Privacy-Centric AI and IoT Solutions for Smart Rural Farm Monitoring and Control.

The integration of artificial intelligence (AI) and the Internet of Things (IoT) in agriculture has significantly transformed rural farming. However, the adoption of these technologies has also introduced privacy and security concerns, particularly unauthorized breaches and cyber-attacks on data collected from IoT devices and sensitive information. The present study addresses these concerns by developing a comprehensive framework that provides practical, privacy-centric AI and IoT solutions for monitoring smart rural farms. This is performed by designing a framework that includes a three-phase protocol that secures data exchange between the User, the IoT Sensor Layer, and the Central Server. In the proposed protocol, the Central Server is responsible for establishing a secure communication channel by verifying the legitimacy of the IoT Sensor devices and the User and securing the data using rigorous cryptographic techniques. The proposed protocol is also validated using the Automated Validation of Internet Security Protocols and Applications (AVISPA) tool. The formal security analysis confirms the robustness of the protocol and its suitability for real-time applications in AI and IoT-enabled smart rural farms, demonstrating resistance against various attacks and enhanced performance metrics, including a computation time of 0.04 s for 11 messages and a detailed search where 119 nodes were visited at a depth of 12 plies in a mere search time of 0.28 s.

Enhanced therapeutic effects of mesenchymal stem cell-derived extracellular vesicles within chitosan hydrogel in the treatment of diabetic foot ulcers.

Extracellular vesicles (EVs) derived from human umbilical cord mesenchymal stem cells (hUCMSCs) have emerged as promising candidates for cell-free therapy in various diseases, including chronic cutaneous wounds. However, the lack of standardized protocols for EVs' preparation and identification poses a significant challenge to their clinical application. Thus, the objective was to develop a safe and efficient method for the large-scale production of hUCMSC-derived EVs while establishing a comprehensive identification protocol encompassing morphology, particle size distribution, protein expression, and purity. This study observed that most of the EVs acquired through the protocol exhibited either a cup-shaped or round-shaped structure, with a median diameter of ~73.25 nm. The proportions of EVs positive for CD9, CD63, and CD81 were 37.5%, 38.6%, and 19.8%, respectively. To enhance their therapeutic potential in wound treatment, EVs were incorporated into chitosan hydrogel, forming chitosan hydrogel-EVs (CS-EVs). Furthermore, it was demonstrated that CS-EVs exhibited continuous release of EVs into the surrounding environment and, importantly, that the released EVs were internalized by human umbilical vein endothelial cells (HUVECs), resulting in significant enhancement of cell migration and angiogenesis. Additionally, in a rat model of diabetic foot ulcers, CS-EVs demonstrated a robust therapeutic effect in promoting wound healing. Following a 15-day treatment period, the group treated with CS-EVs demonstrated an impressive 93.3% wound closure ability, accompanied by a high degree of re-epithelialization. In contrast, the control group exhibited only a 71.5% reduction in wound size. In summary, this study offers solutions for the purification, characterization, and application of EVs in clinical wound treatment. These results not only offer fresh perspectives on the involvement of hUCMSC-derived EVs in wound healing but also introduce a non-invasive approach for applying EVs that holds practical significance in skin repair.

RISK OF NEW ONSET TYPE II DM IN MDD PATIENTS RECEIVING SECOND-GENERATION ANTIPSYCHOTICS TREATMENT: A NATIONWIDE COHORT STUDY.

BACKGROUND: Second-generation antipsychotics (SGA) augmentation treatment has showed better efficacy in patients with major depressive disorder (MDD). However, the association between SGA and diabetes mellitus (DM) in MDD patients deserves further investigation. The study aimed to examine the risk of new onset type II DM in MDD patients receiving SGA treatment. METHODS: From the Psychiatric Inpatient Medical Claim Dataset, MDD patients treated with SGA continuously for more than 8 weeks were analyzed in a 1:1 propensity score matched pair sample to 1,049 patients that had never been treated with SGA. Patients were followed up to 5 years based on ICD-9 CM codes indicating incident type II DM. Cumulative incidences of type II DM were calculated and the Cox proportional hazards model with competing risk was applied to determine the risk factors for type II DM onset. RESULTS: Cumulative incidences of new-onset type II DM between the two groups were similar. Use of SGA showed no significant increase in risk for new-onset type II DM (hazard ratio [HR] = 0.898; 95% confidence interval [CI], 0.605-1.334; P-value = 0.596). Increased risk for type II DM was shown to be associated with aging (per year) (HR = 1.039; 95% CI, 1.026-1.053; P-value < 0.001) and history of hyperlipidemia (HR = 2.323; 95% CI, 1.469-3.675; P-value < 0.001). CONCLUSIONS: This study indicated that there is no significant difference in the risk of developing type II DM between MDD patients with and without SGA exposure. More studies focused on the benefit-risk assessment of SGA treatment in patients with MDD are warranted.

