Recent advances in plant translational genomics for crop improvement.

The growing population, climate change, and limited agricultural resources put enormous pressure on agricultural systems. A plateau in crop yields is occurring and extreme weather events and urbanization threaten the livelihood of farmers. It is imperative that immediate attention is paid to addressing the increasing food demand, ensuring resilience against emerging threats, and meeting the demand for more nutritious, safer food. Under uncertain conditions, it is essential to expand genetic diversity and discover novel crop varieties or variations to develop higher and more stable yields. Genomics plays a significant role in developing abundant and nutrient-dense food crops. An alternative to traditional breeding approach, translational genomics is able to improve breeding programs in a more efficient and precise manner by translating genomic concepts into practical tools. Crop breeding based on genomics offers potential solutions to overcome the limitations of conventional breeding methods, including improved crop varieties that provide more nutritional value and are protected from biotic and abiotic stresses. Genetic markers, such as SNPs and ESTs, contribute to the discovery of QTLs controlling agronomic traits and stress tolerance. In order to meet the growing demand for food, there is a need to incorporate QTLs into breeding programs using marker-assisted selection/breeding and transgenic technologies. This chapter primarily focuses on the recent advances that are made in translational genomics for crop improvement and various omics techniques including transcriptomics, metagenomics, pangenomics, single cell omics etc. Numerous genome editing techniques including CRISPR Cas technology and their applications in crop improvement had been discussed.

Metagenomics analysis of water samples collected from the Yamuna River of Agra city, India.

Yamuna River water in Agra city of India is contaminated with toxic pollutants, including heavy metals that cause damage to the environment and human health. At present, the direct use of river water for drinking purposes and household activities lead to the direct exposure of society to the contaminants. In this study, Yamuna River water samples were collected from three different sites in Agra city during the monsoon, summer, and winter seasons. The physico-chemical parameters were estimated along with heavy metals. In physico-chemical parameter, the values found were mostly above the permissible limits. The results water samples contain high levels of cadmium, chromium, lead, and nickel above the desirable levels in most cases. The metagenomic analysis revealed that Proteobacteria, Bacteroidetes, Verrucomicrobia, Actinobacteria, and Planctobacteria were the most abundant phyla with a relative abundance of 61%, 9.34%, 5.23%, 4.64%, and 4.3%, respectively. The Comamonadaceae, the most abundant family consists of the genera involved in hydrogen oxidation, iron reduction, degraders of polycyclic aromatic hydrocarbons, and fermentation. The presence of Pseudomonas, Nitrosomonas sp., Thauera humireducens and Dechloromonas denitrificans (decomposition of sewage and organic matter) and Pseudomonas aeruginosa indicates the presence of heavy metal degrading bacteria in water sample. Functional prediction showed the presence of genes responsible for different metabolic pathways that could help developing new bioremediation strategies. The study concludes the status of water contamination, the presence of complex microbial community and suggests the futuristic use and their role in bioremediation.

Diosgenin biosynthesis investigation in medicinal herb (Tribulus terrestris) by transcriptome analysis.

Next-generation sequencing (NGS) has revolutionized the analysis of specific genes, pathways, and their regulation in various species. Tribulus terrestris L., an annual medicinal herb of Zygophyllaceae family, has gained significant attention due to its diverse medicinal properties, including anti-inflammatory, antimicrobial, and anti-cancer effects. Diosgenin, a steroidal saponin, is the major bioactive compound responsible for the medicinal importance of T. terrestris. However, there is a paucity of information regarding the genes involved in the diosgenin biosynthetic pathway in T. terrestris. To address this gap, this study aimed to identify candidate genes associated with diosgenin biosynthesis through whole transcriptome profiling. A total of ∼7.9 GB of data, comprising 482 million reads, was obtained and assembled into 148,871 unigenes. Subsequently, functional annotations were assigned to 50 % of the unigenes using sequence similarity searches against the NCBI non-redundant (NR), Uniprot, KEGG, Pfam, GO, and COG databases, primarily based on Gene Ontology and KEGG-KAAS pathways. The majority of unigenes associated with the biosynthesis of the steroidal diosgenin backbone exhibited up-regulation in the fruit, leaf, and root tissues, except the SQE gene in root. The differential expression of selected genes was further validated through quantitative real-time polymerase chain reaction (qRT-PCR). Additionally, the study identified 21,026 unigenes related to transcription factors and 15,551 unigenes containing simple sequence repeats (SSR). Notably, di-nucleotide SSR motifs exhibited a high repeat frequency. These findings greatly enhance our understanding of the diosgenin biosynthesis pathway and provide a basis for future research in molecular investigation and metabolic engineering, specifically for boosting diosgenin content.

