Infant Cry Signal Diagnostic System Using Deep Learning and Fused Features.

Early diagnosis of medical conditions in infants is crucial for ensuring timely and effective treatment. However, infants are unable to verbalize their symptoms, making it difficult for healthcare professionals to accurately diagnose their conditions. Crying is often the only way for infants to communicate their needs and discomfort. In this paper, we propose a medical diagnostic system for interpreting infants' cry audio signals (CAS) using a combination of different audio domain features and deep learning (DL) algorithms. The proposed system utilizes a dataset of labeled audio signals from infants with specific pathologies. The dataset includes two infant pathologies with high mortality rates, neonatal respiratory distress syndrome (RDS), sepsis, and crying. The system employed the harmonic ratio (HR) as a prosodic feature, the Gammatone frequency cepstral coefficients (GFCCs) as a cepstral feature, and image-based features through the spectrogram which are extracted using a convolution neural network (CNN) pretrained model and fused with the other features to benefit multiple domains in improving the classification rate and the accuracy of the model. The different combination of the fused features is then fed into multiple machine learning algorithms including random forest (RF), support vector machine (SVM), and deep neural network (DNN) models. The evaluation of the system using the accuracy, precision, recall, F1-score, confusion matrix, and receiver operating characteristic (ROC) curve, showed promising results for the early diagnosis of medical conditions in infants based on the crying signals only, where the system achieved the highest accuracy of 97.50% using the combination of the spectrogram, HR, and GFCC through the deep learning process. The finding demonstrated the importance of fusing different audio features, especially the spectrogram, through the learning process rather than a simple concatenation and the use of deep learning algorithms in extracting sparsely represented features that can be used later on in the classification problem, which improves the separation between different infants' pathologies. The results outperformed the published benchmark paper by improving the classification problem to be multiclassification (RDS, sepsis, and healthy), investigating a new type of feature, which is the spectrogram, using a new feature fusion technique, which is fusion, through the learning process using the deep learning model.

The emerging role of microRNAs in fish ovary: A mini review.

MicroRNAs (miRNAs) are small non-coding RNAs that regulate gene expression primarily at the post-transcriptional levels. It is now well established that miRNAs are crucial regulators of many developmental and physiological processes, including reproduction. In teleosts, expression profiling studies have shown that miRNAs are expressed in the fish ovary and their levels are regulated during follicle development and by hormones. Using CRISPR/Cas9 mediated gene knockout strategies, several recent studies have provided strong evidence that miR-202 and miR-200s on chromosome 23 play critical roles in regulating ovarian development, oogenesis, and ovulation. In this mini review, we provide a brief overview of canonical miRNA biogenesis and functions; summarize miRNAs that are expressed in fish ovary; and discuss the emerging role of miRNAs in regulating fish ovarian functions.

Nodal regulates ovarian functions in zebrafish.

Nodal, a member of the transforming growth factor-ß (TGF-ß) superfamily, plays critical roles during embryo development. Several studies suggest that Nodal also regulates reproduction. The objective of this study was to investigate if Nodal is expressed in zebrafish ovary and if it is involved in the regulation of ovarian functions. Using real-time PCR, we detected two Nodal homologs, nodal-related (ndr)1, and ndr2 in zebrafish ovarian follicles. We further compared the mRNA levels of ndr1, ndr2, and their receptors between maturational incompetent early vitellogenic follicles (stage IIIa) and mid- to late-vitellogenic follicles (stage IIIb) which are capable of undergoing maturation when they are induced by hormones. We found that mRNAs for ndr1 and ndr2, as well as a type I receptor, acvr1ba, were significantly increased in follicular cells isolated from stage IIIb follicles. In primary cultures of ovarian follicular cells, treatment with recombinant human Nodal inhibited cell proliferation. On the other hand, Nodal increased the mRNA levels of two steroidogenic enzymes hsd3b2 and cyp17a1, as well as paqr8, which encodes the membrane progestin receptor-ß (mPR-ß). Conversely, knockdown of ndr1 and ndr2 using siRNAs decreased the mRNA levels of hsd3b2, cyp17a1, and paqr8. Finally, treatment of Nodal significantly induced oocyte maturation. Taken together, these findings suggest that Nodal exerts multiple effects on zebrafish ovary to regulate follicle growth, steroidogenesis, and oocyte maturation.

