Structure-based Methods Research Articles

POLAT: Protein function prediction based on soft mask graph network and residue-Label ATtention

Motivation:Elucidating protein function is a central problem in biochemistry, genetics, and molecular biology. Developing computational methods for protein function prediction is critical due to the significant gap between sequence and functional data. Recent advances in protein structure prediction, which strongly correlates with function, make it feasible to use structure to predict function. However, current structure-based methods overlook the fact that individual residues may contribute differently to the protein’s function and do not take into account the correlation between protein residues and their functions. The challenge of effectively utilizing the relationship between protein residues and function-level information to predict protein function remains unsolved. Result:We proposed a protein function prediction method based on Soft Mask Graph Networks and Residue-Label Attention (POLAT), which could combine sequence features, predicted structure features, and function-level information to get an accurate prediction. We use soft mask graph networks to adaptively extract the residues relevant to functions. A residue-label attention mechanism is adopted to obtain the protein-level encoded features of a protein, which are then concatenated with a protein-level embedding and fed into a dense classifier to determine the probabilities of each function. POLAT achieves 0.670, 0.515, 0.578 Fmax and 0.677, 0.409, 0.507 AUPR on the PDB cdhit test set for the MFO, BPO, and CCO domains, respectively, outperforming the existing structure-based SOTA method GAT-GO (Fmax 0.633, 0.492, 0.547; AUPR 0.660, 0.381, 0.479). POLAT is also competitive in extensive experiments among sequence-based and multimodal methods and achieves the SOTA performance in three out of six metrics.

Comparative Analysis of Deep Generative Model for Industrial Enzyme Design

Abstract: Although enzymes have the advantage of efficient catalysis, natural enzymes lack stability in industrial environments and do not even meet the required catalytic reactions. This prompted us to urgently de novo design new enzymes. Computational design is a powerful tool, allowing rapid and efficient exploration of sequence space and facilitating the design of novel enzymes tailored to specific conditions and requirements. It is beneficial to de novo design industrial enzymes using computational methods. Currently, only one tool explicitly designed for the enzyme-only generation performs unsatisfactorily. We have selected several general protein sequence design tools and systematically evaluated their effectiveness when applied to specific industrial enzymes. We investigated the literature related to protein generation. We summarized the computational methods used for sequence generation into three categories: structure-conditional sequence generation, sequence generation without structural constraints, and co-generation of sequence and structure. To effectively evaluate the ability of six computational tools to generate enzyme sequences, we first constructed a luciferase dataset named Luc_64. Then we assessed the quality of enzyme sequences generated by these methods on this dataset, including amino acid distribution, EC number validation, etc. We also assessed sequences generated by structure-based methods on existing public datasets using sequence recovery rates and root-mean-square deviation (RMSD) from a sequence and structure perspective. In the functionality dataset, Luc_64, ABACUS-R, and ProteinMPNN stood out for producing sequences with amino acid distributions and functionalities closely matching those of naturally occurring luciferase enzymes, suggesting their effectiveness in preserving essential enzymatic characteristics. Across both benchmark datasets, ABACUS-R and ProteinMPNN, have also exhibited the highest sequence recovery rates, indicating their superior ability to generate sequences closely resembling the original enzyme structures. Our study provides a crucial reference for researchers selecting appropriate enzyme sequence design tools, highlighting the strengths and limitations of each tool in generating accurate and functional enzyme sequences. ProteinMPNN and ABACUS-R emerged as the most effective tools in our evaluation, offering high accuracy in sequence recovery and RMSD and maintaining the functional integrity of enzymes through accurate amino acid distribution. Meanwhile, the performance of protein general tools for migration to specific industrial enzymes was fairly evaluated on our specific industrial enzyme benchmark.

Tensor structure-based ground clutter suppression approaches for pulse doppler radar

ABSTRACT For pulse doppler (PD) radar, two tensor structure-based methods are proposed to improve the clutter suppression performance. One is tensor singular value decomposition (TSVD) and the other is tensor robust principal component analysis (TRPCA). Two algorithms both stack the range-Doppler matrices of multiple coherent processing intervals (CPI) into a tensor structure, which helps make the most of the temporal information across CPIs. TSVD utilizes the strong temporal correlation of ground clutter data to estimate the clutter subspace. Meanwhile, TRPCA exactly separates both low-rank clutter component and sparse target components from the time series range-Doppler tensor structure. Experimental results indicate that compared with conventional matrix-based schemes such as singular value decomposition (SVD) or singular value decomposition (RPCA), the proposed methods have significant advantages in keeping the target echo while suppressing the clutter. In addition, the computational complexity of each algorithm is analysed in detail.