An Improved Image Compression Algorithm Using 2D DWT and PCA with Canonical Huffman Encoding.

Of late, image compression has become crucial due to the rising need for faster encoding and decoding. To achieve this objective, the present study proposes the use of canonical Huffman coding (CHC) as an entropy coder, which entails a lower decoding time compared to binary Huffman codes. For image compression, discrete wavelet transform (DWT) and CHC with principal component analysis (PCA) were combined. The lossy method was introduced by using PCA, followed by DWT and CHC to enhance compression efficiency. By using DWT and CHC instead of PCA alone, the reconstructed images have a better peak signal-to-noise ratio (PSNR). In this study, we also developed a hybrid compression model combining the advantages of DWT, CHC and PCA. With the increasing use of image data, better image compression techniques are necessary for the efficient use of storage space. The proposed technique achieved up to 60% compression while maintaining high visual quality. This method also outperformed the currently available techniques in terms of both PSNR (in dB) and bit-per-pixel (bpp) scores. This approach was tested on various color images, including Peppers 512 × 512 × 3 and Couple 256 × 256 × 3, showing improvements by 17 dB and 22 dB, respectively, while reducing the bpp by 0.56 and 0.10, respectively. For grayscale images as well, i.e., Lena 512 × 512 and Boat 256 × 256, the proposed method showed improvements by 5 dB and 8 dB, respectively, with a decrease of 0.02 bpp in both cases.

Correlation between Estimated Average Glucose Levels Calculated from HbA1c Values and Random Blood Glucose Levels in a Cohort of Subjects.

Objective Hemoglobin A1c (HbA1c) level remains the gold standard test for the assessment of glycemic control, and it reflects the mean glucose values in the previous 3-month period. HbA1c is expressed as a percentage, whereas the monitoring and treatment of diabetes are based on blood glucose levels expressed as mg/dL. It is appropriate to make it easy for the patient to understand both random blood sugar (RBS) and estimated average glucose (eAG) expressed with the same units. This will enhance the usefulness of eAG. This article determines the statistical correlation between eAG derived from HBA1C with RBS values both in diabetic and prediabetic subjects. Methods The RBS and HbA1c levels of 178 males and 283 females (12-90 years) were obtained and the eAG levels were calculated using Nathan's regression equation. The samples were divided into four groups based on HbA1c levels-group 1: HbA1c greater than 9%, group 2: HbA1c 6.5 to 9%, group 3: HbA1c 5.7 to 6.4%; and group 4: HbA1c less than 5.7%. Results There was a statistically significant positive correlation between RBS and eAG values for the study group 1 and 2. Also, the median values of RBS and eAG showed a significant difference ( p < 0.001). Conclusion As the association between the RBS and eAG levels is strong in a fairly and poorly controlled diabetic population, reporting the eAG level together with the HbA1c level at no additional cost may assist in effective blood glucose control in clinical care. However, eAG and RBS values cannot be used interchangeably.

Diabetic post-covid mucormycosis: A dermatoglyphic prediction.

Aim: To identify the characteristic pattern/parameter among diabetic post-covid mucormycosis patients which may further help in identifying such susceptible patients in a much earlier course of the disease. Materials and Methods: The study was done with 30 diabetic patients (21 males and 9 females) admitted in RIMS Ranchi during the second wave of Covid-19 for post-covid complications. Palm and fingerprint pattern was taken by ink and pad method to measure the qualitative and quantitative parameters. Result: Diabetic post-covid mucormycosis patients were found to have predominantly whorl pattern in males, loop in females, and C-line pattern absent in 36.6%. Proximal axial triradii with ulnar deviation was 76.6%. All the ridge counts (except ab ridge count of right hand) when compared with hypothesized value were found to be significant with P value (<0.005). None of the three angles measured were found to be significant. Conclusion: All the ridge counts (except ab ridge count of right hand) were found to be a reliable parameter for the diagnosis of diabetic post-covid mucormycosis. ATD angle known to be the most reliable parameter for diagnosis of diabetes mellitus in dermatoglyphics is found to be nonreliable with respect to diabetes post-covid mucormycosis.

Genetic circuits in microbial biosensors for heavy metal detection in soil and water.

