昼夜节律系统是生物体内一种约24小时周期的内源性调节机制，通过转录-翻译反馈回路调控基因的周期性表达，从而维持机体稳态。大量研究表明，昼夜节律系统是代谢综合征、神经退行性疾病及恶性肿瘤等多种病理进程的重要分子靶标，其基因表达的昼夜节律改变可能导致疾病的发生和进展。研究基因表达的昼夜节律，有望揭示复杂疾病发生发展的分子机制，为疾病的临床诊断和靶向治疗提供新的思路。然而，现有公共数据资源规模有限且分散，缺乏统一的标准化格式与注释体系，导致多源数据的整合分析十分困难。此外，基因表达的昼夜节律分析主要依赖于统计学方法，这些方法通常假设数据满足特定的数学分布，难以有效捕捉复杂的周期节律模式，从而导致节律信号识别的灵敏度不足，易出现假阴性结果。数据资源和分析方法的不足，已极大地阻碍了科学家对昼夜节律与疾病进展双向调控机制的深入解析。

为了解决上述挑战，本文首先开发了CircaKB，一个跨物种的昼夜节律基因综合知识库。CircaKB是首个在全基因组范围内，针对15个代表性物种的基因表达振荡模式进行系统注释的知识库。目前，CircaKB包含226个时间序列转录组数据集，涵盖多种组织、器官和细胞系。此外，CircaKB集成了12种计算模型，以支持可靠的数据分析，并识别基因表达中的振荡模式及其变化。通过在小鼠肝脏昼夜节律识别等多个案例中的应用，验证了其在实际研究中的实用性和有效性。CircaKB还为用户提供了强大的功能，包括便捷的搜索、快速浏览、强大的可视化和自定义上传。我们相信，CircaKB将成为昼夜节律研究领域宝贵的工具和资源，有助于发现疾病预防和治疗的新靶标。CircaKB现已开放访问，网址为：https://cdsic.njau.edu.cn/CircaKB。

其次，为了提高基因表达昼夜节律识别的精度，我们设计并开发了首个昼夜节律分析大语言模型CircaLLM。该模型整合了数值、位置和时间戳嵌入，并结合Transformer编码器的时序特征编码，从而精准捕获时间序列数据的周期性特征，实现对基因表达振荡模式及其变化的精准识别与分类。为了证明CircaLLM模型的有效性，我们生成了18个人工数据集对模型进行训练；然后，基于CircaKB平台筛选15个转录组数据集全面测试了模型的预测性能。实验结果表明，CircaLLM在人工合成数据和真实数据上均表现优异。与六种主流昼夜节律分析算法相比，CircaLLM在多个关键指标上显著优于其他算法，特别是在多时间分辨率基因节律检测和复杂节律模式分析方面。通过跨物种条件下的昼夜节律基因检测和间歇性缺氧对小鼠肺相关基因昼夜节律的影响分析等三个应用案例的验证，我们进一步证实了CircaLLM模型的鲁棒性和实用性，为该模型在更广泛的生物医学研究领域的应用奠定了基础。

综上所述，本文提出的 CircaKB知识库和 CircaLLM模型为昼夜节律研究提供了强有力的工具支持，有望推动昼夜节律机制的深入解析及其在疾病诊断与治疗中的应用，并为相关研究提供新的视角和方法。

The circadian system, an endogenous regulatory mechanism with intrinsic ~24-hour periodicity, maintains homeostasis by modulating the cyclical expression of genes through transcriptional-translational feedback loops. Numerous studies have demonstrated that the circadian system serves as a crucial molecular target in various pathological processes, including metabolic syndrome, neurodegenerative diseases, and malignant tumors, with alterations in the circadian rhythm of gene expression potentially contributing to disease onset and progression. Investigating the circadian rhythm of gene expression holds promise for elucidating the molecular mechanisms underlying the development of complex diseases, thereby providing novel insights for clinical diagnosis and targeted therapy. However, the existing public data resources are limited in scale and fragmented, lacking a unified standardized format and annotation system, which poses significant challenges for the integration and analysis of multi-source data. Furthermore, the analysis of the circadian rhythm of gene expression primarily relies on statistical methods, which often assume that the data conforms to specific mathematical distributions, making it difficult to effectively capture complex periodic rhythm patterns. This, in turn, leads to insufficient sensitivity in rhythm signal identification and a tendency for false-negative results. The limitations in data resources and analytical methods have significantly hindered scientists' in-depth understanding of the bidirectional regulatory mechanisms between circadian rhythms and disease progression.

