Hernandonine-mediated autophagic cell death in hepatocellular carcinoma: Interplay of p53 and YAP signaling pathways.

Hepatocellular carcinoma (HCC), the primary form of liver cancer, is the third leading cause of cancer-related death globally. Hernandonine is a natural alkaloid derived from Hernandia nymphaeifolia that has been shown to exert various biological functions. In a previous study, hernandonine was shown to suppress the proliferation of several solid tumor cell lines without affecting normal human cell lines. However, little is known about the effect of hernandonine on HCC. Therefore, this study aimed to investigate the effect and mechanism of hernandonine on HCC in relation to autophagy. We found that hernandonine inhibited HCC cell growth in vitro and in vivo. In addition, hernandonine elicited autophagic cell death and DNA damage in HCC cells. RNA-seq analysis revealed that hernandonine upregulated p53 and Hippo signaling pathway-related genes in HCC cells. Small RNA interference of p53 resulted in hernandonine-induced autophagic cell death attenuation. However, inhibition of YAP sensitized HCC cells to hernandonine by increasing the autophagy induction. This is the first study to illustrate the complex involvement of p53 and YAP in the hernandonine-induced autophagic cell death in human HCC cells. Our findings provide novel evidence for the potential of hernandonine as a therapeutic agent for HCC treatment.

Integrating In Silico and In Vitro Approaches to Identify Natural Peptides with Selective Cytotoxicity against Cancer Cells.

Anticancer peptides (ACPs) are bioactive compounds known for their selective cytotoxicity against tumor cells via various mechanisms. Recent studies have demonstrated that in silico machine learning methods are effective in predicting peptides with anticancer activity. In this study, we collected and analyzed over a thousand experimentally verified ACPs, specifically targeting peptides derived from natural sources. We developed a precise prediction model based on their sequence and structural features, and the model's evaluation results suggest its strong predictive ability for anticancer activity. To enhance reliability, we integrated the results of this model with those from other available methods. In total, we identified 176 potential ACPs, some of which were synthesized and further evaluated using the MTT colorimetric assay. All of these putative ACPs exhibited significant anticancer effects and selective cytotoxicity against specific tumor cells. In summary, we present a strategy for identifying and characterizing natural peptides with selective cytotoxicity against cancer cells, which could serve as novel therapeutic agents. Our prediction model can effectively screen new molecules for potential anticancer activity, and the results from in vitro experiments provide compelling evidence of the candidates' anticancer effects and selective cytotoxicity.

iDVEIP: A computer-aided approach for the prediction of viral entry inhibitory peptides.

With the notable surge in therapeutic peptide development, various peptides have emerged as potential agents against virus-induced diseases. Viral entry inhibitory peptides (VEIPs), a subset of antiviral peptides (AVPs), offer a promising avenue as entry inhibitors (EIs) with distinct advantages over chemical counterparts. Despite this, a comprehensive analytical platform for characterizing these peptides and their effectiveness in blocking viral entry remains lacking. In this study, we introduce a groundbreaking in silico approach that leverages bioinformatics analysis and machine learning to characterize and identify novel VEIPs. Cross-validation results demonstrate the efficacy of a model combining sequence-based features in predicting VEIPs with high accuracy, validated through independent testing. Additionally, an EI type model has been developed to distinguish peptides specifically acting as Eis from AVPs with alternative activities. Notably, we present iDVEIP, a web-based tool accessible at http://mer.hc.mmh.org.tw/iDVEIP/, designed for automatic analysis and prediction of VEIPs. Emphasizing its capabilities, the tool facilitates comprehensive analyses of peptide characteristics, providing detailed amino acid composition data for each prediction. Furthermore, we showcase the tool's utility in identifying EIs against severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2).

Microbiome analysis of maternal and neonatal microbial communities associated with the different delivery modes based on 16S rRNA gene amplicon sequencing.

