Sequence Elements Research Articles

A Comparative Study on Fixed-Order Event Sequence Visualizations: Gantt, Extended Gantt, and Stringline Charts.

We conduct two in-lab experiments (N = 93) to evaluate the effectiveness of Gantt charts, extended Gantt charts, and stringline charts for visualizing fixed-order event sequence data. We first formulate five types of event sequences and define three types of sequence elements: point events, interval events, and the temporal gaps between them. Our two experiments focus on event sequences with a pre-defined, fixed order and measure task error rates and completion time. The first experiment shows single sequences and assesses the three charts' performance in comparing event duration or gap. The second experiment shows multiple sequences and evaluates how well the charts reveal temporal patterns. The results suggest that when visualizing single fixed-order event sequences, 1) Gantt and extended Gantt charts lead to comparable error rates in the duration-comparing task; 2) Gantt charts exhibit either shorter or equal completion time than extended Gantt charts; 3) both Gantt and extended Gantt charts demonstrate shorter completion times than stringline charts; 4) however, stringline charts outperform the other two charts with fewer errors in the comparing task when event type counts are high. Additionally, when visualizing multiple point-based fixed-order event sequences, stringline charts require less time than Gantt charts for people to find temporal patterns. Based on these findings, we discuss design opportunities for visualizing fixed-order event sequences and discuss future avenues for optimizing these charts.

Exploring the dynamics of messenger ribonucleoprotein-mediated translation repression.

Translational control is crucial for well-balanced cellular function and viability of organisms. Different mechanisms have evolved to up- and down-regulate protein synthesis, including 3' untranslated region (UTR)-mediated translation repression. RNA binding proteins or microRNAs interact with regulatory sequence elements located in the 3' UTR and interfere most often with the rate-limiting initiation step of translation. Dysregulation of post-transcriptional gene expression leads to various kinds of diseases, emphasizing the significance of understanding the mechanisms of these processes. So far, only limited mechanistic details about kinetics and dynamics of translation regulation are understood. This mini-review focuses on 3' UTR-mediated translational regulation mechanisms and demonstrates the potential of using single-molecule fluorescence-microscopy for kinetic and dynamic studies of translation regulation in vivo and in vitro.

Identification of the P24 Gene Family Related to Vesicular Transport in Cyclocarya paliurus and Their Expression Analysis Under Salt Stress

Vesicle transport is a fundamental mechanism for intracellular substance transfer and signal transduction, involving the formation, transport, fusion with target membranes, and release of vesicle contents within cells. Issues such as disruption of water balance, difficulty in regulating osmotic pressure, and oxidative stress caused by salt stress can lead to disturbances in the secretion system of plants, thus affecting plant growth and development. Cyclocarya paliurus (C. paliurus), widely used in traditional Chinese medicine, has not been previously reported in terms of how the vesicle transport P24 gene regulates its adaptation to salt stress. In this research project, a total of eight CpP24 genes were successfully identified. Upon examination of gene architecture and conserved sequence elements, the CpP24 genes exhibited a variation in exon count, ranging from 4 to 6. Moreover, the CpP24 gene family’s reaction to salt stress and specific stressors including methyl jasmonate (MeJA), sodium hydrosulfide (NaHS), and sodium nitroprusside (SNP) was further explored in our study. Comprehensive analysis of the expression patterns of CpP24 genes under various conditions showed that salt stress induced the expression of these genes, and the combined treatment of salt stress with specific stresses caused changes in their expression. This study lays a theoretical foundation for further probing into the physiological functions of C. paliurus and the underlying mechanisms regarding its response to environmental stress.

Mitochondrial mRNA and the Small Subunit rRNA in Budding Yeasts Undergo 3'-End Processing at Conserved Species-specific Elements.

