Structure-based Methods Research Articles

Engineering Applications of Urban Green Space Planning in Mountainous Areas: An Improved Structure-based RS Land Class Information Extraction Method for U-Net Networks

Engineering Applications of Urban Green Space Planning in Mountainous Areas: An Improved Structure-based RS Land Class Information Extraction Method for U-Net Networks

MFF-SC: A multi-feature fusion method for smart contract classification

The classification of the smart contract can effectively reduce the search space and improve retrieval efficiency. The existing classification methods are based on natural language processing technologies. Because the processing of source code by these technologies lacks extraction and processing in the software engineering field, there is still a lot of room for improvement in their methods of feature extraction. Therefore, this paper proposes a multi-feature fusion method for smart contract classification (MFF-SC) based on the code processing technology. From the source code perspective, source code processing method and attention mechanism are used to extract local code features. Structure-based traversal method are used to extract global code features from abstract syntax tree. Local and global code features introduce attention mechanism to generate code semantic features. From the perspective of account transaction, the feature of account transaction is extracted by using TransR. Next, the code semantic features and account transaction features generate smart contract semantic features by an attention mechanism. Finally, the smart contract semantic features are fed into a stacked denoising autoencoder and a softmax classifier for classification. Experimental results on a real dataset show that MFF-SC achieves an accuracy rate of 83.9%, compared with other baselines and variants.

SAM: Query-efficient Adversarial Attacks against Graph Neural Networks

Recent studies indicate that Graph Neural Networks (GNNs) are vulnerable to adversarial attacks. Particularly, adversarially perturbing the graph structure, e.g., flipping edges, can lead to salient degeneration of GNNs’ accuracy. In general, efficiency and stealthiness are two significant metrics to evaluate an attack method in practical use. However, most prevailing graph structure-based attack methods are query intensive, which impacts their practical use. Furthermore, while the stealthiness of perturbations has been discussed in previous studies, the majority of them focus on the attack scenario targeting a single node. To fill the research gap, we present a global attack method against GNNs, Saturation adversarial Attack with Meta-gradient, in this article. We first propose an enhanced meta-learning-based optimization method to obtain useful gradient information concerning graph structural perturbations. Then, leveraging the notion of saturation attack, we devise an effective algorithm to determine the perturbations based on the derived meta-gradients. Meanwhile, to ensure stealthiness, we introduce a similarity constraint to suppress the number of perturbed edges. Thorough experiments demonstrate that our method can effectively depreciate the accuracy of GNNs with a small number of queries. While achieving a higher misclassification rate, we also show that the perturbations developed by our method are not noticeable.

DG-Affinity: predicting antigen–antibody affinity with language models from sequences

BackgroundAntibody-mediated immune responses play a crucial role in the immune defense of human body. The evolution of bioengineering has led the progress of antibody-derived drugs, showing promising efficacy in cancer and autoimmune disease therapy. A critical step of this development process is obtaining the affinity between antibodies and their binding antigens.ResultsIn this study, we introduce a novel sequence-based antigen–antibody affinity prediction method, named DG-Affinity. DG-Affinity uses deep neural networks to efficiently and accurately predict the affinity between antibodies and antigens from sequences, without the need for structural information. The sequences of both the antigen and the antibody are first transformed into embedding vectors by two pre-trained language models, then these embeddings are concatenated into an ConvNeXt framework with a regression task. The results demonstrate the superiority of DG-Affinity over the existing structure-based prediction methods and the sequence-based tools, achieving a Pearson’s correlation of over 0.65 on an independent test dataset.ConclusionsCompared to the baseline methods, DG-Affinity achieves the best performance and can advance the development of antibody design. It is freely available as an easy-to-use web server at https://www.digitalgeneai.tech/solution/affinity.

THPLM: a sequence-based deep learning framework for protein stability changes prediction upon point variations using pretrained protein language model.

