTarget-first drug discovery relies heavily on protein structure information, which severely limits its application. In recent years, fragment-based drug Design (FBDD) has been identified as an alternative solution, where screening of smaller molecules for lower affinity allowed the use of focused libraries with a higher hit rate. It is shown that coupling an sp2-rich heteroaromatic group with a monofunctional sp3-rich core gives fragments (186 examples) with advantageous physical-chemical properties, covering a chemical space often neglected in traditional libraries.

PCP-GC-LM: single-sequence-based protein contact prediction using dual graph convolutional neural network and convolutional neural network

BackgroundRecently, the process of evolution information and the deep learning network has promoted the improvement of protein contact prediction methods. Nevertheless, still remain some bottleneck: (1) One of the bottlenecks is the prediction of orphans and other fewer evolution information proteins. (2) The other bottleneck is the method of predicting single-sequence-based proteins mainly focuses on selecting protein sequence features and tuning the neural network architecture, However, while the deeper neural networks improve prediction accuracy, there is still the problem of increasing the computational burden. Compared with other neural networks in the field of protein prediction, the graph neural network has the following advantages: due to the advantage of revealing the topology structure via graph neural network and being able to take advantage of the hierarchical structure and local connectivity of graph neural networks has certain advantages in capturing the features of different levels of abstraction in protein molecules. When using protein sequence and structure information for joint training, the dependencies between the two kinds of information can be better captured. And it can process protein molecular structures of different lengths and shapes, while traditional neural networks need to convert proteins into fixed-size vectors or matrices for processing.ResultsHere, we propose a single-sequence-based protein contact map predictor PCP-GC-LM, with dual-level graph neural networks and convolution networks. Our method performs better with other single-sequence-based predictors in different independent tests. In addition, to verify the validity of our method against complex protein structures, we will also compare it with other methods in two homodimers protein test sets (DeepHomo test dataset and CASP-CAPRI target dataset). Furthermore, we also perform ablation experiments to demonstrate the necessity of a dual graph network. In all, our framework presents new modules to accurately predict inter-chain contact maps in protein and it’s also useful to analyze interactions in other types of protein complexes.

Accurate prediction of protein function using statistics-informed graph networks

Understanding protein function is pivotal in comprehending the intricate mechanisms that underlie many crucial biological activities, with far-reaching implications in the fields of medicine, biotechnology, and drug development. However, more than 200 million proteins remain uncharacterized, and computational efforts heavily rely on protein structural information to predict annotations of varying quality. Here, we present a method that utilizes statistics-informed graph networks to predict protein functions solely from its sequence. Our method inherently characterizes evolutionary signatures, allowing for a quantitative assessment of the significance of residues that carry out specific functions. PhiGnet not only demonstrates superior performance compared to alternative approaches but also narrows the sequence-function gap, even in the absence of structural information. Our findings indicate that applying deep learning to evolutionary data can highlight functional sites at the residue level, providing valuable support for interpreting both existing properties and new functionalities of proteins in research and biomedicine.

MGPPI: multiscale graph neural networks for explainable protein-protein interaction prediction.

Protein-Protein Interactions (PPIs) involves in various biological processes, which are of significant importance in cancer diagnosis and drug development. Computational based PPI prediction methods are more preferred due to their low cost and high accuracy. However, existing protein structure based methods are insufficient in the extraction of protein structural information. Furthermore, most methods are less interpretable, which hinder their practical application in the biomedical field. In this paper, we propose MGPPI, which is a Multiscale graph convolutional neural network model for PPI prediction. By incorporating multiscale module into the Graph Neural Network (GNN) and constructing multi convolutional layers, MGPPI can effectively capture both local and global protein structure information. For model interpretability, we introduce a novel visual explanation method named Gradient Weighted interaction Activation Mapping (Grad-WAM), which can highlight key binding residue sites. We evaluate the performance of MGPPI by comparing with state-of-the-arts methods on various datasets. Results shows that MGPPI outperforms other methods significantly and exhibits strong generalization capabilities on the multi-species dataset. As a practical case study, we predicted the binding affinity between the spike (S) protein of SARS-COV-2 and the human ACE2 receptor protein, and successfully identified key binding sites with known binding functions. Key binding sites mutation in PPIs can affect cancer patient survival statues. Therefore, we further verified Grad-WAM highlighted residue sites in separating patients survival groups in several different cancer type datasets. According to our results, some of the highlighted residues can be used as biomarkers in predicting patients survival probability. All these results together demonstrate the high accuracy and practical application value of MGPPI. Our method not only addresses the limitations of existing approaches but also can assists researchers in identifying crucial drug targets and help guide personalized cancer treatment.

Deep learning methods for protein function prediction.