Respiration in eukaryotes depends on mitochondrial protein synthesis, which is performed by organelle-specific ribosomes translating organelle-encoded mRNAs. Although RNA maturation and stability are central events controlling mitochondrial gene expression, many of the molecular details in this pathway remain elusive. These include cis- and trans-regulatory factors that generate and protect the 3' ends. Here, we mapped the 3' ends of mitochondrial mRNAs of yeasts classified into multiple families of the subphylum Saccharomycotina. We found that the processing of mitochondrial 15S rRNA and mRNAs involves species-specific sequence elements, which we term 3'-end RNA processing elements (3'-RPEs). In Saccharomyces cerevisiae, the 3'-RPE has long been recognized as a conserved dodecamer sequence, which recent studies have shown to specifically interact with the nuclear genome-encoded pentatricopeptide repeat protein Rmd9. We also demonstrate that, analogous to Rmd9 in Saccharomyces cerevisiae, two Rmd9 orthologs from the Debaryomycetaceae family interact with their respective 3'-RPEs found in mRNAs and 15S rRNA. Thus, Rmd9-dependent processing of mitochondrial RNA precursors is a common mechanism among the families of the Saccharomycotina subphylum. This represents an example of mitochondrial-nuclear co-evolution. Surprisingly, we observed that 3'-RPEs often occur upstream of stop codons in complex I subunit mRNAs from yeasts of the CUG-Ser1 clade. We examined two of these mature mRNAs and found that their stop codons are indeed removed. Thus, translation of these transcripts would require a novel termination mechanism. Our findings establish Rmd9 as a key evolutionarily conserved factor in both mitochondrial mRNA metabolism and mitoribosome biogenesis in a variety of yeasts.

Anti-Jamming Power Control Algorithm for Wireless Communication Systems Based on MPC

In complex electromagnetic environments, wireless communication system reliability can be compromised by various types of jamming. To improve reliability in the presence of malicious jamming, this paper introduces an anti-jamming power control algorithm for wireless communication systems, grounded in model predictive control (MPC) principles. The algorithm models the Yescommunication system as a linear control system, using the current signal-to-jamming-and-noise ratio (SJNR) to predict future system states and transmission power over a defined time horizon. Only the first element of the optimal control sequence is then applied to manage system power. Simulation results indicate that, compared to traditional adaptive power control algorithms, the proposed algorithm responds more swiftly to jamming variations, significantly enhancing communication reliability in high-jamming environments.

Comparative Genomics and Epigenomics of Transcriptional Regulation.

Transcriptional regulation in response to diverse physiological cues involves complicated biological processes. Recent initiatives that leverage whole genome sequencing and annotation of regulatory elements significantly contribute to our understanding of transcriptional gene regulation. Advances in the data sets available for comparative genomics and epigenomics can identify evolutionarily constrained regulatory variants and shed light on noncoding elements that influence transcription in different tissues and developmental stages across species. Most epigenomic data, however, are generated from healthy subjects at specific developmental stages. To bridge the genotype-phenotype gap, future research should focus on generating multidimensional epigenomic data under diverse physiological conditions. Farm animal species offer advantages in terms of feasibility, cost, and experimental design for such integrative analyses in comparison to humans. Deep learning modeling and cutting-edge technologies in sequencing and functional screening and validation also provide great promise for better understanding transcriptional regulation in this dynamic field.

PiRNA Defense Against Endogenous Retroviruses.

Infection by retroviruses and the mobilization of transposable elements cause DNA damage that can be catastrophic for a cell. If the cell survives, the mutations generated by retrotransposition may confer a selective advantage, although, more commonly, the effect of new integrants is neutral or detrimental. If retrotransposition occurs in gametes or in the early embryo, it introduces genetic modifications that can be transmitted to the progeny and may become fixed in the germline of that species. PIWI-interacting RNAs (piRNAs) are single-stranded, 21-35 nucleotide RNAs generated by the PIWI clade of Argonaute proteins that maintain the integrity of the animal germline by silencing transposons. The sequence specific manner by which piRNAs and germline-encoded PIWI proteins repress transposons is reminiscent of CRISPR, which retains memory for invading pathogen sequences. piRNAs are processed preferentially from the unspliced transcripts of piRNA clusters. Via complementary base pairing, mature antisense piRNAs guide the PIWI clade of Argonaute proteins to transposon RNAs for degradation. Moreover, these piRNA-loaded PIWI proteins are imported into the nucleus to modulate the co-transcriptional repression of transposons by initiating histone and DNA methylation. How retroviruses that invade germ cells are first recognized as foreign by the piRNA machinery, as well as how endogenous piRNA clusters targeting the sequences of invasive genetic elements are acquired, is not known. Currently, koalas (Phascolarctos cinereus) are going through an epidemic due to the horizontal and vertical transmission of the KoRV-A gammaretrovirus. This provides an unprecedented opportunity to study how an exogenous retrovirus becomes fixed in the genome of its host, and how piRNAs targeting this retrovirus are generated in germ cells of the infected animal. Initial experiments have shown that the unspliced transcript from KoRV-A proviruses in koala testes, but not the spliced KoRV-A transcript, is directly processed into sense-strand piRNAs. The cleavage of unspliced sense-strand transcripts is thought to serve as an initial innate defense until antisense piRNAs are generated and an adaptive KoRV-A-specific genome immune response is established. Further research is expected to determine how the piRNA machinery recognizes a new foreign genetic invader, how it distinguishes between spliced and unspliced transcripts, and how a mature genome immune response is established, with both sense and antisense piRNAs and the methylation of histones and DNA at the provirus promoter.