To overcome these challenges, this study initiated the development of CircaKB, a comprehensive knowledgebase of circadian genes across multiple species. CircaKB is the first knowledgebase that provides systematic annotations of the oscillatory patterns of gene expression at a genome-wide level for 15 representative species. Currently, CircaKB contains 226 time-course transcriptome datasets, covering a wide variety of tissues, organs, and cell lines. In addition, CircaKB integrates 12 computational models to facilitate reliable data analysis and identify oscillatory patterns and their variations in gene expression. Its practicality and effectiveness in real-world research have been validated through applications in several case studies, such as the identification of circadian rhythms in mouse livers. CircaKB also offers powerful functionalities to its users, including easy search, fast browsing, strong visualization, and custom upload. We believe that CircaKB will be a valuable tool and resource for the circadian research community, contributing to the identification of new targets for disease prevention and treatment. We have made CircaKB freely accessible at https://cdsic.njau.edu.cn/CircaKB.

Furthermore, to enhance the accuracy of circadian gene expression identification, we designed and developed CircaLLM, the first large language model for circadian rhythm analysis. This model combines numerical, positional, and timestamp embeddings with Transformer encoding to capture periodic characteristics of time-series data. This enables accurate identification and classification of oscillatory patterns and their variations in gene expression. To demonstrate the effectiveness of the CircaLLM model, we trained the model on 18 artificial datasets. Subsequently, we conducted a comprehensive evaluation of the model's predictive performance using 15 transcriptomic datasets selected from the CircaKB platform. The experimental results showed that CircaLLM performed exceptionally well on both synthetic and real-world data. Compared to six mainstream circadian rhythm analysis algorithms, CircaLLM significantly outperformed the others across several key metrics, particularly in the detection of multi-time resolution gene rhythms and the analysis of complex rhythm patterns. Through validation via three application cases, including the detection of circadian rhythm genes across different species and the analysis of the impact of intermittent hypoxia on the circadian rhythm of mouse lung-related genes, we further confirmed the robustness and practicality of the CircaLLM model, laying the foundation for its application in a broader range of biomedical research fields.

In summary, the CircaKB knowledgebase and the CircaLLM model presented in this study provide robust tool support for circadian rhythm research. They have the potential to facilitate the in-depth elucidation of circadian rhythm mechanisms and their application in disease diagnosis and treatment, while also offering novel perspectives and methodologies for related research.

[1] Agostinelli F, Ceglia N, Shahbaba B, et al. What time is it? Deep learning approaches for circadian rhythms[J]. Bioinformatics, 2016, 32(19):3051.

[2] Ahdesmaki M, Lahdesmaki H, Pearson R, et al. Robust detection of periodic time series measured from biological systems[J]. BMC Bioinformatics, 2005, 6:117.

[3] Ameur A, Zaghlool A, Halvardson J, et al. Total RNA sequencing reveals nascent transcription and widespread co-transcriptional splicing in the human brain[J]. Nature Structural & Molecular Biology, 2011, 18(12):1435-1440.

[4] Andersen J V, Schousboe A, Verkhratsky A. Astrocyte energy and neurotransmitter metabolism in Alzheimer's disease: Integration of the glutamate/GABA-glutamine cycle[J]. Progress in Neurobiology, 2022, 217:102331.

[5] Arul M, Kareem A. Applications of shapelet transform to time series classification of earthquake, wind and wave data[J]. Engineering Structures, 2021, 228:111564.

[6] Athar A, Fullgrabe A, George N, et al. ArrayExpress update - from bulk to single-cell expression data[J]. Nucleic Acids Research, 2019, 47(D1):D711-D715.

[7] Bolshette N, Ibrahim H, Reinke H, et al. Circadian regulation of liver function: from molecular mechanisms to disease pathophysiology[J]. Nature Reviews Gastroenterology & Hepatology, 2023, 20(11):695-707.

[8] Bonnot T, Nagel D H. Time of the day prioritizes the pool of translating mRNAs in response to heat stress[J]. Plant Cell, 2021, 33(7):2164-2182.

[9] Brown A V, Conners S I, Huang W, et al. A new decade and new data at SoyBase, the USDA-ARS soybean genetics and genomics database[J]. Nucleic Acids Research, 2021, 49(D1):D1496-D1501.

[10] Castellana S, Biagini T, Petrizzelli F, et al. RhythmicDB: A Database of Predicted Multi-Frequency Rhythmic Transcripts[J]. Frontiers in Genetics, 2022, 13:882044.

[11] Ch R, Rey G, Ray S, et al. Rhythmic glucose metabolism regulates the redox circadian clockwork in human red blood cells[J]. Nature Communications, 2021, 12(1):377.

[12] Chen C Y, Logan R W, Ma T, et al. Effects of aging on circadian patterns of gene expression in the human prefrontal cortex[J]. Proceedings of the National Academy of Sciences of the United States of America, 2016, 113(1):206-211.

[13] Chen J, Zhou J, Li M, et al. Systematic analysis of circadian disrupting substances with a high-throughput zebrafish circadian behavior screening approach[J]. Science of the Total Environment, 2023, 904:167037.

