A risk assessment framework for multidrug-resistant Staphylococcus aureus using machine learning and mass spectrometry technology.

The emergence of multidrug-resistant bacteria is a critical global crisis that poses a serious threat to public health, particularly with the rise of multidrug-resistant Staphylococcus aureus. Accurate assessment of drug resistance is essential for appropriate treatment and prevention of transmission of these deadly pathogens. Early detection of drug resistance in patients is critical for providing timely treatment and reducing the spread of multidrug-resistant bacteria. This study aims to develop a novel risk assessment framework for S. aureus that can accurately determine the resistance to multiple antibiotics. The comprehensive 7-year study involved ˃20 000 isolates with susceptibility testing profiles of six antibiotics. By incorporating mass spectrometry and machine learning, the study was able to predict the susceptibility to four different antibiotics with high accuracy. To validate the accuracy of our models, we externally tested on an independent cohort and achieved impressive results with an area under the receiver operating characteristic curve of 0. 94, 0.90, 0.86 and 0.91, and an area under the precision-recall curve of 0.93, 0.87, 0.87 and 0.81, respectively, for oxacillin, clindamycin, erythromycin and trimethoprim-sulfamethoxazole. In addition, the framework evaluated the level of multidrug resistance of the isolates by using the predicted drug resistance probabilities, interpreting them in the context of a multidrug resistance risk score and analyzing the performance contribution of different sample groups. The results of this study provide an efficient method for early antibiotic decision-making and a better understanding of the multidrug resistance risk of S. aureus.

dbAMP 2.0: updated resource for antimicrobial peptides with an enhanced scanning method for genomic and proteomic data.

The last 18 months, or more, have seen a profound shift in our global experience, with many of us navigating a once-in-100-year pandemic. To date, COVID-19 remains a life-threatening pandemic with little to no targeted therapeutic recourse. The discovery of novel antiviral agents, such as vaccines and drugs, can provide therapeutic solutions to save human beings from severe infections; however, there is no specifically effective antiviral treatment confirmed for now. Thus, great attention has been paid to the use of natural or artificial antimicrobial peptides (AMPs) as these compounds are widely regarded as promising solutions for the treatment of harmful microorganisms. Given the biological significance of AMPs, it was obvious that there was a significant need for a single platform for identifying and engaging with AMP data. This led to the creation of the dbAMP platform that provides comprehensive information about AMPs and facilitates their investigation and analysis. To date, the dbAMP has accumulated 26 447 AMPs and 2262 antimicrobial proteins from 3044 organisms using both database integration and manual curation of >4579 articles. In addition, dbAMP facilitates the evaluation of AMP structures using I-TASSER for automated protein structure prediction and structure-based functional annotation, providing predictive structure information for clinical drug development. Next-generation sequencing (NGS) and third-generation sequencing have been applied to generate large-scale sequencing reads from various environments, enabling greatly improved analysis of genome structure. In this update, we launch an efficient online tool that can effectively identify AMPs from genome/metagenome and proteome data of all species in a short period. In conclusion, these improvements promote the dbAMP as one of the most abundant and comprehensively annotated resources for AMPs. The updated dbAMP is now freely accessible at http://awi.cuhk.edu.cn/dbAMP.

Large-scale mass spectrometry data combined with demographics analysis rapidly predicts methicillin resistance in Staphylococcus aureus.

BACKGROUND: A mass spectrometry-based assessment of methicillin resistance in Staphylococcus aureus would have huge potential in addressing fast and effective prediction of antibiotic resistance. Since delays in the traditional antibiotic susceptibility testing, methicillin-resistant S. aureus remains a serious threat to human health. RESULTS: Here, linking a 7 years of longitudinal study from two cohorts in the Taiwan area of over 20 000 individually resolved methicillin susceptibility testing results, we identify associations of methicillin resistance with the demographics and mass spectrometry data. When combined together, these connections allow for machine-learning-based predictions of methicillin resistance, with an area under the receiver operating characteristic curve of >0.85 in both the discovery [95% confidence interval (CI) 0.88-0.90] and replication (95% CI 0.84-0.86) populations. CONCLUSIONS: Our predictive model facilitates early detection for methicillin resistance of patients with S. aureus infection. The large-scale antibiotic resistance study has unbiasedly highlighted putative candidates that could improve trials of treatment efficiency and inform on prescriptions.

