Original Sequence Research Articles

Assessing the Effect of Coriolis Acceleration on the Coherent Structures in the Wake of a Wind Turbine using DMD

Abstract The present work aims to study the effect of veer, namely, the height-dependent lateral deflection of wind velocity due to Coriolis acceleration, on the coherent structures in the wake of the NREL 5-MW reference wind turbine using the sparsity-promoting dynamic mode decomposition (SP-DMD) method for the detection of dynamically-relevant flow structures. Large eddy simulation of the flow impacting the wind turbine is carried out by solving the filtered Navier-Stokes equations for incompressible flows. The effects of both tower and nacelle are included in the simulation using the immersed boundary method. Simulations are performed at Re ≈ 108, generating the inlet velocity profile by a precursor simulation of the atmospheric boundary layer subjected to Coriolis acceleration. The analysis of the DMD results allows to study the effects of the Coriolis acceleration on the most relevant dynamic modes in the turbine wake and to understand the basic mechanisms by which the wind veer significantly affects the wake recovery rate. Moreover, as a result of the SP-DMD methodology, the most relevant modes are extracted from the wake and a limited subset of relevant flow features that optimally approximates the original data sequence is identified. This small number of modes represent the kernel that can be employed for developing an accurate reduced order model of the wake.

Mutations in CsWOX4 Regulate Leaf Vein Pattern and Leaf Size in Cucumber (Cucumis sativus L.)

The leaf morphology is an important agronomic trait in crop production. Our study identified a maple leaf type (mlt) cucumber mutant and located the regulatory gene for leaf shape changes through BSA results. Hybrid F1 and F2 populations were generated by F1 self-crossing, and the candidate mlt genes were identified within the 2.8 Mb region of chromosome 2 using map cloning. Through the sequencing and expression analysis of genes within the bulk segregant analysis (BSA) region, we identified the target gene for leaf shape regulation as CsWOX4 (CsaV3_2G026510). The change from base C to T in the original sequence led to frameshift mutations and the premature termination of translation, resulting in shortened encoded proteins and conserved WUSCHEL (WUS) box sequence loss. The specific expression analysis of the CsWOX4/Cswox4 genes in the roots, stems, leaves and other tissue types of wild-type (WT) and mutant plants revealed that CsWOX4 was higher in the root, but Cswox4 (mutant gene) was significantly higher in the leaf. Subcellular localization analysis revealed that CsWOX4 was localized in the nucleus. RNA-seq analysis revealed that the differentially expressed genes were mainly enriched in the mitochondrial cell cycle phase transition, nucleosome and microtubule binding pathways. Simultaneously, the quantitative analysis of the expression trends of 25 typical genes regulating the leaf types revealed the significant upregulation of CsPIN3. In our study, we found that the conserved domain of CsWOX4 was missing in the mutant, and the transcriptome data revealed that the expression of some genes, such as CsPIN3, changed simultaneously, thereby jointly regulating changes in the cucumber leaf type.

New Results on Graph Matching from Degree-Preserving Growth

The recently introduced model in S. R. Kharel et al.’s study [Degree-preserving network growth. Nature Physics 2022, 18, 100–106] uses matchings to insert new vertices of prescribed degrees into the current graph of an ever-growing graph sequence. The process depends both on the size of the largest available matching, which is the focus of this paper, as well as on the actual choice of the matching. Here, we first show that the question of whether a graphic degree sequence, extended with a new degree 2δ, remains graphic and is equivalent to the existence of a realization of the original degree sequence with a matching of size δ. Secondly, we present lower bounds for the size of the maximum matchings in any realization of the degree sequence. We then study the bounds on the size of maximal matchings in some realizations of the sequence, known as the potential matching number. We also estimate the minimum size of both maximal and maximum matchings, as determined by the degree sequence, independently of graphical realizations. Along this line we answer a question raised by T. Biedl et al.: Tight bounds on maximal and maximum matchings. Discrete Mathematics 2004, 285, 7–15.