Enhancing link prediction efficiency with shortest path and structural attributes

Link prediction is one of the most essential and crucial tasks in complex network research since it seeks to forecast missing links in a network based on current ones. This problem has applications in a variety of scientific disciplines, including social network research, recommendation systems, and biological networks. In previous work, link prediction has been solved through different methods such as path, social theory, topology, and similarity-based. The main issue is that path-based methods ignore topological features, while structure-based methods also fail to combine the path and structured-based features. As a result, a new technique based on the shortest path and topological features’ has been developed. The method uses both local and global similarity indices to measure the similarity. Extensive experiments on real-world datasets from a variety of domains are utilized to empirically test and compare the proposed framework to many state-of-the-art prediction techniques. Over 100 iterations, the collected data showed that the proposed method improved on the other methods in terms of accuracy. SI and AA, among the existing state-of-the-art algorithms, fared best with an AUC value of 82%, while the proposed method has an AUC value of 84%.

CATH 2024: CATH-AlphaFlow Doubles the Number of Structures in CATH and Reveals Nearly 200 New Folds

CATH (https://www.cathdb.info) classifies domain structures from experimental protein structures in the PDB and predicted structures in the AlphaFold Database (AFDB). To cope with the scale of the predicted data a new NextFlow workflow (CATH-AlphaFlow), has been developed to classify high-quality domains into CATH superfamilies and identify novel fold groups and superfamilies. CATH-AlphaFlow uses a novel state-of-the-art structure-based domain boundary prediction method (ChainSaw) for identifying domains in multi-domain proteins. We applied CATH-AlphaFlow to process PDB structures not classified in CATH and AFDB structures from 21 model organisms, expanding CATH by over 100%.Domains not classified in existing CATH superfamilies or fold groups were used to seed novel folds, giving 253 new folds from PDB structures (September 2023 release) and 96 from AFDB structures of proteomes of 21 model organisms. Where possible, functional annotations were obtained using (i) predictions from publicly available methods (ii) annotations from structural relatives in AFDB/UniProt50. We also predicted functional sites and highly conserved residues. Some folds are associated with important functions such as photosynthetic acclimation (in flowering plants), iron permease activity (in fungi) and post-natal spermatogenesis (in mice).CATH-AlphaFlow will allow us to identify many more CATH relatives in the AFDB, further characterising the protein structure landscape.

Computational Characterization of Membrane Proteins as Anticancer Targets: Current Challenges and Opportunities.

Cancer remains a leading cause of mortality worldwide and calls for novel therapeutic targets. Membrane proteins are key players in various cancer types but present unique challenges compared to soluble proteins. The advent of computational drug discovery tools offers a promising approach to address these challenges, allowing for the prioritization of "wet-lab" experiments. In this review, we explore the applications of computational approaches in membrane protein oncological characterization, particularly focusing on three prominent membrane protein families: receptor tyrosine kinases (RTKs), G protein-coupled receptors (GPCRs), and solute carrier proteins (SLCs). We chose these families due to their varying levels of understanding and research data availability, which leads to distinct challenges and opportunities for computational analysis. We discuss the utilization of multi-omics data, machine learning, and structure-based methods to investigate aberrant protein functionalities associated with cancer progression within each family. Moreover, we highlight the importance of considering the broader cellular context and, in particular, cross-talk between proteins. Despite existing challenges, computational tools hold promise in dissecting membrane protein dysregulation in cancer. With advancing computational capabilities and data resources, these tools are poised to play a pivotal role in identifying and prioritizing membrane proteins as personalized anticancer targets.