A large-scale investigation and identification of methicillin-resistant Staphylococcus aureus based on peaks binning of matrix-assisted laser desorption ionization-time of flight MS spectra.

Recent studies have demonstrated that the matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) could be used to detect superbugs, such as methicillin-resistant Staphylococcus aureus (MRSA). Due to an increasingly clinical need to classify between MRSA and methicillin-sensitive Staphylococcus aureus (MSSA) efficiently and effectively, we were motivated to develop a systematic pipeline based on a large-scale dataset of MS spectra. However, the shifting problem of peaks in MS spectra induced a low effectiveness in the classification between MRSA and MSSA isolates. Unlike previous works emphasizing on specific peaks, this study employs a binning method to cluster MS shifting ions into several representative peaks. A variety of bin sizes were evaluated to coalesce drifted or shifted MS peaks to a well-defined structured data. Then, various machine learning methods were performed to carry out the classification between MRSA and MSSA samples. Totally 4858 MS spectra of unique S. aureus isolates, including 2500 MRSA and 2358 MSSA instances, were collected by Chang Gung Memorial Hospitals, at Linkou and Kaohsiung branches, Taiwan. Based on the evaluation of Pearson correlation coefficients and the strategy of forward feature selection, a total of 200 peaks (with the bin size of 10 Da) were identified as the marker attributes for the construction of predictive models. These selected peaks, such as bins 2410-2419, 2450-2459 and 6590-6599 Da, have indicated remarkable differences between MRSA and MSSA, which were effective in the prediction of MRSA. The independent testing has revealed that the random forest model can provide a promising prediction with the area under the receiver operating characteristic curve (AUC) at 0.8450. When comparing to previous works conducted with hundreds of MS spectra, the proposed scheme demonstrates that incorporating machine learning method with a large-scale dataset of clinical MS spectra may be a feasible means for clinical physicians on the administration of correct antibiotics in shorter turn-around-time, which could reduce mortality, avoid drug resistance and shorten length of stay in hospital in the future.

Towards Accurate Identification of Antibiotic-Resistant Pathogens through the Ensemble of Multiple Preprocessing Methods Based on MALDI-TOF Spectra.

Matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) has been used to identify microorganisms and predict antibiotic resistance. The preprocessing method for the MS spectrum is key to extracting critical information from complicated MS spectral data. Different preprocessing methods yield different data, and the optimal approach is unclear. In this study, we adopted an ensemble of multiple preprocessing methods--FlexAnalysis, MALDIquant, and continuous wavelet transform-based methods--to detect peaks and build machine learning classifiers, including logistic regressions, naïve Bayes classifiers, random forests, and a support vector machine. The aim was to identify antibiotic resistance in Acinetobacter baumannii, Acinetobacter nosocomialis, Enterococcus faecium, and Group B Streptococci (GBS) based on MALDI-TOF MS spectra collected from two branches of a referral tertiary medical center. The ensemble method was compared with the individual methods. Random forest models built with the data preprocessed by the ensemble method outperformed individual preprocessing methods and achieved the highest accuracy, with values of 84.37% (A. baumannii), 90.96% (A. nosocomialis), 78.54% (E. faecium), and 70.12% (GBS) on independent testing datasets. Through feature selection, important peaks related to antibiotic resistance could be detected from integrated information. The prediction model can provide an opinion for clinicians. The discriminative peaks enabling better prediction performance can provide a reference for further investigation of the resistance mechanism.

Characterization and identification of antimicrobial peptides with different functional activities.