An Ultra‐Short‐Term Multi‐Step Prediction Model for Wind Power Based on Sparrow Search Algorithm, Variational Mode Decomposition, Gated Recurrent Unit, and Support Vector Regression

ABSTRACTAccurate ultra‐short‐term wind power prediction techniques are crucial for ensuring the efficient and safe operation of wind farms and power systems. Combined models based on data decomposition‐prediction techniques have shown excellent performance in ultra‐short‐term wind power forecasting. This study introduces a novel ultra‐short‐term multi‐step prediction model for wind power, which integrates the sparrow search algorithm (SSA), variational mode decomposition (VMD), gated recurrent unit (GRU), and support vector regression (SVR). An optimization variational mode decomposition technique is developed by adaptively determining VMD hyperparameters using SSA. The optimization VMD decomposes the original wind power sequence into sub‐modes, and the resulting sequence of decomposed sub‐modes calculates permutation entropy (PE) values. Sub‐modes with similar PE values are combined, reorganized, and categorized into high‐frequency and low‐frequency. High‐frequency sub‐modes data with high complexity and non‐stationarity are predicted by the GRU neural network. Low‐frequency sub‐modes data with low complexity and strong nonlinearity are predicted with SVR. The proposed model was evaluated against seven others using three error metrics: MAE, RMSE, and R2, along with their corresponding enhancement percentages. Experimental results indicate that the proposed model extracts detailed and trend information from the wind power series more effectively and stably than the comparison models. It also demonstrates superior multi‐step prediction performance, offering significant value for practical engineering applications.

A Hybrid Model Combined Deep Neural Network and Beluga Whale Optimizer for China Urban Dissolved Oxygen Concentration Forecasting

The dissolved oxygen concentration (DOC) is an important indicator of water quality. Accurate DOC predictions can provide a scientific basis for water environment management and pollution prevention. This study proposes a hybrid DOC forecasting framework combined with Variational Mode Decomposition (VMD), a convolutional neural network (CNN), a Gated Recurrent Unit (GRU), and the Beluga Whale Optimization (BWO) algorithm. Specifically, the original DOC sequences were decomposed using VMD. Then, CNN-GRU combined with an attention mechanism was utilized to extract the key features and local dependency of the decomposed sequences. Introducing the BWO algorithm solved the correction coefficients of the proposed system, with the aim of improving prediction accuracy. This study used 4-h monitoring China urban water quality data from November 2020 to November 2023. Taking Lianyungang as an example, the empirical findings exhibited noteworthy enhancements in performance metrics such as MSE, RMSE, MAE, and MAPE within the VMD-BWO-CNN-GRU-AM, with reductions of 0.2859, 0.3301, 0.2539, and 0.0406 compared to a GRU. These results affirmed the superior precision and diminished prediction errors of the proposed hybrid model, facilitating more precise DOC predictions. This proposed DOC forecasting system is pivotal for sustainably monitoring and regulating water quality, particularly in terms of addressing pollution concerns.

Cleaning method for abnormal energy big data based on sparse self-coding

In order to reduce the interference of abnormal energy big data and improve the accuracy of anomaly cleaning and detection, this paper proposes a method for cleaning abnormal energy big database based on sparse self-coding. Firstly, the abnormal data detection method based on multi-criteria evaluation is used to analyze the spectral feature distribution of abnormal energy big data. By using chaotic time series reconstruction model, robust local weighted regression analysis and sparse self-coding method, the feature decomposition of time series of energy data is realized. Then, according to the periodicity of the original sequence, the original sequence is segmitated adaptively to represent the morphological characteristics of the abnormal energy data sub-sequences driven by dynamic carbon emissions, and the anomaly index of each sub-sequence is obtained by AFCM algorithm. Secondly, an energy anomaly evaluation model based on LOF value is established. Finally, the output decision function of data cleaning is constructed to realize the abnormal energy big data cleaning. The test results show that the error detection rate of this method is 0.24%, the missing detection rate is 0.27%, the cleaning rate can reach 99.49%, and the cleaning time is less than 2s.

