Three-dimensional Structural Features Research Articles

MulTFBS: A Spatial-Temporal Network with Multichannels for Predicting Transcription Factor Binding Sites.

Revealing the mechanisms that influence transcription factor binding specificity is the key to understanding gene regulation. In previous studies, DNA double helix structure and one-hot embedding have been used successfully to design computational methods for predicting transcription factor binding sites (TFBSs). However, DNA sequence as a kind of biological language, the method of word embedding representation in natural language processing, has not been considered properly in TFBS prediction models. In our work, we integrate different types of features of DNA sequence to design a multichanneled deep learning framework, namely MulTFBS, in which independent one-hot encoding, word embedding encoding, which can incorporate contextual information and extract the global features of the sequences, and double helix three-dimensional structural features have been trained in different channels. To extract sequence high-level information effectively, in our deep learning framework, we select the spatial-temporal network by combining convolutional neural networks and bidirectional long short-term memory networks with attention mechanism. Compared with six state-of-the-art methods on 66 universal protein-binding microarray data sets of different transcription factors, MulTFBS performs best on all data sets in the regression tasks, with the average R2 of 0.698 and the average PCC of 0.833, which are 5.4% and 3.2% higher, respectively, than the suboptimal method CRPTS. In addition, we evaluate the classification performance of MulTFBS for distinguishing bound or unbound regions on TF ChIP-seq data. The results show that our framework also performs well in the TFBS classification tasks.

Three-dimensional forest structure features extraction based on TomoSAR

Abstract. Forest structure is an important indicator for evaluating forest ecosystem and an indispensable input parameter for estimating forest carbon sink. Synthetic Aperture Radar (SAR) Tomography (TomoSAR), as a novel microwave remote sensing technique with 3D imaging capability, has been demonstrated to be an valuable tool for accurate inversion of forest structure. At present, the forest vertical structure parameters inversion is almost all concentrated on the forest height estimation. However, the spatial structure of forests is complex, and it is not enough to only use the forest height to express the forest structure. This fails to identify tree canopy, branch layer and underlying vegetation layer, etc., resulting in the partial and inaccurate forest vertical structure information. To solve this problem, this paper constructs 3D structural indices from tomograms, namely Horizontal Structure Index (HS) and Vertical Structure Index (VS). The HS primarily describes canopy density, compensating for the lack of information on the horizontal dimension of forest structure provided by traditional TomoSAR techniques; while VS describes the complexity of canopy distribution in the altitude direction, further enriching information on forest structure vertically. In order to verify their feasibility and validity, HS and VS are extracted using six fully-polarized L-band SAR images covering the Krycklan watershed in Sweden. Moreover, the accuracy is verified by using external high-precision LiDAR data. The results indicate a strong correlation between the structural indices extracted from TomoSAR and those extracted from LiDAR.

Language models can identify enzymatic binding sites in protein sequences

Recent advances in language modeling have had a tremendous impact on how we handle sequential data in science. Language architectures have emerged as a hotbed of innovation and creativity in natural language processing over the last decade, and have since gained prominence in modeling proteins and chemical processes, elucidating structural relationships from textual/sequential data. Surprisingly, some of these relationships refer to three-dimensional structural features, raising important questions on the dimensionality of the information encoded within sequential data. Here, we demonstrate that the unsupervised use of a language model architecture to a language representation of bio-catalyzed chemical reactions can capture the signal at the base of the substrate-binding site atomic interactions. This allows us to identify the three-dimensional binding site position in unknown protein sequences. The language representation comprises a reaction-simplified molecular-input line-entry system (SMILES) for substrate and products, and amino acid sequence information for the enzyme. This approach can recover, with no supervision, 52.13% of the binding site when considering co-crystallized substrate-enzyme structures as ground truth, vastly outperforming other attention-based models.

Behaviour of alkali-activated fly ash-slag paste at elevated temperatures: An experimental study