In recent years, antimicrobial peptides (AMPs) have become an emerging area of focus when developing therapeutics hot spot residues of proteins are dominant against infections. Importantly, AMPs are produced by virtually all known living organisms and are able to target a wide range of pathogenic microorganisms, including viruses, parasites, bacteria and fungi. Although several studies have proposed different machine learning methods to predict peptides as being AMPs, most do not consider the diversity of AMP activities. On this basis, we specifically investigated the sequence features of AMPs with a range of functional activities, including anti-parasitic, anti-viral, anti-cancer and anti-fungal activities and those that target mammals, Gram-positive and Gram-negative bacteria. A new scheme is proposed to systematically characterize and identify AMPs and their functional activities. The 1st stage of the proposed approach is to identify the AMPs, while the 2nd involves further characterization of their functional activities. Sequential forward selection was employed to extract potentially informative features that are possibly associated with the functional activities of the AMPs. These features include hydrophobicity, the normalized van der Waals volume, polarity, charge and solvent accessibility-all of which are essential attributes in classifying between AMPs and non-AMPs. The results revealed the 1st stage AMP classifier was able to achieve an area under the receiver operating characteristic curve (AUC) value of 0.9894. During the 2nd stage, we found pseudo amino acid composition to be an informative attribute when differentiating between AMPs in terms of their functional activities. The independent testing results demonstrated that the AUCs of the multi-class models were 0.7773, 0.9404, 0.8231, 0.8578, 0.8648, 0.8745 and 0.8672 for anti-parasitic, anti-viral, anti-cancer, anti-fungal AMPs and those that target mammals, Gram-positive and Gram-negative bacteria, respectively. The proposed scheme helps facilitate biological experiments related to the functional analysis of AMPs. Additionally, it was implemented as a user-friendly web server (AMPfun, http://fdblab.csie.ncu.edu.tw/AMPfun/index.html) that allows individuals to explore the antimicrobial functions of peptides of interest.

Characterization and Identification of Natural Antimicrobial Peptides on Different Organisms.

Because of the rapid development of multidrug resistance, conventional antibiotics cannot kill pathogenic bacteria efficiently. New antibiotic treatments such as antimicrobial peptides (AMPs) can provide a possible solution to the antibiotic-resistance crisis. However, the identification of AMPs using experimental methods is expensive and time-consuming. Meanwhile, few studies use amino acid compositions (AACs) and physicochemical properties with different sequence lengths against different organisms to predict AMPs. Therefore, the major purpose of this study is to identify AMPs on seven categories of organisms, including amphibians, humans, fish, insects, plants, bacteria, and mammals. According to the one-rule attribute evaluation, the selected features were used to construct the predictive models based on the random forest algorithm. Compared to the accuracies of iAMP-2L (a web-server for identifying AMPs and their functional types), ADAM (a database of AMP), and MLAMP (a multi-label AMP classifier), the proposed method yielded higher than 92% in predicting AMPs on each category. Additionally, the sensitivities of the proposed models in the prediction of AMPs of seven organisms were higher than that of all other tools. Furthermore, several physicochemical properties (charge, hydrophobicity, polarity, polarizability, secondary structure, normalized van der Waals volume, and solvent accessibility) of AMPs were investigated according to their sequence lengths. As a result, the proposed method is a practical means to complement the existing tools in the characterization and identification of AMPs in different organisms.

Association of Fenofibrate and Diabetic Retinopathy in Type 2 Diabetic Patients: A Population-Based Retrospective Cohort Study in Taiwan.