Interpreting deep neural networks for the prediction of translation rates

BackgroundThe 5’ untranslated region of mRNA strongly impacts the rate of translation initiation. A recent convolutional neural network (CNN) model accurately quantifies the relationship between massively parallel synthetic 5’ untranslated regions (5’UTRs) and translation levels. However, the underlying biological features, which drive model predictions, remain elusive. Uncovering sequence determinants predictive of translation output may allow us to develop a more detailed understanding of translation regulation at the 5’UTR.ResultsApplying model interpretation, we extract representations of regulatory logic from CNNs trained on synthetic and human 5’UTR reporter data. We reveal a complex interplay of regulatory sequence elements, such as initiation context and upstream open reading frames (uORFs) to influence model predictions. We show that models trained on synthetic data alone do not sufficiently explain translation regulation via the 5’UTR due to differences in the frequency of regulatory motifs compared to natural 5’UTRs.ConclusionsOur study demonstrates the significance of model interpretation in understanding model behavior, properties of experimental data and ultimately mRNA translation. By combining synthetic and human 5’UTR reporter data, we develop a model (OptMRL) which better captures the characteristics of human translation regulation. This approach provides a general strategy for building more successful sequence-based models of gene regulation, as it combines global sampling of random sequences with the subspace of naturally occurring sequences. Ultimately, this will enhance our understanding of 5’UTR sequences in disease and our ability to engineer translation output.

Phoneme-by-Phoneme Speech Recognition as a Classification of Series on a Set of Sequences of Elements of Complex Objects Using an Improved Trie-Tree

Sequences, including vector sequences, are applicable in any subject domains. Sequences of scalar values or vectors (series) can be produced by higher-order sequences, for example: a series of states, or elements of complex objects. This academic paper is devoted to the application of an improved trie-tree in the classification of series on a set of sequences of elements of complex objects using the dynamic programming method. The implementation areas of dynamic programming have been considered. It has been shown that dynamic programming is adapted to multi-step operations of calculating additive (multiplicative) similarity/difference measures. It is argued that the improved trie-tree is applicable in the problem of classifying a series on a set of sequences of elements of complex objects using such similarity/difference measures. An analysis of hierarchical representations of sets of sequences has been performed. The advantages of the improved trie-tree over traditional representations of other highly branching trees have been described. A formal description of the improved trie-tree has been developed. An explanation has been given to the previously obtained data on a significant speed gain for operations of adding and deleting sequences in the improved trie-tree relative to the use of an array with an index table (24 and 380 times, respectively). The problem of phoneme-by-phoneme recognition of speech commands has been formulated as a problem of classifying series on a set of sequences of elements of complex objects and a method for its solving has been presented. A method for classifying a series on a set of sequences of elements of complex objects using the improved trie-tree is developed. The method has been studied using the example of phoneme-by-phoneme recognition with a hierarchical representation of the dictionary of speech command classes. In this method, recognition of speech commands is executed traversing the improved trie-tree that stores a set of transcriptions of speech commands – sequences of transcription symbols that denote classes of sounds. Numerical studies have shown that classifying a series as sequences of elements of complex objects increases the frequency of correct classification compared to classifying a series on a set of series, and using the improved trie-tree reduces the time spent on classification.