Clinical relevance and genotypes of circulating noroviruses in northern Taiwan, 2006-2011.

The incidence of noroviral gastroenteritis has increased dramatically in recent years, and norovirus (NoV) genogroup II.4 (GII.4) is associated with outbreaks worldwide. The NoV genotypes and their clinical relevance in children hospitalized with acute gastroenteritis between 2006 and 2011 in northern Taiwan were evaluated in this study. NoV sequences were amplified from 47 clinical specimens and phylogenetic analysis was performed. Based on noroviral capsid protein (VP1) and RNA dependent RNA polymerase (RdRp) phylogeny, circulating NoV could be divided into GII.2, GII.3, GII.12, and GII.4 and GII.16, GII.12, GII.g, and GII.4; respectively. The GII.4 subtype was predominant and could be divided further into the 2004 (Hunter), 2006b, and 2010 (New Orleans) subtypes. Regarding clinical manifestations, convulsive disorder occurred only in cases caused by NoV GII.4 2006b. Patients affected by NoV GII.4 2006b presented with a higher frequency of diarrhea (P = 0.0204), longer duration of diarrhea (P = 0.0215), more frequent hypoglycemia (P = 0.038), and electrolyte imbalance (P = 0.0487) than acute gastroenteritis caused by NoV GII.4 2010. Structural analysis showed that the amino acid changes in viral VP1 between GII.4 2006b and 2010 subtype were located mainly in the protruding domain 2 (P2 domain). In conclusion, the NoV GII.4 variants 2006b and 2010 were the main causes of acute gastroenteritis in hospitalized children in northern Taiwan during 2006-2011. The clinical presentations and structural changes in VP1 of the two NoV GII.4 variants should be evaluated in the future.

Inverse association between cancer risks and age in schizophrenic patients: a 12-year nationwide cohort study.

The association between schizophrenia and cancer risk is contentious in the clinical and epidemiological literature. Studies from different populations, tumor sites, or health care systems have provided inconsistent findings. In the present study, we examined a less well-investigated hypothesis that age plays a crucial role in cancer risk in schizophrenia. We conducted a nationwide cohort study using Taiwan's National Health Insurance Research Database (NHIRD) between 1995 and 2007. Overall, gender-, and age-stratified standardized incidence ratios (SIR) were used to investigate the pattern of cancer risk by age. Of the 102 202 schizophrenic patients, 1738 developed cancer after a diagnosis of schizophrenia (SIR = 0.92; 95% confidence interval [CI] 0.90-0.96). However, the age-stratified SIR declined with age (e.g. SIR [95% CI] = 1.97 [1.85-2.33], 0.68 [0.65-0.78], and 0.36 [0.34-0.45] for those aged 20-29, 60-69, and ≥70 years, respectively) in both genders and for major cancers. Cancer risks in schizophrenic patients were lower for cancers that are more likely to develop at an older age in the general population (e.g. stomach cancer [SIR = 0.62; 95% CI 0.57-0.80], pancreatic cancer [SIR = 0.49; 95% CI 0.39-0.84], and prostate cancer [SIR = 0.35; 95% CI 0.29-0.58]). In contrast, cancer risks were higher for cancers that have a younger age of onset, such as cancers of the nasopharynx (SIR = 1.18; 95% CI 1.08-1.49), breast (SIR = 1.50; 95% CI 1.44-1.66) and uterine corpus (SIR = 2.15; 95% CI 1.98-2.74). The unique age structures and early aging potential of schizophrenia populations may contribute to the observed inverse relationship between age and cancer risk. Higher cancer comorbidity in young schizophrenic patients deserves more attention.

Design checkpoint kinase 2 inhibitors by pharmacophore modeling and virtual screening techniques.