Background and Objectives: Fenofibrate, a PPAR-α agonist, has been demonstrated to reduce the progression of diabetic retinopathy (DR) and the need for laser treatment in a FIELD (Fenofibrate Intervention and Event Lowering in Diabetes) study. However, in the subgroup of patients without pre-existing DR, there was no significant difference in the progression of DR between the fenofibrate group and the placebo group. In this study, we aim to investigate whether fenofibrate can decrease the risk of incident DR in a population-based cohort study of type 2 diabetic patients in Taiwan. Materials and Methods: A total of 32,253 type 2 diabetic patients without previous retinopathy were retrieved from 892,419 patients in 2001-2002. They were then divided into two groups based on whether they were exposed to fenofibrate or not. The patients were followed until a diagnosis of diabetic retinopathy was made or until the year 2008. Results: With a follow-up period of 6.8 ± 1.5 years and 5.4 ± 2.6 years for 2500 fenofibrate users and 29,753 non-users, respectively, the Cox proportional hazard regression analysis revealed that the hazard ratio (HR) of new onset retinopathy was 0.57 (95% CI 0.57-0.62, p < 0.001). After adjusting for hypertension; the Charlson comorbidity index (CCI); and medications such as angiotensin-converting enzyme inhibitors (ACE-I), angiotensin receptor blockers (ARB), anticoagulants, gemfibrozil, statins, and hypoglycemic agents, the adjusted HR was 0.75 (95% CI 0.68-0.82, p < 0.001). The need for laser treatment has an HR and adjusted HR of 0.59 (95% CI 0.49-0.71, p < 0.001) and 0.67 (95% CI 0.56-0.81, p < 0.001), respectively. Conclusion: Our study showed that the long-term and regular use of fenofibrate may decrease the risk of incident retinopathy and the need for laser treatment in type 2 diabetic patients. Since there are limitations associated with our study, further investigations are necessary to confirm such an association.

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.

Plasma miRNA profile is a biomarker associated with urothelial carcinoma in chronic hemodialysis patients.

The incidence of urothelial carcinoma (UC) is higher in patients undergoing chronic dialysis than in the general population. This study investigated plasma miRNA profiling as the ancillary diagnosis biomarker associated with UC in patients undergoing chronic hemodialysis. We successfully screened out and detected miRNA expression from plasma in eight patients undergoing dialysis through quantitative real-time PCR array analysis and identified eight candidate miRNAs. The candidate miRNAs were then validated using single quantitative RT-PCR assays from 52 plasma samples. The miRNA classifier for ancillary UC detection was developed by multiple logistic regression analyses. Moreover, we validated the classifier by testing another nine samples. Expression levels of miR-150-5p, miR-150-5p/miR-155-5p, miR-378a-3p/miR-150-5p, miR-636/miR-150-5p, miR-150-5p/miR-210-3p, and miR-19b-1-5p/miR-378a-3p were shown to be significantly different between UC and non-UC samples (P = 0.035, 0.0048, 0.016, 0.024, 0.038, and 0.048). Kaplan-Meier curve analysis also showed that low miR-19b-1-5p expression was associated with a worse prognosis (P = 0.0382). We also developed a miRNA classifier based on five miRNA expression levels to predict UC and found that the area under curve was 0.882. The classifier had a sensitivity of 80% (95% confidence interval: 0.5191% to 0.9567%) and a specificity of 83.7% (95% confidence interval: 0.6799% to 0.9381%). This classifier was tested by nine samples with 100% accuracy. The miRNA classifier offers higher sensitivity and specificity than the existing makers. Thus, this approach will improve the prospective diagnosis of UC in patients undergoing chronic hemodialysis.

Performance enhancement of procalcitonin by high-sensitivity C-reactive protein at the optimal cutoff in predicting bacteremia in emergency department adult patients.