[14] Chen W, Shi K. Multi-scale Attention Convolutional Neural Network for time series classification[J]. Neural Networks, 2021, 136:126-140.

[15] Chen Y, Chen L, Lun A T L, et al. edgeR v4: powerful differential analysis of sequencing data with expanded functionality and improved support for small counts and larger datasets[J]. Nucleic Acids Research, 2025, 53(2):gkaf018.

[16] Chou S J, Wang C, Sintupisut N, et al. Analysis of spatial-temporal gene expression patterns reveals dynamics and regionalization in developing mouse brain[J]. Scientific Reports, 2016, 6:19274.

[17] Clough E, Barrett T, Wilhite S E, et al. NCBI GEO: archive for gene expression and epigenomics data sets: 23-year update[J]. Nucleic Acids Research, 2024, 52(D1):D138-D144.

[18] Cornelissen G. Cosinor-based rhythmometry[J]. Theoretical Biology and Medical Modelling, 2014, 11:16.

[19] Cui P, Zhong T, Wang Z, et al. Identification of human circadian genes based on time course gene expression profiles by using a deep learning method[J]. Biochimica et Biophysica Acta-Molecular Basis of Disease, 2018, 1864(6 Pt B):2274-2283.

[20] Cunningham F, Achuthan P, Akanni W, et al. Ensembl 2019[J]. Nucleic Acids Research, 2019, 47(D1):D745-D751.

[21] De Leeuw M, Verhoeve S I, Van Der Wee N J A, et al. The role of the circadian system in the etiology of depression[J]. Neuroscience and Biobehavioral Reviews, 2023, 153:105383.

[22] Deckard A, Anafi R C, Hogenesch J B, et al. Design and analysis of large-scale biological rhythm studies: a comparison of algorithms for detecting periodic signals in biological data[J]. Bioinformatics, 2013, 29(24):3174-3180.

[23] Del Olmo M, Sporl F, Korge S, et al. Inter-layer and inter-subject variability of diurnal gene expression in human skin[J]. NAR Genomics and Bioinformatics, 2022, 4(4):lqac097.

[24] Dempster A, Schmidt D F, Webb G I. MiniRocket: A Very Fast (Almost) Deterministic Transform for Time Series Classification[C]. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual Event, Singapore, 2021:248–257.

[25] Ding H, Meng L, Liu A C, et al. Likelihood-based tests for detecting circadian rhythmicity and differential circadian patterns in transcriptomic applications[J]. Briefings in Bioinformatics, 2021, 22(6).

[26] Ding H, Zhang Y, Meng L, et al. CosinorTest: An R Shiny App for Cosinor-model-based circadian and differential analysis in transcriptomic applications[J]. bioRxiv, 2024:2024.11.06.622324.

[27] Dobin A, Davis C A, Schlesinger F, et al. STAR: ultrafast universal RNA-seq aligner[J]. Bioinformatics, 2013, 29(1):15-21.

[28] Dong Y, Li G, Tao Y, et al. FAN: Fourier Analysis Networks[J]. arXiv preprint arXiv:2410.02675, 2024.

[29] Duncan M J. Interacting influences of aging and Alzheimer's disease on circadian rhythms[J]. European Journal of Neuroscience, 2020, 51(1):310-325.

[30] Ector C, Schmal C, Didier J, et al. Time-of-day effects of cancer drugs revealed by high-throughput deep phenotyping[J]. Nature Communications, 2024, 15(1):7205.

[31] Emms D M, Kelly S. OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy[J]. Genome Biology, 2015, 16(1):157.

[32] Fan Y, Li L, Sun S. Powerful and accurate detection of temporal gene expression patterns from multi-sample multi-stage single-cell transcriptomics data with TDEseq[J]. Genome Biology, 2024, 25(1):96.

[33] Farzan M, Schnitzler C E, Vasilieva N, et al. BACE2, a beta -secretase homolog, cleaves at the beta site and within the amyloid-beta region of the amyloid-beta precursor protein[J]. Proceedings of the National Academy of Sciences of the United States of America, 2000, 97(17):9712-9717.

[34] Federico A, Saarimaki L A, Serra A, et al. Microarray Data Preprocessing: From Experimental Design to Differential Analysis[J]. Methods in Molecular Biology, 2022, 2401:79-100.

[35] Foumani N M, Tan C W, Webb G I, et al. Improving position encoding of transformers for multivariate time series classification[J]. Data mining and knowledge discovery, 2024, 38(1):22-48.

[36] Gabriel B M, Altıntaş A, Smith J A, et al. Disrupted circadian oscillations in type 2 diabetes are linked to altered rhythmic mitochondrial metabolism in skeletal muscle[J]. Science Advances, 2021, 7(43):eabi9654.

