Splice site recognition - deciphering Exon-Intron transitions for genetic insights using Enhanced integrated Block-Level gated LSTM model.

Bioinformatics is a contemporary interdisciplinary area focused on analyzing the growing number of genome sequences. Gene variants are differences in DNA sequences among individuals within a population. Splice site recognition is a crucial step in the process of gene expression, where the coding sequences of genes are joined together to form mature messenger RNA (mRNA). These genetic variants that disrupt genes are believed to be the primary reason for neuro-developmental disorders like ASD (Autism Spectrum Disorder) is a neuro-developmental disorder that is diagnosed in individuals, families, and society and occurs as the developmental delay in one among the hundred genes that are associated with these disorders. Missense variants, premature stop codons, or deletions alter both the quality and quantity of encoded proteins. Predicting genes within exons and introns presents main challenges, such as dealing with sequencing errors, short reads, incomplete genes, overlapping, and more. Although many traditional techniques have been utilized in creating an exon prediction system, the primary challenge lies in accurately identifying the length and spliced strand location classification of exons in conjunction with introns. From now on, the suggested approach utilizes a Deep Learning algorithm to analyze intricate and extensive genomic datasets. M-LSTM is utilized to categorize three binary combinations (EI as 1, IE as 2, and none as 3) using spliced DNA strands. The M-LSTM system is able to sequence extensive datasets, ensuring that long information can be stored without any impact on the current input or output. This enables it to recognize and address long-term connections and problems with rapidly increasing gradients. The proposed model is compared internally with Naïve Bayes and Random Forest to assess its efficacy. Additionally, the proposed model's performance is forecasted by utilizing probabilistic parameters like recall, F1-score, precision, and accuracy to assess the effectiveness of the proposed system.

Cascade-EC Network: Recognition of Gastrointestinal Multiple Lesions Based on EfficientNet and CA_stm_Retinanet.

Capsule endoscopy (CE) is non-invasive and painless during gastrointestinal examination. However, capsule endoscopy can increase the workload of image reviewing for clinicians, making it prone to missed and misdiagnosed diagnoses. Current researches primarily concentrated on binary classifiers, multiple classifiers targeting fewer than four abnormality types and detectors within a specific segment of the digestive tract, and segmenters for a single type of anomaly. Due to intra-class variations, the task of creating a unified scheme for detecting multiple gastrointestinal diseases is particularly challenging. A cascade neural network designed in this study, Cascade-EC, can automatically identify and localize four types of gastrointestinal lesions in CE images: angiectasis, bleeding, erosion, and polyp. Cascade-EC consists of EfficientNet for image classification and CA_stm_Retinanet for lesion detection and location. As the first layer of Cascade-EC, the EfficientNet network classifies CE images. CA_stm_Retinanet, as the second layer, performs the target detection and location task on the classified image. CA_stm_Retinanet adopts the general architecture of Retinanet. Its feature extraction module is the CA_stm_Backbone from the stack of CA_stm Block. CA_stm Block adopts the split-transform-merge strategy and introduces the coordinate attention. The dataset in this study is from Shanghai East Hospital, collected by PillCam SB3 and AnKon capsule endoscopes, which contains a total of 7936 images of 317 patients from the years 2017 to 2021. In the testing set, the average precision of Cascade-EC in the multi-lesions classification task was 94.55%, the average recall was 90.60%, and the average F1 score was 92.26%. The mean mAP@ 0.5 of Cascade-EC for detecting the four types of diseases is 85.88%. The experimental results show that compared with a single target detection network, Cascade-EC has better performance and can effectively assist clinicians to classify and detect multiple lesions in CE images.

Laser Sources for Traditional and Spectral Flow Cytometry.

Lasers for light scattering measurement and fluorescence excitation are essential components of all flow cytometers. Flow cytometers now typically rely on multiple laser wavelengths allowing excitation of a constantly increasing variety of fluorescent probes. The expanding use of spectral flow cytometry to increase the magnitude of multiparametric analysis is also changing the significance of laser choice in cytometry. In this chapter, we review the lasers available for flow cytometry and provide guidance in choosing laser wavelengths and characteristics to best match the needs of modern cell analysis by both conventional and spectral cytometry. We also discuss the recent advances in laser technology as the push to expand the palette of laser wavelength for cytometry continues.

Modeling of liquid-liquid hollow fiber supported membrane equilibrium including the non-ideality of the aqueous and organic phases in the recovery systems of radionuclides in sulphate-halide/aliquat-336 in O-xylene.