Pathogenic bacteremia portends a high mortality risk in adult patients admitted to an Emergency Department (ED). This study aims to investigate the effect of adding high-sensitivity C-reactive protein (hs-CRP) to procalcitonin (PCT) and lactate in predicting bacteremia, Gram-negative (GNB) and Gram-positive bacteremia (GPB), using the optimal cutoff derived from the receiver operating characteristics analysis. We evaluated the diagnostic measures, including the positive-test likelihood (LR+), the negative-test likelihood (LR-), and the diagnostic odds ratio (DOR) using a single-center retrospective analysis design. This Standards for Reporting Diagnostic-compliant study comprised 886 consecutive adults who were admitted to the ED in 2010; to this cohort, a 22.2% prevalence of true bacteremia was subsequently confirmed. At the cutoff of 3.9 µg/L, PCT had a DOR of 5.3 (95% confidence interval [CI]: 3.76-7.61) and LR + of 2.8 (95% CI: 2.3-3.4) in predicting overall bacteremia. Elevated PCT and lactate (cutoff at 2 mmol/L), increased the DOR and LR + to 6.3 (95% CI: 4.27-9.29) and 4.0 (95% CI: 3.1-5.2). The DOR and LR + were further improved to 7.1 (95% CI: 4.2-11.95) and 5.6 (95% CI: 3.7-8.6), respectively, when hs-CRP at the cutoff of 1238 nmol/L was added to PCT plus lactate. High-sensitivity CRP at the cutoff of 1,255 nmol/L can enhance the discriminative power raising DOR and LR + values for GPB. The elevation of hs-CRP at the optimal cutoff might improve the diagnostic performance to predict unspecified bacteremia and GPB, but not GNB.

Risk of Autoimmune Disease in Adults with Chronic Insomnia Requiring Sleep-Inducing Pills: A Population-Based Longitudinal Study.

BACKGROUND: Recent studies indicate that chronic insomnia is associated with the development of certain somatic diseases. Whether it would be associated with the development of an autoimmune disease (AID) was unknown. OBJECTIVE: We aimed to examine the association and quantify the magnitude of risk for AID in individuals suffering from chronic insomnia requiring sleep-inducing pills. DESIGN: This was a population-based, nationwide longitudinal study. PARTICIPANTS: Using a claims data set containing 1 million randomly sampled, insured subjects derived from the National Health Insurance Research Database, we assembled a chronic insomnia group and a 1:3 propensity score-matched comparison group (CP), which were balanced in terms of sex, age, insurance premium, urbanization, alcohol use disorder, smoking-related diagnoses, and morbid obesity. MAIN MEASURES: Person-time data with incidence rate, adjusted hazard ratios (aHR) by the Cox model, AID-free survival functions compared with the log-rank test, and a sensitivity analysis on the time lag effect were presented. Incident AID within the first year of follow-up were excluded. The error rate was controlled using the Benjamini-Hochberg procedure. KEY RESULTS: With 39,550 and 129,914 person-years' follow-up for the chronic insomnia and CP groups (n = 5,736 and 17,208), respectively, we found an increased risk for subsequent AID, representing a 70 % increase in the aHR (1.7; 95 % confidence interval [CI], 1.5-1.9, p < 0.0001). A positive association between chronic insomnia and primary Sjögren's syndrome (pSS) was observed (aHR, 1.3; 95 % CI, 1.1-1.6). Sensitivity analysis disclosed that AID risk was even stronger after 5 years of follow-up (aHR, 2.0; 95 % CI, 1.7-2.4). CONCLUSION: Chronic insomnia requiring sleep-inducing pills may be associated with a 70 % increased risk for future AID, particularly pSS.

Population-based cohort study on the risk of malignancy in East Asian children with juvenile idiopathic arthritis.

BACKGROUND: To investigate the association and magnitude of risk between JIA, its associated treatment and cancer development in Taiwanese children. METHODS: Nationwide population-based 1:4 age- and gender-matched retrospective cohort study was designed using the National Health Insurance Research Database of Taiwan. A cohort of 2,892 children <16 years old with JIA was formed as well as a non-JIA cohort of 11,568 in year 2003 to 2005. They were followed up till a diagnosis of malignancy or up to 8 years until 2010. Relative risk (RR), incidence rate ratio (IRR), and adjusted hazard ratio (aHR) of developing malignancy were calculated. RESULTS: The female to male ratio was 0.79:1. There were 3 cases of incident cancer in the "MTX use, biologics-naïve" group, only 1 in the anti-TNF biologics-containing group and 29 in the "both MTX- and biologics-naïve" group, in comparison, there were 50 cases of cancer in the non-JIA comparator group. During a 16114.16 patient-years follow-up, the RR and IRR for developing a malignancy in both methotrexate- and anti-tumor necrosis factor (TNF) biologics-naïve JIA children were 2.75 (95% confidence interval, 1.75 - 4.32) and 3.21 (2.01 - 5.05), respectively. For leukemia, the IRR was 7.38 (2.50 - 22.75); lymphoma, 8.30 (1.23 - 69.79); and soft tissue sarcoma, 11.07 (0.84 - 326.4). The IRR of other cancers was 2.08 (1.11 - 3.71). The aHR on cancer risk was 3.14 (1.98 - 4.98) in methotrexate- and biologics-naïve group. There were no statistically significant increased risk in JIA patients treated with methotrexate and/or anti-TNF biologics. CONCLUSIONS: Compared with children without JIA, children with JIA have 3-fold increase of risk on malignancy in East Asia. Seemingly neither methotrexate nor anti-TNF biologics increases the risk further.