Identification of Novel MicroRNAs and Characterization of MicroRNA Expression Profiles in Zebrafish Ovarian Follicular Cells.

MicroRNAs (miRNAs) are small non-coding RNAs that regulate gene expression primarily at the post-transcriptional levels and thereby play important roles in regulating many physiological and developmental processes. Oocyte maturation in fish is induced by hormones produced from the hypothalamus, pituitary, and ovary. Gonadotropin-releasing hormone (GnRH) stimulates the secretion of luteinizing hormone (LH), which in turn, induces the secretion of maturation-inducing hormone (MIH) from the ovary. It is documented that small early vitellogenic (or stage IIIa) follicles are unable to undergo oocyte maturation whereas oocytes in mid- to late vitellogenic (stage IIIb) follicles can be induced by LH and MIH to become mature. To determine whether miRNAs may be involved in the growth and acquisition of maturational competency of ovarian follicles, we determined the miRNA expression profiles in follicular cells collected from stage IIIa and IIIb follicles using next-generation sequencing. It was found that miRNAs are abundantly expressed in the follicular cells from both stages IIIa and IIIb follicles. Furthermore, bioinformatics analysis revealed the presence of 214 known, 31 conserved novel and 44 novel miRNAs in zebrafish vitellogenic ovarian follicular cells. Most mature miRNAs in follicular cells were found to be in the length of 22 nucleotides. Differential expression analysis revealed that 11 miRNAs were significantly up-regulated, and 13 miRNAs were significantly down-regulated in the stage IIIb follicular cells as compared with stage IIIa follicular cells. The expression of four of the significantly regulated miRNAs, dre-miR-22a-3p, dre-miR-16a, dre-miR-181a-3p, and dre-miR-29a, was validated by real-time PCR. Finally, gene enrichment and pathway analyses of the predicted targets of the significantly regulated miRNAs supported the involvement of several key signaling pathways in regulating ovarian function, including oocyte maturation. Taken together, this study identifies novel zebrafish miRNAs and characterizes miRNA expression profiles in somatic cells within the zebrafish ovarian follicles. The differential expression of miRNAs between stage IIIa and IIIb follicular cells suggests that these miRNAs are important regulators of zebrafish ovarian follicle development and/or oocyte maturation.

Overview of MicroRNA Biogenesis, Mechanisms of Actions, and Circulation.

MicroRNAs (miRNAs) are a class of non-coding RNAs that play important roles in regulating gene expression. The majority of miRNAs are transcribed from DNA sequences into primary miRNAs and processed into precursor miRNAs, and finally mature miRNAs. In most cases, miRNAs interact with the 3' untranslated region (3' UTR) of target mRNAs to induce mRNA degradation and translational repression. However, interaction of miRNAs with other regions, including the 5' UTR, coding sequence, and gene promoters, have also been reported. Under certain conditions, miRNAs can also activate translation or regulate transcription. The interaction of miRNAs with their target genes is dynamic and dependent on many factors, such as subcellular location of miRNAs, the abundancy of miRNAs and target mRNAs, and the affinity of miRNA-mRNA interactions. miRNAs can be secreted into extracellular fluids and transported to target cells via vesicles, such as exosomes, or by binding to proteins, including Argonautes. Extracellular miRNAs function as chemical messengers to mediate cell-cell communication. In this review, we provide an update on canonical and non-canonical miRNA biogenesis pathways and various mechanisms underlying miRNA-mediated gene regulations. We also summarize the current knowledge of the dynamics of miRNA action and of the secretion, transfer, and uptake of extracellular miRNAs.