Study of modeling of L/LHFSLM equilibrium based on the Non-ideality of the Aqueous and Organic Phases in the Recovery of 152+154Eu in H2SO4-Halides/Aliquat-336 in 20% kerosene as feeding phase at pH 3.78-4.55, by the ratio 89.7%,while separation of 90Sr and 134Cs there was a problem between them by using hollow HFSLM only, the reason for that the organic solvents affect the rate of reaction in the Diamino-1,2-cyclohexane/tetraacetic acid (DCTA) as stripping phase concentration from 0.15 to 0.55 mol/L. The system has been developed; this led to the extraction of elements in the same time. The Matlab software program was introduced to obtain some mathematical parameters like, standard deviation (SD), equilibrium constant Kex and standard deviation coefficient (SDC).

Mathematical definition and rules of the splitting/merging patterns in bundles of human peripheral nerve segment.

Accurately measuring the spatial extension distance of nerve bundles in completing a split/merge is impossible because no clear mathematical definition exists for the starting and ending positions in nerve-bundle splitting/merging. We manually count the number of nerve-bundle splits/merges in long nerve segments, which is labor-intensive, inefficient, and prone to counting errors. Currently, the mathematics are unclear for the nerve-bundle diameter before and after splitting/merging. This paper explores these problems and proposes nerve-bundle splitting/merging rules. Based on the method of defining the beginning and ending positions of nerve-bundle splitting/merging, we explored the mathematical law of equivalent diameter of nerve bundles before and after splitting/merging. The experimental results revealed that the moving average of circularity of nerve bundle accurately defines the beginning and ending positions of nerve-bundle splitting/merging. The diameter of the nerve bundles before and after split/merge approximately conforms to the principles of the Da Vinci formula. The proposed automatic counting algorithm based on centroid offset matching obtains the number of split/merged nerve bundles in the sequence scan images with 100 % accuracy. The mathematical definition of the starting and ending positions of nerve-bundle splitting/merging proposed in this paper is accurate and strict and is the foundation of subsequent research. The proposed automatic counting algorithm based on centroid offset matching (ACA-COM) can accurately and efficiently count the number of times the nerve bundles split and merge in sequential images. The mathematical law satisfied by the diameter of the nerve bundles before and after splitting/merging reflects that the nerve bundles tend to have better capability to resist breaking.

Investigating the impact of HMI on drivers' merging performance in intelligent connected vehicle environment.

Intelligent Connected Vehicle (ICV) is considered one of the most promising active safety technologies to address current transportation challenges. Human-Machine Interface (HMI) plays a vital role in enhancing user driving experience with ICV technology. However, in an ICV environment, drivers may exhibit excessive reliance on HMI, resulting in diminished proactive observation and analysis of the road environment, and subsequently leading to a potential decrease in drivers' situational awareness. This reduced situational awareness may consequently lead to a decline in their overall engagement in driving tasks. Therefore, to comprehensively investigate the impact of HMI on driver performance in various ICV environments, this study incorporates three distinct HMI systems: Control group, Warning group, and Guidance group. The Control group provides basic information, the Warning group adds front vehicle icon and real-time headway information, while the Guidance group further includes speed and voice guidance features. Additionally, the study considers three types of mainline vehicle gaps, namely, 30 m, 20 m, and 15 m. Through our self-developed ICV testing platform, we conducted driving simulation experiments on 43 participants in a freeway interchange merging area. The findings reveal that, drivers in the Guidance group exhibited explicit acceleration while driving on the ramp. Drivers in the Guidance and Warning groups demonstrated smoother speed change trends and lower mean longitudinal acceleration upon entering the acceleration lane compared to the Control group, indicating a preference for more cautious driving strategies. During the pre-merging section, drivers in the Warning group demonstrated a more cautious and smooth longitudinal acceleration. The Guidance group's HMI system assisted drivers in better speed control during the post-merging section. Differences in mainline vehicle gaps did not significantly impact the merging positions of participants across the three HMI groups. Drivers in the Guidance group merged closest to the left side of the taper section, while the Control group merged farthest. The research findings offer valuable insights for developing dynamic human-machine interfaces tailored to specific driving scenarios in the environment of ICVs. Future research should investigate the effects of various HMIs on driver safety, workload, energy efficiency, and overall driving experience. Conducting real-world tests will further validate the findings obtained from driving simulators.