OBJECTIVE: With the rising number of cases of non-vaginal delivery worldwide, scientists have been concerned about the influence of the different delivery modes on maternal and neonatal microbiomes. Although the birth rate trend is decreasing rapidly in Taiwan, more than 30 percent of newborns are delivered by caesarean section every year. However, it remains unclear whether the different delivery modes could have a certain impact on the postpartum maternal microbiome and whether it affects the mother-to-newborn vertical transmission of bacteria at birth. MATERIALS AND METHODS: To address this, we recruited 30 mother-newborn pairs to participate in this study, including 23 pairs of vaginal delivery (VD) and seven pairs of caesarean section (CS). We here investigate the development of the maternal prenatal and postnatal microbiomes across multiple body habitats. Moreover, we also explore the early acquisition of neonatal gut microbiome through a vertical multi-body site microbiome analysis. RESULTS AND CONCLUSION: The results indicate that no matter the delivery mode, it only slightly affects the maternal microbiome in multiple body habitats from pregnancy to postpartum. On the other hand, about 95% of species in the meconium microbiome were derived from one of the maternal body habitats; notably, the infants born by caesarean section acquire bacterial communities resembling their mother's oral microbiome. Consequently, the delivery modes play a crucial role in the initial colonization of the neonatal gut microbiome, potentially impacting children's health and development.

Efficient methods for multiple types of precise gene-editing in Chlamydomonas.

Precise gene-editing using CRISPR/Cas9 technology remains a long-standing challenge, especially for genes with low expression and no selectable phenotypes in Chlamydomonas reinhardtii, a classic model for photosynthesis and cilia research. Here, we developed a multi-type and precise genetic manipulation method in which a DNA break was generated by Cas9 nuclease and the repair was mediated using a homologous DNA template. The efficacy of this method was demonstrated for several types of gene editing, including inactivation of two low-expression genes (CrTET1 and CrKU80), the introduction of a FLAG-HA epitope tag into VIPP1, IFT46, CrTET1 and CrKU80 genes, and placing a YFP tag into VIPP1 and IFT46 for live-cell imaging. We also successfully performed a single amino acid substitution for the FLA3, FLA10 and FTSY genes, and documented the attainment of the anticipated phenotypes. Lastly, we demonstrated that precise fragment deletion from the 3'-UTR of MAA7 and VIPP1 resulted in a stable knock-down effect. Overall, our study has established efficient methods for multiple types of precise gene editing in Chlamydomonas, enabling substitution, insertion and deletion at the base resolution, thus improving the potential of this alga in both basic research and industrial applications.

A flexible liposomal polymer complex as a platform of specific and regulable immune regulation for individual cancer immunotherapy.

BACKGROUND: The applicability and therapeutic efficacy of specific personalized immunotherapy for cancer patients is limited by the genetic diversity of the host or the tumor. Side-effects such as immune-related adverse events (IRAEs) derived from the administration of immunotherapy have also been observed. Therefore, regulatory immunotherapy is required for cancer patients and should be developed. METHODS: The cationic lipo-PEG-PEI complex (LPPC) can stably and irreplaceably adsorb various proteins on its surface without covalent linkage, and the bound proteins maintain their original functions. In this study, LPPC was developed as an immunoregulatory platform for personalized immunotherapy for tumors to address the barriers related to the heterogenetic characteristics of MHC molecules or tumor associated antigens (TAAs) in the patient population. Here, the immune-suppressive and highly metastatic melanoma, B16F10 cells were used to examine the effects of this platform. Adsorption of anti-CD3 antibodies, HLA-A2/peptide, or dendritic cells' membrane proteins (MP) could flexibly provide pan-T-cell responses, specific Th1 responses, or specific Th1 and Th2 responses, depending on the host needs. Furthermore, with regulatory antibodies, the immuno-LPPC complex properly mediated immune responses by adsorbing positive or negative antibodies, such as anti-CD28 or anti-CTLA4 antibodies. RESULTS: The results clearly showed that treatment with LPPC/MP/CD28 complexes activated specific Th1 and Th2 responses, including cytokine release, CTL and prevented T-cell apoptosis. Moreover, LPPC/MP/CD28 complexes could eliminate metastatic B16F10 melanoma cells in the lung more efficiently than LPPC/MP. Interestingly, the melanoma resistance of mice treated with LPPC/MP/CD28 complexes would be reversed to susceptible after administration with LPPC/MP/CTLA4 complexes. NGS data revealed that LPPC/MP/CD28 complexes could enhance the gene expression of cytokine and chemokine pathways to strengthen immune activation than LPPC/MP, and that LPPC/MP/CTLA4 could abolish the LPPC/MP complex-mediated gene expression back to un-treatment. CONCLUSIONS: Overall, we proved a convenient and flexible immunotherapy platform for developing personalized cancer therapy.