PNeRFLoc: Visual Localization with Point-Based Neural Radiance Fields

Due to the ability to synthesize high-quality novel views, Neural Radiance Fields (NeRF) has been recently exploited to improve visual localization in a known environment. However, the existing methods mostly utilize NeRF for data augmentation to improve the regression model training, and their performances on novel viewpoints and appearances are still limited due to the lack of geometric constraints. In this paper, we propose a novel visual localization framework, i.e., PNeRFLoc, based on a unified point-based representation. On one hand, PNeRFLoc supports the initial pose estimation by matching 2D and 3D feature points as traditional structure-based methods; on the other hand, it also enables pose refinement with novel view synthesis using rendering-based optimization. Specifically, we propose a novel feature adaption module to close the gaps between the features for visual localization and neural rendering. To improve the efficacy and efficiency of neural rendering-based optimization, we also developed an efficient rendering-based framework with a warping loss function. Extensive experiments demonstrate that PNeRFLoc performs the best on the synthetic dataset when the 3D NeRF model can be well learned, and significantly outperforms all the NeRF-boosted localization methods with on-par SOTA performance on the real-world benchmark localization datasets. Project webpage: https://zju3dv.github.io/PNeRFLoc/.

Abstract 2340: STRUMP-I: Structure-based binding prediction of MHC class I

Abstract The presentation of short peptides derived from endogenously expressed proteins within the Major Histocompatability Complex-I (MHC-I), together known as the pMHC, allows the adaptive immune system to monitor the internal functioning of a cell and surveil for foreign or mutated self-proteins. With the rising importance of immunotherapies targeting neoantigens in cancers, the ability to accurately predict which peptides will bind to the diverse population of MHC alleles is critically important. Computational methods for predicting MHC/peptide interactions fall into two broad categories: sequence-based methods that utilize machine learning or deep learning to predict binding from information about the MHC and peptide sequence alone, and structure-based methods that leverage the computed structure and energetics of the pMHC to predict binding. While sequence-based methods have outperformed structure-based methods, their performance varies with the quantity and quality of training data for each MHC allele. The pMHC structure also provides additional insights into downstream analyses, such as predicting the immunogenicity of cancer neoantigens, that cannot be determined from the sequence alone. We developed a STRUMP-I (STRUcture-based pMHC Prediction (for class I)), a novel pMHC binding prediction tool that combines structural modelling with a machine learning-based classifier to discriminate binders from non-binders. STRUMP-I has comparable performance to the state-of-the-art sequence-based methods on data taken from IEDB, the HLAthena training set, TESLA, PRIME, and an in-house cancer neoantigen dataset. However, it generalizes better to alleles with low representation or a lower proportion of positive examples in the training data than the sequence-based methods. Additionally, we demonstrate how STRUMP-I can be used in conjunction with PRIME, a sequence-based immunogenicity prediction method, to use structural information about the peptide to filter out false positive predictions and increase the precision of immunogenicity predictions, increasing the precision by up to 2-fold. Further, on a set of 10 experimentally validated peptides from the in-house cancer neoantigen dataset containing only a single immunogenic peptide, STRUMP-I filtered all false positive predictions and retained only the true positive prediction. By leveraging structural information about the pMHC, STRUMP-I provides robust binding predicting performance across MHC alleles and increases the precision of immunogenicity prediction for neoantigen screening. Citation Format: Adam Voshall, Woongyang Park, Eunjung Alice Lee, Yoonjoo Choi. STRUMP-I: Structure-based binding prediction of MHC class I [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2340.

SpatialPPI: Three-dimensional space protein-protein interaction prediction with AlphaFold Multimer

Rapid advancements in protein sequencing technology have resulted in gaps between proteins with identified sequences and those with mapped structures. Although sequence-based predictions offer insights, they can be incomplete due to the absence of structural details. Conversely, structure-based methods face challenges with respect to newly sequenced proteins. The AlphaFold Multimer has remarkable accuracy in predicting the structure of protein complexes. However, it cannot distinguish whether the input protein sequences can interact. Nonetheless, by analyzing the information in the models predicted by the AlphaFold Multimer, we propose a highly accurate method for predicting protein interactions. This study focuses on the use of deep neural networks, specifically to analyze protein complex structures predicted by the AlphaFold Multimer. By transforming atomic coordinates and utilizing sophisticated image-processing techniques, vital 3D structural details were extracted from protein complexes. Recognizing the significance of evaluating residue distances in protein interactions, this study leveraged image recognition approaches by integrating Densely Connected Convolutional Networks (DenseNet) and Deep Residual Network (ResNet) within 3D convolutional networks for protein 3D structure analysis. When benchmarked against leading protein-protein interaction prediction methods, such as SpeedPPI, D-script, DeepTrio, and PEPPI, our proposed method, named SpatialPPI, exhibited notable efficacy, emphasizing the promising role of 3D spatial processing in advancing the realm of structural biology. The SpatialPPI code is available at: https://github.com/ohuelab/SpatialPPI.