RNA Silencing of Exocyst Genes in the Stigma Impairs the Acceptance of Compatible Pollen in Arabidopsis.

Initial pollen-pistil interactions in the Brassicaceae are regulated by rapid communication between pollen grains and stigmatic papillae and are fundamentally important, as they are the first step toward successful fertilization. The goal of this study was to examine the requirement of exocyst subunits, which function in docking secretory vesicles to sites of polarized secretion, in the context of pollen-pistil interactions. One of the exocyst subunit genes, EXO70A1, was previously identified as an essential factor in the stigma for the acceptance of compatible pollen in Arabidopsis (Arabidopsis thaliana) and Brassica napus. We hypothesized that EXO70A1, along with other exocyst subunits, functions in the Brassicaceae dry stigma to deliver cargo-bearing secretory vesicles to the stigmatic papillar plasma membrane, under the pollen attachment site, for pollen hydration and pollen tube entry. Here, we investigated the functions of exocyst complex genes encoding the remaining seven subunits, SECRETORY3 (SEC3), SEC5, SEC6, SEC8, SEC10, SEC15, and EXO84, in Arabidopsis stigmas following compatible pollinations. Stigma-specific RNA-silencing constructs were used to suppress the expression of each exocyst subunit individually. The early postpollination stages of pollen grain adhesion, pollen hydration, pollen tube penetration, seed set, and overall fertility were analyzed in the transgenic lines to evaluate the requirement of each exocyst subunit. Our findings provide comprehensive evidence that all eight exocyst subunits are necessary in the stigma for the acceptance of compatible pollen. Thus, this work implicates a fully functional exocyst complex as a component of the compatible pollen response pathway to promote pollen acceptance.

PERK-KIPK-KCBP signalling negatively regulates root growth in Arabidopsis thaliana.

The Arabidopsis proline-rich, extensin-like receptor-like kinases (PERKs) are a small group of receptor-like kinases that are thought to act as sensors at the cell wall through their predicted proline-rich extracellular domains. In this study, we focused on the characterization of a subclade of three Arabidopsis predicted PERK genes, PERK8, -9, and -10, for which no functions were known. Yeast two-hybrid interaction studies were conducted with the PERK8,- 9, and -10 cytosolic kinase domains, and two members of the Arabidopsis AGC VIII kinase family were identified as interacting proteins: AGC1-9 and the closely related kinesin-like calmodulin-binding protein (KCBP)-interacting protein kinase (KIPK). As KIPK has been identified previously as an interactor of KCBP, these interactions were also examined further and confirmed in this study. Finally, T-DNA mutants for each gene were screened for altered phenotypes under different conditions, and from these screens, a role for the PERK, KIPK, and KCBP genes in negatively regulating root growth was uncovered.

Irrepressible MONOPTEROS/ARF5 promotes de novo shoot formation.

In vitro regeneration of complete organisms from diverse cell types is a spectacular property of plant cells. Despite the great importance of plant regeneration for plant breeding and biotechnology, its molecular basis is still largely unclear and many important crop plants have remained recalcitrant to regeneration. Hormone-exposure protocols to trigger the de novo formation of either roots or shoots from callus tissue demonstrate the importance of auxin and cytokinin signaling pathways, and genetic differences in these pathways may contribute to the highly divergent responsiveness of plant species to regeneration protocols. In this study, we show that signaling through MONOPTEROS (MP)/AUXIN RESPONSE FACTOR 5 is necessary for the formation of shoots from Arabidopsis calli. Most strikingly, an irrepressible variant of MP, MPΔ, is sufficient for promoting de novo shoot formation through pathways involving the genetically downstream functions of SHOOT MERISTEMLESS (STM) and CYTOKININ RESPONSE FACTOR2 (CRF2). We conclude that the MPΔ genotype can promote de novo shoot formation and can be used to probe corresponding signaling pathways.