VMD-HPCA-GRU ultra-short-term wind power forecasting based on COOT algorithm

In order to improve the prediction accuracy of ultra-short-term wind power, a combined prediction model of variational mode decomposition (VMD), hierarchical principal component analysis (HPCA) and gated recurrent unit neural network (GRU) based on COOT algorithm optimization is proposed. Firstly, the energy difference method is used to determine the number of sub-modes of variational mode decomposition, so that the original power sequence with strong nonlinearity is decomposed into a group of relatively stable sub-modes. Secondly, the correlation value between high-dimensional meteorological characteristics and power sequence is calculated by grey correlation analysis and sorted and layered. The first principal component of each layered characteristic variable is extracted by principal component analysis to achieve dimensionality reduction of high-dimensional meteorological characteristics. Finally, the COOT algorithm is introduced to optimize the hyperparameters of the gated recurrent unit prediction model, accelerate the model convergence speed, and improve the prediction accuracy of the model. The measured data of a wind farm in Guizhou are simulated and analyzed. The results show that compared with the prediction results of the traditional GRU model, the root mean square error, mean absolute error, and mean absolute percentage error of the proposed method are reduced 67.41%、72.25%、45.69%, and the prediction accuracy is higher than that of the other four combined prediction models, which effectively improves the prediction accuracy of ultra-short-term wind power.

UTran-DSR: a novel transformer-based model using feature enhancement for dysarthric speech recognition

Over the past decade, the prevalence of neurological diseases has significantly risen due to population growth and aging. Individuals suffering from spastic paralysis, brain attack, and idiopathic Parkinson’s disease (PD), among other neurological illnesses, commonly suffer from dysarthria. Early detection and treatment of dysarthria in these patients are essential for effectively managing the progression of their disease. This paper provides UTrans-DSR, a novel encoder-decoder architecture for analyzing Mel-spectrograms (generated from audios) and classifying speech as healthy or dysarthric. Our model employs transformer encoder features based on a hybrid design, which includes the feature enhancement block (FEB) and the vision transformer (ViT) encoders. This combination effectively extracts global and local pixel information regarding localization while optimizing the mel-spectrograms feature extraction process. We keep up with the original class-token grouping sequence in the vision transformer while generating a new equivalent expanding route. More specifically, two unique growing pathways use a deep-supervision approach to increase spatial data recovery and expedite model convergence. We add consecutive residual connections to the system to reduce feature loss while increasing spatial data retrieval. Our technique is based on identifying gaps in mel-spectrograms distinguishing between normal and dysarthric speech. We conducted several experiments on UTrans-DSR using the UA speech and TORGO datasets, and it outperformed the existing top models. The model performed significantly in pixel’s localized and spatial feature extraction, effectively detecting and classifying spectral gaps. The Tran-DSR model outperforms previous research models, achieving an accuracy of 97.75%.

Biodiversity of symbiotic gastropods (Mollusca, Eulimidae) in Vietnamese waters barcoded

ABSTRACT Eulimidae is a prominent group within the class Gastropoda, comprising 1087 species that have developed specialised symbiotic relationships with all extant echinoderm classes. At least 47 species of eulimids can be found in the waters of Vietnam. Representatives of the genus Pulicicochlea, the species Vitreobalcis tripneusticola, and four new undescribed species were observed for the first time. In this study, we update the existing checklists of Vietnamese eulimids, emphasising the use of molecular barcoding to determine the phylogenetic relationships among the collected species. The classical taxonomy of molluscs relies heavily on the morphology of the shell and radula. The family Eulimidae presents challenges as in many species these features are poorly developed, and molecular phylogenetic methods have proven to be more informative for the taxonomy and systematics of this family. To understand the evolutionary pathways in Eulimidae, we constructed a COI-based phylogenetic tree, which included original sequences primarily from Vietnam and all available sequences for Eulimidae from GenBank. The newly obtained genetic information is crucial for enhancing our understanding of this family of gastropod mollusсs, as well as for any future revisions that may be necessary.