[37] Gardiner L J, Rusholme-Pilcher R, Colmer J, et al. Interpreting machine learning models to investigate circadian regulation and facilitate exploration of clock function[J]. Proceedings of the National Academy of Sciences of the United States of America, 2021, 118(32):e2103070118.

[38] Geneva N, Zabaras N. Transformers for modeling physical systems[J]. Neural Networks, 2022, 146:272-289.

[39] Glynn E F, Chen J, Mushegian A R. Detecting periodic patterns in unevenly spaced gene expression time series using Lomb-Scargle periodograms[J]. Bioinformatics, 2006, 22(3):310-316.

[40] Grandi F C, Modi H, Kampman L, et al. Chromatin accessibility profiling by ATAC-seq[J]. Nature Protocols, 2022, 17(6):1518-1552.

[41] Hamilton J P, Brose J, Buell C R. SpudDB: a database for accessing potato genomic data[J]. Genetics, 2025, 229(3):iyae205.

[42] Harris C, Czaja K. Can Circadian Eating Pattern Adjustments Reduce Risk or Prevent Development of T2D?[J]. Nutrients, 2023, 15(7):1762.

[43] Hastings M H, Brancaccio M, Gonzalez-Aponte M F, et al. Circadian Rhythms and Astrocytes: The Good, the Bad, and the Ugly[J]. Annual Review of Neuroscience, 2023, 46:123-143.

[44] Helfrich-Forster C. Light input pathways to the circadian clock of insects with an emphasis on the fruit fly Drosophila melanogaster[J]. Journal Of Comparative Physiology A-neuroethology Sensory Neural And Behavioral Physiology, 2020, 206(2):259-272.

[45] Herzog V A, Reichholf B, Neumann T, et al. Thiol-linked alkylation of RNA to assess expression dynamics[J]. Nature Methods, 2017, 14(12):1198-1204.

[46] Hidalgo S, Anguiano M, Tabuloc C A, et al. Seasonal cues act through the circadian clock and pigment-dispersing factor to control EYES ABSENT and downstream physiological changes[J]. Current Biology, 2023, 33(5):1006-1008.

[47] Hou R, Tomalin L E, Suarez-Farinas M. cosinoRmixedeffects: an R package for mixed-effects cosinor models[J]. BMC Bioinformatics, 2021, 22(1):553.

[48] Hsu P Y, Harmer S L. Circadian phase has profound effects on differential expression analysis[J]. Public Library of Science One, 2012, 7(11):e49853.

[49] Hu E J, Shen Y, Wallis P, et al. Lora: Low-rank adaptation of large language models[J]. International Conference on Learning Representations, 2022, 1(2):3.

[50] Hughes M E, Abruzzi K C, Allada R, et al. Guidelines for Genome-Scale Analysis of Biological Rhythms[J]. Journal of Biological Rhythms, 2017, 32(5):380-393.

[51] Hughes M E, Ditacchio L, Hayes K R, et al. Harmonics of circadian gene transcription in mammals[J]. Public Library of Science Genetics, 2009, 5(4):e1000442.

[52] Hughes M E, Hogenesch J B, Kornacker K. JTK_CYCLE: an efficient nonparametric algorithm for detecting rhythmic components in genome-scale data sets[J]. Journal of Biological Rhythms, 2010, 25(5):372-380.

[53] Hughey J J, Butte A J. Differential Phasing between Circadian Clocks in the Brain and Peripheral Organs in Humans[J]. Journal of Biological Rhythms, 2016, 31(6):588-597.

[54] Hüsken M, Stagge P. Recurrent neural networks for time series classification[J]. Neurocomputing, 2003, 50:223-235.

[55] Hutchison A L, Allada R, Dinner A R. Bootstrapping and Empirical Bayes Methods Improve Rhythm Detection in Sparsely Sampled Data[J]. Journal of Biological Rhythms, 2018, 33(4):339-349.

[56] Jones J R, Chaturvedi S, Granados-Fuentes D, et al. Circadian neurons in the paraventricular nucleus entrain and sustain daily rhythms in glucocorticoids[J]. Nature Communications, 2021, 12(1):5763.

[57] Jones P, Binns D, Chang H Y, et al. InterProScan 5: genome-scale protein function classification[J]. Bioinformatics, 2014, 30(9):1236-1240.

[58] Kim D, Langmead B, Salzberg S L. HISAT: a fast spliced aligner with low memory requirements[J]. Nature Methods, 2015, 12(4):357-360.

[59] Kim G I, Chung K. Extraction of Features for Time Series Classification Using Noise Injection[J]. Sensors, 2024, 24(19):6402.

[60] Kim H Y, Kim H S. Podoplanin depletion in tonsil-derived mesenchymal stem cells induces cellular senescence via regulation of the p16(Ink4a)/Rb pathway[J]. Cell Communication and Signaling, 2024, 22(1):323.