Eccentric p-Summing Lipschitz Operators and Integral Inequalities on Metric Spaces and Graphs

The extension of the concept of p-summability for linear operators to the context of Lipschitz operators on metric spaces has been extensively studied in recent years. This research primarily uses the linearization of the metric space M afforded by the associated Arens–Eells space, along with the duality between M and the metric dual space M# defined by the real-valued Lipschitz functions on M. However, alternative approaches to measuring distances between sequences of elements of metric spaces (essentially involved in the definition of p-summability) exist. One approach involves considering specific subsets of the unit ball of M# for computing the distances between sequences, such as the real Lipschitz functions derived from evaluating the difference in the values of the metric from two points to a fixed point. We introduce new notions of summability for Lipschitz operators involving such functions, which are characterized by integral dominations for those operators. To show the applicability of our results, in the last part of this paper, we use the theoretical tools obtained in the first part to analyze metric graphs. In particular, we show new results on the behavior of numerical indices defined on these graphs satisfying certain conditions of summability and symmetry.

Evolutionary History and Ecology of Andrena (Foveoandrena) androfovea: A New Nearctic Mining Bee (Hymenoptera, Andrenidae) Species and Subgenus.

With about 1700 described species, the mining bee genus Andrena is a rapidly diversifying lineage and one of the most species-rich groups of bees. Recent phylogenomic advances have greatly improved our understanding of the phylogeny of the genus, yet many species still await description, subgeneric assignments that are in line with their evolutionary history, as well as study of their morphology and behavior. Here we provide a comprehensive account of a newly discovered species, Andrena androfovea n. sp. We sequence the genome of the new species and include it in the presently most comprehensive phylogenomic analysis of Andrena using ultraconserved element (UCE) sequence data, comprising 264 samples and 249 species. Given the recovered phylogenetic position of the new species, we establish a new subgenus, Foveoandrena, provide a detailed morphological description, and discuss the antiquity and historical biogeography of the lineage in light of molecular divergence time estimates. Lastly, we study and document the foraging behavior of the new species with photos and video footage, and discuss the species' unusual host plant associations with Chamaesaracha and Quincula, both Solanaceae. Being likely oligolectic on these plants, we present the first documented case of an Andrena species being narrowly associated with members of this plant family. By integrating multiple lines of documentation, our study provides a particularly detailed account of species discovery and description.

Arbitrary Random Variables and Wiman’s Inequality

We study the class of random entire functions given by power series, in which the coefficients are formed as the product of an arbitrary sequence of complex numbers and two sequences of random variables. One of them is the Rademacher sequence, and the other is an arbitrary complex-valued sequence from the class of sequences of random variables, determined by a certain restriction on the growth of absolute moments of a fixed degree from the maximum of the module of each finite subset of random variables. In the paper we prove sharp Wiman–Valiron’s type inequality for such random entire functions, which for given p∈(0;1) holds with a probability p outside some set of finite logarithmic measure. We also considered another class of random entire functions given by power series with coefficients, which, as above, are pairwise products of the elements of an arbitrary sequence of complex numbers and a sequence of complex-valued random variables described above. In this case, similar new statements about not improvable inequalities are also obtained.

Identification of the HbZAR1 Gene and Its Potential Role as a Minor Gene in Response to Powdery Mildew and Anthracnose of Hevea brasiliensis

Powdery mildew and anthracnose are the main diseases of rubber trees. In recent years, there have been large outbreaks in the rubber-planting areas of Asia, seriously affecting the yield and quality of rubber latex. ZAR1 is a conserved and distinctive coiled-coil nucleotide-binding leucine-rich (CNL) repeat in the plant kingdom, playing a crucial role in disease-resistance processes. To elucidate the function of the HbZAR1 gene in rubber trees (Hevea brasiliensis), three candidate HbZAR1 genes were identified using bioinformatics methods and comprehensively analyzed. The results indicate that the HbZAR1 protein is conserved in different plant species. Examination of cis-regulatory element sequences of HbZAR1genes reveals that the HbZAR1 gene promoter exhibits a remarkable enrichment of stress, light, and hormone elements. An expression analysis shows that the expression levels of the three HbZAR1 genes are highest in the bark and lowest in latex. Three HbZAR1 genes can respond to both rubber tree Erysiphe quercicola and Colletotrichum siamense infection; especially, HbZAR1.1 and HbZAR1.2 show significant upregulation in expression levels during the early stages of infection. These findings suggest that the three HbZAR1 genes may be involved in rubber tree susceptibility to E. quercicola and C. siamense through different immune mechanisms. Subcellular localization results indicate that the HbZAR1 genes are expressed in the nucleus and plasma membrane. This study also shows that the three HbZAR1 genes and activated mutant HbZAR1.1D481V do not induce stable ROS production and cell death, suggesting possible gene degradation, functional redundancy, or acting as minor genes in disease resistance. This research provides valuable insights for further studying the function of HbZAR1 genes in rubber trees and the mechanisms of immune molecules.