Cleavage of DNA Substrate Containing Nucleotide Mismatch in the Complementary Region to sgRNA by Cas9 Endonuclease: Thermodynamic and Structural Features

The non-ideal accuracy and insufficient selectivity of CRISPR/Cas9 systems is a serious problem for their use as a genome editing tool. It is important to select the target sequence correctly so that the CRISPR/Cas9 system does not cut similar sequences. This requires an understanding of how and why mismatches in the target sequence can affect the efficiency of the Cas9/sgRNA complex. In this work, we studied the catalytic activity of the Cas9 enzyme to cleave DNA substrates containing nucleotide mismatch at different positions relative to the PAM in the “seed” sequence. We show that mismatches in the complementarity of the sgRNA/DNA duplex at different positions relative to the protospacer adjacent motif (PAM) sequence tend to decrease the cleavage efficiency and increase the half-maximal reaction time. However, for two mismatches at positions 11 and 20 relative to the PAM, an increase in cleavage efficiency was observed, both with and without an increase in half-reaction time. Thermodynamic parameters were obtained from molecular dynamics results, which showed that mismatches at positions 8, 11, and 20 relative to the PAM thermodynamically stabilize the formed complex, and a mismatch at position 2 of the PAM fragment exerts the greatest stabilization compared to the original DNA sequence. The weak correlation of the thermodynamic binding parameters of the components of the Cas9/sgRNA:dsDNA complex with the cleavage data of DNA substrates containing mismatches indicates that the efficiency of Cas9 operation is mainly affected by the conformational changes in Cas9 and the mutual arrangement of sgRNA and substrates.

Predictive Model for O3 in Shanghai Based on the KZ Filtering Technique and LSTM

In this study, a Kolmogorov-Zurbenko （KZ） filter was proposed to decompose the original ozone （O3） sequence to improve the accuracy of ozone long-term series prediction and select relevant meteorological features. Furthermore, the enhanced maximal minimal redundancy （mRMR） feature selection technique was combined with the support vector regression （SVR） approach to select the most illuminating meteorological features. Subsequently, from May to August 2023, during high ozone concentration periods, a long short-term memory network （LSTM） was utilized to assess and predict high ozone concentration periods at the monitoring stations of Jingan （urban area）, Pudong-Chuansha （suburban area）, and Dianshan Lake （suburban area） in Shanghai. The results showed that pressure, temperature, humidity, boundary layer height, and wind direction were the best combinations of O3 baseline and short-term components, as chosen by feature screening. The R2 values for Jingan Station, Pudong-Chuansha Station, and Dianshan Lake Station were 0.86, 0.83, and 0.85, respectively. The RMSE values were 18.26, 18.74, and 20.02 μg·m-3, respectively. These findings suggest that decomposing the original O3 sequence improved the prediction accuracy of ozone concentrations. Additionally, as indicated by the R2 and RMSE values found for every monitoring station, feature screening preserved the model's predictive performance.

Frequency-specific dual-attention based adversarial network for blood oxygen level-dependent time series prediction.

Functional magnetic resonance imaging (fMRI) is currently one of the most popular technologies for measuring brain activity in both research and clinical contexts. However, clinical constraints often result in short fMRI scan durations, limiting the diagnostic performance for brain disorders. To address this limitation, we developed an end-to-end frequency-specific dual-attention-based adversarial network (FDAA-Net) to extend the time series of existing blood oxygen level-dependent (BOLD) data, enhancing their diagnostic utility. Our approach leverages the frequency-dependent nature of fMRI signals using variational mode decomposition (VMD), which adaptively tracks brain activity across different frequency bands. We integrated the generative adversarial network (GAN) with a spatial-temporal attention mechanism to fully capture relationships among spatially distributed brain regions and temporally continuous time windows. We also introduced a novel loss function to estimate the upward and downward trends of each frequency component. We validated FDAA-Net on the Human Connectome Project (HCP) database by comparing the original and predicted time series of brain regions in the default mode network (DMN), a key network activated during rest. FDAA-Net effectively overcame linear frequency-specific challenges and outperformed other popular prediction models. Test-retest reliability experiments demonstrated high consistency between the functional connectivity of predicted outcomes and targets. Furthermore, we examined the clinical applicability of FDAA-Net using short-term fMRI data from individuals with autism spectrum disorder (ASD) and major depressive disorder (MDD). The model achieved a maximum predicted sequence length of 40% of the original scan durations. The prolonged time series improved diagnostic performance by 8.0% for ASD and 11.3% for MDD compared with the original sequences. These findings highlight the potential of fMRI time series prediction to enhance diagnostic power of brain disorders in short fMRI scans.