As an environmentally friendly material, alkali-activated fly ash-slag (AAFS) is considered as a promising alternative cement because of its excellent mechanical properties and thermal stability. Nevertheless, high temperature induced damage in AAFS can potentially bring serious risks for its practical applications. This paper presents a systematic experimental study on behaviour of AAFS paste subjected to elevated temperatures up to 800 °C in terms of microstructure as well as thermal and mechanical properties. Microstructural evolution was characterised by means of Rietveld-based quantitative X-ray diffraction (QXRD), backscattered scanning electron microscope (BSEM) and X-ray microcomputed tomography (XCT), while thermal and mechanical properties were evaluated from thermogravimetric analysis (TGA), thermal deformation and compressive and flexural strengths. Results indicate that the compressive strength of AAFS paste rises by 77.5 % at 200 °C, followed by a mitigation from 200 to 600 °C and a regain at 800 °C. Different phases in AAFS paste including unreacted particles, reaction products and pores took up 30 %, 67.7 % and 2.31 % at ambient temperature, and 4.95 %, 84.8 % and 10.3 % after exposure to 800 °C, respectively, suggesting the recrystallisation with the formation of nepheline and gehlenite. In addition, the relationships between microstructural characteristics including three-dimensional (3D) pore structure features and thermal and mechanical properties of AAFS paste at elevated temperatures were explored and discussed in depth to gain insights into the underlying degradation mechanisms including pore pressure build-up, thermal gradient and phase transformation.

Cryo-X-ray phase contrast imaging enables whole biopsy imaging prior to multi-omic analysis

Abstract Background Analysis of myocardial biopsies using conventional two-dimensional (2D) histological techniques is limited in the detection of important three-dimensional (3D) structural features, such as disarray, due to sectioning and artefacts from dehydration or chemical processing. More advanced techniques such as light-sheet microscopy, micro-computed tomography or synchrotron radiation-based X-ray phase contrast imaging can provide non-destructive, 3D histological information at high resolution for formalin-fixed and/or paraffin-embedded (FFPE) biopsies. However, formalin fixation induces crosslinking of proteins which can impact quality and their subsequent analysis, for example, fragmentation of nucleic acids. A method for imaging 3D structure of myocardial biopsies in near-native state is needed which can then be followed by downstream multi-omic applications. Purpose To develop a technique called cryogenic X-ray phase contrast imaging (Cryo-X-PCI) to image snap-frozen myocardial biopsies at controlled low temperatures, followed by multi-omic analysis starting with analysis of DNA and RNA. Methods Myocardial biopsies (n=46) were obtained from C57BL/6 mice and snap-frozen in liquid nitrogen fresh or after 4% paraformaldehyde (PFA);10% formalin fixation. Pilot human aortic stenosis biopsies were also included (n=3, fresh). X-PCI was performed at -70°C using a cryojet, 20 keV beam energy and 0.65 µm detector pixel size (Figure 1). Datasets were reconstructed using Gridrec algorithm and Paganin phase retrieval. Morphologic analysis (myocardial disarray index, fractional anisotropy, helical angle, and intrusion angle) of biopsies was performed using a structure tensor-based approach via in-house MATLAB script. After imaging, DNA and RNA were extracted from murine biopsies followed by assessment of quantity and quality. Results Increased intercellular space between aggregates of myocytes was observed in all samples. This is consistent with reported findings in skeletal muscle using cryogenic conditions. Nonetheless, morphologic analysis of the biopsies proved possible (Figure 2). Optimal recovery of DNA and RNA was obtained from fresh frozen samples as compared to 4% PFA-fixed or 10% formalin-fixed samples. Conclusions This study demonstrates Cryo-X-PCI as a potential tool for analysing myocardial biopsies of heart muscle disease including morphologic analyses. Levels of DNA and RNA were not significantly affected indicating that downstream genomics, proteomics and transcriptomics analyses should be feasible.Setup for Cryo-X-PCI of frozen biopsiesMorphologic analysis of a biopsy

Location of S-nitrosylated cysteines in protein three-dimensional structures.

Although S-nitrosylation of cysteines is a common protein posttranslational modification, little is known about its three-dimensional structural features. This paper describes a systematic survey of the data available in the Protein Data Bank. Several interesting observations could be made. (1) As a result of radiation damage, S-nitrosylated cysteines (Snc) are frequently reduced, at least partially. (2) S-nitrosylation may be a protection against irreversible thiol oxidation; because the NO group of Snc is relatively accessible to the solvent, it may act as a cork to protect the sulfur atoms of cysteines from oxidation by molecular oxygen to sulfenic, sulfinic, and sulfonic acid; moreover, Snc are frequently found at the start or end of helices and strands and this might shield secondary structural elements from unfolding.