Characterizing the initial effects of the single accreditation system merge on the ophthalmology residency match.

INTRODUCTION: In 2020, the American Osteopathic Association merged its residency programs into one system under the Accreditation Council for Graduate Medical Education (ACGME). The effects of this transition on the ophthalmology match is not fully understood. The purpose of this study is to assess the early impact of the transition to ACGME accreditation on MD, DO, and IMG representation in ophthalmology residency programs. MATERIALS AND METHODS: Information about resident medical degree and resident medical school was gathered from ophthalmology residency program websites from a resident class before and after the Transition. Additionally, the medical degree of residency program directors (PD) was collected to analyze MD vs DO leadership in ophthalmology residency programs and to further stratify resident data to identify any trends in PD preference for different medical graduates. RESULTS: Data was obtained for 915 ophthalmology residents in 110 residency programs that met the study's inclusion criteria. Of these programs, 102 were allopathic with MD leadership, 1 was allopathic with DO leadership, 3 were osteopathic with MD leadership, and 4 were osteopathic with DO leadership. Overall, MD representation increased while DO and IMG representation decreased although not significantly. For both classes analyzed, DO and IMG representation was disproportionately low. DISCUSSION: The transition to ACGME accreditation seems to have primarily harmed DO and IMG applicants in the ophthalmology match while benefitting MDs. Various factors such as loss of protected residency positions for DO applicants and the closure of osteopathic ophthalmology residency programs are likely reasons to blame for this decrease in osteopathic representation.

Application of 3D MERGE sequence versus 3D SPACE STIR sequence in the examination of lumbar disc herniation / 中国医学物理学杂志

Objective To compare the performances of 3D MERGE sequence and 3D SPACE STIR sequence in detecting lumbar disc herniation(LDH).Methods The clinical data and MRI data of 135 LDH patients admitted between January 2020 and November 2022 were analyzed retrospectively.All patients were examined using conventional MRI,3D MERGE sequence and 3D SPACE STIR sequence.The consistency of 3D MERGE sequence and 3D SPACE STIR sequence in measuring the diameter of nerve root was analyzed,and the image quality parameters[signal-to-noise ratio(SNR),contrast-to-noise ratio(CNR)]and image definition score of the two sequences were evaluated.Results There were no statistically significant differences in L3-S1 nerve root diameters measured by 3D MERGE sequence and 3D SPACE STIR sequence(P＞0.05),and the diameters of L3,L4,L5 and S1 measured by the two sequences showed high correlations(r=0.957,0.986,0.975,0.972,P＜0.05).Compared with 3D SPACE STIR sequence,3D MERGE sequence had higher SNR and CNR,scored better on image definition,and displayed nerve root more clearly(P＜0.05).Conclusion 3D MERGE sequence and 3D SPACE STIR sequence have high consistency in the measurement of LDH nerve root diameter.3D MERGE sequence can display the anatomical morphology of nerve root more clearly as compared with 3D SPACE STIR sequence,and the former one has higher image quality.

Speech Perception Improvement Algorithm Based on a Dual-Path Long Short-Term Memory Network.

Current deep learning-based speech enhancement methods focus on enhancing the time-frequency representation of the signal. However, conventional methods can lead to speech damage due to resolution mismatch problems that emphasize only specific information in the time or frequency domain. To address these challenges, this paper introduces a speech enhancement model designed with a dual-path structure that identifies key speech characteristics in both the time and time-frequency domains. Specifically, the time path aims to model semantic features hidden in the waveform, while the time-frequency path attempts to compensate for the spectral details via a spectral extension block. These two paths enhance temporal and spectral features via mask functions modeled as LSTM, respectively, offering a comprehensive approach to speech enhancement. Experimental results show that the proposed dual-path LSTM network consistently outperforms conventional single-domain speech enhancement methods in terms of speech quality and intelligibility.

Chain Hospitals in the Health Industry: A Scoping Review of Principles and Definitions.