An enhanced computational platform for investigating the roles of regulatory RNA and for identifying functional RNA motifs.

BACKGROUND: Functional RNA molecules participate in numerous biological processes, ranging from gene regulation to protein synthesis. Analysis of functional RNA motifs and elements in RNA sequences can obtain useful information for deciphering RNA regulatory mechanisms. Our previous work, RegRNA, is widely used in the identification of regulatory motifs, and this work extends it by incorporating more comprehensive and updated data sources and analytical approaches into a new platform. METHODS AND RESULTS: An integrated web-based system, RegRNA 2.0, has been developed for comprehensively identifying the functional RNA motifs and sites in an input RNA sequence. Numerous data sources and analytical approaches are integrated, and several types of functional RNA motifs and sites can be identified by RegRNA 2.0: (i) splicing donor/acceptor sites; (ii) splicing regulatory motifs; (iii) polyadenylation sites; (iv) ribosome binding sites; (v) rho-independent terminator; (vi) motifs in mRNA 5'-untranslated region (5'UTR) and 3'UTR; (vii) AU-rich elements; (viii) C-to-U editing sites; (ix) riboswitches; (x) RNA cis-regulatory elements; (xi) transcriptional regulatory motifs; (xii) user-defined motifs; (xiii) similar functional RNA sequences; (xiv) microRNA target sites; (xv) non-coding RNA hybridization sites; (xvi) long stems; (xvii) open reading frames; (xviii) related information of an RNA sequence. User can submit an RNA sequence and obtain the predictive results through RegRNA 2.0 web page. CONCLUSIONS: RegRNA 2.0 is an easy to use web server for identifying regulatory RNA motifs and functional sites. Through its integrated user-friendly interface, user is capable of using various analytical approaches and observing results with graphical visualization conveniently. RegRNA 2.0 is now available at http://regrna2.mbc.nctu.edu.tw.

EuLoc: a web-server for accurately predict protein subcellular localization in eukaryotes by incorporating various features of sequence segments into the general form of Chou's PseAAC.

The function of a protein is generally related to its subcellular localization. Therefore, knowing its subcellular localization is helpful in understanding its potential functions and roles in biological processes. This work develops a hybrid method for computationally predicting the subcellular localization of eukaryotic protein. The method is called EuLoc and incorporates the Hidden Markov Model (HMM) method, homology search approach and the support vector machines (SVM) method by fusing several new features into Chou's pseudo-amino acid composition. The proposed SVM module overcomes the shortcoming of the homology search approach in predicting the subcellular localization of a protein which only finds low-homologous or non-homologous sequences in a protein subcellular localization annotated database. The proposed HMM modules overcome the shortcoming of SVM in predicting subcellular localizations using few data on protein sequences. Several features of a protein sequence are considered, including the sequence-based features, the biological features derived from PROSITE, NLSdb and Pfam, the post-transcriptional modification features and others. The overall accuracy and location accuracy of EuLoc are 90.5 and 91.2 %, respectively, revealing a better predictive performance than obtained elsewhere. Although the amounts of data of the various subcellular location groups in benchmark dataset differ markedly, the accuracies of 12 subcellular localizations of EuLoc range from 82.5 to 100 %, indicating that this tool is much more balanced than other tools. EuLoc offers a high, balanced predictive power for each subcellular localization. EuLoc is now available on the web at http://euloc.mbc.nctu.edu.tw/.