Damage to DNA is caused by ionizing radiation, genotoxic chemicals or collapsed replication forks. When DNA is damaged or cells fail to respond, a mutation that is associated with breast or ovarian cancer may occur. Mammalian cells control and stabilize the genome using a cell cycle checkpoint to prevent damage to DNA or to repair damaged DNA. Checkpoint kinase 2 (Chk2) is one of the important kinases, which strongly affects DNA-damage and plays an important role in the response to the breakage of DNA double-strands and related lesions. Therefore, this study concerns Chk2. Its purpose is to find potential inhibitors using the pharmacophore hypotheses (PhModels) and virtual screening techniques. PhModels can identify inhibitors with high biological activities and virtual screening techniques are used to screen the database of the National Cancer Institute (NCI) to retrieve compounds that exhibit all of the pharmacophoric features of potential inhibitors with high interaction energy. Ten PhModels were generated using the HypoGen best algorithm. The established PhModel, Hypo01, was evaluated by performing a cost function analysis of its correlation coefficient (r), root mean square deviation (RMSD), cost difference, and configuration cost, with the values 0.955, 1.28, 192.51, and 16.07, respectively. The result of Fischer's cross-validation test for the Hypo01 model yielded a 95% confidence level, and the correlation coefficient of the testing set (rtest) had a best value of 0.81. The potential inhibitors were then chosen from the NCI database by Hypo01 model screening and molecular docking using the cdocker docking program. Finally, the selected compounds exhibited the identified pharmacophoric features and had a high interaction energy between the ligand and the receptor. Eighty-three potential inhibitors for Chk2 are retrieved for further study.

Clozapine protects bone mineral density in female patients with schizophrenia.

Decreased bone mineral density (BMD) is common in patients with schizophrenia; however, the pathogenesis is unclear. Different classes of antipsychotic agents may affect BMD. This study systemically examined the effects of clozapine vs. other antipsychotics, and several hormonal and metabolic factors that may contribute to BMD in female patients with schizophrenia, who are more vulnerable than males. Forty-eight women with schizophrenia, treated with long-term antipsychotics of the prototype prolactin-sparing (PS) antipsychotic agent clozapine vs. prolactin-raising (PR) antipsychotics were enrolled. They were matched for demographic and clinical characteristics. Various factors, including blood levels of prolactin and sex hormones, psychopathological symptoms, global assessment of functioning, physical activity, and menopausal status, were determined to explore their contribution to low BMD (LBMD), defined as a dual-energy X-ray absorptiometer (DEXA) T score <-1. Overall, women receiving clozapine have better bone density than women receiving PR antipsychotics. Compared to PR antipsychotics, PS clozapine therapy is a protective factor (odds ratio 28.2, 95% confidence interval 2.37-336.10, p=0.008) for LBMD. Predictors for higher bone density in the clozapine group included higher clozapine dose (p<0.001), younger age (p<0.001), and higher thyroid-stimulating hormone level (p<0.001); in the PR group, higher body mass index (p=0.003) and lower alkaline phosphatase level (p=0.007) were associated with LBMD. This study suggests that clozapine treatment is beneficial for BMD compared to PR antipsychotic treatment in women with chronic schizophrenia, and clozapine's bone-density protecting effect is dose-related.

Design of novel FLT-3 inhibitors based on dual-layer 3D-QSAR model and fragment-based compounds in silico.

FMS-like tyrosine kinase 3 (FLT-3) is strongly correlated with acute myeloid leukemia, but no FLT-3-inhibitor cocomplex structure is available to assist the design of therapeutic inhibitors. Hence, we propose a dual-layer 3D-QSAR model for FLT-3 that integrates the pharmacophore, CoMFA, and CoMSIA. We then coupled the model with the fragment-based design strategy to identify novel FLT-3 inhibitors. In the first layer, the previously established model, Hypo02, was evaluated in terms of its correlation coefficient (r), RMS, cost difference, and configuration cost, with values of 0.930, 1.24, 106.45, and 16.44, respectively. Moreover, Fischer's cross-validation test of data generated by Hypo02 yielded a 98% confidence level, and the validation of the testing set yielded a best r value of 0.87. The features of Hypo02 were separated into two parts and then used to screen the MiniMaybridge fragment compound database. Nine novel FLT-3 inhibitors were generated in this layer. In the second layer, Hypo02 was subjected to an alignment rule to generate CoMFA- and CoMSIA-based models, for which the partial least-squares validation method was utilized. The values of q(2), r(2), and predictive r(2) were 0.58, 0.98, and 0.76, respectively, derived from the CoMFA model with steric and electrostatic fields. The CoMSIA model with five different fields yielded values of 0.54, 0.97, and 0.76 for q(2), r(2), and predictive r(2), respectively. The CoMFA and CoMSIA models were used to constrain 3D structures of the nine novel FLT-3 inhibitors. This dual-layer 3D-QSAR model constitutes a valuable tool to easily and quickly screen and optimize novel potential FLT-3 inhibitors for the treatment of acute myeloid leukemia.