Predicting protein function from protein sequence, structure, interaction, and other relevant information is important for generating hypotheses for biological experiments and studying biological systems, and therefore has been a major challenge in protein bioinformatics. Numerous computational methods had been developed to advance protein function prediction gradually in the last two decades. Particularly, in the recent years, leveraging the revolutionary advances in artificial intelligence (AI), more and more deep learning methods have been developed to improve protein function prediction at a faster pace. Here, we provide an in-depth review of the recent developments of deep learning methods for protein function prediction. We summarize the significant advances in the field, identify several remaining major challenges to be tackled, and suggest some potential directions to explore. The data sources and evaluation metrics widely used in protein function prediction are also discussed to assist the machine learning, AI, and bioinformatics communities to develop more cutting-edge methods to advance protein function prediction.

LVPocket: integrated 3D global-local information to protein binding pockets prediction with transfer learning of protein structure classification

BackgroundPrevious deep learning methods for predicting protein binding pockets mainly employed 3D convolution, yet an abundance of convolution operations may lead the model to excessively prioritize local information, thus overlooking global information. Moreover, it is essential for us to account for the influence of diverse protein folding structural classes. Because proteins classified differently structurally exhibit varying biological functions, whereas those within the same structural class share similar functional attributes.ResultsWe proposed LVPocket, a novel method that synergistically captures both local and global information of protein structure through the integration of Transformer encoders, which help the model achieve better performance in binding pockets prediction. And then we tailored prediction models for data of four distinct structural classes of proteins using the transfer learning. The four fine-tuned models were trained on the baseline LVPocket model which was trained on the sc-PDB dataset. LVPocket exhibits superior performance on three independent datasets compared to current state-of-the-art methods. Additionally, the fine-tuned model outperforms the baseline model in terms of performance.Scientific contributionWe present a novel model structure for predicting protein binding pockets that provides a solution for relying on extensive convolutional computation while neglecting global information about protein structures. Furthermore, we tackle the impact of different protein folding structures on binding pocket prediction tasks through the application of transfer learning methods.Graphical

Structure-independent machine-learning predictions of the CDK12 interactome

Cyclin-dependent kinase 12 (CDK12) is a critical regulatory protein involved in transcription and DNA repair processes. Dysregulation of CDK12 has been implicated in various diseases, including cancer. Understanding the CDK12 interactome is pivotal for elucidating its functional roles and potential therapeutic targets. Traditional methods for interactome prediction often rely on protein structure information, limiting applicability to CDK12 characterized by partly disordered terminal C region. In this study, we present a structure-independent machine-learning model that utilizes proteins’ sequence and functional data to predict the CDK12 interactome. This approach is motivated by the disordered character of the CDK12 C-terminal region mitigating a structure-driven search for binding partners. Our approach incorporates multiple data sources, including protein-protein interaction networks, functional annotations, and sequence-based features, to construct a comprehensive CDK12 interactome prediction model. The ability to predict CDK12 interactions without relying on structural information is a significant advancement, as many potential interaction partners may lack crystallographic data. In conclusion, our structure-independent machine-learning model presents a powerful tool for predicting the CDK12 interactome and holds promise in advancing our understanding of CDK12 biology, identifying potential therapeutic targets, and facilitating precision-medicine approaches for CDK12-associated diseases.

Inferring molecular inhibition potency with AlphaFold predicted structures

Even though in silico drug ligand-based methods have been successful in predicting interactions with known target proteins, they struggle with new, unassessed targets. To address this challenge, we propose an approach that integrates structural data from AlphaFold 2 predicted protein structures into machine learning models. Our method extracts 3D structural protein fingerprints and combines them with ligand structural data to train a single machine learning model. This model captures the relationship between ligand properties and the unique structural features of various target proteins, enabling predictions for never before tested molecules and protein targets. To assess our model, we used a dataset of 144 Human G-protein Coupled Receptors (GPCRs) with over 140,000 measured inhibition constants (Ki) values. Results strongly suggest that our approach performs as well as state-of-the-art ligand-based methods. In a second modeling approach that used 129 targets for training and a separate test set of 15 different protein targets, our model correctly predicted interactions for 73% of targets, with explained variances exceeding 0.50 in 22% of cases. Our findings further verified that the usage of experimentally determined protein structures produced models that were statistically indistinct from the Alphafold synthetic structures. This study presents a proteo-chemometric drug screening approach that uses a simple and scalable method for extracting protein structural information for usage in machine learning models capable of predicting protein-molecule interactions even for orphan targets.

I'm Walking into Spiderwebs: Making Sense of Protein-Protein Interaction Data.

