Computationally reconstructing cotranscriptional RNA folding from experimental data reveals rearrangement of non-native folding intermediates.

The series of RNA folding events that occur during transcription can critically influence cellular RNA function. Here, we present reconstructing RNA dynamics from data (R2D2), a method to uncover details of cotranscriptional RNA folding. We model the folding of the Escherichia coli signal recognition particle (SRP) RNA and show that it requires specific local structural fluctuations within a key hairpin to engender efficient cotranscriptional conformational rearrangement into the functional structure. All-atom molecular dynamics simulations suggest that this rearrangement proceeds through an internal toehold-mediated strand-displacement mechanism, which can be disrupted with a point mutation that limits local structural fluctuations and rescued with compensating mutations that restore these fluctuations. Moreover, a cotranscriptional folding intermediate could be cleaved in vitro by recombinant E. coli RNase P, suggesting potential cotranscriptional processing. These results from experiment-guided multi-scale modeling demonstrate that even an RNA with a simple functional structure can undergo complex folding and processing during synthesis.

Cotranslational sorting and processing of newly synthesized proteins in eukaryotes.

Ribosomes interact with a variety of different protein biogenesis factors that guide newly synthesized proteins to their native 3D shapes and cellular localization. Depending on the type of translated substrate, a distinct set of cotranslational factors must interact with the ribosome in a timely and coordinated manner to ensure proper protein biogenesis. While cytonuclear proteins require cotranslational maturation and folding factors, secretory proteins must be maintained in an unfolded state and processed cotranslationally by transport and membrane translocation factors. Here we explore the specific cotranslational processing steps for cytonuclear, secretory, and membrane proteins in eukaryotes and then discuss how the nascent polypeptide-associated complex (NAC) cotranslationally sorts these proteins into the correct protein biogenesis pathway.

The Biogenesis of SRP RNA Is Modulated by an RNA Folding Intermediate Attained during Transcription.

The signal recognition particle (SRP), responsible for co-translational protein targeting and delivery to cellular membranes, depends on the native long-hairpin fold of its RNA to confer functionality. Since RNA initiates folding during its synthesis, we used high-resolution optical tweezers to follow in real time the co-transcriptional folding of SRP RNA. Surprisingly, SRP RNA folding is robust to transcription rate changes and the presence or absence of its 5'-precursor sequence. The folding pathway also reveals the obligatory attainment of a non-native hairpin intermediate (H1) that eventually rearranges into the native fold. Furthermore, H1 provides a structural platform alternative to the native fold for RNase P to bind and mature SRP RNA co-transcriptionally. Delays in attaining the final native fold are detrimental to the cell, altogether showing that a co-transcriptional folding pathway underpins the proper biogenesis of function-essential SRP RNA.

Unique Archaeal Small RNAs.

Advances in genome-wide sequence technologies allow for detailed insights into the complexity of RNA landscapes of organisms from all three domains of life. Recent analyses of archaeal transcriptomes identified interaction and regulation networks of noncoding RNAs in this understudied domain. Here, we review current knowledge of small, noncoding RNAs with important functions for the archaeal lifestyle, which often requires adaptation to extreme environments. One focus is RNA metabolism at elevated temperatures in hyperthermophilic archaea, which reveals elevated amounts of RNA-guided RNA modification and virus defense strategies. Genome rearrangement events result in unique fragmentation patterns of noncoding RNA genes that require elaborate maturation pathways to yield functional transcripts. RNA-binding proteins, e.g., L7Ae and LSm, are important for many posttranscriptional control functions of RNA molecules in archaeal cells. We also discuss recent insights into the regulatory potential of their noncoding RNA partners.

A non-pheromone GPCR is essential for meiosis and ascosporogenesis in the wheat scab fungus.

Meiosis is essential for generating genetic diversity and sexual spores, but the regulation of meiosis and ascosporogenesis is not clear in filamentous fungi, in which dikaryotic and diploid cells formed inside fruiting bodies are not free living and independent of pheromones or pheromone receptors. In this study, Gia1, a non-pheromone GPCR (G protein-coupled receptor) with sexual-specific expression in Fusarium graminearum, is found to be essential for ascosporogenesis. The gia1 mutant was normal in perithecium development, crozier formation, and karyogamy but failed to undergo meiosis, which could be partially rescued by a dominant active mutation in GPA1 and activation of the Gpmk1 pathway. GIA1 orthologs have conserved functions in regulating meiosis and ascosporogenesis in Sordariomycetes. GIA1 has a paralog, GIP1, in F. graminearum and other Hypocreales species which is essential for perithecium formation. GIP1 differed from GIA1 in expression profiles and downstream signaling during sexual reproduction. Whereas the C-terminal tail and IR3 were important for intracellular signaling, the N-terminal region and EL3 of Gia1 were responsible for recognizing its ligand, which is likely a protein enriched in developing perithecia, particularly in the gia1 mutant. Taken together, these results showed that GIA1 encodes a non-pheromone GPCR that regulates the entry into meiosis and ascosporogenesis via the downstream Gpmk1 MAP kinase pathway in F. graminearum and other filamentous ascomycetes.