Polymorphism in the leucine-rich repeats of TLR7 in different breeds of chicken and in silico analysis of its effect on TLR7 structure and function

Chicken toll-like receptor 7 (chTLR7) is a viral sensing pattern recognition receptor and detects ssRNA. The ligand binding site comprises leucine-rich repeats (LRRs) located in the ectodomain of chTLR7. Hence, any polymorphism in the binding site would modify its functional interaction with the ligand, resulting in varied strength of immune response. This study first aimed to compare the single nucleotide polymorphisms (SNPs) associated with the ligand binding site of TLR7 in three indigenous chicken breeds namely Aseel, Kadaknath, Nicobari along with an exotic breed White Leghorn. Four synonymous SNPs (P123P, I171I, N339N and L421L) and four non-synonymous SNPs (I121V, S135T, F356S and S447G) were identified among various breeds. We employed in silico tools to screen the pathogenic nsSNPs and one nsSNP was identified as having potential impact on chTLR7 protein. Moreover, sequence and structure-based methods were used to determine the effect of nsSNPs on protein stability. It revealed I121V, F356S, and S447G as decreasing the stability while S135T increasing the stability of chTLR7. Additionally, docking analysis confirmed that I121V and F356S reduced the binding affinity of ligands (R-848 and polyU) to chTLR7 protein. The results suggest that the nsSNPs found in this study could alter the ligand binding of chTLR7 and modify the immune response between different breeds further contributing to disease susceptibility or resistance. Further, in vitro and in vivo studies are needed to analyze the effect of these SNPs on susceptibility or resistance against various viral diseases in poultry.

Bioinspired Algorithms for Multiple Sequence Alignment: A Systematic Review and Roadmap

Multiple Sequence Alignment (MSA) plays a pivotal role in bioinformatics, facilitating various critical biological analyses, including the prediction of unknown protein structures and functions. While numerous methods are available for MSA, bioinspired algorithms stand out for their efficiency. Despite the growing research interest in addressing the MSA challenge, only a handful of comprehensive reviews have been undertaken in this domain. To bridge this gap, this study conducts a thorough analysis of bioinspired-based methods for MSA through a systematic literature review (SLR). By focusing on publications from 2010 to 2024, we aim to offer the most current insights into this field. Through rigorous eligibility criteria and quality standards, we identified 45 relevant papers for review. Our analysis predominantly concentrates on bioinspired-based techniques within the context of MSA. Notably, our findings highlight Genetic Algorithm and Memetic Optimization as the most commonly utilized algorithms for MSA. Furthermore, benchmark datasets such as BAliBASE and SABmark are frequently employed in evaluating MSA solutions. Structural-based methods emerge as the preferred approach for assessing MSA solutions, as revealed by our systematic literature review. Additionally, this study explores current trends, challenges, and unresolved issues in the realm of bioinspired algorithms for MSA, offering practitioners and researchers valuable insights and comprehensive understanding of the field.

High-resolution cryo-EM of the human CDK-activating kinase for structure-based drug design

Rational design of next-generation therapeutics can be facilitated by high-resolution structures of drug targets bound to small-molecule inhibitors. However, application of structure-based methods to macromolecules refractory to crystallization has been hampered by the often-limiting resolution and throughput of cryogenic electron microscopy (cryo-EM). Here, we use high-resolution cryo-EM to determine structures of the CDK-activating kinase, a master regulator of cell growth and division, in its free and nucleotide-bound states and in complex with 15 inhibitors at up to 1.8 Å resolution. Our structures provide detailed insight into inhibitor interactions and networks of water molecules in the active site of cyclin-dependent kinase 7 and provide insights into the mechanisms contributing to inhibitor selectivity, thereby providing the basis for rational design of next-generation therapeutics. These results establish a methodological framework for the use of high-resolution cryo-EM in structure-based drug design.