Quantitative determination of protein thermodynamic stability is a critical step in protein and drug design. Reliable prediction of protein stability changes caused by point variations contributes to developing-related fields. Over the past decades, dozens of structure-based and sequence-based methods have been proposed, showing good prediction performance. Despite the impressive progress, it is necessary to explore wild-type and variant protein representations to address the problem of how to represent the protein stability change in view of global sequence. With the development of structure prediction using learning-based methods, protein language models (PLMs) have shown accurate and high-quality predictions of protein structure. Because PLM captures the atomic-level structural information, it can help to understand how single-point variations cause functional changes. Here, we proposed THPLM, a sequence-based deep learning model for stability change prediction using Meta's ESM-2. With ESM-2 and a simple convolutional neural network, THPLM achieved comparable or even better performance than most methods, including sequence-based and structure-based methods. Furthermore, the experimental results indicate that the PLM's ability to generate representations of sequence can effectively improve the ability of protein function prediction. The source code of THPLM and the testing data can be accessible through the following links: https://github.com/FPPGroup/THPLM.

Pseq2Sites: Enhancing protein sequence-based ligand binding-site prediction accuracy via the deep convolutional network and attention mechanism

Protein-ligand interactions play an essential role in many biological processes, and prior knowledge of ligand binding sites is necessary for successful drug design. Many 3D structure- and sequence-based methods have been proposed for identifying ligand binding sites. The 3D structure-based methods typically achieve better binding site prediction than the sequence-based methods. However, as deep-learning techniques that can extract structural information from large-scale sequence data have been developed, the performance gap between 3D structure- and sequence-based methods is narrowing. Nonetheless, there remains room for improvement in sequence-based prediction. We propose Pseq2Sites, a sequence-based deep-learning model for predicting ligand binding sites. Pseq2Sites comprises a 1D convolutional neural network that extracts local features from the protein sequence, and a position-based attention mechanism that captures long-distance dependencies between binding residues. To verify the effectiveness of the proposed method, we compared it with other state-of-the-art methods using three public datasets: COACH420, HOLO4K, and CSAR-NRC HiQ. Utilizing solely protein sequence information, Pseq2Sites outperformed 3D structure-based state-of-the-art methods on external test datasets; within the COACH420 dataset, Pseq2Sites remarkably identified 97% of the binding pockets (at a significance level δ = 0.5), which was 27% higher than the second highest-performing model. Pseq2Sites also achieved outstanding binding site prediction, even for proteins with low similarity to the training dataset. Our code is available at https://github.com/Blue1993/Pseq2Sites.

Ligand and structure based hierarchical virtual screening cascade for finding novel epidermal growth factor receptor inhibitors.

The epidermal growth factor receptor (EGFR) tyrosine kinase plays an important role in tumor formation and growth by mediating cell growth and other physiological processes. Therefore, EGFR is a promising target for the treatment of cancer. In this work, we combined ligand-based and structure-based virtual screening methods to identify novel EGFR inhibitors from a library of more than 103 thousand compounds. We first obtained hundreds of compounds with similar physiochemical properties through 3D molecular shape and electrostatic similarity screening with potent inhibitors AEE788 and Afatinib as queries. Next, we identified compounds with strong binding affinities to the EGFR pocket through molecular docking, which makes good use of the structure information of the receptor. After molecular scaffold analysis, our bioassay confirmed 13 compounds with EGFR inhibitory activity and three compounds had IC50 values below 1000 nM. In addition, we collected 5371 EGFR inhibitors from online databases, and clustered them into 7 groups by K-means method using their ECFP4 fingerprints as input. Each cluster had typical molecular fragments and corresponding activity characteristics, which could guide the design of EGFR inhibitors, and we concluded that the fragments from some of the hits are indicated in the highly active scaffolds.

Structure-Based Virtual Screening of Helicobacter pylori SecA Inhibitors.