Signal recognition particle RNA is critical for genetic competence and virulence of Streptococcus pneumoniae.

Streptococcus pneumoniae (pneumococcus) causes a wide range of important human infectious diseases, including pneumonia, pneumonia-derived sepsis, otitis media, and meningitis. Pneumococcus produces numerous secreted proteins that are critical for normal physiology and pathogenesis. The membrane targeting and translocation of these secreted proteins are partly mediated by the signal recognition particle (SRP) complex, which consists of 4.5S small cytoplasmic RNA (ScRNA), and the Ffh, and FtsY proteins. Here, we report that pneumococcal ∆scRNA, ∆ffh, and ∆ftsY mutants were significantly impaired in competence induction, competence pili production, exogenous DNA uptake, and genetic transformation. Also, the ∆scRNA mutant was significantly attenuated in the mouse models of bacteremia and pneumonia. Interestingly, unlike the ∆scRNA, both ∆ffh and ∆ftsY mutants had growth defects on Todd-Hewitt Agar, which were alleviated by the provision of free amino acids or serum. Differences in nutritional requirements between ∆ffh and ∆ftsY vs ∆scRNA suggest that Ffh and FtsY may be partially functional in the absence of ScRNA. Finally, the insertase YidC2, which could functionally rescue some SRP mutations in other streptococcal species, was not essential for pneumococcal genetic transformation. Collectively, these results indicate that ScRNA is crucial for the successful development of genetic competence and virulence in pneumococcus. IMPORTANCE: Streptococcus pneumoniae (pneumococcus) causes multiple important infectious diseases in humans. The signal recognition particle (SRP) complex, which comprised 4.5S small cytoplasmic RNA (ScRNA), and the Ffh and FtsY proteins, mediates membrane targeting and translocation of secreted proteins in all organisms. However, the role of SRP and ScRNA has not been characterized during the induction of the competence system for genetic transformation and virulence in pneumococcus. By using a combination of genetic, biochemical, proteomic, and imaging approaches, we demonstrated that the SRP complex plays a significant role in membrane targeting of competence system-regulated effectors important for genetic transformation, virulence during bacteremia and pneumonia infections, and nutritional acquisition.

Coping with stress: How bacteria fine-tune protein synthesis and protein transport.

Maintaining a functional proteome under different environmental conditions is challenging for every organism, in particular for unicellular organisms, such as bacteria. In order to cope with changing environments and stress conditions, bacteria depend on strictly coordinated proteostasis networks that control protein production, folding, trafficking, and degradation. Regulation of ribosome biogenesis and protein synthesis are cornerstones of this cellular adaptation in all domains of life, which is rationalized by the high energy demand of both processes and the increased resistance of translationally silent cells against internal or external poisons. Reduced protein synthesis ultimately also reduces the substrate load for protein transport systems, which are required for maintaining the periplasmic, inner, and outer membrane subproteomes. Consequences of impaired protein transport have been analyzed in several studies and generally induce a multifaceted response that includes the upregulation of chaperones and proteases and the simultaneous downregulation of protein synthesis. In contrast, generally less is known on how bacteria adjust the protein targeting and transport machineries to reduced protein synthesis, e.g., when cells encounter stress conditions or face nutrient deprivation. In the current review, which is mainly focused on studies using Escherichia coli as a model organism, we summarize basic concepts on how ribosome biogenesis and activity are regulated under stress conditions. In addition, we highlight some recent developments on how stress conditions directly impair protein targeting to the bacterial membrane. Finally, we describe mechanisms that allow bacteria to maintain the transport of stress-responsive proteins under conditions when the canonical protein targeting pathways are impaired.

Chloroplast SRP43 and SRP54 independently promote thermostability and membrane binding of light-dependent protochlorophyllide oxidoreductases.