Transdermal nanolipoplex simultaneously inhibits subcutaneous melanoma growth and suppresses systemically metastatic melanoma by activating host immunity.

Benefit for clinical melanoma treatments, the transdermal neoadjuvant therapy could reduce surgery region and increase immunotherapy efficacy. Using lipoplex (Lipo-PEG-PEI-complex, LPPC) encapsulated doxorubicin (DOX) and carrying CpG oligodeoxynucleotide; the transdermally administered nano-liposomal drug complex (LPPC-DOX-CpG) would have high cytotoxicity and immunostimulatory activity to suppress systemic metastasis of melanoma. LPPC-DOX-CpG dramatically suppressed subcutaneous melanoma growth by inducing tumor cell apoptosis and recruiting immune cells into the tumor area. Animal studies further showed that the colonization and growth of spontaneously metastatic melanoma cells in the liver and lung were suppressed by transdermal LPPC-DOX-CpG. Furthermore, NGS analysis revealed IFN-γ and NF-κB pathways were triggered to recruit and activate the antigen-presenting-cells and effecter cells, which could activate the anti-tumor responses as the major mechanism responsible for the therapeutic effect of LPPC-DOX-CpG. Finally, we have successfully proved transdermal LPPC-DOX-CpG as a promising penetrative carrier to activate systemic anti-tumor immunity against subcutaneous and metastatic tumor.

Anticancer peptide Q7 suppresses the growth and migration of human endometrial cancer by inhibiting DHCR24 expression and modulating the AKT-mediated pathway.

Endometrial cancer is one of the most common malignancy affecting women in developed countries. Resection uterus or lesion area is usually the first option for a simple and efficient therapy. Therefore, it is necessary to find a new therapeutic drug to reduce surgery areas to preserve fertility. Anticancer peptides (ACP) are bioactive amino acids with lower toxicity and higher specificity than chemical drugs. This study is to address an ACP, herein named Q7, which could downregulate 24-Dehydrocholesterol Reductase (DHCR24) to disrupt lipid rafts formation, and sequentially affect the AKT signal pathway of HEC-1-A cells to suppress their tumorigenicity such as proliferation and migration. Moreover, lipo-PEI-PEG-complex (LPPC) was used to enhance Q7 anticancer activity in vitro and efficiently show its effects on HEC-1-A cells. Furthermore, LPPC-Q7 exhibited a synergistic effect in combination with doxorubicin or paclitaxel. To summarize, Q7 was firstly proved to exhibit an anticancer effect on endometrial cancer cells and combined with LPPC efficiently improved the cytotoxicity of Q7.

iDVIP: identification and characterization of viral integrase inhibitory peptides.

Antiretroviral peptides are a kind of bioactive peptides that present inhibitory activity against retroviruses through various mechanisms. Among them, viral integrase inhibitory peptides (VINIPs) are a class of antiretroviral peptides that have the ability to block the action of integrase proteins, which is essential for retroviral replication. As the number of experimentally verified bioactive peptides has increased significantly, the lack of in silico machine learning approaches can effectively predict the peptides with the integrase inhibitory activity. Here, we have developed the first prediction model for identifying the novel VINIPs using the sequence characteristics, and the hybrid feature set was considered to improve the predictive ability. The performance was evaluated by 5-fold cross-validation based on the training dataset, and the result indicates the proposed model is capable of predicting the VINIPs, with a sensitivity of 85.82%, a specificity of 88.81%, an accuracy of 88.37%, a balanced accuracy of 87.32% and a Matthews correlation coefficient value of 0.64. Most importantly, the model also consistently provides effective performance in independent testing. To sum up, we propose the first computational approach for identifying and characterizing the VINIPs, which can be considered novel antiretroviral therapy agents. Ultimately, to facilitate further research and development, iDVIP, an automatic computational tool that predicts the VINIPs has been developed, which is now freely available at http://mer.hc.mmh.org.tw/iDVIP/.