Complex dynamic behavioral transitions in auditory neurons induced by chaotic activity

Chaotic sequences are widely used in secure communication due to their high randomness. Chaotic resonance (CR) refers to the resonant response of a system to weak signals induced by chaotic activity, but its practical application remains limited. This study designs a simplified FitzHugh-Nagumo (FHN) auditory neuron model by simulating the physiological activities of auditory neurons and considering the combined stimulation of chaotic activity and sound signals. It is found that the neuron dynamics depend on both external sound stimuli and chaotic current intensity. Chaotic currents induce spikes in the neuron output sequence through CR, and the spikes become more frequent with increasing current intensity, eventually leading to a chaotic state regardless of the initial state. However, the sensitivity of the initial value of this chaotic sequence shifts to the chaotic current excitation system. The injection of chaotic currents can reduce the system's average Hamiltonian energy under certain conditions. By measuring the complexity of the generated sequences, we find that the addition of chaotic currents can enhance the complexity of the original sequences, and the enhancement ability increases with the intensity. This provides a new approach to enhance the complexity of original chaotic sequences. Moreover, different chaotic currents can induce different chaotic sequences with varying abilities to enhance the complexity of the original sequences. We hope our work can contribute to secure communication.

A novel combined model based on advanced optimization algorithm, and deep learning model for abnormal wind speed identification and reconstruction

When the state of the sensors of the wind turbine, especially the anemometer, is abnormal, it will affect the correctness of other parameters of the whole power system. To recognize and reconstruct the abnormal data accurately and efficiently, this study proposes an improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), extreme learning machine (ELM), crazy improve butterfly optimization algorithm (CIBOA), and bi-directional long short-term memory (BILSTM). In this system, the ICEEMDAN is utilized to decompose the original wind speed sequence, and then the ELM is employed as the initial prediction engine to extract the features of each sub-sequence to achieve the preliminary prediction outcomes. The CIBOA is employed to optimize the BILSTM model parameters. To further explore the unsteady features in the wind speed series, the residual results of the preliminary prediction are modeled using BILSTM, and the predicted residuals and preliminary results are integrated to obtain the final reconstructed values. In addition, the combined model is discussed in detail employing six assessment indicators, improvements of the reconstruction model, Diebold-Mariano test, operation time, and sensitivity analysis. The results indicate that the Pearson correlation coefficient (PCC) values of the proposed model are 0.9986, 0.9978, and 0.9979, respectively. It is concluded that the proposed hybrid reconstruction model accurately identifies and reconstructs abnormal wind speed, which provides a new technique for the reasonable utilization of wind energy.