In order to provide quality and cost-effective health care, hospitals have used a variety of organizational models. Chain hospitals are one type of organization and service delivery model. Based on the diversity, multiplicity, and ambiguous nature of concepts related to chain hospitals, this study is an attempt to explain the concepts and components of such hospitals. Five main databases were searched for this purpose. Scopus, PubMed, WOS, ProQuest, and Wiley library databases were accessed from inception to September 2022. English-language studies describing chain hospital models were included. Two independent authors screened full-text papers, and data were extracted using a self-designed form. A thematic analysis was used to identify key components of the chain hospitals. A total of 38 papers from 8472 documents met the inclusion criteria and were included in the study. Among the selected studies, there were 23 quantitative studies, 6 qualitative studies, 5 mixed studies, 3 review studies, and 1 gray report. A review of the results revealed 55 different definitions of chain hospitals, as well as 6 main components and 16 subcomponents. Among the extracted components, 60% were related to the organization dimension, 15% to governance, 9% to decision rights, 8% to policies and procedures, and 4% to service delivery. In order to launch a multihospital system involving chain hospitals in a country, it is necessary first to define the concept of this hospital. The study's findings should be used by policymakers and officials in each country before implementing an inter-hospital cooperation system (MHS, chain hospital, etc.). Future researchers may also find inspiration in the study's findings and focus on these hospitals' establishment, effectiveness, and financial effects.

Image Preprocessing with Enhanced Feature Matching for Map Merging in the Presence of Sensing Error.

Autonomous robots heavily rely on simultaneous localization and mapping (SLAM) techniques and sensor data to create accurate maps of their surroundings. When multiple robots are employed to expedite exploration, the resulting maps often have varying coordinates and scales. To achieve a comprehensive global view, the utilization of map merging techniques becomes necessary. Previous studies have typically depended on extracting image features from maps to establish connections. However, it is important to note that maps of the same location can exhibit inconsistencies due to sensing errors. Additionally, robot-generated maps are commonly represented in an occupancy grid format, which limits the availability of features for extraction and matching. Therefore, feature extraction and matching play crucial roles in map merging, particularly when dealing with uncertain sensing data. In this study, we introduce a novel method that addresses image noise resulting from sensing errors and applies additional corrections before performing feature extraction. This approach allows for the collection of features from corresponding locations in different maps, facilitating the establishment of connections between different coordinate systems and enabling effective map merging. Evaluation results demonstrate the significant reduction of sensing errors during the image stitching process, thanks to the proposed image pre-processing technique.

Differential networks for processing structural dependencies in human language: linguistic capacity vs. memory-based ordering.

Surface linear (left-to-right) arrangements of human languages are actually an amalgam of the core language system and systems that are not inherently related to language. It has been widely recognized that an unbounded array of hierarchically structured linguistic expressions is generated by the simplest combinatorial operation "Merge," and the notion of Merge-generability has been proposed as a key feature that characterizes structural dependencies among linguistic elements. Here we tested Merge-generable dependencies by using a Subject-Predicate matching task, which required both linguistic capacity and short-term memory. We used three types of dependency: Nesting, Crossing, and Grouping as the control. The Nesting dependency is totally Merge-generable, while the Crossing dependency requires some additional processes for memory-based ordering. In order to identify the regions employed for these two dependencies, we directly compared cortical responses to the sentence stimuli (with noun phrases and an adverb as the first half of stimuli, and with verbs as the latter) using functional magnetic resonance imaging (fMRI), and the following results were obtained. First, for the Nesting - Crossing contrast, significant activations were observed in the bilateral lateral premotor cortices (LPMCs) and inferior frontal gyri, left middle temporal gyrus, and bilateral angular/supramarginal gyri, indicating engagement of the syntax-related networks. In contrast, the Crossing - Nesting contrast showed focal activations in the left fusiform gyrus, lingual gyrus, and middle occipital gyrus (L. FG/LG/MOG). Secondly, for the first half of the Nesting stimuli, signal changes in the bilateral LPMCs were well fitted with the estimates of computational costs to search the workspace and to select items (Σ operations). Moreover, for the latter half of the Crossing stimuli, the signal changes in the L. FG/LG/MOG were differentially fitted with the estimates of loads related to the ordering of elements/words (numbers of Ordering). Thirdly, these fitting models were by far more likely than the exchanged estimates between bilateral LPMCs and L. FG/LG/MOG, confirming a double dissociation for primary processes with Σ and Ordering. In conclusion, these results indicate that separate cortical networks are differentially employed, and their careful elucidation will provide further insights and challenges.

Climate concerns and the future of nonfungible tokens: Leveraging environmental benefits of the Ethereum Merge.