Global characterization of macrophage polarization mechanisms and identification of M2-type polarization inhibitors.

Macrophages undergoing M1- versus M2-type polarization differ significantly in their cell metabolism and cellular functions. Here, global quantitative time-course proteomics and phosphoproteomics paired with transcriptomics provide a comprehensive characterization of temporal changes in cell metabolism, cellular functions, and signaling pathways that occur during the induction phase of M1- versus M2-type polarization. Significant differences in, especially, metabolic pathways are observed, including changes in glucose metabolism, glycosaminoglycan metabolism, and retinoic acid signaling. Kinase-enrichment analysis shows activation patterns of specific kinases that are distinct in M1- versus M2-type polarization. M2-type polarization inhibitor drug screens identify drugs that selectively block M2- but not M1-type polarization, including mitogen-activated protein kinase kinase (MEK) and histone deacetylase (HDAC) inhibitors. These datasets provide a comprehensive resource to identify specific signaling and metabolic pathways that are critical for macrophage polarization. In a proof-of-principle approach, we use these datasets to show that MEK signaling is required for M2-type polarization by promoting peroxisome proliferator-activated receptor-γ (PPARγ)-induced retinoic acid signaling.

Identification of subtypes of anticancer peptides based on sequential features and physicochemical properties.

Anticancer peptides (ACPs) are a kind of bioactive peptides which could be used as a novel type of anticancer drug that has several advantages over chemistry-based drug, including high specificity, strong tumor penetration capacity, and low toxicity to normal cells. As the number of experimentally verified bioactive peptides has increased significantly, various of in silico approaches are imperative for investigating the characteristics of ACPs. However, the lack of methods for investigating the differences in physicochemical properties of ACPs. In this study, we compared the N- and C-terminal amino acid composition for each peptide, there are three major subtypes of ACPs that are defined based on the distribution of positively charged residues. For the first time, we were motivated to develop a two-step machine learning model for identification of the subtypes of ACPs, which classify the input data into the corresponding group before applying the classifier. Further, to improve the predictive power, the hybrid feature sets were considered for prediction. Evaluation by five-fold cross-validation showed that the two-step model trained with sequence-based features and physicochemical properties was most effective in discriminating between ACPs and non-ACPs. The two-step model trained with the hybrid features performed well, with a sensitivity of 86.75%, a specificity of 85.75%, an accuracy of 86.08%, and a Matthews Correlation Coefficient value of 0.703. Furthermore, the model also consistently provides the effective performance in independent testing set, with sensitivity of 77.6%, specificity of 94.74%, accuracy of 88.99% and the MCC value reached 0.75. Finally, the two-step model has been implemented as a web-based tool, namely iDACP, which is now freely available at http://mer.hc.mmh.org.tw/iDACP/ .

UbiNet 2.0: a verified, classified, annotated and updated database of E3 ubiquitin ligase-substrate interactions.

Ubiquitination is an important post-translational modification, which controls protein turnover by labeling malfunctional and redundant proteins for proteasomal degradation, and also serves intriguing non-proteolytic regulatory functions. E3 ubiquitin ligases, whose substrate specificity determines the recognition of target proteins of ubiquitination, play crucial roles in ubiquitin-proteasome system. UbiNet 2.0 is an updated version of the database UbiNet. It contains 3332 experimentally verified E3-substrate interactions (ESIs) in 54 organisms and rich annotations useful for investigating the regulation of ubiquitination and the substrate specificity of E3 ligases. Based on the accumulated ESIs data, the recognition motifs in substrates for each E3 were also identified and a functional enrichment analysis was conducted on the collected substrates. To facilitate the research on ESIs with different categories of E3 ligases, UbiNet 2.0 performed strictly evidence-based classification of the E3 ligases in the database based on their mechanisms of ubiquitin transfer and substrate specificity. The platform also provides users with an interactive tool that can visualize the ubiquitination network of a group of self-defined proteins, displaying ESIs and protein-protein interactions in a graphical manner. The tool can facilitate the exploration of inner regulatory relationships mediated by ubiquitination among proteins of interest. In summary, UbiNet 2.0 is a user-friendly web-based platform that provides comprehensive as well as updated information about experimentally validated ESIs and a visualized tool for the construction of ubiquitination regulatory networks available at http://awi.cuhk.edu.cn/~ubinet/index.php.