Protochlorophyllide oxidoreductase (POR), which converts protochlorophyllide into chlorophyllide, is the only light-dependent enzyme in chlorophyll biosynthesis. While its catalytic reaction and importance for chloroplast development are well understood, little is known about the post-translational control of PORs. Here, we show that cpSRP43 and cpSRP54, two components of the chloroplast signal recognition particle pathway, play distinct roles in optimizing the function of PORB, the predominant POR isoform in Arabidopsis. The chaperone cpSRP43 stabilizes the enzyme and provides appropriate amounts of PORB during leaf greening and heat shock, whereas cpSRP54 enhances its binding to the thylakoid membrane, thereby ensuring adequate levels of metabolic flux in late chlorophyll biosynthesis. Furthermore, cpSRP43 and the DnaJ-like protein CHAPERONE-LIKE PROTEIN of POR1 concurrently act to stabilize PORB. Overall, these findings enhance our understanding of the coordinating role of cpSPR43 and cpSRP54 in the post-translational control of chlorophyll synthesis and assembly of photosynthetic chlorophyll-binding proteins.

Effects of PNA Sequence and Target Site Selection on Function of a 4.5S Non-Coding RNA.

Peptide nucleic acid (PNA) based antisense strategy is a promising therapeutic approach to specifically inhibit target gene expression. However, unlike protein coding genes, identification of an ideal PNA binding site for non-coding RNA is not straightforward. Here, we compare the inhibitory activities of PNA molecules that bind a non-coding 4.5S RNA called SRP RNA, a key component of the bacterial signal recognition particle (SRP). A 9-mer PNA (PNA9) complementary to the tetraloop region of the RNA was more potent in inhibiting its interaction with the SRP protein, compared to an 8-mer PNA (PNA8) targeting a stem-loop. PNA9, which contained a homo-pyrimidine sequence could form a triplex with the complementary stretch of RNA in vitro as confirmed using a fluorescent derivative of PNA9 (F-PNA13). The RNA-PNA complex formation resulted in inhibition of SRP function with PNA9 and F-PNA13, but not PNA8 highlighting the importance of target site selection. Surprisingly, F-PNA13 which was more potent in inhibiting SRP function in vitro, showed weaker antibacterial activity compared to PNA9 likely due to poor cell penetration of the longer PNA. Our results underscore the importance of suitable target site selection and optimum PNA length to develop better antisense molecules against non-coding RNA.

Immune-mediated necrotizing myopathy: A comprehensive review of the pathogenesis, clinical features, and treatments.

Immune-mediated necrotizing myopathy (IMNM) is a rare and newly recognized autoimmune disease within the spectrum of idiopathic inflammatory myopathies. It is characterized by myositis-specific autoantibodies, elevated serum creatine kinase levels, inflammatory infiltrate, and weakness. IMNM can be classified into three subtypes based on the presence or absence of specific autoantibodies: anti-signal recognition particle myositis, anti-3-hydroxy-3-methylglutaryl-coenzyme A reductase myositis, and seronegative IMNM. In recent years, IMNM has gained increasing attention and emerged as a research hotspot. Recent studies have suggested that the pathogenesis of IMNM is linked to aberrant activation of immune system, including immune responses mediated by antibodies, complement, and immune cells, particularly macrophages, as well as abnormal release of inflammatory factors. Non-immune mechanisms such as autophagy and endoplasmic reticulum stress also participate in this process. Additionally, genetic variations associated with IMNM have been identified, providing new insights into the genetic mechanisms of the disease. Progress has also been made in IMNM treatment research, including the use of immunosuppressants and the development of biologics. Despite the challenges in understanding the etiology and treatment of IMNM, the latest research findings offer important guidance and insights for delving deeper into the disease's pathogenic mechanisms and identifying new therapeutic strategies.

The role of chloroplast SRP54 domains and its C-terminal tail region in post- and co-translational protein transport in vivo.

In the chloroplast, the 54 kDa subunit of the signal recognition particle (cpSRP54) is involved in the post-translational transport of the light-harvesting chlorophyll a/b-binding proteins (LHCPs) and the co-translational transport of plastid-encoded subunits of the photosynthetic complexes to the thylakoid membrane. It forms a high-affinity complex with plastid-specific cpSRP43 for post-translational transport, while a ribosome-associated pool coordinates its co-translational function. CpSRP54 constitutes a conserved multidomain protein, comprising a GTPase (NG) and a methionine-rich (M) domain linked by a flexible region. It is further characterized by a plastid-specific C-terminal tail region containing the cpSRP43-binding motif. To characterize the physiological role of the various regions of cpSRP54 in thylakoid membrane protein transport, we generated Arabidopsis cpSRP54 knockout (ffc1-2) lines producing truncated cpSRP54 variants or a GTPase point mutation variant. Phenotypic characterization of the complementation lines demonstrated that the C-terminal tail region of cpSRP54 plays an important role exclusively in post-translational LHCP transport. Furthermore, we show that the GTPase activity of cpSRP54 plays an essential role in the transport pathways for both nuclear as well as plastid-encoded proteins. In addition, our data revealed that plants expressing cpSRP54 without the C-terminal region exhibit a strongly increased accumulation of a photosystem I assembly intermediate.