Buckling of constant/variable stiffness curved arbitrary layup composite beams by renewed constitutive relations-based sine finite element with improved in-plane and transverse responses

The elastic stability performance of constant- and variable-stiffness based composite curved beams with general layups is evaluated using an enriched finite element that accounts for three-dimensional structural response features. The variable stiffness is spatially created over the beam by layers with curvilinear fibers. The structural model in the present work is represented by sinusoidal variation based higher-order shear deformable model, augmented with improved in-plane response by zig-zag function and stretching in thickness direction by higher polynomial order. The appropriate constitutive relationships for laminated composite curved beam with arbitrary layup producing stiffness coupling effects are deduced from three-dimensional elasticity relations. The beam governing equations are formed applying the total potential energy minimum principle and the buckling parameters are predicted employing the eigenvalue analysis. The curved laminated beam element efficacy is examined for the known analytical solutions in the literature. Extensive numerical analysis by opting for different structural parameters like curved beam angle, thickness, ply-angle, curvilinear fiber angle variation from center-to-edge, layup, and beam end condition are made to visualize the buckling characteristics of general layup composite curved beams.

Molecular dynamics simulation reveals DNA-specific recognition mechanism via c-Myb in pseudo-palindromic consensus of mim-1 promoter.

This study aims to gain insight into the DNA-specific recognition mechanism of c-Myb transcription factor during the regulation of cell early differentiation and proliferation. Therefore, we chose the chicken myeloid gene, mitochondrial import protein 1 (mim-1), as a target to study the binding specificity between potential dual-Myb-binding sites. The c-Myb-binding site in mim-1 is a pseudo-palindromic sequence AACGGTT, which contains two AACNG consensuses. Simulation studies in different biological scenarios revealed that c-Myb binding with mim-1 in the forward strand (complex F) ismore stable than that inthereverse strand (complex R). The principal component analysis (PCA) dynamics trajectory analyses suggested an opening motion of the recognition helices of R2 and R3 (R2R3), resulting in the dissociation of DNA from c-Myb in complex R at 330 K, triggered by the reduced electrostatic potential on the surface of R2R3. Furthermore, the DNA confirmation and hydrogen-bond interaction analyses indicated that the major groove width of DNA increased in complex R, which affected on the hydrogen-bond formation ability between R2R3 and DNA, and directly resulted in the dissociation of DNA from R2R3. The steered molecular dynamics (SMD) simulation studies also suggested that the electrostatic potential, major groove width, and hydrogen bonds made major contribution to the DNA‍-specific recognition. In vitro trials confirmed the simulation results that c-Myb specifically bound to mim-1 in the forward strand. This study indicates that the three-dimensional (3D) structure features play an important role in the DNA-specific recognition mechanism by c-Myb besides the AACNG consensuses, which is beneficial to understanding the cell early differentiation and proliferation regulated by c-Myb, as well as the prediction of novel c-Myb-binding motifs in tumorigenesis.

Variable-stiffness curved laminated-beams by curvilinear fibers with arbitrarily layup – Vibrational features by sine-based higher-order beam model with renewed-constitutive relations and improved-kinematics

The vibration characteristics of variable-stiffness based composite curved beams with general layups are examined using a higher-order beam theory that accounts for three-dimensional structural response features. The variable stiffness is spatially considered in the laminated beam by introducing the curvilinear fibres-based layers. The structural model is here represented by a sine-based shear deformable model considering zig-zag function for improving in-plane response and higher order polynomial for capturing through-thickness stretching effect. The appropriate constitutive relationships for laminated composite curved beam with arbitrary layup producing stiffness coupling effects are deduced from three-dimensional elasticity equations. The beam governing equations are then formed applying Hamilton’s principle and the free vibration features are predicted employing the eigenvalue analysis. The effectiveness of the curved laminated beam element developed here is tested against the available analytical solutions in the literature. A detailed numerical analysis by opting for different structural parameters like curved beam angle, thickness, ply-angle, layup, and beam end condition are made to investigate the vibration characteristics of general layup constant stiffness laminated curved beams and by including additional parameter, curvilinear fibre angle variation from centre-to-edge, for variable stiffness laminates.

Graph neural networks classify molecular geometry and design novel order parameters of crystal and liquid.