[61] Kim J, Kim H, Kim H, et al. A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges[J]. Artificial Intelligence Review, 2025, 58(7):216.

[62] Kingma D P. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014.

[63] Kinsella R J, Kahari A, Haider S, et al. Ensembl BioMarts: a hub for data retrieval across taxonomic space[J]. Database-the Journal Of Biological Databases And Curation, 2011, 2011:bar030.

[64] Kolberg L, Raudvere U, Kuzmin I, et al. g:Profiler-interoperable web service for functional enrichment analysis and gene identifier mapping (2023 update)[J]. Nucleic Acids Research, 2023, 51(W1):W207-W212.

[65] Koritala B S C, Lee Y Y, Gaspar L S, et al. Obstructive sleep apnea in a mouse model is associated with tissue-specific transcriptomic changes in circadian rhythmicity and mean 24-hour gene expression[J]. Public Library of Science Biology, 2023, 21(5):e3002139.

[66] Kozomara A, Birgaoanu M, Griffiths-Jones S. miRBase: from microRNA sequences to function[J]. Nucleic Acids Research, 2019, 47(D1):D155-D162.

[67] Kumar A, Vaca-Dempere M, Mortimer T, et al. Brain-muscle communication prevents muscle aging by maintaining daily physiology[J]. Science, 2024, 384(6695):563-572.

[68] Laloum D, Robinson-Rechavi M. Methods detecting rhythmic gene expression are biologically relevant only for strong signal[J]. Public Library of Science Computational Biology, 2020, 16(3):e1007666.

[69] Langmead B, Salzberg S L. Fast gapped-read alignment with Bowtie 2[J]. Nature Methods, 2012, 9(4):357-359.

[70] Li B, Dewey C N. RSEM: accurate transcript quantification from RNA-Seq data with or without a reference genome[J]. BMC Bioinformatics, 2011, 12:323.

[71] Li D, Yang R, Miao Z, et al. BioClock: a web server and database aimed for interpreting circadian rhythm[C]. Intelligent Systems for Molecular Biology 2010 meeting, 2010.

[72] Li G, Guo L, Zhang R, et al. Transgait: Multimodal-based gait recognition with set transformer[J]. Applied Intelligence, 2023, 53(2):1535-1547.

[73] Li H, Yang Y, Li B, et al. Comprehensive Analysis Reveals the Potential Diagnostic Value of Biomarkers Associated With Aging and Circadian Rhythm in Knee Osteoarthritis[J]. Orthopaedic Surgery, 2025, 17(3):922-938.

[74] Li J Z, Bunney B G, Meng F, et al. Circadian patterns of gene expression in the human brain and disruption in major depressive disorder[J]. Proceedings of the National Academy of Sciences of the United States of America, 2013, 110(24):9950-9955.

[75] Li S, Shui K, Zhang Y, et al. CGDB: a database of circadian genes in eukaryotes[J]. Nucleic Acids Research, 2017, 45(D1):D397-D403.

[76] Li X, Shi L, Zhang K, et al. CirGRDB: a database for the genome-wide deciphering circadian genes and regulators[J]. Nucleic Acids Research, 2018, 46(D1):D64-D70.

[77] Lim A S, Klein H U, Yu L, et al. Diurnal and seasonal molecular rhythms in human neocortex and their relation to Alzheimer's disease[J]. Nature Communications, 2017, 8:14931.

[78] Liu Z, Zhang L, Wu J, et al. Machine learning-based classification of circadian rhythm characteristics for mild cognitive impairment in the elderly[J]. Frontiers in Public Health, 2022, 10:1036886.

[79] Lundell L S, Parr E B, Devlin B L, et al. Time-restricted feeding alters lipid and amino acid metabolite rhythmicity without perturbing clock gene expression[J]. Nature Communications, 2020, 11(1):4643.

[80] Malhan D, Yalcin M, Schoenrock B, et al. Skeletal muscle gene expression dysregulation in long-term spaceflights and aging is clock-dependent[J]. NPJ Microgravity, 2023, 9(1):30.

[81] Mayor-Ruiz C, Dominguez O, Fernandez-Capetillo O. Trap(Seq): An RNA Sequencing-Based Pipeline for the Identification of Gene-Trap Insertions in Mammalian Cells[J]. Journal of Molecular Biology, 2017, 429(18):2780-2789.

[82] Mei W, Jiang Z, Chen Y, et al. Genome-wide circadian rhythm detection methods: systematic evaluations and practical guidelines[J]. Briefings in Bioinformatics, 2021, 22(3):bbaa135.

[83] Meyer N, Harvey A G, Lockley S W, et al. Circadian rhythms and disorders of the timing of sleep[J]. Lancet, 2022, 400(10357):1061-1078.