Revisiting the functional annotation of TriTryp using sequence similarity tools

Trypanosomatids are the causative agents of deadly diseases in humans and livestock. Given the high phylogenetic distance of trypanosomatids from model organisms, these organisms have ample unannotated genes. Manual functional annotation is time-consuming, highlighting the importance of automated functional annotation tools. The development of automated functional tools is a hot research topic, and multiple tools have been developed for the task. PANNZER2 is an automated functional annotation tool that merely relies on the sequence similarity of the query to the annotated proteins. We tried PANNZER2 on Trypanosoma brucei, the most studied organism among trypanosomatids, to see if it could improve our knowledge of the functions of the genes.Even with the availability of automated annotation tools like InterPro2GO in databases such as TriTrypDB, PANNZER2 has made surprisingly confident predictions for some hypothetical proteins in T. brucei. In this study, we identify gaps in such annotations because of not employing pairwise sequence alignment tools in TriTrypDB's automated annotation process. Our findings demonstrate that even the use of stringent cutoffs can successfully annotate a significant number of proteins. Additionally, we discovered that adjusting the open reading frames in certain genes leads to sequences with increased sequence signature coverage—characterized by the length covered by at least one sequence signature—compared to the original sequences. This enhanced sequence signature coverage suggests these genomic fragments could be pseudogenes. To facilitate further exploration, we developed a script to help identify potential pseudogenes within an organism's genome, offering researchers a new tool for genomic analysis and understanding. We extended all our analysis to Trypanosoma cruzi and Leishmania major to assess the impact of this approach across different species.Our study demonstrates that by utilizing pairwise sequence similarity alignment, even with stringent cutoffs, we can attribute 2986, 3953, and 3798 new GO terms to the genomes of T. brucei, T. cruzi, and L. major. Additionally, we found that 210, 239, and 29 genes exhibit increased sequence signature coverage following frame correction, suggesting the presence of pseudogenes.

Mapping Start Codons of Small Open Reading Frames by N-Terminomics Approach

sORF-encoded peptides (SEPs) refer to proteins encoded by small open reading frames (sORFs) with a length of less than 100 amino acids, which play an important role in various life activities. Analysis of known SEPs showed that using non-canonical initiation codons of SEPs was more common. However, the current analysis of SEP sequences mainly relies on bioinformatics prediction, and most of them use AUG as the start site, which may not be completely correct for SEPs. Chemical labeling was used to systematically analyze the N-terminal sequences of SEPs to accurately define the start sites of SEPs. By comparison, we found that dimethylation and guanidinylation are more efficient than acetylation. The ACN precipitation and heating precipitation performed better in SEP enrichment. As an N-terminal peptide enrichment material, Hexadhexaldehyde was superior to CNBr-activated agarose and NHS-activated agarose. Combining these methods, we identified 128 SEPs with 131 N-terminal sequences. Among them, two-thirds are novel N-terminal sequences, and most of them start from the 11-31st amino acids of the original sequence. Partial novel N-termini were produced by proteolysis or signal peptide removal. Some SEPs' transcription start sites were corrected to be non-AUG start codons. One novel start codon was validated using GFP-tag vectors. These results demonstrated that the chemical labeling approaches would be beneficial for identifying the start codons of sORFs and the real N-terminal of their encoded peptides, which helps better understand the characterization of SEPs.

Indian Sequins: A Jeweled Textile of India

Looking back from the time of civilization, India always has rich competencies in the field of fascinating arts, crafts, and cultures along with its high-end heritage. From that time competent craftsmen not only used their skills to fulfill the needs and wants of society but also trade overseas. This used to be a reason for their earning and livelihood. Little by little these skills started demolishing, mukeish or badla or kamdani work is one of them. Mukeish (also known as Badla work or Kamdani in the local language) is a type of old-age metal wire embroidery with its legacy in the capital of Uttar Pradesh, Lucknow, the city of Nawabs. Mukeish work involves twisting metallic thread to create patterns over the surface of the fabrics. Earlier original gold and silver wires were used to make these patterns, depicting royalty. With the passage of time, mukeish work lost its shine and royalty. Though it is not vaporized completely, only a handful of skilled craftsmen are available in Uttar Pradesh. The core reason for the decreasing demand for Mukeish work is not crystal clear but a small number of craftsmen are available who work on mukeish embroidery. It is said that mukeish or badla work is the original sequence of India that paves out the track of sequence work around the fashion globe. It is an expensive and indeed time-consuming craft. This meticulous work has lost its shine and glamour due to the lack of skilled artisans. The availability of substitute sequences in embroidery is also the reason for its blurry image in the world of Embroidery. The purpose of shedding light on mukeish or badla work is to review this meticulous craft of India and promote this precious craft around the globe.