Molecular dynamics simulation produces three-dimensional data on molecular structures. The classification of molecular structure is an important task. Conventionally, various order parameters are used to classify different structures of liquid and crystal. Recently, machine learning (ML) methods have been proposed based on order parameters to find optimal choices or use them as input features of neural networks. Conventional ML methods still require manual operation, such as calculating the conventional order parameters and manipulating data to impose rotational/translational invariance. Conversely, deep learning models that satisfy invariance are useful because they can automatically learn and classify three-dimensional structural features. However, in addition to the difficulty of making the learned features explainable, deep learning models require information on large structures for highly accurate classification, making it difficult to use the obtained parameters for structural analysis. In this work, we apply two types of graph neural network models, the graph convolutional network (GCN) and the tensor embedded atom network (TeaNet), to classify the structures of Lennard-Jones (LJ) systems and water systems. Both models satisfy invariance, while GCN uses only length information between nodes. TeaNet uses length and orientation information between nodes and edges, allowing it to recognize molecular geometry efficiently. TeaNet achieved a highly accurate classification with an extremely small molecular structure, i.e., when the number of input molecules is 17 for the LJ system and 9 for the water system, the accuracy is 98.9% and 99.8%, respectively. This is an advantage of our method over conventional order parameters and ML methods such as GCN, which require a large molecular structure or the information of wider area neighbors. Furthermore, we verified that TeaNet could build novel order parameters without manual operation. Because TeaNet can recognize extremely small local structures with high accuracy, all structures can be mapped to a low-dimensional parameter space that can explain structural features. TeaNet offers an alternative to conventional order parameters because of its novelty.

A Highly Sensitive Model Based on Graph Neural Networks for Enzyme Key Catalytic Residue Prediction.

Determining the catalytic site of enzymes is a great help for understanding the relationship between protein sequence, structure, and function, which provides the basis and targets for designing, modifying, and enhancing enzyme activity. The unique local spatial configuration bound to the substrate at the active center of the enzyme determines the catalytic ability of enzymes and plays an important role in the catalytic site prediction. As a suitable tool, the graph neural network can better understand and identify the residue sites with unique local spatial configurations due to its remarkable ability to characterize the three-dimensional structural features of proteins. Consequently, a novel model for predicting enzyme catalytic sites has been developed, which incorporates a uniquely designed adaptive edge-gated graph attention neural network (AEGAN). This model is capable of effectively handling sequential and structural characteristics of proteins at various levels, and the extracted features enable an accurate description of the local spatial configuration of the enzyme active site by sampling the local space around candidate residues and special design of amino acid physical and chemical properties. To evaluate its performance, the model was compared with existing catalytic site prediction models using different benchmark datasets and achieved the best results on each benchmark dataset. The model exhibited a sensitivity of 0.9659, accuracy of 0.9226, and area under the precision-recall curve (AUPRC) of 0.9241 on the independent test set constructed for evaluation. Furthermore, the F1-score of this model is nearly four times higher than that of the best-performing similar model in previous studies. This research can serve as a valuable tool to help researchers understand protein sequence-structure-function relationships while facilitating the characterization of novel enzymes of unknown function.

Endoglucanase effects on energy consumption in the mechanical fibrillation of cellulose fibers into nanocelluloses

Enzymatic processing is considered a promising approach for advancing environmentally friendly industrial processes, such as the use of endoglucanase (EG) enzyme in the production of nanocellulose. However, there is ongoing debate regarding the specific properties that make EG pretreatment effective in isolating fibrillated cellulose. To address this issue, we investigated EGs from four glycosyl hydrolase (GH) families (5, 6, 7, and 12) and examined the roles of the three-dimensional structure and catalytic features, with a focus on the presence of a carbohydrate binding module (CBM). Using eucalyptus Kraft wood fibers, we produced cellulose nanofibrils (CNFs) through mild enzymatic pretreatment, followed by disc ultra-refining. Comparing the results with the control (without pretreatment), we observed that GH5 and GH12 enzymes (without CBM) reduced fibrillation energy by approximately 15 %. The most significant energy reduction, 25 and 32 %, was achieved with GH5 and GH6 linked to CBM, respectively. Notably, these CBM-linked EGs improved the rheological properties of CNF suspensions without releasing soluble products. In contrast, GH7-CBM exhibited significant hydrolytic activity, resulting in the release of soluble products, but did not contribute to a reduction in fibrillation energy. This discrepancy can be attributed to the large molecular weight and wide cleft of GH7-CBM, which led to the release of soluble sugars but had little impact on fibrillation. Our findings suggest that the improved fibrillation observed with EG pretreatment is primarily driven by efficient enzyme adsorption on the substrate and modification of the surface viscoelasticity (amorphogenesis), rather than hydrolytic activity or release of products.