The human bacterial pathogen Helicobacter pylori causes a range of gastric diseases. The killing rate of Helicobacter pylori is declining year by year because of high antibiotics resistance. It is urgent to develop new target and novel anti- Helicobacter pylori drugs. As an "energy pump" for bacterial cells, SecA is essential for bacterial growth and drives bacterial protein transmembrane transport, moreover SecA is absent in mammals, all of which nominate SecA as an attractive antimicrobial target. Here, we provided a structure-based virtual screening method to screen the 3D-diversity natural-product-like screening library against SecA for novel anti- Helicobacter pylori inhibitors with novel scaffolds. In this study, homology modeling was used to construct the three-dimensional structure of Helicobacter pylori SecA. Two rounds of molecular docking were then used to find new small-molecule inhibitors of SecA, identifying six lead candidates that maintained key interactions with the binding pocket. After that, molecular dynamics simulations were used to explore more accurate ligand-receptor binding modes in states close to natural conditions. Encouragingly, all six compounds were relatively stable during the simulation. Apart from that the binding free energy calculation based on MM/PBSA demonstrated favorable results of < -13.642 kcal/mol. Finally, ADME-T analysis indicated that these compounds were also sufficiently druggable. All six compounds can be well combined with the crystal structure, which further facilitate the development of SecA inhibitors and lead compounds against Helicobacter pylori.

Accurately identifying nucleic-acid-binding sites through geometric graph learning on language model predicted structures.

The interactions between nucleic acids and proteins are important in diverse biological processes. The high-quality prediction of nucleic-acid-binding sites continues to pose a significant challenge. Presently, the predictive efficacy of sequence-based methods is constrained by their exclusive consideration of sequence context information, whereas structure-based methods are unsuitable for proteins lacking known tertiary structures. Though protein structures predicted by AlphaFold2 could be used, the extensive computing requirement of AlphaFold2 hinders its use for genome-wide applications. Based on the recent breakthrough of ESMFold for fast prediction of protein structures, we have developed GLMSite, which accurately identifies DNA- and RNA-binding sites using geometric graph learning on ESMFold predicted structures. Here, the predicted protein structures are employed to construct protein structural graph with residues as nodes and spatially neighboring residue pairs for edges. The node representations are further enhanced through the pre-trained language model ProtTrans. The network was trained using a geometric vector perceptron, and the geometric embeddings were subsequently fed into a common network to acquire common binding characteristics. Finally, these characteristics were input into two fully connected layers to predict binding sites with DNA and RNA, respectively. Through comprehensive tests on DNA/RNA benchmark datasets, GLMSite was shown to surpass the latest sequence-based methods and be comparable with structure-based methods. Moreover, the prediction was shown useful for inferring nucleic-acid-binding proteins, demonstrating its potential for protein function discovery. The datasets, codes, and trained models are available at https://github.com/biomed-AI/nucleic-acid-binding.

Selective modifications of lactose and N-acetyllactosamine with sulfate and aromatic bulky groups unveil unique structural insights in galectin-1-ligand recognition

Galectins, a family of endogenous glycan-binding proteins, play crucial roles in a broad range of physiological and pathological processes. Galectin-1 (Gal-1), a proto-type member of this family, is overexpressed in several cancers and plays critical roles in tumor-immune escape, angiogenesis and metastasis. Thus, generation of high-affinity Gal-1 inhibitors emerges as an attractive therapeutic approach for a wide range of neoplastic conditions. Small-molecule carbohydrate inhibitors based on lactose (Lac) and N-acetyllactosamine (LacNAc) structures have been tested showing different results. In this study, we evaluated Lac- and LacNAc-based compounds with specific chemical modifications at key positions as Gal-1 ligands by competitive solid-phase assays (SPA) and isothermal titration calorimetry (ITC). Both assays showed excellent correlation, highlighting that lactosides bearing bulky aromatic groups at the anomeric carbon and sulfate groups at the O3′ position exhibited the highest binding affinities. To dissect the atomistic determinants for preferential affinity of the different tested Gal-1 ligands, molecular docking simulations were conducted and PRODIGY-LIG structure-based method was employed to predict binding affinity in protein–ligand complexes. Notably, calculated binding free energies derived from the molecular docking were in accordance with experimental values determined by SPA and ITC, showing excellent correlation between theoretical and experimental approaches. Moreover, this analysis showed that 3′-O-sulfate groups interact with residues of the Gal-1 subsite B, mainly with Asn33, while the ester groups of the aromatic anomeric group interact with Gly69 and Thr70 at Gal-1 subsite E, extending deeper into the pocket, which could account for the enhanced binding affinity. This study contributes to the rational design of highly optimized Gal-1 inhibitors to be further studied in cancer models and other pathologic conditions.