[84] Micikevicius P, Narang S, Alben J, et al. Mixed precision training[J]. arXiv preprint arXiv:1710.03740, 2017.

[85] Moller-Levet C S, Archer S N, Bucca G, et al. Effects of insufficient sleep on circadian rhythmicity and expression amplitude of the human blood transcriptome[J]. Proceedings of the National Academy of Sciences of the United States of America, 2013, 110(12):E1132-1141.

[86] Morel M, Achard C, Kulpa R, et al. Time-series averaging using constrained dynamic time warping with tolerance[J]. Pattern Recognition, 2018, 74:77-89.

[87] Mortazavi A, Williams B A, Mccue K, et al. Mapping and quantifying mammalian transcriptomes by RNA-Seq[J]. Nature Methods, 2008, 5(7):621-628.

[88] Nassan M, Videnovic A. Circadian rhythms in neurodegenerative disorders[J]. Nature Reviews Neurology, 2022, 18(1):7-24.

[89] Nassiri K, Akhloufi M. Transformer models used for text-based question answering systems[J]. Applied Intelligence, 2023, 53(9):10602-10635.

[90] Ng J W X, Tan Q W, Ferrari C, et al. Diurnal.plant.tools: Comparative Transcriptomic and Co-expression Analyses of Diurnal Gene Expression of the Archaeplastida Kingdom[J]. Plant Cell Physiology, 2020, 61(1):212-220.

[91] O'leary N A, Wright M W, Brister J R, et al. Reference sequence (RefSeq) database at NCBI: current status, taxonomic expansion, and functional annotation[J]. Nucleic Acids Research, 2016, 44(D1):D733-745.

[92] Parsons R, Parsons R, Garner N, et al. CircaCompare: a method to estimate and statistically support differences in mesor, amplitude and phase, between circadian rhythms[J]. Bioinformatics, 2020, 36(4):1208-1212.

[93] Pizarro A, Hayer K, Lahens N F, et al. CircaDB: a database of mammalian circadian gene expression profiles[J]. Nucleic Acids Research, 2013, 41(Database issue):D1009-1013.

[94] Ritchie M E, Phipson B, Wu D, et al. limma powers differential expression analyses for RNA-sequencing and microarray studies[J]. Nucleic Acids Research, 2015, 43(7):e47.

[95] Robinson M D, Oshlack A. A scaling normalization method for differential expression analysis of RNA-seq data[J]. Genome Biology, 2010, 11(3):R25.

[96] Ruan W, Yuan X, Eltzschig H K. Circadian rhythm as a therapeutic target[J]. Nature Reviews Drug Discovery, 2021, 20(4):287-307.

[97] Sakai H, Lee S S, Tanaka T, et al. Rice Annotation Project Database (RAP-DB): an integrative and interactive database for rice genomics[J]. Plant Cell Physiology, 2013, 54(2):e6.

[98] Saliba A E, Westermann A J, Gorski S A, et al. Single-cell RNA-seq: advances and future challenges[J]. Nucleic Acids Research, 2014, 42(14):8845-8860.

[99] Samad M, Agostinelli F, Sato T, et al. CircadiOmics: circadian omic web portal[J]. Nucleic Acids Research, 2022, 50(W1):W183-W190.

[100] Samanta S, Ali S A. Impact of circadian clock dysfunction on human health[J]. Exploration of Neuroscience, 2022, 1(1):4-30.

[101] Sancar A, Van Gelder R N. Clocks, cancer, and chronochemotherapy[J]. Science, 2021, 371(6524):eabb0738.

[102] Satam H, Joshi K, Mangrolia U, et al. Next-Generation Sequencing Technology: Current Trends and Advancements[J]. Biology-Basel, 2023, 12(7):997.

[103] Sayers E W, Bolton E E, Brister J R, et al. Database resources of the national center for biotechnology information[J]. Nucleic Acids Research, 2022, 50(D1):D20-D26.

[104] Sciarra F, Franceschini E, Palmieri G, et al. Complex gene-dependent and-independent mechanisms control daily rhythms of hematopoietic cells[J]. Biomed Pharmacother, 2025, 183:117803.

[105] Seney M L, Cahill K, Enwright J F, 3rd, et al. Diurnal rhythms in gene expression in the prefrontal cortex in schizophrenia[J]. Nature Communications, 2019, 10(1):3355.

[106] She X, Zhai Y, Henao R, et al. Adaptive Multi-Channel Event Segmentation and Feature Extraction for Monitoring Health Outcomes[J]. IEEE Transactions on Biomedical Engineering, 2021, 68(8):2377-2388.

[107] Shim J W. Enhancing cross entropy with a linearly adaptive loss function for optimized classification performance[J]. Scientific Reports, 2024, 14(1):27405.