Unveiling potential repurposed drug candidates for Plasmodium falciparum through in silico evaluation: A synergy of structure-based approaches, structure prediction, and molecular dynamics simulations

The rise of drug resistance in Plasmodium falciparum, rendering current treatments ineffective, has hindered efforts to eliminate malaria. To address this issue, the study employed a combination of Systems Biology approach and a structure-based pharmacophore method to identify a target against P. falciparum. Through text mining, 448 genes were extracted, and it was discovered that plasmepsins, found in the Plasmodium genus, play a crucial role in the parasite's survival. The metabolic pathways of these proteins were determined using the PlasmoDB genomic database and recreated using CellDesigner 4.4.2. To identify a potent target, Plasmepsin V (PF13_0133) was selected and examined for protein-protein interactions (PPIs) using the STRING Database. Topological analysis and global-based methods identified PF13_0133 as having the highest centrality. Moreover, the static protein knockout PPIs demonstrated the essentiality of PF13_0133 in the modeled network. Due to the unavailability of the protein’s crystal structure, it was modeled and subjected to a molecular dynamics simulation study. The structure-based pharmacophore modeling utilized the modeled PF13_0133 (PfPMV), generating 10 pharmacophore hypotheses with a library of active and inactive compounds against PfPMV. Through virtual screening, two potential candidates, hesperidin and rutin, were identified as potential drugs which may be repurposed as potential anti-malarial agents.

Utilizing Artificial Intelligence in the Development of Medicinal Drugs: Practical Applications

The COVID-19 pandemic has underscored the critical need for innovative drug discovery methods. The journey from conceptualizing a drug to its clinical application is fraught with potential pitfalls, including extensive complexity, significant expenses, and a high risk of failure. Recent years have witnessed remarkable advancements in technologies such as cloud computing, GPUs, and TPUs. These developments, coupled with the surge in medical data availability and the emergence of deep learning, present an unprecedented opportunity to enhance drug discovery processes. By leveraging artificial intelligence (AI) to analyze vast amounts of data-from extensive molecular screening outcomes to individual health records and public health data-the efficiency of the drug discovery pipeline could be significantly improved, minimizing the likelihood of failure. This paper explores the application of AI in various phases of drug development, including the use of computational strategies for de novo drug design and the prediction of drug properties. We address challenges associated with molecular representation, data acquisition, complexity, and the inconsistencies in labeling across open-source databases and AI-powered tools that support drug discovery efforts. Furthermore, we examine the role of advanced AI techniques, such as graph neural networks, reinforcement learning, generative models, and structure-based methods like molecular docking and dynamics simulations, in enhancing drug discovery and evaluating drug efficacy.

Molecular Docking: Principles, Advances, and Its Applications in Drug Discovery

Abstract: Molecular docking is a structure-based computational method that generates the binding pose and affinity between ligands and targets. There are many powerful docking programs. However, there is no single program that is suitable for every system. Hence, an appropriate program is chosen based on availability, need, and computer capacity. Molecular docking has clear steps that should be followed carefully to get a good result. : Molecular docking has many applications at various stages in drug discovery. Although it has various application areas, it is commonly applied in virtual screening and drug repurposing. As a result, it is playing a substantial role in the endeavor to discover a potent drug against COVID-19. There are also approved drugs in the pharmaceutical market that are developed through the use of molecular docking. As the accessible data is increasing and the method is advancing with the contribution of the latest computational developments, its use in drug discovery is also increasing. : Molecular docking has played a crucial role in making drug discovery faster, cheaper, and more effective. More advances in docking algorithms, integration with other computational methods, and the introduction of new approaches are expected. Thus, more applications that will make drug discovery easier are expected.

DiscoTope-3.0: improved B-cell epitope prediction using inverse folding latent representations.

Accurate computational identification of B-cell epitopes is crucial for the development of vaccines, therapies, and diagnostic tools. However, current structure-based prediction methods face limitations due to the dependency on experimentally solved structures. Here, we introduce DiscoTope-3.0, a markedly improved B-cell epitope prediction tool that innovatively employs inverse folding structure representations and a positive-unlabelled learning strategy, and is adapted for both solved and predicted structures. Our tool demonstrates a considerable improvement in performance over existing methods, accurately predicting linear and conformational epitopes across multiple independent datasets. Most notably, DiscoTope-3.0 maintains high predictive performance across solved, relaxed and predicted structures, alleviating the need for experimental structures and extending the general applicability of accurate B-cell epitope prediction by 3 orders of magnitude. DiscoTope-3.0 is made widely accessible on two web servers, processing over 100 structures per submission, and as a downloadable package. In addition, the servers interface with RCSB and AlphaFoldDB, facilitating large-scale prediction across over 200 million cataloged proteins. DiscoTope-3.0 is available at: https://services.healthtech.dtu.dk/service.php?DiscoTope-3.0.