Expanding the repertoire of human tandem repeat RNA-binding proteins.

Protein regions consisting of arrays of tandem repeats are known to bind other molecular partners, including nucleic acid molecules. Although the interactions between repeat proteins and DNA are already widely explored, studies characterising tandem repeat RNA-binding proteins are lacking. We performed a large-scale analysis of human proteins devoted to expanding the knowledge about tandem repeat proteins experimentally reported as RNA-binding molecules. This work is timely because of the release of a full set of accurate structural models for the human proteome amenable to repeat detection using structural methods. The main goal of our analysis was to build a comprehensive set of human RNA-binding proteins that contain repeats at the sequence or structure level. Our results showed that the combination of sequence and structural methods finds significantly more tandem repeat proteins than either method alone. We identified 219 tandem repeat proteins that bind RNA molecules and characterised the overlap between repeat regions and RNA-binding regions as a first step towards assessing their functional relationship. We observed differences in the characteristics of repeat regions predicted by sequence-based or structure-based methods in terms of their sequence composition, their functions and their protein domains.

Descriptor-Driven de Novo Design Algorithms for DOCK6 Using RDKit.

Structure-based methods that employ principles of de novo design can be used to construct small organic molecules from scratch using pre-existing fragment libraries to sample chemical space and are an important class of computational algorithms for drug-lead discovery. Here, we present a powerful new design method for DOCK6 that employs a Descriptor-Driven De Novo strategy (termed D3N) in which user-defined cheminformatics descriptors (and their target ranges) are calculated at each layer of growth using the open-source toolkit RDKit. The objective is to tailor ligand growth toward desirable regions of chemical space. The approach was extensively validated through: (1) comparison of cheminformatics descriptors computed using the new DOCK6/RDKit interface versus the standard Python/RDKit installation, (2) examination of descriptor distributions generated using D3N growth under different conditions (target ranges and environments), and (3) construction of ligands with very tight (pinpoint) descriptor ranges using clinically relevant compounds as a reference. Our testing confirms that the new DOCK6/RDKit integration is robust, showcases how the new D3N routines can be used to direct sampling around user-defined chemical spaces, and highlights the utility of on-the-fly descriptor calculations for ligand design to important drug targets.

Protein remote homology detection and structural alignment using deep learning

Exploiting sequence–structure–function relationships in biotechnology requires improved methods for aligning proteins that have low sequence similarity to previously annotated proteins. We develop two deep learning methods to address this gap, TM-Vec and DeepBLAST. TM-Vec allows searching for structure–structure similarities in large sequence databases. It is trained to accurately predict TM-scores as a metric of structural similarity directly from sequence pairs without the need for intermediate computation or solution of structures. Once structurally similar proteins have been identified, DeepBLAST can structurally align proteins using only sequence information by identifying structurally homologous regions between proteins. It outperforms traditional sequence alignment methods and performs similarly to structure-based alignment methods. We show the merits of TM-Vec and DeepBLAST on a variety of datasets, including better identification of remotely homologous proteins compared with state-of-the-art sequence alignment and structure prediction methods.