ON THE BINARY SEQUENCE $(1,1,0,1,0^3,1,0^7,1,0^{15},\ldots )$

Abstract Let $\mathbb {F}$ be a field and $(s_0,\ldots ,s_{n-1})$ be a finite sequence of elements of $\mathbb {F}$ . In an earlier paper [G. H. Norton, ‘On the annihilator ideal of an inverse form’, J. Appl. Algebra Engrg. Comm. Comput.28 (2017), 31–78], we used the $\mathbb {F}[x,z]$ submodule $\mathbb {F}[x^{-1},z^{-1}]$ of Macaulay’s inverse system $\mathbb {F}[[x^{-1},z^{-1}]]$ (where z is our homogenising variable) to construct generating forms for the (homogeneous) annihilator ideal of $(s_0,\ldots ,s_{n-1})$ . We also gave an $\mathcal {O}(n^2)$ algorithm to compute a special pair of generating forms of such an annihilator ideal. Here we apply this approach to the sequence r of the title. We obtain special forms generating the annihilator ideal for $(r_0,\ldots ,r_{n-1})$ without polynomial multiplication or division, so that the algorithm becomes linear. In particular, we obtain its linear complexities. We also give additional applications of this approach.

Template switching enables chemical probing of native RNA structures.

RNAs are often studied in non-native sequence contexts to facilitate structural studies. However, seemingly innocuous changes to an RNA sequence may perturb the native structure and generate inaccurate or ambiguous structural models. To facilitate the investigation of native RNA secondary structure by selective 2' hydroxyl acylation analyzed by primer extension (SHAPE), we engineered an approach that couples minimal enzymatic steps to RNA chemical probing and mutational profiling (MaP) reverse transcription (RT) methods - a process we call template switching and mutational profiling (Switch-MaP). In Switch-MaP, RT templates and additional library sequences are added post-probing through ligation and template switching, capturing reactivities for every nucleotide. For a candidate SAM-I riboswitch, we compared RNA structure models generated by the Switch-MaP approach to those of traditional primer-based MaP, including RNAs with or without appended structure cassettes. Primer-based MaP masked reactivity data in the 5' and 3' ends of the RNA, producing ambiguous ensembles inconsistent with the conserved SAM-I riboswitch secondary structure. Structure cassettes enabled unambiguous modeling of an aptamer-only construct but introduced non-native interactions in the full length riboswitch. In contrast, Switch-MaP provided reactivity data for all nucleotides in each RNA and enabled unambiguous modeling of secondary structure, consistent with the conserved SAM-I fold. Switch-MaP is a straightforward alternative approach to primer-based and cassette-based chemical probing methods that precludes primer masking and the formation of alternative secondary structures due to non-native sequence elements.

Mechanism of bacterial predation via ixotrophy.

Ixotrophy is a contact-dependent predatory strategy of filamentous bacteria in aquatic environments for which the molecular mechanism remains unknown. We show that predator-prey contact can be established by gliding motility or extracellular assemblages we call "grappling hooks." Cryo-electron microscopy identified the grappling hooks as heptamers of a type IX secretion system substrate. After close predator-prey contact is established, cryo-electron tomography and functional assays showed that puncturing by a type VI secretion system mediated killing. Single-cell analyses with stable isotope-labeled prey revealed that prey components are taken up by the attacker. Depending on nutrient availability, insertion sequence elements toggle the activity of ixotrophy. A marine metagenomic time series shows coupled dynamics of ixotrophic bacteria and prey. We found that the mechanism of ixotrophy involves multiple cellular machineries, is conserved, and may shape microbial populations in the environment.

The NHR-23-regulated putative protease inhibitor mlt-11 gene is necessary for C. elegans cuticle structure and function.