With the rapid population growth, the world is witnessing an ever-increasing demand for energy and natural resources. Consequently, soil, air, and water are polluted with diverse pollutants, including heavy metals (HM). The detection of heavy metals is necessary to remediate them, which is achieved with biosensors. Initially, these HM were detected using atomic absorption spectroscopy (AAS), emission spectroscopy, mass spectrometry, gas chromatography etc., but these were costly and time consuming which further paved a way for microbe-based biosensors. The development of genetic circuits for microbe-based biosensors has become more popular in recent years for heavy metal detection. In this review, we have especially discussed the various types of genetic circuits such as toggle switches, logic gates, and amplification modules used in these biosensors as they are used to enhance sensitivity and specificity. Genetic circuits also allow for rapid and multiple analyte detection at the same time. The use of microbial biosensors for the detection of HM in the soil as well as the water is also described below. Although with a higher success rate than classical biosensors, these microbial biosensors still have some drawbacks like bioavailability and size of the analyte which are needed to be addressed.

Cerebroplacental Ratio as a Predictor of Perinatal Outcome in Hypertensive Disorders of Pregnancy and Its Comparison With Its Constituent Doppler Indices.

Objective Doppler velocimetry is an established method of antepartum fetal surveillance in pre-eclampsia. Cerebroplacental ratio detects the centralization of fetal blood flow and the insufficiency in placental circulation. It is postulated to be a better marker of perinatal outcome than either vessel Doppler alone. The current study aims to assess the cerebroplacental ratio as a predictor of adverse perinatal outcomes and compare it to the systolic/diastolic (S/D) ratio of umbilical artery (UA) and middle cerebral artery (MCA) in hypertensive disorders of pregnancy. Material and methods The present prospective observational cohort study included 100 patients with hypertensive disorders of pregnancies between 32 and 37 weeks. Ultrasound with Doppler was done and the following parameters were assessed: fetal biometry, amniotic fluid index, umbilical artery pulsatility index, middle cerebral artery pulsatility index, S/D ratio of umbilical artery, S/D ratio of middle cerebral artery, and cerebroplacental ratio. Sensitivity, specificity, positive and negative predictive values were calculated for the cerebroplacental ratio and S/D ratios of umbilical and middle cerebral arteries. McNemar's test was used for the comparison of sensitivity and specificity. Results Thirty-two patients had an abnormal cerebroplacental ratio. Adverse perinatal outcomes such as a cesarean section for fetal distress, small for gestational age, APGAR < 7 at 1 and 5 minutes, NICU admission, and perinatal mortality were more in the group with abnormal cerebraplacental ratio and the difference was statistically significant. Conclusion The cerebroplacental ratio is a more reliable predictor of adverse perinatal outcomes and should be routinely calculated during obstetrical Doppler for antepartum fetal surveillance in case of hypertensive disorders of pregnancy.It suggested that the cerebroplacental ratio may be calibrated in the software ofthe Doppler ultrasonography machine for routine use in high-risk pregnancies.

FedMSA: A Model Selection and Adaptation System for Federated Learning.

Federated Learning (FL) enables multiple clients to train a shared model collaboratively without sharing any personal data. However, selecting a model and adapting it quickly to meet user expectations in a large-scale FL application with heterogeneous devices is challenging. In this paper, we propose a model selection and adaptation system for Federated Learning (FedMSA), which includes a hardware-aware model selection algorithm that trades-off model training efficiency and model performance base on FL developers' expectation. Meanwhile, considering the expected model should be achieved by dynamic model adaptation, FedMSA supports full automation in building and deployment of the FL task to different hardware at scale. Experiments on benchmark and real-world datasets demonstrate the effectiveness of the model selection algorithm of FedMSA in real devices (e.g., Raspberry Pi and Jetson nano).

Anatomical Study of the Variants of the Extrapelvic Part of the Pudendal Nerve.