[108] Singer J M, Hughey J J. LimoRhyde: A Flexible Approach for Differential Analysis of Rhythmic Transcriptome Data[J]. Journal of Biological Rhythms, 2019, 34(1):5-18.

[109] Singh G B. Biological Databases [M]//Singh G B. Fundamentals of Bioinformatics and Computational Biology: Methods and Exercises in MATLAB. Cham; Springer Nature Switzerland. 2025: 71-112.

[110] Sivaji A, Tzuaan S S. Website user experience (UX) testing tool development using Open Source Software (OSS)[C]. 2012 Southeast Asian Network of Ergonomics Societies Conference (SEANES), 2012:1-6.

[111] Smith L N. Cyclical learning rates for training neural networks[C]. 2017 IEEE winter conference on applications of computer vision (WACV), 2017:464-472.

[112] Stark R, Grzelak M, Hadfield J. RNA sequencing: the teenage years[J]. Nature Reviews Genetics, 2019, 20(11):631-656.

[113] Stenson P D, Mort M, Ball E V, et al. The Human Gene Mutation Database (HGMD((R))): optimizing its use in a clinical diagnostic or research setting[J]. Human Genetics, 2020, 139(10):1197-1207.

[114] Su W, Wang Y, Li K, et al. Hybrid token transformer for deep face recognition[J]. Pattern Recognition, 2023, 139:109443.

[115] Sun S Y, Chen G H. Treatment of Circadian Rhythm Sleep-Wake Disorders[J]. Current Neuropharmacology, 2022, 20(6):1022-1034.

[116] Tahara Y, Shibata S. Circadian rhythms of liver physiology and disease: experimental and clinical evidence[J]. Nature Reviews Gastroenterology & Hepatology, 2016, 13(4):217-226.

[117] Talamanca L, Gobet C, Naef F. Sex-dimorphic and age-dependent organization of 24-hour gene expression rhythms in humans[J]. Science, 2023, 379(6631):478-483.

[118] Tam S, Tsao M S, Mcpherson J D. Optimization of miRNA-seq data preprocessing[J]. Briefings in Bioinformatics, 2015, 16(6):950-963.

[119] Thaben P F, Westermark P O. Detecting rhythms in time series with RAIN[J]. Journal of Biological Rhythms, 2014, 29(6):391-400.

[120] Thaben P F, Westermark P O. Differential rhythmicity: detecting altered rhythmicity in biological data[J]. Bioinformatics, 2016, 32(18):2800-2808.

[121] Tong Y, Liu J, Yu L, et al. Technology investigation on time series classification and prediction[J]. PeerJ Computer Science, 2022, 8:e982.

[122] Trapnell C, Pachter L, Salzberg S L. TopHat: discovering splice junctions with RNA-Seq[J]. Bioinformatics, 2009, 25(9):1105-1111.

[123] Trapnell C, Williams B A, Pertea G, et al. Transcript assembly and quantification by RNA-Seq reveals unannotated transcripts and isoform switching during cell differentiation[J]. Nature Biotechnology, 2010, 28(5):511-515.

[124] Ventresca C, Mohamed W, Russel W A, et al. Machine learning analyses reveal circadian clock features predictive of anxiety among UK biobank participants[J]. Scientific Reports, 2023, 13(1):22304.

[125] Wang J. An Intuitive Tutorial to Gaussian Process Regression[J]. Computing in Science & Engineering, 2023, 25(4):4-11.

[126] Wang J, Li S, Ji W, et al. A T-CNN time series classification method based on Gram matrix[J]. Scientific Reports, 2022a, 12(1):15731.

[127] Wang L, Wang Y, Chen C, et al. BLM knockdown promotes cells autophagy via p53-AMPK-mTOR pathway in triple negative breast cancer cells[J]. Molecular Biology Reports, 2025, 52(1):243.

[128] Wang M, Qin F. A TCN-Linear Hybrid Model for Chaotic Time Series Forecasting[J]. Entropy, 2024, 26(6):467.

[129] Wang Q. Semantic Analysis Technology of English Translation Based on Deep Neural Network[J]. Computational Intelligence and Neuroscience, 2022, 2022:1176943.

[130] Wang Y, Peng D, Huang Y, et al. Podoplanin: Its roles and functions in neurological diseases and brain cancers[J]. Frontiers in Pharmacology, 2022b, 13:964973.

[131] Wang Z, Xie X, Liu S, et al. scFseCluster: a feature selection-enhanced clustering for single-cell RNA-seq data[J]. Life Science Alliance, 2023, 6(12):e202302103.

[132] Wangdi K, Singhasivanon P, Silawan T, et al. Development of temporal modelling for forecasting and prediction of malaria infections using time-series and ARIMAX analyses: a case study in endemic districts of Bhutan[J]. Malaria Journal, 2010, 9:251.