C. elegans molting offers a powerful entry point to understanding developmentally programmed apical extracellular matrix remodeling. However, the gene regulatory network controlling this process remains poorly understood. Focusing on targets of NHR-23, a key transcription factor that drives molting, we confirmed the Kunitz family protease inhibitor gene mlt-11 as an NHR-23 target. Through reporter assays, we identified NHR-23-binding sites that are necessary and sufficient for epithelial expression. We generated a translational fusion and demonstrated that MLT-11 is localized to the cuticle and lined openings to the exterior (vulva, rectum, mouth). We created a set of strains expressing varied levels of MLT-11 by deleting endogenous cis-regulatory element sequences. Combined deletion of two cis-regulatory elements caused developmental delay, motility defects, and failure of the cuticle barrier. Inactivation of mlt-11 by RNAi produced even more pronounced defects. mlt-11 is necessary to pattern every layer of the adult cuticle, suggesting a broad patterning role prior to the formation of the mature cuticle. Together these studies provide an entry point into understanding how individual cis-regulatory elements function to coordinate expression of oscillating genes involved in molting and how MLT-11 ensures proper cuticle assembly.

Monitoring for PERV Following Xenotransplantation.

Porcine endogenous retroviruses (PERVs) are integrated in the genome of all pigs. PERV-A, PERV-B and PERV-C can be released as infectious virus particles and PERV-A and PERV-B can infect human cells in culture. PERV-C does not infect human cells, but high-titer recombinant PERV-A/C can infect them. Retroviruses are able to induce immunosuppression and/or tumors in the infected host. Numerous methods have been developed to study PERV in donor pigs. No PERV infections were observed in infection experiments as well as in preclinical and clinical xenotransplantation trials. Despite this, several strategies have been developed to prevent PERV infection of the recipient. PCR-based and immunological methods are required to screen xenotransplant recipients. Since the proviruses are integrated into the pig genome, PERV infection has to be distinguished from microchimerism, e.g., the presence of pig cells in the recipient, which is common in xenotransplantation. Sensitive PCR methods using pig short interspersed nuclear elements (SINE) sequences allow to detect pig cells easily. Virus infection can also be detected by an increase of viral genomic or mRNA in human cells. The method of choice, however, is to screen for specific antibodies against PERV using different recombinant PERV proteins, purified viruses or peptides.

Syntenic lncRNA locus exhibits DNA regulatory functions with sequence evolution

Syntenic long non-coding RNAs (lncRNAs) often show limited sequence conservation across species, prompting concern in the field. This study delves into functional signatures of syntenic lncRNAs between humans and zebrafish. Syntenic lncRNAs are highly expressed in zebrafish, with ∼90 % located near protein-coding genes, either in sense or antisense orientation. During early zebrafish development and in human embryonic stem cells (H1-hESC), syntenic lncRNA loci are enriched with cis-regulatory repressor signatures, influencing the expression of development-associated genes. In later zebrafish developmental stages and specific human cell lines, these syntenic lncRNA loci function as enhancers or transcription start sites (TSS) for protein-coding genes. Analysis of transposable elements (TEs) in syntenic lncRNA sequences revealed intriguing patterns: human lncRNAs are enriched in simple repeat elements, while their zebrafish counterparts show enrichment in LTR elements. This sequence evolution likely arises from post-rearrangement mutations that enhance DNA elements or cis-regulatory functions. It may also contribute to vertebrate innovation by creating novel transcription factor binding sites within the locus. This study highlights the conserved functionality of syntenic lncRNA loci through DNA elements, emphasizing their conserved roles across species despite sequence divergence.

TE-LSTM: A Prediction Model for Temperature Based on Multivariate Time Series Data

In the era of big data, prediction has become a fundamental capability. Current prediction methods primarily focus on sequence elements; however, in multivariate time series forecasting, time is a critical factor that must not be overlooked. While some methods consider time, they often neglect the temporal distance between sequence elements and the predicted target time, a relationship essential for identifying patterns such as periodicity, trends, and other temporal dynamics. Moreover, the extraction of temporal features is often inadequate, and discussions on how to comprehensively leverage temporal data are limited. As a result, model performance can suffer, particularly in prediction tasks with specific time requirements. To address these challenges, we propose a new model, TE-LSTM, based on LSTM, which employs a temporal encoding method to fully extract temporal features. A temporal weighting strategy is also used to optimize the integration of temporal information, capturing the temporal relationship of each element relative to the target element, and integrating it into the LSTM. Additionally, this study examines the impact of different time granularities on the model. Using the Beijing International Airport station as the study area, we applied our method to temperature prediction. Compared to the baseline model, our model showed an improvement of 0.7552% without time granularity, 1.2047% with a time granularity of 3, and 0.0953% when addressing prediction tasks with specific time requirements. The final results demonstrate the superiority of the proposed method and highlight its effectiveness in overcoming the limitations of existing approaches.