Metagenomic analysis of the gut microbiome composition associated with vitamin D supplementation in Taiwanese infants.

Early childhood is a critical stage for the foundation and development of the gut microbiome, large amounts of essential nutrients are required such as vitamin D. Vitamin D plays an important role in regulating calcium homeostasis, and deficiency can impair bone mineralization. In addition, most people know that breastfeeding is advocated to be the best thing for a newborn; however, exclusively breastfeeding infants are not easily able to absorb an adequate amount of vitamin D from breast milk. Understanding the effects of vitamin D supplementation on gut microbiome can improve the knowledge of infant health and development. A total of 62 fecal sample from healthy infants were collected in Taiwan. Of the 62 infants, 31 were exclusively breastfed infants and 31 were mixed- or formula-fed infants. For each feeding type, one subgroup of infants received 400 IU of vitamin D per day, and the remaining infants received a placebo. In total, there are 15 breastfed and 20 formula-fed infants with additional vitamin D supplementation, and 16 breastfed and 11 formula-fed infants belong to control group, respectively. We performed a comparative metagenomic analysis to investigate the distribution and diversity of infant gut microbiota among different types of feeding regimes with and without vitamin D supplementation. Our results reveal that the characteristics of infant gut microbiota not only depend on the feeding types but also on nutrients intake, and demonstrated that the vitamin D plays an important role in modulating the infant gut microbiota, especially increase the proportion of probiotics in breast-fed infants.

iDPGK: characterization and identification of lysine phosphoglycerylation sites based on sequence-based features.

BACKGROUND: Protein phosphoglycerylation, the addition of a 1,3-bisphosphoglyceric acid (1,3-BPG) to a lysine residue of a protein and thus to form a 3-phosphoglyceryl-lysine, is a reversible and non-enzymatic post-translational modification (PTM) and plays a regulatory role in glucose metabolism and glycolytic process. As the number of experimentally verified phosphoglycerylated sites has increased significantly, statistical or machine learning methods are imperative for investigating the characteristics of phosphoglycerylation sites. Currently, research into phosphoglycerylation is very limited, and only a few resources are available for the computational identification of phosphoglycerylation sites. RESULT: We present a bioinformatics investigation of phosphoglycerylation sites based on sequence-based features. The TwoSampleLogo analysis reveals that the regions surrounding the phosphoglycerylation sites contain a high relatively of positively charged amino acids, especially in the upstream flanking region. Additionally, the non-polar and aliphatic amino acids are more abundant surrounding phosphoglycerylated lysine following the results of PTM-Logo, which may play a functional role in discriminating between phosphoglycerylation and non-phosphoglycerylation sites. Many types of features were adopted to build the prediction model on the training dataset, including amino acid composition, amino acid pair composition, positional weighted matrix and position-specific scoring matrix. Further, to improve the predictive power, numerous top features ranked by F-score were considered as the final combination for classification, and thus the predictive models were trained using DT, RF and SVM classifiers. Evaluation by five-fold cross-validation showed that the selected features was most effective in discriminating between phosphoglycerylated and non-phosphoglycerylated sites. CONCLUSION: The SVM model trained with the selected sequence-based features performed well, with a sensitivity of 77.5%, a specificity of 73.6%, an accuracy of 74.9%, and a Matthews Correlation Coefficient value of 0.49. Furthermore, the model also consistently provides the effective performance in independent testing set, yielding sensitivity of 75.7% and specificity of 64.9%. Finally, the model has been implemented as a web-based system, namely iDPGK, which is now freely available at http://mer.hc.mmh.org.tw/iDPGK/ .

Incorporating deep learning and multi-omics autoencoding for analysis of lung adenocarcinoma prognostication.