Background A comprehensive understanding of the anatomy of the extra pelvic course of the pudendal nerve and its variations is crucial when undertaking perineal and perirectal procedures to safeguard the integrity of the extrapelvic segment of the pudendal nerve and its branches. So we aimed to identify the changes in the pudendal nerve's extrapelvic branching pattern before it enters the pudendal canal and its relationships and connections. Materials and Methods A cross-sectional descriptive study was carried out on 26 formalin embalmed adult human cadavers between 20 to 65 years (16 male and 10 female) of north Indian origin. Anatomical course, variations, and connections of the pudendal nerve before entering the pudendal canal were noted. Results The extrapelvic course of the pudendal nerve was examined in 52 hemipelves (26 cadavers) after meticulous dissection. Single pudendal nerve trunk (type I) was identified in 51.9% of hemipelves. Two trunked pudendal nerve with inferior gluteal nerve piercing the sacrospinous ligament (type IIa) was observed in 13.5% of hemipelves. 23.1% of hemipelves exhibited two trunked pudendal nerves with inferior gluteal nerve not piercing the sacrospinous ligament(type IIb). Three trunked pudendal nerve (type III) was observed in 11.5% of hemipelves. In 14/52 hemipelves (26.9%), communication with the sciatic nerve was noted, whereas, in 38/52 hemipelves (73.1%), no communication with the sciatic nerve was present. Conclusion The extrapelvic course of the pudendal nerve may present with an earlier subdivision or even an aberrant connection with the sciatic nerve. These anatomical variations of the extra pelvic course of the pudendal nerve, its variations, and connections are essential for all surgeons and anesthetists operating in the perineal and perirectal region to avoid unwanted complications.

Dynamic Data Streams for Time-Critical IoT Systems in Energy-Aware IoT Devices Using Reinforcement Learning.

Thousands of energy-aware sensors have been placed for monitoring in a variety of scenarios, such as manufacturing, control systems, disaster management, flood control and so on, requiring time-critical energy-efficient solutions to extend their lifetime. This paper proposes reinforcement learning (RL) based dynamic data streams for time-critical IoT systems in energy-aware IoT devices. The designed solution employs the Q-Learning algorithm. The proposed mechanism has the potential to adjust the data transport rate based on the amount of renewable energy resources that are available, to ensure collecting reliable data while also taking into account the sensor battery lifetime. The solution was evaluated using historical data for solar radiation levels, which shows that the proposed solution can increase the amount of transmitted data up to 23%, ensuring the continuous operation of the device.

Upcoming progress of transcriptomics studies on plants: An overview.

Transcriptome sequencing or RNA-Sequencing is a high-resolution, sensitive and high-throughput next-generation sequencing (NGS) approach used to study non-model plants and other organisms. In other words, it is an assembly of RNA transcripts from individual or whole samples of functional and developmental stages. RNA-Seq is a significant technique for identifying gene predictions and mining functional analysis that improves gene ontology understanding mechanisms of biological processes, molecular functions, and cellular components, but there is limited information available on this topic. Transcriptomics research on different types of plants can assist researchers to understand functional genes in better ways and regulatory processes to improve breeding selection and cultivation practices. In recent years, several advancements in RNA-Seq technology have been made for the characterization of the transcriptomes of distinct cell types in biological tissues in an efficient manner. RNA-Seq technologies are briefly introduced and examined in terms of their scientific applications. In a nutshell, it introduces all transcriptome sequencing and analysis techniques, as well as their applications in plant biology research. This review will focus on numerous existing and forthcoming strategies for improving transcriptome sequencing technologies for functional gene mining in various plants using RNA- Seq technology, based on the principles, development, and applications.

Delineation of molecular interactions of plant growth promoting bacteria induced ß-1,3-glucanases and guanosine triphosphate ligand for antifungal response in rice: a molecular dynamics approach.

BACKGROUND: The plant growth is influenced by multiple interactions with biotic (microbial) and abiotic components in their surroundings. These microbial interactions have both positive and negative effects on plant. Plant growth promoting bacterial (PGPR) interaction could result in positive growth under normal as well as in stress conditions. METHODS: Here, we have screened two PGPR's and determined their potential in induction of specific gene in host plant to overcome the adverse effect of biotic stress caused by Magnaporthe grisea, a fungal pathogen that cause blast in rice. We demonstrated the glucanase protein mode of action by performing comparative modeling and molecular docking of guanosine triphosphate (GTP) ligand with the protein. Besides, molecular dynamic simulations have been performed to understand the behavior of the glucanase-GTP complex. RESULTS: The results clearly showed that selected PGPR was better able to induce modification in host plant at morphological, biochemical, physiological and molecular level by activating the expression of ß-1,3-glucanases gene in infected host plant. The docking results indicated that Tyr75, Arg256, Gly258, and Ser223 of glucanase formed four crucial hydrogen bonds with the GTP, while, only Val220 found to form hydrophobic contact with ligand. CONCLUSIONS: The PGPR able to induce ß-1,3-glucanases gene in host plant upon pathogenic interaction and ß-1,3-glucanases form complex with GTP by hydrophilic interaction for induction of defense cascade for acquiring resistance against Magnaporthe grisea.