A data-driven dual-optimization hybrid machine learning model for predicting carbon dioxide trapping efficiency in saline aquifers: Application in carbon capture and storage

Geological carbon sequestration (GCS) is a promising method to reduce global carbon emissions. To better understand the CO2 trapping mechanism, the CO2 sequestration process was simulated through a physics-based reservoir simulator, and the residual trapping (RTI) and solubility trapping (STI) efficiencies were analyzed. Through the experiments, a database containing 4543 data points with reservoir physical parameters and rock properties was established. In this study, a kernel extreme learning machine (KELM) model based on variational mode decomposition (VMD) and dung beetle optimization optimizer (DBO) was proposed to perform the prediction task. Through the VMD, the original data sequences were decomposed and combined, and the obtained subsequences were executed modeling prediction and reconstruction respectively. The reliability of the prediction model was confirmed to be greater than 97.71% through domain analysis. In addition, it was applied to a tight gas reservoir in China in to confirm its validity in field applications. Comparative results indicated a high agreement between the prediction results and the simulation results, suggesting that the proposed method can complement numerical simulations and help users understand the application of machine learning in carbon capture and storage (CCS).

Novel discretized gravitational search algorithm for effective medical hyperspectral band selection

Medical hyperspectral imaging present a promising avenue for non-invasive diagnostic methods for diseases. Nonetheless, the sparsity of medical hyperspectral data within high-dimensional spaces introduces the “curse of dimensionality”, which diminishes the efficiency and accuracy of data processing efforts. Therefore, spectral dimensionality reduction emerges as an essential process in the analysis and utilization of MHSIs data. To retain the intrinsic properties of the spectral bands, an effective unsupervised band selection algorithm is proposed leveraging the gravitational search algorithm (GSA-UBS) to identify the optimal band subset. Taking into account the informational content and redundancy among candidate bands, a comprehensive evaluation criterion is established that incorporates a band distance matrix and an information entropy vector. Additionally, a straightforward discrete search strategy is developed that enables gravitational search algorithm to directly retrieve the original sequence numbers of the selected bands, bypassing the conventional 0–1 band weighting approach. The extensive evaluation of GSA-UBS on three publicly available invivo brain cancer MHSIs datasets and a remote sensing hyperspectral image demonstrates its superior performance compared to various state-of-the-art methods. The source code for GSA-UBS can be accessed at https://github.com/zhangchenglong1116/GSA_UBS.

All‐Atom Protein Sequence Design Based on Geometric Deep Learning

Designing sequences for specific protein backbones is a key step in creating new functional proteins. Here, we introduce GeoSeqBuilder, a deep learning framework that integrates protein sequence generation with side chain conformation prediction to produce the complete all‐atom structures for designed sequences. GeoSeqBuilder uses spatial geometric features from protein backbones and explicitly includes three‐body interactions of neighboring residues. GeoSeqBuilder achieves native residue type recovery rate of 51.6%, comparable to ProteinMPNN and other leading methods, while accurately predicting side chain conformations. We first used GeoSeqBuilder to design sequences for thioredoxin and a hallucinated three‐helical bundle protein. All the 15 tested sequences expressed as soluble monomeric proteins with high thermal stability, and the 2 high‐resolution crystal structures solved closely match the designed models. The generated protein sequences exhibit low similarity (minimum 23%) to the original sequences, with significantly altered hydrophobic cores. We further redesigned the hydrophobic core of glutathione peroxidase 4, and 3 of the 5 designs showed improved enzyme activity. Although further testing is needed, the high experimental success rate in our testing demonstrates that GeoSeqBuilder is a powerful tool for designing novel sequences for predefined protein structures with atomic details. GeoSeqBuilder is available at https://github.com/PKUliujl/GeoSeqBuilder