Crystal structural analysis and characterization for MlrC enzyme of Sphingomonas sp. ACM-3962 involved in linearized microcystin degradation

Microcystinase C (MlrC), one key hydrolase of the microcystinase family, plays an important role in linearized microsystin (L-MC) degradation. However, the three-dimensional structure and structural features of MlrC are still unclear. This study obtained high specific activity and high purity of MlrC by heterologous expression, and revealed that MlrC derived from Sphingomonas sp. ACM-3962 (ACM-MlrC) can degrade linearized products of MC-LR, MC-RR and MC-YR to product 3-amino-9-methoxy-2,6,8-trimethyl-10-phenyldeca-4,6-dienoic acid (Adda), indicating the degradation function and significance in MC-detoxification. More importantly, this study reported the crystal structure of ACM-MlrC at 2.6 Å resolution for the first time, which provides a basis for further understanding the structural characteristics and functions of MlrC. MlrC had a dual-domain feature, namely N and C terminal domain respectively. The N-terminal domain contained a Glutamate-Aspartate-Histidine-Histidine catalytic quadruplex coordinated with zinc ion in each monomer. The importance of zinc ions and their coordinated residues was analyzed by dialysis and site-directed mutagenesis methods. Moreover, the important influence of the N/C-terminal flexible regions of ACM-MlrC was also analyzed by sequence truncation, and then the higher yield and total activity of variants were obtained, which was beneficial to study the better function and application of MlrC.

AI-based clinical assessment of optic nerve head robustness superseding biomechanical testing

Background/aimsTo use artificial intelligence (AI) to: (1) exploit biomechanical knowledge of the optic nerve head (ONH) from a relatively large population; (2) assess ONH robustness (ie, sensitivity of the ONH...

Extraction of Submarine Gas Plume Based on Multibeam Water Column Point Cloud Model

The gas plume is a direct manifestation of sea cold seep and one of the most significant symbol indicators of the presence of gas hydrate reservoirs. The multibeam water column (MWC) data can be used to extract and identify the gas plume efficiently and accurately. The current research methods mostly start from the perspective of image theory, which cannot identify the three-dimensional (3D) spatial structure features of gas plumes, reducing the efficiency and accuracy of detection. Therefore, this paper proposes a method for identifying and extracting the gas plume based on an MWC point cloud model, which calculates the spatially resolved homing of MWC data and constructs a 3D point cloud model of MWC containing acoustic reflection intensity information. It first performs noise suppression of the 3D point cloud of the MWC based on the symmetric subtraction and Otsu algorithm by leveraging the noise distribution of the MWC and the reflection intensity characteristics of the gas plume. Then, it extracts the point cloud clusters containing the gas plume based on Density-Based Spatial Clustering of Applications with Noise (DBSCAN) according to the density difference between the gas plume point cloud and the background MWC point cloud and next identifies the point cloud clusters by feature matching based on fast point feature histograms (FPFHs). Finally, it extracts the gas plume point cloud set in the MWC. As evidenced by the MWC data collected from gas hydrate enrichment zones in the Gulf of Mexico, the location of gas plume extracted by this method is highly consistent with that of gas leakage points measured during the cruise. Using this method, we obtained the point cloud data set of gas plume for the first time and accurately characterized the 3D spatial morphology of the subsea gas plume, providing technical support for gas hydrate exploration, subsea gas seepage area delineation, and subsea seepage gas flux estimation.

Prediction of post-translational modification cross-talk and mutation within proteins via imbalanced learning

Post-translational modification (PTM) is crucial for various cell signaling pathways and biological processes. However, the interactions between PTMs (PTM cross-talk) or PTMs and other sites (PTM mutation) are still in there infancy, with many challenges remaining unexplored. Since PTMs play a fundamental role in cell biology, many mutations cause abnormalities in many PTM sites and affect many human diseases. In this research, we propose an algorithm to improve PTM sites and PTM sites (PTM cross-talk) prediction and to study the interaction between PTM sites and mutation sites (PTM mutation). In addition to the primary network features of three-dimensional protein structure and sequence features, the dynamic features based on ENMs (elastic network models) are also used to improve model performance. Through feature selection, we reserved 48 features and developed a predictor for predicting PTM cross-talk and mutation. According to the evaluation based on PTM cross-talk, the area under the curve of our best prediction model reaches 0.911, which exceeds the state-of-art-model PCTpred. Based on the evaluation of PTM mutation, our prediction model is highly reliable, with an AUC score of 0.935. Even with the removal of the distance, the performance of our model (which is the most excellent model of the nine models, Random Forest model) is relatively stable.