Metachronous colorectal cancer in Taiwan: analyzing 20 years of data from Taiwan Cancer Registry.

BACKGROUND: The risk of metachronous colorectal cancer in patients with colorectal cancer is higher than the rate of sporadic colorectal cancer in the average population. We conducted a large-scale, population-based study, with many more clinical cases than in previously published studies, to calculate the incidence of metachronous colorectal cancer. METHODS: This is a retrospective study based on data obtained from the Taiwan Cancer Registry from 1988 to 2007. Between 1988 and 2002, we analyzed 70,906 patients who were diagnosed with colon or rectal cancer and traced the occurrence of metachronous lesions with at least 5 years of follow-up. RESULTS: Of these patients, 1,192 (730 males, 462 females; mean age 62.73 ± 12.92 years) developed metachronous cancers. The 15-year cumulative incidence of metachronous cancer was 1.68%. Within 2 years of the index cancer, 51.69% of the metachronous cancers appeared, and 61.27% of the metachronous cancers appeared within 3 years. CONCLUSIONS: Most metachronous lesions were noted within 3 years of initial diagnosis of the index cancer. Surveillance colonoscopy to ensure the absence of metachronous disease is essential for patients after curative surgery within 1 year, especially for those patients who did not receive complete colonoscopy before their first operation for colorectal cancer.

Burden of systemic lupus erythematosus in Taiwan: a population-based survey.

This population-based study aimed to determine the trend of incidence, prevalence, and mortality of systemic lupus erythematosus (SLE) in a 6-year period in Taiwan. Patients with international classification of diseases ninth revision (ICD-9) code 710.0 were retrieved from the Taiwanese National Health Insurance Research Database (NHIRD), which covered more than 96 % of the entire population, and from the Ministry of Interior between 2003 and 2008 in Taiwan. Patients with SLE registered as catastrophic illness were enrolled for analysis. The incidence rate, prevalence ratio, and mortality rate stratified by sex and age were analyzed. There were a total of 6,675 SLE patients (5,836 females and 839 in males) during the study period. The average annual incidence rate was 4.87 per 100,000 population, and the average female-to-male incidence ratio was 7.15. The ratio increased with age and peaked at the age of 40-49 years, then decreased thereafter. The incidence rate decreased by 4.2 % per year. The highest incidence rate was noted in the 20-29-year-old age group in females and the 70-79-year-old age group in males. The average prevalence and mortality rates were 97.5 and 1.2 per 100,000 population, respectively. Mortality was 3.2 % in patients diagnosed within 1 year and is more prevalent in young patients with average age of 15.6 years. Incidence rate of SLE has been declining in recent years but the prevalence rate has remained steady. The highest mortality rate is among younger patients diagnosed with SLE within 1 year.

Identifying transcriptional start sites of human microRNAs based on high-throughput sequencing data.

MicroRNAs (miRNAs) are critical small non-coding RNAs that regulate gene expression by hybridizing to the 3'-untranslated regions (3'-UTR) of target mRNAs, subsequently controlling diverse biological processes at post-transcriptional level. How miRNA genes are regulated receives considerable attention because it directly affects miRNA-mediated gene regulatory networks. Although numerous prediction models were developed for identifying miRNA promoters or transcriptional start sites (TSSs), most of them lack experimental validation and are inadequate to elucidate relationships between miRNA genes and transcription factors (TFs). Here, we integrate three experimental datasets, including cap analysis of gene expression (CAGE) tags, TSS Seq libraries and H3K4me3 chromatin signature derived from high-throughput sequencing analysis of gene initiation, to provide direct evidence of miRNA TSSs, thus establishing an experimental-based resource of human miRNA TSSs, named miRStart. Moreover, a machine-learning-based Support Vector Machine (SVM) model is developed to systematically identify representative TSSs for each miRNA gene. Finally, to demonstrate the effectiveness of the proposed resource, an important human intergenic miRNA, hsa-miR-122, is selected to experimentally validate putative TSS owing to its high expression in a normal liver. In conclusion, this work successfully identified 847 human miRNA TSSs (292 of them are clustered to 70 TSSs of miRNA clusters) based on the utilization of high-throughput sequencing data from TSS-relevant experiments, and establish a valuable resource for biologists in advanced research in miRNA-mediated regulatory networks.