Lung cancer is the most occurring cancer type, and its mortality rate is also the highest, among them lung adenocarcinoma (LUAD) accounts for about 40 % of lung cancer. There is an urgent need to develop a prognosis prediction model for lung adenocarcinoma. Previous LUAD prognosis studies only took single-omics data, such as mRNA or miRNA, into consideration. To this end, we proposed a deep learning-based autoencoding approach for combination of four-omics data, mRNA, miRNA, DNA methylation and copy number variations, to construct an autoencoder model, which learned representative features to differentiate the two optimal patient subgroups with a significant difference in survival (P = 4.08e-09) and good consistency index (C-index = 0.65). The multi-omics model was validated though four independent datasets, i.e. GSE81089 for mRNA (n = 198, P = 0.0083), GSE63805 for miRNA (n = 32, P = 0.018), GSE63384 for DNA methylation (n = 35, P = 0.009), and TCGA independent samples for copy number variations (n = 94, P = 0.0052). Finally, a functional analysis was performed on two survival subgroups to discover genes involved in biological processes and pathways. This is the first study incorporating deep autoencoding and four-omics data to construct a robust survival prediction model, and results show the approach is useful at predicting LUAD prognostication.

SuccSite: Incorporating Amino Acid Composition and Informative k-spaced Amino Acid Pairs to Identify Protein Succinylation Sites.

Protein succinylation is a biochemical reaction in which a succinyl group (-CO-CH2-CH2-CO-) is attached to the lysine residue of a protein molecule. Lysine succinylation plays important regulatory roles in living cells. However, studies in this field are limited by the difficulty in experimentally identifying the substrate site specificity of lysine succinylation. To facilitate this process, several tools have been proposed for the computational identification of succinylated lysine sites. In this study, we developed an approach to investigate the substrate specificity of lysine succinylated sites based on amino acid composition. Using experimentally verified lysine succinylated sites collected from public resources, the significant differences in position-specific amino acid composition between succinylated and non-succinylated sites were represented using the Two Sample Logo program. These findings enabled the adoption of an effective machine learning method, support vector machine, to train a predictive model with not only the amino acid composition, but also the composition of k-spaced amino acid pairs. After the selection of the best model using a ten-fold cross-validation approach, the selected model significantly outperformed existing tools based on an independent dataset manually extracted from published research articles. Finally, the selected model was used to develop a web-based tool, SuccSite, to aid the study of protein succinylation. Two proteins were used as case studies on the website to demonstrate the effective prediction of succinylation sites. We will regularly update SuccSite by integrating more experimental datasets. SuccSite is freely accessible at http://csb.cse.yzu.edu.tw/SuccSite/.

miRTarBase 2020: updates to the experimentally validated microRNA-target interaction database.

MicroRNAs (miRNAs) are small non-coding RNAs (typically consisting of 18-25 nucleotides) that negatively control expression of target genes at the post-transcriptional level. Owing to the biological significance of miRNAs, miRTarBase was developed to provide comprehensive information on experimentally validated miRNA-target interactions (MTIs). To date, the database has accumulated >13,404 validated MTIs from 11,021 articles from manual curations. In this update, a text-mining system was incorporated to enhance the recognition of MTI-related articles by adopting a scoring system. In addition, a variety of biological databases were integrated to provide information on the regulatory network of miRNAs and its expression in blood. Not only targets of miRNAs but also regulators of miRNAs are provided to users for investigating the up- and downstream regulations of miRNAs. Moreover, the number of MTIs with high-throughput experimental evidence increased remarkably (validated by CLIP-seq technology). In conclusion, these improvements promote the miRTarBase as one of the most comprehensively annotated and experimentally validated miRNA-target interaction databases. The updated version of miRTarBase is now available at http://miRTarBase.cuhk.edu.cn/.

Rapid classification of group B Streptococcus serotypes based on matrix-assisted laser desorption ionization-time of flight mass spectrometry and machine learning techniques.