Multifaceted Computational Modeling in Glycoscience

Glycoscience assembles all the scientific disciplines involved in studying various molecules and macromolecules containing carbohydrates and complex glycans. Such an ensemble involves one of the most extensive sets of molecules in quantity and occurrence since they occur in all microorganisms and higher organisms. Once the compositions and sequences of these molecules are established, the determination of their three-dimensional structural and dynamical features is a step toward understanding the molecular basis underlying their properties and functions. The range of the relevant computational methods capable of addressing such issues is anchored by the specificity of stereoelectronic effects from quantum chemistry to mesoscale modeling throughout molecular dynamics and mechanics and coarse-grained and docking calculations. The Review leads the reader through the detailed presentations of the applications of computational modeling. The illustrations cover carbohydrate-carbohydrate interactions, glycolipids, and N- and O-linked glycans, emphasizing their role in SARS-CoV-2. The presentation continues with the structure of polysaccharides in solution and solid-state and lipopolysaccharides in membranes. The full range of protein-carbohydrate interactions is presented, as exemplified by carbohydrate-active enzymes, transporters, lectins, antibodies, and glycosaminoglycan binding proteins. A final section features a list of 150 tools and databases to help address the many issues of structural glycobioinformatics.

Co-operative halogen bonds and nonconventional sp-C-H...O hydrogen bonds in 1:1 cocrystals formed between diethynylpyridines and N-halosuccinimides.

The rapid evaporation of 1:1 solutions of diethynylpyridines and N-halosuccinimides, that react together to form haloalkynes, led to the isolation of unreacted 1:1 cocrystals of the two components. The 1:1 cocrystal formed between 2,6-diethynylpyridine and N-iodosuccinimide (C4H4INO2·C9H5N) contains an N-iodosuccinimide-pyridine I...N halogen bond and two terminal alkyne-succinimide carbonyl C-H...O hydrogen bonds. The three-dimensional extended structure features interwoven double-stranded supramolecular polymers that are interconnected through halogen bonds. The cocrystal formed between 3,5-diethynylpyridine and N-iodosuccinimide (C4H4INO2·C9H5N) also features an I...N halogen bond and two C-H...O hydrogen bonds. However, the components form essentially planar double-stranded one-dimensional zigzag supramolecular polymers. The cocrystal formed between 3,5-diethynylpyridine and N-bromosuccinimide (C4H4BrNO2·C9H5N) is isomorphous to the cocrystal formed between 3,5-diethynylpyridine and N-iodosuccinimide, with a Br...N halogen bond instead of an I...N halogen bond.

1H, 13C, 15N backbone and side‐chain resonance assignments of the pathogenic G131V mutant of human prion protein (91–231)

Human prion disease, also known as transmissible spongiform encephalopathy (TSEs), is caused by the conformational conversion of the normal cellular prion protein (PrPC) into the scrapie form (PrPSc). Pathogenic point mutations of prion proteins typically facilitate conformational conversion and lead to inherited prion diseases. A previous study has demonstrated that the pathogenic G131V mutation of human prion protein (HuPrP) brings in Gerstmann-Sträussler-Scheinker syndrome. However, the three-dimensional structure and dynamic features of the HuPrP(G131V) mutant remain unclear. It is expected that the determination of these structural bases will be beneficial to the pathogenic mechanistic understanding of G131V-related prion diseases. Here, we performed 1H, 15N, 13C backbone and side-chain resonance assignments of the G131V mutant of HuPrP(91-231) by using heteronuclear multi-dimensional NMR spectroscopy, and predicted the secondary structural elements and order parameters of the protein based on the assigned backbone chemical shifts. Our work lays the necessary foundation for further structural determination, dynamics characterization, and intermolecular interaction assay for the G131V mutant.

Tree species classification of LiDAR data based on 3D deep learning

Accurate tree species identification is essential for ecological evaluation and other forest applications. In this paper, we proposed a point-based deep neural network called LayerNet. For light detection and ranging (LiDAR) data in forest regions, the network can divide multiple overlapping layers in Euclidean space to obtain the local three-dimensional (3D) structural features of the tree. The features of all layers are aggregated, and the global feature is obtained by convolution to classify the tree species. To validate the proposed framework, multiple experiments, including airborne and ground-based LiDAR datasets, are conducted and compared with several existing tree species classification algorithms. The test results show that LayerNet can directly use 3D data to accurately classify tree species, with the highest classification accuracy of 92.5%. Also, the results of comparative experiments demonstrate that the proposed framework has obvious advantages in classification accuracy and provides an effective solution for tree species classification tasks.