Immune-Mediated Necrotizing Myopathies: Current Landscape.

PURPOSE OF REVIEW: Immune-mediated necrotizing myopathy (IMNM), characterized by acute or subacute onset, severe weakness, and elevated creatine kinase levels, poses diagnostic and therapeutic challenges. This article provides a succinct overview of IMNM, including clinical features, diagnostic strategies, and treatment approaches. RECENT FINDINGS: Recent insights highlight the different clinical presentations and therapeutic options of IMNM stratified by autoantibody positivity and type. Additionally, recent findings call into question the reported link between statin use and IMNM. This review synthesizes current knowledge on IMNM, emphasizing its distinct clinical features and challenging management. The evolving understanding of IMNM underscores the need for a comprehensive diagnostic approach that utilizes a growing range of modalities. Early and aggressive immunomodulatory therapy remains pivotal. Ongoing research aims to refine diagnostic tools and therapeutic interventions for this challenging muscle disorder, underscoring the importance of advancing our understanding to enhance patient outcomes.

Time-Frequency Aliased Signal Identification Based on Multimodal Feature Fusion.

The identification of multi-source signals with time-frequency aliasing is a complex problem in wideband signal reception. The traditional method of first separation and identification especially fails due to the significant separation error under underdetermined conditions when the degree of time-frequency aliasing is high. The single-mode recognition method does not need to be separated first. However, the single-mode features contain less signal information, making it challenging to identify time-frequency aliasing signals accurately. To solve the above problems, this article proposes a time-frequency aliasing signal recognition method based on multi-mode fusion (TRMM). This method uses the U-Net network to extract pixel-by-pixel features of the time-frequency and wave-frequency images and then performs weighted fusion. The multimodal feature scores are used as the classification basis to realize the recognition of the time-frequency aliasing signals. When the SNR is 0 dB, the recognition rate of the four-signal aliasing model can reach more than 97.3%.

Efficient FPGA Implementation of Convolutional Neural Networks and Long Short-Term Memory for Radar Emitter Signal Recognition.

In recent years, radar emitter signal recognition has enjoyed a wide range of applications in electronic support measure systems and communication security. More and more deep learning algorithms have been used to improve the recognition accuracy of radar emitter signals. However, complex deep learning algorithms and data preprocessing operations have a huge demand for computing power, which cannot meet the requirements of low power consumption and high real-time processing scenarios. Therefore, many research works have remained in the experimental stage and cannot be actually implemented. To tackle this problem, this paper proposes a resource reuse computing acceleration platform based on field programmable gate arrays (FPGA), and implements a one-dimensional (1D) convolutional neural network (CNN) and long short-term memory (LSTM) neural network (NN) model for radar emitter signal recognition, directly targeting the intermediate frequency (IF) data of radar emitter signal for classification and recognition. The implementation of the 1D-CNN-LSTM neural network on FPGA is realized by multiplexing the same systolic array to accomplish the parallel acceleration of 1D convolution and matrix vector multiplication operations. We implemented our network on Xilinx XCKU040 to evaluate the effectiveness of our proposed solution. Our experiments show that the system can achieve 7.34 giga operations per second (GOPS) data throughput with only 5.022 W power consumption when the radar emitter signal recognition rate is 96.53%, which greatly improves the energy efficiency ratio and real-time performance of the radar emitter recognition system.

Radio Signal Modulation Recognition Method Based on Hybrid Feature and Ensemble Learning: For Radar and Jamming Signals.