Synthetic Biology in Plants, a Boon for Coming Decades.

Recently an enormous expansion of knowledge is seen in various disciplines of science. This surge of information has given rise to concept of interdisciplinary fields, which has resulted in emergence of newer research domains, one of them is 'Synthetic Biology' (SynBio). It captures basics from core biology and integrates it with concepts from the other areas of study such as chemical, electrical, and computational sciences. The essence of synthetic biology is to rewire, re-program, and re-create natural biological pathways, which are carried through genetic circuits. A genetic circuit is a functional assembly of basic biological entities (DNA, RNA, proteins), created using typical design, built, and test cycles. These circuits allow scientists to engineer nearly all biological systems for various useful purposes. The development of sophisticated molecular tools, techniques, genomic programs, and ease of nucleic acid synthesis have further fueled several innovative application of synthetic biology in areas like molecular medicines, pharmaceuticals, biofuels, drug discovery, metabolomics, developing plant biosensors, utilization of prokaryotic systems for metabolite production, and CRISPR/Cas9 in the crop improvement. These applications have largely been dominated by utilization of prokaryotic systems. However, newer researches have indicated positive growth of SynBio for the eukaryotic systems as well. This paper explores advances of synthetic biology in the plant field by elaborating on its core components and potential applications. Here, we have given a comprehensive idea of designing, development, and utilization of synthetic biology in the improvement of the present research state of plant system.

Prophylactic administration of podophyllotoxin and rutin combination assists the revival of radiation-induced hematopoietic suppression in lethally irradiated mice.

Hematopoietic syndrome contributes to mortality after exposure to high doses of low LET radiation. In this context, we have earlier demonstrated the potential of G-003 M (a combination of podophyllotoxin and rutin) in alleviating radiation-induced bone marrow suppression. Similarly, we here demonstrate that G-003 M protected mice from death (>83% protection) and increased the populations of CD 34 (Cluster of differentiation 34) as well as CD 117 (Cluster of differentiation 117) positive cell population and their colony forming capacity. This was accompanied with increase in the serum titre of granulocyte colony stimulating factor (G-CSF), granulocyte-macrophage colony stimulating factor (GM-CSF). Interestingly, G-003 M lowered down the titre of fms-like tyrosine kinase (Flt-3) ligands. Our results furthermore demonstrates that G-003 M facilitated the nuclear translocation of ß-catenin and upregulated the expression of Wnt 10b. Conditioning of animal with G-003 M activated the expression of survivin, inhibited the activation of Caspase-3 in CD 34/117+ progenitor stem cells and protected the bone marrow vascularity and splenic colonies in lethally irradiated animals, which collectively promoted hemopoietic recovery in lethally irradiated mice.

Development of efficient synthetic promoters derived from pararetrovirus suitable for translational research.

MAIN CONCLUSION: In this study, useful hybrid promoters were developed for efficient ectopic gene expression in monocot and dicot plants, and they hold strong prominence in both transgenic research and biotech industries. This study deals with developing novel synthetic promoters derived from Rice Tungro Bacilliform Virus (RTBV) and Mirabilis Mosaic Virus (MMV). Despite numerous availability, there is a severe scarcity of promoters universally suitable for monocot and dicot plants. Here, eight chimeric promoter constructs were synthesized as gBlocks gene fragments through domain swapping and hybridization by incorporating important domains of previously characterized RTBV and MMV promoters. The developed promoter constructs were assessed for transient GUS expression in tobacco protoplast (Xanthi Brad) and agro-infiltrated tobacco, petunia, rice and pearl millet. Protoplast expression analysis showed that two promoter constructs, namely pUPMA-RP1-MP1GUS and pUPMA-RP4-MP1GUS exhibited 3.56 and 2.5 times higher activities than that of the CaMV35S promoter. We had observed the similar type of expression patterns of these promoters in agroinfiltration-based transient studies. RP1-MP1 and RP4-MP1 promoters exhibited 1.87- and 1.68-fold increase expression in transgenic tobacco plants; while, a 1.95-fold increase was found in RP1-MP1 transgenic rice plants when compared their activities with CaMV35S promoter. Furthermore, on evaluating these promoter constructs for their expression in the bacterial system, pUPMA-RP1-MP1GFP was found to have the highest GFP expression. Moreover, the promoter construct was also evaluated for its capacity to express the HMP3 gene. Biobeads of encapsulated bacterial cells expressing HMP3 gene under control of the pUPMA-RP4-MP1 promoter were found to reduce 72.9% copper and 29.2% zinc concentration from wastewater. Our results had demonstrated that the developed promoter constructs could be used for translational research in dicot, monocot plants and bacterial systems for efficient gene expression.