Protein-protein interactions (PPIs) are at the heart of the molecular landscape permeating life. Proteomics studies can explore this protein interaction landscape using mass spectrometry (MS). Thanks to their high sensitivity, mass spectrometers can easily identify thousands of proteins within a single sample, but that same sensitivity generates tangled spiderwebs of data that hide biologically relevant findings. So, what does a researcher do when she finds herself walking into spiderwebs? In a field focused on discovery, MS data require rigor in their analysis, experimental validation, or a combination of both. In this Review, we provide a brief primer on MS-based experimental methods to identify PPIs. We discuss approaches to analyze the resulting data and remove the proteomic background. We consider the advantages between comprehensive and targeted studies. We also discuss how scoring might be improved through AI-based protein structure information. Women have been essential to the development of proteomics, so we will specifically highlight work by women that has made this field thrive in recent years.

GEFormerDTA: drug target affinity prediction based on transformer graph for early fusion

Predicting the interaction affinity between drugs and target proteins is crucial for rapid and accurate drug discovery and repositioning. Therefore, more accurate prediction of DTA has become a key area of research in the field of drug discovery and drug repositioning. However, traditional experimental methods have disadvantages such as long operation cycles, high manpower requirements, and high economic costs, making it difficult to predict specific interactions between drugs and target proteins quickly and accurately. Some methods mainly use the SMILES sequence of drugs and the primary structure of proteins as inputs, ignoring the graph information such as bond encoding, degree centrality encoding, spatial encoding of drug molecule graphs, and the structural information of proteins such as secondary structure and accessible surface area. Moreover, previous methods were based on protein sequences to learn feature representations, neglecting the completeness of information. To address the completeness of drug and protein structure information, we propose a Transformer graph-based early fusion research approach for drug-target affinity prediction (GEFormerDTA). Our method reduces prediction errors caused by insufficient feature learning. Experimental results on Davis and KIBA datasets showed a better prediction of drugtarget affinity than existing affinity prediction methods.

G-K BertDTA: A graph representation learning and semantic embedding-based framework for drug-target affinity prediction

Developing new drugs is costly, time-consuming, and risky. Drug-target affinity (DTA), indicating the binding capability between drugs and target proteins, is a crucial indicator for drug development. Accurately predicting interaction strength between new drug-target pairs by analyzing previous experiments aids in screening potential drug molecules, repurposing them, and developing safe and effective medicines. Existing computational models for DTA prediction rely on strings or single-graph neural networks, lacking consideration of protein structure and molecular semantic information, leading to limited accuracy. Our experiments demonstrate that string-based methods may overlook protein conformations, causing a high root mean square error (RMSE) of 3.584 in affinity due to a lack of spatial context. Single graph networks also underperform on topology features, with a 6% lower confidence interval (CI) for activity classification. Absent semantic information also limits generalization across diverse compounds, resulting in 18% increment in RMSE and 5% in misclassifications within quantifications study, restricting potential drug discovery. To address these limitations, we propose G-K BertDTA, a novel framework for accurate DTA prediction incorporating protein features, molecular semantic features, and molecular structural information. In this proposed model, we represent drugs as graphs, with a GIN employed to learn the molecular topological information. For the extraction of protein structural features, we utilize a DenseNet architecture. A knowledge-based BERT semantic model is incorporated to obtain rich pre-trained semantic embeddings, thereby enhancing the feature information. We extensively evaluated our proposed approach on the publicly available benchmark datasets (i.e., KIBA and Davis), and experimental results demonstrate the promising performance of our method, which consistently outperforms previous state-of-the-art approaches. Code is available at https://github.com/AmbitYuki/G-K-BertDTA.

Structure-guided discovery of anti-CRISPR and anti-phage defense proteins

Bacteria use a variety of defense systems to protect themselves from phage infection. In turn, phages have evolved diverse counter-defense measures to overcome host defenses. Here, we use protein structural similarity and gene co-occurrence analyses to screen >66 million viral protein sequences and >330,000 metagenome-assembled genomes for the identification of anti-phage and counter-defense systems. We predict structures for ~300,000 proteins and perform large-scale, pairwise comparison to known anti-CRISPR (Acr) and anti-phage proteins to identify structural homologs that otherwise may not be uncovered using primary sequence search. This way, we identify a Bacteroidota phage Acr protein that inhibits Cas12a, and an Akkermansia muciniphila anti-phage defense protein, termed BxaP. Gene bxaP is found in loci encoding Bacteriophage Exclusion (BREX) and restriction-modification defense systems, but confers immunity independently. Our work highlights the advantage of combining protein structural features and gene co-localization information in studying host-phage interactions.

Classification of MLH1 Missense VUS Using Protein Structure-Based Deep Learning-Ramachandran Plot-Molecular Dynamics Simulations Method.