The detection performance of radar is significantly impaired by active jamming and mutual interference from other radars. This paper proposes a radio signal modulation recognition method to accurately recognize these signals, which helps in the jamming cancellation decisions. Based on the ensemble learning stacking algorithm improved by meta-feature enhancement, the proposed method adopts random forests, K-nearest neighbors, and Gaussian naive Bayes as the base-learners, with logistic regression serving as the meta-learner. It takes the multi-domain features of signals as input, which include time-domain features including fuzzy entropy, slope entropy, and Hjorth parameters; frequency-domain features, including spectral entropy; and fractal-domain features, including fractal dimension. The simulation experiment, including seven common signal types of radar and active jamming, was performed for the effectiveness validation and performance evaluation. Results proved the proposed method's performance superiority to other classification methods, as well as its ability to meet the requirements of low signal-to-noise ratio and few-shot learning.

Expression of signal recognition particle 14 in hepatocellular carcinoma and its relationship with disease progression and patient survival. / 信号识别颗粒14è°ƒæŽ§è‚ç»†èƒžç™Œè¿›ç¨‹å¹¶å½±å“æ‚£è€ é¢„åŽ.

OBJECTIVES: To investigate the expression of signal recognition particle 14 (SRP14) in hepatocellular carcinoma (HCC) and its clinical significance. METHODS: The data of SRP14 expression in HCC were obtained from bioinformatics study, and from investigation with quantitative reverse transcription polymerase chain reaction (qRT-PCR), immunohistochemical staining and Western blotting in clinical samples. The Kaplan-Meier analysis was used to determine the associations between SRP14 mRNA expression and the overall survival, progression-free survival, and disease-specific survival of HCC patients. The effect of SRP14 on the proliferation and migration of HCC cells were determined by EdU staining, MTS, Transwell and wound-healing assays. The potential mechanism for SRP14 regulating HCC was explored through Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) enrichment analysis as well as qRT-PCR. RESULTS: According to the data from GSE14520, TNMplot database and clinical samples, compared with paired tumor-adjacent tissues, non-paired tumor-adjacent tissues and normal tissues, the mRNA expression of SPR14 in HCC tissues was upregulated (all P<0.05). In clinical samples, compared with paired tumor-adjacent tissues, the protein expression of SPR14 in HCC tissues was increased (P<0.05). The increased mRNA expression of SRP14 was associated with good overall survival, progression-free survival, and disease-specific survival in HCC patients. SRP14 inhibited the proliferation and migration of HCC cells in vitro. According to the KEGG and GO enrichment analysis, in non-specific HCC, the genes co-expressed with SRP14 may predominantly regulate protein synthesis, processing, and transport, while in nonalcoholic fatty liver disease related HCC, the genes co-expressed with SRP14 could control multiple signaling pathways such as MAPK, cAMP, PI3K-Akt, and Wnt. Mechanistically, SRP14 up-regulated the mRNA expression of tumor suppressor gene GPRC5A inHCC cells (P<0.05). CONCLUSIONS: SRP14 may regulate HCC progression and influence patient prognosis.

Female preferences for the spectral content of advertisement calls in Cope's gray treefrog (Hyla chrysoscelis).

Amphibians have inner ears with two sensory papillae tuned to different frequency ranges of airborne sounds. In frogs, male advertisement calls possess distinct spectral components that match the tuning of one or both sensory papillae. Female preferences for the spectral content of advertisement calls can depend on signal amplitude and can vary among closely related lineages. In this study of Cope's gray tree frog (Hyla chrysoscelis), we investigated the amplitude dependence of female preferences for the spectral content of male advertisement calls, which have a "bimodal" spectrum with separate low-frequency (1.25 kHz) and high-frequency (2.5 kHz) components. In two-alternative choice tests, females generally preferred synthetic calls with bimodal spectra over "unimodal" calls having only one of the two spectral components. They also preferred unimodal calls with a high-frequency component over one with the low-frequency component. With few exceptions, preferences were largely independent of amplitude across both a 30 dB range of overall signal amplitude and an 11 dB range in the relative amplitudes of the two spectral components. We discuss these results in the context of evolutionary lability in female preferences for the spectral content of advertisement calls in North American tree frogs in the genus Hyla.

Anti-signal recognition particle positive necrotizing myopathy-sjogren's syndrome overlap syndrome: a descriptive study on clinical and myopathology features.