In silico characterization of synthetic promoters designed from mirabilis mosaic virus and rice tungro bacilliform virus.

CaMV35S is the most extensively used promoter for ectopic gene expression in plant system. However, multiple use of this promoter possesses several limitation i.e. homologous based gene silencing and differential suitability in monocot and dicot plants. The strength of a promoter is defined by the presence of cis-acting elements and trans acting nucleic binding factors, thus its strength can be regulated by changing the architecture of these regulatory elements. In the present study, eight hybrid promoters were designed from two parareteroviruses, rice tungro bacilliform viruses (RTBV) and mirabilis mosaic virus (MMV). The eight hybrid promoters, along with parental promoters were characterized for the presence of functional cis-elements and transcription factor binding sites (TFBS), which were predicted using bioinformatics tools such as PLACE and Matinspector. Presence of mirabilis mosaic virus modules for specific functions and over-represented modules was determined using Model inspector. A broad range of cis-elements (85), TFBS (1471) was obtained. Presence of Dehydration responsive element binding factors, Apetala 2 (AP2), WRKY, DNA binding with one finger DOF (DOFF) motifs had shown the functional relevance of these designed promoters with abiotic stress inducibility. In addition to these stress regulating TFBS, the presence of some enhancer like motifs such as P$OCSE, P$TERE, P$TODS, P$ASRC had shown the functional relevance of these promoters as a strong candidate for enhanced expression of ectopic gene.

Gummatous Syphilis: A Rare Entity Mimicking Carcinoma Penis.

OBJECTIVE: To describe a rare case of gummatous syphilis of the penis with urethrocutaneous fistula mimicking penile carcinoma causing a diagnostic dilemma. METHOD: A 54 year old man presented with an ulcerative lesion on glans penis. Patient was managed with partial penectomy in view of erosive growth giving rise to urethrocutaneous fistula. RESULTS: Histopathology showed granulation tissue, necrotizing vasculitis and epithelioid cell granuloma. Immunohistochemistry stained positive for Treponema and patient was treated accordingly. CONCLUSION: Syphilis is rarely encountered in daily clinical practice in the penicillin era. Despite a negative serology and the clinical picture highly suggestive of malignancy, the histopathology helped in clinching the rare diagnosis.

Temporal Convolutional Networks for the Advance Prediction of ENSO.

El Niño-Southern Oscillation (ENSO), which is one of the main drivers of Earth's inter-annual climate variability, often causes a wide range of climate anomalies, and the advance prediction of ENSO is always an important and challenging scientific issue. Since a unified and complete ENSO theory has yet to be established, people often use related indicators, such as the Niño 3.4 index and southern oscillation index (SOI), to predict the development trends of ENSO through appropriate numerical simulation models. However, because the ENSO phenomenon is a highly complex and dynamic model and the Niño 3.4 index and SOI mix many low- and high-frequency components, the prediction accuracy of current popular numerical prediction methods is not high. Therefore, this paper proposed the ensemble empirical mode decomposition-temporal convolutional network (EEMD-TCN) hybrid approach, which decomposes the highly variable Niño 3.4 index and SOI into relatively flat subcomponents and then uses the TCN model to predict each subcomponent in advance, finally combining the sub-prediction results to obtain the final ENSO prediction results. Niño 3.4 index and SOI reanalysis data from 1871 to 1973 were used for model training, and the data for 1984-2019 were predicted 1 month, 3 months, 6 months, and 12 months in advance. The results show that the accuracy of the 1-month-lead Niño 3.4 index prediction was the highest, the 12-month-lead SOI prediction was the slowest, and the correlation coefficient between the worst SOI prediction result and the actual value reached 0.6406. Furthermore, the overall prediction accuracy on the Niño 3.4 index was better than that on the SOI, which may have occurred because the SOI contains too many high-frequency components, making prediction difficult. The results of comparative experiments with the TCN, LSTM, and EEMD-LSTM methods showed that the EEMD-TCN provides the best overall prediction of both the Niño 3.4 index and SOI in the 1-, 3-, 6-, and 12-month-lead predictions among all the methods considered. This result means that the TCN approach performs well in the advance prediction of ENSO and will be of great guiding significance in studying it.