ChemFlow_py: a flexible toolkit for docking and rescoring.

The design of accurate virtual screening tools is an open challenge in drug discovery. Several structure-based methods have been developed at different levels of approximation. Among them, molecular docking is an established technique with high efficiency, but typically low accuracy. Moreover, docking performances are known to be target-dependent, which makes the choice of the docking program and corresponding scoring function critical when approaching a new protein target. To compare the performances of different docking protocols, we developed ChemFlow_py, an automated tool to perform docking and rescoring. Using four protein systems extracted from DUD-E with 100 known active compounds and 3000 decoys per target, we compared the performances of several rescoring strategies including consensus scoring. We found that the average docking results can be improved by consensus ranking, which emphasizes the relevance of consensus scoring when little or no chemical information is available for a given target. ChemFlow_py is a free toolkit to optimize the performances of virtual high-throughput screening (vHTS). The software is publicly available at https://github.com/IFMlab/ChemFlow_py .

Selective modulation of the farnesoid X receptor using structure-based methods

Selective modulation of the farnesoid X receptor using structure-based methods

Functional analysis, virtual screening, and molecular dynamics revealed potential novel drug targets and their inhibitors against cardiovascular disease in human

Cardiovascular disease (CVD) is a group of diseases, affecting the human heart and accounting for 30% of deaths worldwide. Major CVDs include heart failure, hypertension, stroke, etc. Various therapeutics are available against CVD, still there is a dire need to find out potential protein drug targets to reduce economic burden and mortality rate. Goal of the current study was to utilize sequential computational techniques to find the best cardiovascular drug targets and their inhibitors. Common human cardiovascular targets of both databases (GeneCards and Uniprot) were subjected to bioinformatics analyses. Purpose was to validate putative therapeutic targets employing the structure-based bioinformatics methods to determine their physiochemical properties and biological processes. Three stable proteins, that have 0 transmembrane helices, and possess biological processes were screened as potential protein-based therapeutic targets: Hemoglobin subunit beta (HBB), Gamma-enolase (ENO2), and Cholesteryl ester transfer protein (CETP). Tertiary structures of target proteins were retrieved from PDB, and molecular docking technique was utilized to evaluate a library of 5000 phytochemicals against the interacting residues of the target protein as well as their respective standard drugs through MOE and Pyrx software. Top five phytochemicals (d-Sesamin, 1,3-benzodioxole, Sativanone, Thiamine, and Cajanol) were identified based on their RMSD and docking scores as compared to their standard drugs. The docking studies were also validated by MM-GBSA binding free energy and molecular dynamics simulations. According to the study’s findings, these phytochemicals may eventually be used as drugs to treat CVD. Further in vitro testing is required to confirm their efficacy and drug potency. Communicated by Ramaswamy H. Sarma

Modulation of NRF2/KEAP1-Mediated Oxidative Stress for Cancer Treatment by Natural Products Using Pharmacophore-Based Screening, Molecular Docking, and Molecular Dynamics Studies.

Oxidative stress plays a significant role in the development of cancer. Inhibiting the protein-protein interaction (PPI) between Keap1 and Nrf2 offers a promising strategy to activate the Nrf2 antioxidant pathway, which is normally suppressed by the binding of Keap1 to Nrf2. This study aimed to identify natural compounds capable of targeting the kelch domain of KEAP1 using structure-based drug design methods. A pharmacophore model was constructed based on the KEAP1-inhibitor complex, leading to the selection of 6178 compounds that matched the model. Subsequently, docking and MM/GBSA analyses were conducted, resulting in the identification of 10 compounds with superior binding energies compared to the reference compound. From these, three compounds (ZINC000002123788, ZINC000002111341, and ZINC000002125904) were chosen for further investigation. Ligand-residue interaction analysis revealed specific interactions between these compounds and key residues, indicating their stability within the binding site. ADMET analysis confirmed that the selected compounds possessed desirable drug-like properties. Furthermore, molecular dynamics simulations were performed, demonstrating the stability of the ligand-protein complexes over a 100 ns duration. These findings underscore the potential of the selected natural compounds as agents targeting KEAP1 and provide valuable insights for future experimental studies.