Multi-label classification and features investigation of antimicrobial peptides with various functional classes.

The challenge of drug-resistant bacteria to global public health has led to increased attention on antimicrobial peptides (AMPs) as a targeted therapeutic alternative with a lower risk of resistance. However, high production costs and limitations in functional class prediction have hindered progress in this field. In this study, we used multi-label classifiers with binary relevance and algorithm adaptation techniques to predict different functions of AMPs across a wide range of pathogen categories, including bacteria, mammalian cells, fungi, viruses, and cancer cells. Our classifiers attained promising AUC scores varying from 0.8492 to 0.9126 on independent testing data. Forward feature selection identified sequence order and charge as critical, with specific amino acids (C and E) as discriminative. These findings provide valuable insights for the design of antimicrobial peptides (AMPs) with multiple functionalities, thus contributing to the broader effort to combat drug-resistant pathogens.

Data-Driven Two-Stage Framework for Identification and Characterization of Different Antibiotic-Resistant Escherichia coli Isolates Based on Mass Spectrometry Data.

In clinical microbiology, matrix-assisted laser desorption ionization-time-of-flight mass spectrometry (MALDI-TOF MS) is frequently employed for rapid microbial identification. However, rapid identification of antimicrobial resistance (AMR) in Escherichia coli based on a large amount of MALDI-TOF MS data has not yet been reported. This may be because building a prediction model to cover all E. coli isolates would be challenging given the high diversity of the E. coli population. This study aimed to develop a MALDI-TOF MS-based, data-driven, two-stage framework for characterizing different AMRs in E. coli. Specifically, amoxicillin (AMC), ceftazidime (CAZ), ciprofloxacin (CIP), ceftriaxone (CRO), and cefuroxime (CXM) were used. In the first stage, we split the data into two groups based on informative peaks according to the importance of the random forest. In the second stage, prediction models were constructed using four different machine learning algorithms-logistic regression, support vector machine, random forest, and extreme gradient boosting (XGBoost). The findings demonstrate that XGBoost outperformed the other four machine learning models. The values of the area under the receiver operating characteristic curve were 0.62, 0.72, 0.87, 0.72, and 0.72 for AMC, CAZ, CIP, CRO, and CXM, respectively. This implies that a data-driven, two-stage framework could improve accuracy by approximately 2.8%. As a result, we developed AMR prediction models for E. coli using a data-driven two-stage framework, which is promising for assisting physicians in making decisions. Further, the analysis of informative peaks in future studies could potentially reveal new insights. IMPORTANCE Based on a large amount of matrix-assisted laser desorption ionization-time-of-flight mass spectrometry (MALDI-TOF MS) clinical data, comprising 37,918 Escherichia coli isolates, a data-driven two-stage framework was established to evaluate the antimicrobial resistance of E. coli. Five antibiotics, including amoxicillin (AMC), ceftazidime (CAZ), ciprofloxacin (CIP), ceftriaxone (CRO), and cefuroxime (CXM), were considered for the two-stage model training, and the values of the area under the receiver operating characteristic curve (AUC) were 0.62 for AMC, 0.72 for CAZ, 0.87 for CIP, 0.72 for CRO, and 0.72 for CXM. Further investigations revealed that the informative peak m/z 9714 appeared with some important peaks at m/z 6809, m/z 7650, m/z 10534, and m/z 11783 for CIP and at m/z 6809, m/z 10475, and m/z 8447 for CAZ, CRO, and CXM. This framework has the potential to improve the accuracy by approximately 2.8%, indicating a promising potential for further research.