BACKGROUND AND OBJECTIVE: The aim of this study was to elucidate the clinical and myopathological characteristics of patients with anti-signal recognition particle (SRP) positive immune-mediated necrotizing myopathy (IMNM) overlap Sjogren's syndrome (SS). MATERIALS AND METHODS: We retrospectively analyzed the data of anti-SRP positive IMNM patients admitted in the Neurology Department of Tongji Hospital between January 2011 to December 2020. Patients were divided into two groups: anti-SRP IMNM overlap SS group and anti-SRP IMNM control group. The clinical features, laboratory results, histological features, treatment, and prognosis were compared between the two groups. RESULTS: A total of 30 patients with anti-SRP IMNM were included, including six anti-SRP IMNM overlap SS patients (two males, four females), with a median age of 39 years, and 24 anti-SRP IMNM patients (ten males, fourteen females), with a median age of 46 years. The anti-SRP IMNM overlap SS group had a lower prevalence of muscle atrophy (0 vs 50%, p = 0.019), and a higher prevalence of extramuscular manifestations, including cardiac abnormalities and ILD (Interstitial lung disease). CD4 + and CD68 + inflammatory infiltrations were significantly increased in anti-SRP IMNM overlap SS patients, with an increased presence of CD4 + cells in both necrotic(p = 0.023) and endomysial areas (p = 0.013), and more CD68 + cells (p = 0.016) infiltrated the endomysial area. Deposition of membrane attack complex (MAC) on sarcolemma (p = 0.013) was more commonly seen in the anti-SRP IMNM overlap SS group. CONCLUSION: Our data revealed that anti-SRP IMNM-SS overlap patients may present with milder muscular manifestation, but worse extramuscular manifestations compared to anti-SRP IMNM patients without SS. CD4 + and CD68 + inflammatory infiltrations and MAC deposition were remarkably increased in anti-SRP IMNM-SS overlap patients.

SFBC Recognition over Orthogonal Frequency Division Multiplexing Schemes in the Presence of Inphase and Quadrature Phase Discrepancies for Cognitive Radio Applications.

A radio is adaptive if it can autonomously analyze the communications environment and instantly modify its settings to achieve the best possible efficiency. In orthogonal frequency division multiplexing (OFDM) transmissions, identifying the space frequency block coding (SFBC) category utilized is one of the most important tasks of an adaptive receiver. Previous approaches to this problem did not take into consideration the fact that real systems typically suffer from transmission defects. This study offers a novel maximum likelihood recognizer capable of distinguishing between SFBC OFDM waveforms in the context of inphase and quadrature phase differences (IQDs). The theoretical findings show that IQDs arising from the transmitter and recipient can be combined with channel paths to generate so-called effective channel paths. The conceptual examination demonstrates that the outlined maximum likelihood strategy of the SFBC recognition and effective channel estimation processes is implemented by an expectation maximization tool utilizing the error control decoders' soft outputs. The simulations results reveal that the suggested strategy delivers a much greater recognition accuracy than the typical approaches outlined in the comparable literature. At a signal-to-noise ratio (SNR) of 14 dB, for example, the proposed approach achieves a bit error rate (BER) of 0.00002, which is very close to the case of perfect estimation and compensation for IQDs, outperforming the previous reported works which achieved BERs of 0.01 and 0.02.

Real-Time Recognition Method for Key Signals of Rock Fracture Acoustic Emissions Based on Deep Learning.

The characteristics of acoustic emission signals generated in the process of rock deformation and fission contain rich information on internal rock damage. The use of acoustic emissions monitoring technology can analyze and identify the precursor information of rock failure. At present, in the field of acoustic emissions monitoring and the early warning of rock fracture disasters, there is no real-time identification method for a disaster precursor characteristic signal. It is easy to lose information by analyzing the characteristic parameters of traditional acoustic emissions to find signals that serve as precursors to disasters, and analysis has mostly been based on post-analysis, which leads to poor real-time recognition of disaster precursor characteristics and low application levels in the engineering field. Based on this, this paper regards the acoustic emissions signal of rock fracture as a kind of speech signal generated by rock fracture uses this idea of speech recognition for reference alongside spectral analysis (STFT) and Mel frequency analysis to realize the feature extraction of acoustic emissions from rock fracture. In deep learning, based on the VGG16 convolutional neural network and AlexNet convolutional neural network, six intelligent real-time recognition models of rock fracture and key acoustic emission signals were constructed, and the network structure and loss function of traditional VGG16 were optimized. The experimental results show that these six deep-learning models can achieve the real-time intelligent recognition of key signals, and Mel, combined with the improved VGG16, achieved the best performance with 87.68% accuracy and 81.05% recall. Then, by comparing multiple groups of signal recognition models, Mel+VGG-FL proposed in this paper was verified as having a high recognition accuracy and certain recognition efficiency, performing the intelligent real-time recognition of key acoustic emission signals in the process of rock fracture more accurately, which can provide new ideas and methods for related research and the real-time intelligent recognition of rock fracture precursor characteristics.