A Visual Positioning Method of UAV in a Large-Scale Outdoor Environment.

Visual positioning is a basic component for UAV operation. The structure-based methods are, widely applied in most literature, based on local feature matching between a query image that needs to be localized and a reference image with a known pose and feature points. However, the existing methods still struggle with the different illumination and seasonal changes. In outdoor regions, the feature points and descriptors are similar, and the number of mismatches will increase rapidly, leading to the visual positioning becoming unreliable. Moreover, with the database growing, the image retrieval and feature matching are time-consuming. Therefore, in this paper, we propose a novel hierarchical visual positioning method, which includes map construction, landmark matching and pose calculation. First, we combine brain-inspired mechanisms and landmarks to construct a cognitive map, which can make image retrieval efficient. Second, the graph neural network is utilized to learn the inner relations of the feature points. To improve matching accuracy, the network uses the semantic confidence in matching score calculations. Besides, the system can eliminate the mismatches by analyzing all the matching results in the same landmark. Finally, we calculate the pose by using a PnP solver. Furthermore, we evaluate both the matching algorithm and the visual positioning method experimentally in the simulation datasets, where the matching algorithm performs better in some scenes. The results demonstrate that the retrieval time can be shortened by three-thirds with an average positioning error of 10.8 m.

PocketAnchor: Learning structure-based pocket representations for protein-ligand interaction prediction.

Protein-ligand interactions are essential for cellular activities and drug discovery processes. Appropriately and effectively representing protein features is of vital importance for developing computational approaches, especially data-driven methods, for predicting protein-ligand interactions. However, existing approaches may not fully investigate the features of the ligand-occupying regions in the protein pockets. Here, we design a structure-based protein representation method, named PocketAnchor, for capturing the local environmental and spatial features of protein pockets to facilitate protein-ligand interaction-related learning tasks. We define "anchors" as probe points reaching into the cavities and those located near the surface of proteins, and we design a specific message passing strategy for gathering local information from the atoms and surface neighboring these anchors. Comprehensive evaluation of our method demonstrated its successful applications in pocket detection and binding affinity prediction, which indicated that our anchor-based approach can provide effective protein feature representations for improving the prediction of protein-ligand interactions.

Structure-based virtual screening approach reveals natural multi-target compounds for the development of antimalarial drugs to combat drug resistance

Compared to the previous year, there has been an increase of nearly 2 million malaria cases in 2021. The emergence of drug-resistant strains of Plasmodium falciparum, the most deadly malaria parasite, has led to a decline in the effectiveness of existing antimalarial drugs. To address this problem, the present study aimed to identify natural compounds with the potential to inhibit multiple validated antimalarial drug targets. The natural compounds from the Natural Product Activity and Species Source (NPASS) database were screened against ten validated drug targets of Plasmodium falciparum using a structure-based molecular docking method. Twenty compounds, with targets ranging from three to five, were determined as the top hits. The molecular dynamics simulations of the top six complexes (NPC246162 in complex with PfAdSS, PfGDH, and PfNMT; NPC271270 in complex with PfCK, PfGDH, and PfdUTPase) confirmed their stable binding affinity in the dynamic environment. The Tanimoto coefficient and distance matrix score analysis show the structural divergence of all the hit compounds from known antimalarials, indicating minimum chances of cross-resistance. Thus, we propose further investigating these compounds in biochemical and parasite inhibition studies to reveal the real therapeutic potential. If found successful, these compounds may be a new avenue for future drug discovery efforts to combat existing antimalarial drug resistance. Communicated by Ramaswamy H. Sarma