BACKGROUND: Group B streptococcus (GBS) is an important pathogen that is responsible for invasive infections, including sepsis and meningitis. GBS serotyping is an essential means for the investigation of possible infection outbreaks and can identify possible sources of infection. Although it is possible to determine GBS serotypes by either immuno-serotyping or geno-serotyping, both traditional methods are time-consuming and labor-intensive. In recent years, the matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) has been reported as an effective tool for the determination of GBS serotypes in a more rapid and accurate manner. Thus, this work aims to investigate GBS serotypes by incorporating machine learning techniques with MALDI-TOF MS to carry out the identification. RESULTS: In this study, a total of 787 GBS isolates, obtained from three research and teaching hospitals, were analyzed by MALDI-TOF MS, and the serotype of the GBS was determined by a geno-serotyping experiment. The peaks of mass-to-charge ratios were regarded as the attributes to characterize the various serotypes of GBS. Machine learning algorithms, such as support vector machine (SVM) and random forest (RF), were then used to construct predictive models for the five different serotypes (Types Ia, Ib, III, V, and VI). After optimization of feature selection and model generation based on training datasets, the accuracies of the selected models attained 54.9-87.1% for various serotypes based on independent testing data. Specifically, for the major serotypes, namely type III and type VI, the accuracies were 73.9 and 70.4%, respectively. CONCLUSION: The proposed models have been adopted to implement a web-based tool (GBSTyper), which is now freely accessible at http://csb.cse.yzu.edu.tw/GBSTyper/, for providing efficient and effective detection of GBS serotypes based on a MALDI-TOF MS spectrum. Overall, this work has demonstrated that the combination of MALDI-TOF MS and machine intelligence could provide a practical means of clinical pathogen testing.

Characterization and Identification of Lysine Succinylation Sites based on Deep Learning Method.

Succinylation is a type of protein post-translational modification (PTM), which can play important roles in a variety of cellular processes. Due to an increasing number of site-specific succinylated peptides obtained from high-throughput mass spectrometry (MS), various tools have been developed for computationally identifying succinylated sites on proteins. However, most of these tools predict succinylation sites based on traditional machine learning methods. Hence, this work aimed to carry out the succinylation site prediction based on a deep learning model. The abundance of MS-verified succinylated peptides enabled the investigation of substrate site specificity of succinylation sites through sequence-based attributes, such as position-specific amino acid composition, the composition of k-spaced amino acid pairs (CKSAAP), and position-specific scoring matrix (PSSM). Additionally, the maximal dependence decomposition (MDD) was adopted to detect the substrate signatures of lysine succinylation sites by dividing all succinylated sequences into several groups with conserved substrate motifs. According to the results of ten-fold cross-validation, the deep learning model trained using PSSM and informative CKSAAP attributes can reach the best predictive performance and also perform better than traditional machine-learning methods. Moreover, an independent testing dataset that truly did not exist in the training dataset was used to compare the proposed method with six existing prediction tools. The testing dataset comprised of 218 positive and 2621 negative instances, and the proposed model could yield a promising performance with 84.40% sensitivity, 86.99% specificity, 86.79% accuracy, and an MCC value of 0.489. Finally, the proposed method has been implemented as a web-based prediction tool (CNN-SuccSite), which is now freely accessible at http://csb.cse.yzu.edu.tw/CNN-SuccSite/ .

Increase Trichomonas vaginalis detection based on urine routine analysis through a machine learning approach.

Trichomonas vaginalis (T. vaginalis) detection remains an unsolved problem in using of automated instruments for urinalysis. The study proposes a machine learning (ML)-based strategy to increase the detection rate of T. vaginalis in urine. On the basis of urinalysis data from a teaching hospital during 2009-2013, individuals underwent at least one urinalysis test were included. Logistic regression, support vector machine, and random forest, were used to select specimens with a high risk of T. vaginalis infection for confirmation through microscopic examinations. A total of 410,952 and 428,203 specimens from men and women were tested, of which 91 (0.02%) and 517 (0.12%) T. vaginalis-positive specimens were reported, respectively. The prediction models of T. vaginalis infection attained an area under the receiver operating characteristic curve of more than 0.87 for women and 0.83 for men. The Lift values of the top 5% risky specimens were above eight. While the most risky vigintile was picked out by the models and confirmed by microscopic examination, the incremental cost-effectiveness ratios for T. vaginalis detection in men and women were USD$170.1 and USD$29.7, respectively. On the basis of urinalysis, the proposed strategy can significantly increase the detection rate of T. vaginalis in a cost-effective manner.