Pathogenic variation in DNA mismatch repair (MMR) gene MLH1 is associated with Lynch syndrome (LS), an autosomal dominant hereditary cancer. Of the 3798 MLH1 germline variants collected in the ClinVar database, 38.7% (1469) were missense variants, of which 81.6% (1199) were classified as Variants of Uncertain Significance (VUS) due to the lack of functional evidence. Further determination of the impact of VUS on MLH1 function is important for the VUS carriers to take preventive action. We recently developed a protein structure-based method named "Deep Learning-Ramachandran Plot-Molecular Dynamics Simulation (DL-RP-MDS)" to evaluate the deleteriousness of MLH1 missense VUS. The method extracts protein structural information by using the Ramachandran plot-molecular dynamics simulation (RP-MDS) method, then combines the variation data with an unsupervised learning model composed of auto-encoder and neural network classifier to identify the variants causing significant change in protein structure. In this report, we applied the method to classify 447 MLH1 missense VUS. We predicted 126/447 (28.2%) MLH1 missense VUS were deleterious. Our study demonstrates that DL-RP-MDS is able to classify the missense VUS based solely on their impact on protein structure.

ZMPY3D: accelerating protein structure volume analysis through vectorized 3D Zernike moments and Python-based GPU integration.

Volumetric 3D object analyses are being applied in research fields such as structural bioinformatics, biophysics, and structural biology, with potential integration of artificial intelligence/machine learning (AI/ML) techniques. One such method, 3D Zernike moments, has proven valuable in analyzing protein structures (e.g., protein fold classification, protein-protein interaction analysis, and molecular dynamics simulations). Their compactness and efficiency make them amenable to large-scale analyses. Established methods for deriving 3D Zernike moments, however, can be inefficient, particularly when higher order terms are required, hindering broader applications. As the volume of experimental and computationally-predicted protein structure information continues to increase, structural biology has become a "big data" science requiring more efficient analysis tools. This application note presents a Python-based software package, ZMPY3D, to accelerate computation of 3D Zernike moments by vectorizing the mathematical formulae and using graphical processing units (GPUs). The package offers popular GPU-supported libraries such as CuPy and TensorFlow together with NumPy implementations, aiming to improve computational efficiency, adaptability, and flexibility in future algorithm development. The ZMPY3D package can be installed via PyPI, and the source code is available from GitHub. Volumetric-based protein 3D structural similarity scores and transform matrix of superposition functionalities have both been implemented, creating a powerful computational tool that will allow the research community to amalgamate 3D Zernike moments with existing AI/ML tools, to advance research and education in protein structure bioinformatics. ZMPY3D, implemented in Python, is available on GitHub (https://github.com/tawssie/ZMPY3D) and PyPI, released under the GPL License.

Progress in protein pre-training models integrating structural knowledge

The AI revolution, sparked by natural language and image processing, has brought new ideas and research paradigms to the field of protein computing. One significant advancement is the development of pre-training protein language models through self-supervised learning from massive protein sequences. These pre-trained models encode various information about protein sequences, evolution, structures, and even functions, which can be easily transferred to various downstream tasks and demonstrate robust generalization capabilities. Recently, researchers have further developed multimodal pre-trained models that integrate more diverse types of data. The recent studies in this direction are summarized and reviewed from the following aspects in this paper. Firstly, the protein pre-training models that integrate protein structures into language models are reviewed: this is particularly important, for protein structure is the primary determinant of its function. Secondly, the pre-trained models that integrate protein dynamic information are introduced. These models may benefit downstream tasks such as protein-protein interactions, soft docking of ligands, and interactions involving allosteric proteins and intrinsic disordered proteins. Thirdly, the pre-trained models that integrate knowledge such as gene ontology are described. Fourthly, we briefly introduce pre-trained models in RNA fields. Finally, we introduce the most recent developments in protein designs and discuss the relationship of these models with the aforementioned pre-trained models that integrate protein structure information.

SIGMA leverages protein structural information to predict the pathogenicity of missense variants

Leveraging protein structural information to evaluate pathogenicity has been hindered by the scarcity of experimentally determined 3D protein. With the aid of AlphaFold2 predictions, we developed the structure-informed genetic missense mutation assessor (SIGMA) to predict missense variant pathogenicity. In comparison with existing predictors across labeled variant datasets and experimental datasets, SIGMA demonstrates superior performance in predicting missense variant pathogenicity (AUC= 0.933). We found that the relative solvent accessibility of the mutated residue contributed greatly to the predictive ability of SIGMA. We further explored combining SIGMA with other top-tier predictors to create SIGMA+, proving highly effective for variant pathogenicity prediction (AUC= 0.966). To facilitate the application of SIGMA, we pre-computed SIGMA scores for over 48 million possible missense variants across 3,454 disease-associated genes and developed an interactive online platform (https://www.sigma-pred.org/). Overall, by leveraging protein structure information, SIGMA offers an accurate structure-based approach to evaluating the pathogenicity of missense variants.