The world is facing a formidable climate predicament due to elevated greenhouse gas (GHG) emissions from fossil fuels. The preceding decade has also witnessed a dramatic surge in blockchain-based applications, constituting yet another substantial energy consumer. Nonfungible tokens (NFTs) are one such application traded on Ethereum (ETH) marketplaces that have raised concerns about their climate impacts. The transition of ETH from proof of work (PoW) to proof of stake (PoS) is a step toward reducing the carbon footprint of the NFT sector. However, this alone will not address the climate impacts of the growing blockchain industry. Our analysis indicates that NFTs can cause yearly GHG emissions of up to 18% of the peak under the energy-intensive PoW algorithm. This results in a significant carbon debt of 4.56 Mt CO2-eq by the end of this decade, equivalent to CO2 emissions from a 600-MW coal-fired power plant in 1 y which would meet residential power demand in North Dakota. To mitigate the climate impact, we propose technological solutions to sustainably power the NFT sector using unutilized renewable energy sources in the United States. We find that 15% utilization of curtailed solar and wind power in Texas or 50 MW of potential hydropower from existing nonpowered dams can support the exponential growth of NFT transactions. In summary, the NFT sector has the potential to generate significant GHG emissions, and measures are necessary to mitigate its climate impact. The proposed technological solutions and policy support can help promote climate-friendly development in the blockchain industry.

Exploring the neurobiology of Merge at a basic level: insights from a novel artificial grammar paradigm.

Introduction: Human language allows us to generate an infinite number of linguistic expressions. It's proposed that this competence is based on a binary syntactic operation, Merge, combining two elements to form a new constituent. An increasing number of recent studies have shifted from complex syntactic structures to two-word constructions to investigate the neural representation of this operation at the most basic level. Methods: This fMRI study aimed to develop a highly flexible artificial grammar paradigm for testing the neurobiology of human syntax at a basic level. During scanning, participants had to apply abstract syntactic rules to assess whether a given two-word artificial phrase could be further merged with a third word. To control for lower-level template-matching and working memory strategies, an additional non-mergeable word-list task was set up. Results: Behavioral data indicated that participants complied with the experiment. Whole brain and region of interest (ROI) analyses were performed under the contrast of "structure > word-list." Whole brain analysis confirmed significant involvement of the posterior inferior frontal gyrus [pIFG, corresponding to Brodmann area (BA) 44]. Furthermore, both the signal intensity in Broca's area and the behavioral performance showed significant correlations with natural language performance in the same participants. ROI analysis within the language atlas and anatomically defined Broca's area revealed that only the pIFG was reliably activated. Discussion: Taken together, these results support the notion that Broca's area, particularly BA 44, works as a combinatorial engine where words are merged together according to syntactic information. Furthermore, this study suggests that the present artificial grammar may serve as promising material for investigating the neurobiological basis of syntax, fostering future cross-species studies.

The gradual coevolution of syntactic combinatorics and categorization under the effects of human self-domestication: a proposal.

The gradual emergence of syntax has been claimed to be engaged in a feedback loop with Human Self-Domestication (HSD), both processes resulting from, and contributing to, enhanced connectivity in selected cortico-striatal networks, which is the mechanism for attenuating reactive aggression, the hallmark of HSD, but also the mechanism of cross-modality, relevant for syntax. Here, we aim to bridge the gap between these brain changes and further changes facilitated by the gradual complexification of grammars. We propose that increased cross-modality would have enabled and supported, more specifically, a feedback loop between categorization abilities relevant for vocabulary building and the gradual emergence of syntactic structure, including Merge. In brief, an enhanced categorization ability not only brings about more distinct categories, but also a critical number of tokens in each category necessary for Merge to take off in a systematic and productive fashion; in turn, the benefits of expressive capabilities brought about by productive Merge encourage more items to be categorized, and more categories to be formed, thus further potentiating categorization abilities, and with it, syntax again. We support our hypothesis with evidence from the domains of language development and animal communication, but also from biology, neuroscience, paleoanthropology, and clinical linguistics.

COVID-19 detection and analysis from lung CT images using novel channel boosted CNNs.