[133] Watson A, Mazumder A, Stewart M, et al. Technology for microarray analysis of gene expression[J]. Current Opinion in Biotechnology, 1998, 9(6):609-614.

[134] Wen S, Ma D, Zhao M, et al. Spatiotemporal single-cell analysis of gene expression in the mouse suprachiasmatic nucleus[J]. Nature Neuroscience, 2020, 23(3):456-467.

[135] Wichert S, Fokianos K, Strimmer K. Identifying periodically expressed transcripts in microarray time series data[J]. Bioinformatics, 2004, 20(1):5-20.

[136] Wijnen H, Naef F, Young M W. Molecular and statistical tools for circadian transcript profiling[J]. Methods in Enzymology, 2005, 393:341-365.

[137] Wilson D, Passmore S, Tang Y, et al. Bidirectional Long Short-Term Memory Networks for Rapid Fault Detection in Marine Hydrokinetic Turbines[C]. 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), 2018:495-500.

[138] Wood S H, Hindle M M, Mizoro Y, et al. Circadian clock mechanism driving mammalian photoperiodism[J]. Nature Communications, 2020, 11(1):4291.

[139] Wu G, Anafi R C, Hughes M E, et al. MetaCycle: an integrated R package to evaluate periodicity in large scale data[J]. Bioinformatics, 2016, 32(21):3351-3353.

[140] Wu G, Lee Y Y, Gulla E M, et al. Short-term exposure to intermittent hypoxia leads to changes in gene expression seen in chronic pulmonary disease[J]. Elife, 2021, 10:e63003.

[141] Wu G, Zhu J, He F, et al. Gene and genome parameters of mammalian liver circadian genes (LCGs)[J]. Public Library of Science One, 2012, 7(10):e46961.

[142] Wu G, Zhu J, Yu J, et al. Evaluation of five methods for genome-wide circadian gene identification[J]. Journal of Biological Rhythms, 2014, 29(4):231-242.

[143] Wu H. Revisiting Attention for Multivariate Time Series Forecasting[J]. arXiv preprint arXiv:2407.13806, 2024.

[144] Wu Y, Lian C, Zeng Z, et al. An Aggregated Convolutional Transformer Based on Slices and Channels for Multivariate Time Series Classification[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2023, 7(3):768-779.

[145] Xiao Z, Xu X, Xing H, et al. RTFN: A robust temporal feature network for time series classification[J]. Information Sciences, 2021, 571:65-86.

[146] Yanai S, Endo S. PDE3 Inhibitors Repurposed as Treatments for Age-Related Cognitive Impairment[J]. Molecular Neurobiology, 2019, 56(6):4306-4316.

[147] Yang R, Su Z. Analyzing circadian expression data by harmonic regression based on autoregressive spectral estimation[J]. Bioinformatics, 2010, 26(12):i168-174.

[148] Yeap Y J, Kandiah N, Nizetic D, et al. BACE2: A Promising Neuroprotective Candidate for Alzheimer's Disease[J]. Journal of Alzheimer's Disease, 2023, 94(s1):S159-S171.

[149] Yi X, Lu H, Liu X, et al. Unravelling the enigma of the human microbiome: Evolution and selection of sequencing technologies[J]. Microbial Biotechnology, 2024, 17(1):e14364.

[150] Yu F, Zhang Y, Cheng C, et al. Poly(A)-seq: A method for direct sequencing and analysis of the transcriptomic poly(A)-tails[J]. Public Library of Science One, 2020, 15(6):e0234696.

[151] Zeng Y, Guo Z, Wu M, et al. Circadian rhythm regulates the function of immune cells and participates in the development of tumors[J]. Cell Death Discovery, 2024, 10(1):199.

[152] Zhang C, Zhao H, Cai Y, et al. Cyclic nucleotide phosphodiesterase 1C contributes to abdominal aortic aneurysm[J]. Proceedings of the National Academy of Sciences of the United States of America, 2021, 118(31):e2107898118.

[153] Zhao L, Mo C, Ma J, et al. LSTM-MFCN: A time series classifier based on multi-scale spatial–temporal features[J]. Computer Communications, 2022, 182:52-59.

[154] Zhao Y, Li M C, Konate M M, et al. TPM, FPKM, or Normalized Counts? A Comparative Study of Quantification Measures for the Analysis of RNA-seq Data from the NCI Patient-Derived Models Repository[J]. Journal of Translational Medicine, 2021, 19(1):269.

[155] Zhou Y, Wang X, Zhang M, et al. MPCE: a maximum probability based cross entropy loss function for neural network classification[J]. IEEE Access, 2019, 7:146331-146341.

[156] Zong W, Seney M L, Ketchesin K D, et al. Experimental design and power calculation in omics circadian rhythmicity detection using the cosinor model[J]. Statistics in Medicine, 2023, 42(18):3236-3258.