Structure-based virtual screening and molecular dynamics studies to explore potential natural inhibitors against 3C protease of foot-and-mouth disease virus.

Foot-and-mouth disease (FMD) is a highly infectious animal disease caused by foot-and-mouth disease virus (FMDV) and primarily infects cloven-hoofed animals such as cattle, sheep, goats, and pigs. It has become a significant health concern in global livestock industries because of diverse serotypes, high mutation rates, and contagious nature. There is no specific antiviral treatment available for FMD. Hence, based on the importance of 3C protease in FMDV viral replication and pathogenesis, we have employed a structure-based virtual screening method by targeting 3C protease with a natural compounds dataset (n = 69,040) from the InterBioScreen database. Virtual screening results identified five potential compounds, STOCK1N-62634, STOCK1N-96109, STOCK1N-94672, STOCK1N-89819, and STOCK1N-80570, with a binding affinity of -9.576 kcal/mol, -8.1 kcal/mol, -7.744 kcal/mol, -7.647 kcal/mol, and - 7.778 kcal/mol, respectively. The compounds were further validated through physiochemical properties and density functional theory (DFT). Subsequently, the comparative 300-ns MD simulation of all five complexes exhibited overall structural stability from various MD analyses such as root mean square deviation (RMSD), root mean square fluctuation (RMSF), radius of gyration (Rg), solvent accessible surface area (SASA), H-bonds, principal component analysis (PCA), and free energy landscape (FEL). Furthermore, MM-PBSA calculation suggests that all five compounds, particularly STOCK1N-62634, STOCK1N-96109, and STOCK1N-94672, can be considered as potential inhibitors because of their strong binding affinity toward 3C protease. Thus, we hope that these identified compounds can be studied extensively to develop natural therapeutics for the better management of FMD.

Improving structure-based protein-ligand affinity prediction by graph representation learning and ensemble learning.

Predicting protein-ligand binding affinity presents a viable solution for accelerating the discovery of new lead compounds. The recent widespread application of machine learning approaches, especially graph neural networks, has brought new advancements in this field. However, some existing structure-based methods treat protein macromolecules and ligand small molecules in the same way and ignore the data heterogeneity, potentially leading to incomplete exploration of the biochemical information of ligands. In this work, we propose LGN, a graph neural network-based fusion model with extra ligand feature extraction to effectively capture local features and global features within the protein-ligand complex, and make use of interaction fingerprints. By combining the ligand-based features and interaction fingerprints, LGN achieves Pearson correlation coefficients of up to 0.842 on the PDBbind 2016 core set, compared to 0.807 when using the features of complex graphs alone. Finally, we verify the rationalization and generalization of our model through comprehensive experiments. We also compare our model with state-of-the-art baseline methods, which validates the superiority of our model. To reduce the impact of data similarity, we increase the robustness of the model by incorporating ensemble learning.

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.

A computational approach to analyzing the functional and structural impacts of Tripeptidyl-Peptidase 1 missense mutations in neuronal ceroid lipofuscinosis.

Neuronal ceroid-lipofuscinosis (NCLs) are a group of severe neurodegenerative conditions, most likely present in infantile, late infantile, juvenile, and adult-onset forms. Their phenotypic characteristics comprise eyesight damage, reduced motor activity and cognitive function, and sometimes tend to die in the initial stage. In recent studies, NCLs have been categorized into at least 14 genetic collections (CLN1-14). CLN2 gene encodes Tripeptidyl peptidase 1 (TPP1), which affects late infantile-onset form. In this study, we retrieved a mutational dataset screening for TPP1 protein from various databases (ClinVar, UniProt, HGMD). Fifty-six missense mutants were enumerated with computational methods to perceive the significant mutants (G475R and G501C) and correlated with clinical and literature data. A structure-based screening method was initiated to understand protein-ligand interaction and dynamic simulation. The docking procedure was performed for the native (3EDY) and mutant (G473R and G501C) structures with Gemfibrozil (gem), which lowers the lipid level, decreases the triglycerides amount in the blood circulation, and controls hyperlipidemia. The Native had an interaction score of -5.57kcal/mol, and the mutants had respective average binding scores of -6.24 (G473R) and - 5.17 (G501C) kcal/mol. Finally, molecular dynamics simulation showed that G473R and G501C mutants had better flexible and stable orientation in all trajectory analyses. Therefore, this work gives an extended understanding of both functional and structural levels of influence for the mutant form that leads to NCL disorder.