In December 2019, the global pandemic COVID-19 in Wuhan, China, affected human life and the worldwide economy. Therefore, an efficient diagnostic system is required to control its spread. However, the automatic diagnostic system poses challenges with a limited amount of labeled data, minor contrast variation, and high structural similarity between infection and background. In this regard, a new two-phase deep convolutional neural network (CNN) based diagnostic system is proposed to detect minute irregularities and analyze COVID-19 infection. In the first phase, a novel SB-STM-BRNet CNN is developed, incorporating a new channel Squeezed and Boosted (SB) and dilated convolutional-based Split-Transform-Merge (STM) block to detect COVID-19 infected lung CT images. The new STM blocks performed multi-path region-smoothing and boundary operations, which helped to learn minor contrast variation and global COVID-19 specific patterns. Furthermore, the diverse boosted channels are achieved using the SB and Transfer Learning concepts in STM blocks to learn texture variation between COVID-19-specific and healthy images. In the second phase, COVID-19 infected images are provided to the novel COVID-CB-RESeg segmentation CNN to identify and analyze COVID-19 infectious regions. The proposed COVID-CB-RESeg methodically employed region-homogeneity and heterogeneity operations in each encoder-decoder block and boosted-decoder using auxiliary channels to simultaneously learn the low illumination and boundaries of the COVID-19 infected region. The proposed diagnostic system yields good performance in terms of accuracy: 98.21 %, F-score: 98.24%, Dice Similarity: 96.40 %, and IOU: 98.85 % for the COVID-19 infected region. The proposed diagnostic system would reduce the burden and strengthen the radiologist's decision for a fast and accurate COVID-19 diagnosis.

An idea to explore: Augmented reality and LEGO® brick modeling in the biochemistry and cell biology classroom-two tactile ways to teach biomolecular structure-Function.

We present here two accessible ways for enhanced understanding of complex biological structures and their function in undergraduate Biology and Biochemistry classrooms. These methods can be applied for in-class instruction as well as for remote lessons, as they are cheap, easily available and easy to implement. LEGO® bricks and MERGE CUBE based augmented reality can be applied to make three-dimensional representation for any structure available on PDB. We envisage these techniques to be useful for students when visualizing simple stereochemical problems or complex pathway interactions.

An Evaluation of Non-Contact Photoplethysmography-Based Methods for Remote Respiratory Rate Estimation.

The respiration rate (RR) is one of the physiological signals deserving monitoring for assessing human health and emotional states. However, traditional devices, such as the respiration belt to be worn around the chest, are not always a feasible solution (e.g., telemedicine, device discomfort). Recently, novel approaches have been proposed aiming at estimating RR in a less invasive yet reliable way, requiring the acquisition and processing of contact or remote Photoplethysmography (contact reference and remote-PPG, respectively). The aim of this paper is to address the lack of systematic evaluation of proposed methods on publicly available datasets, which currently impedes a fair comparison among them. In particular, we evaluate two prominent families of PPG processing methods estimating Respiratory Induced Variations (RIVs): the first encompasses methods based on the direct extraction of morphological features concerning the RR; and the second group includes methods modeling respiratory artifacts adopting, in the most promising cases, single-channel blind source separation. Extensive experiments have been carried out on the public BP4D+ dataset, showing that the morphological estimation of RIVs is more reliable than those produced by a single-channel blind source separation method (both in contact and remote testing phases), as well as in comparison with a representative state-of-the-art Deep Learning-based approach for remote respiratory information estimation.

Secondary and Topological Structural Merge Prediction of Alpha-Helical Transmembrane Proteins Using a Hybrid Model Based on Hidden Markov and Long Short-Term Memory Neural Networks.

Alpha-helical transmembrane proteins (αTMPs) play essential roles in drug targeting and disease treatments. Due to the challenges of using experimental methods to determine their structure, αTMPs have far fewer known structures than soluble proteins. The topology of transmembrane proteins (TMPs) can determine the spatial conformation relative to the membrane, while the secondary structure helps to identify their functional domain. They are highly correlated on αTMPs sequences, and achieving a merge prediction is instructive for further understanding the structure and function of αTMPs. In this study, we implemented a hybrid model combining Deep Learning Neural Networks (DNNs) with a Class Hidden Markov Model (CHMM), namely HDNNtopss. DNNs extract rich contextual features through stacked attention-enhanced Bidirectional Long Short-Term Memory (BiLSTM) networks and Convolutional Neural Networks (CNNs), and CHMM captures state-associative temporal features. The hybrid model not only reasonably considers the probability of the state path but also has a fitting and feature-extraction capability for deep learning, which enables flexible prediction and makes the resulting sequence more biologically meaningful. It outperforms current advanced merge-prediction methods with a Q4 of 0.779 and an MCC of 0.673 on the independent test dataset, which have practical, solid significance. In comparison to advanced prediction methods for topological and secondary structures, it achieves the highest topology prediction with a Q2 of 0.884, which has a strong comprehensive performance. At the same time, we implemented a joint training method, Co-HDNNtopss, and achieved a good performance to provide an important reference for similar hybrid-model training.