Gender Differences in Gut Microbiome Composition Between Schizophrenia Patients With Normal Body Weight and Central Obesity.

Background: Obesity is a common health problem among patients with schizophrenia, but the precise mechanisms are not fully understood. There has been much interest in the relationship between gut microbiome and development of obesity. Gender-dependent microbial alteration has been reported in previous studies. However, the gender factor in gut microbiome composition of schizophrenia patients has been less investigated. Our study aimed to identify differences in gut microbiota between schizophrenia patients with normal weight and central obesity and investigate the gender specific features. Method: Twenty participants (10 males, 10 females) with central obesity (CO) and 20 participants (10 males, 10 females) with normal weight (NW) were recruited from two rehabilitation wards in a psychiatric hospital in central Taiwan. Fecal samples from 40 participants were processed for microbiota analysis. The intestinal microbiota composition was analyzed using next-generation sequencing and QIIME software. Results: Significantly higher richness of gut microbiota at the class level (measured by the number of observed OTUs) was observed in female NW subjects than in female CO subjects (P = 0.033). Furthermore, female NW subjects showed higher alpha diversity at both phylum and class levels (measured by the Shannon, Simpson, and Inverse-Simpson indexes) compared with female CO subjects. Males showed no significant difference in alpha diversity between groups. Taxonomic analysis showed that female CO subjects had significantly lower abundance of Verrucomicrobia (P = 0.004) at the phylum level, reduced abundance of Akkermansia (P = 0.003) and elevated level of Prevotella (P = 0.038) and Roseburia (P = 0.005) at the genus level. Conclusions: The present results evidenced altered microbiome composition in schizophrenia patients with central obesity and further suggested the role of the gender factor in the process of gut dysbiosis.

A review for cell and particle tracking on microscopy images using algorithms and deep learning technologies.

Time-lapse microscopy images generated by biological experiments have been widely used for observing target activities, such as the motion trajectories and survival states. Based on these observations, biologists can conclude experimental results or present new hypotheses for several biological applications, i.e. virus research or drug design. Many methods or tools have been proposed in the past to observe cell and particle activities, which are defined as single cell tracking and single particle tracking problems, by using algorithms and deep learning technologies. In this article, a review for these works is presented in order to summarize the past methods and research topics at first, then points out the problems raised by these works, and finally proposes future research directions. The contributions of this article will help researchers to understand past development trends and further propose innovative technologies.

Pharmacophore modeling and virtual screening to identify potential RET kinase inhibitors.

Chemical features based 3D pharmacophore model for REarranged during Transfection (RET) tyrosine kinase were developed by using a training set of 26 structurally diverse known RET inhibitors. The best pharmacophore hypothesis, which identified inhibitors with an associated correlation coefficient of 0.90 between their experimental and estimated anti-RET values, contained one hydrogen-bond acceptor, one hydrogen-bond donor, one hydrophobic, and one ring aromatic features. The model was further validated by a testing set, Fischer's randomization test, and goodness of hit (GH) test. We applied this pharmacophore model to screen NCI database for potential RET inhibitors. The hits were docked to RET with GOLD and CDOCKER after filtering by Lipinski's rules. Ultimately, 24 molecules were selected as potential RET inhibitors for further investigation.

Development of novel 3D-QSAR combination approach for screening and optimizing B-Raf inhibitors in silico.

B-Raf is a member of the RAF family of serine/threonine kinases: it mediates cell division, differentiation, and apoptosis signals through the RAS-RAF-MAPK pathway. Thus, B-Raf is of keen interest in cancer therapy, such as melanoma. In this study, we propose the first combination approach to integrate the pharmacophore (PhModel), CoMFA, and CoMSIA models for B-Raf, and this approach could be used for screening and optimizing potential B-Raf inhibitors in silico. Ten PhModels were generated based on the HypoGen BEST algorithm with the flexible fit method and diverse inhibitor structures. Each PhModel was designated to the alignment rule and screening interface for CoMFA and CoMSIA models. Therefore, CoMFA and CoMSIA models could align and recognize diverse inhibitor structures. We used two quality validation methods to test the predication accuracy of these combination models. In the previously proposed combination approaches, they have a common factor in that the number of training set inhibitors is greater than that of testing set inhibitors. In our study, the 189 known diverse series B-Raf inhibitors, which are 7-fold the number of training set inhibitors, were used as a testing set in the partial least-squares validation. The best validation results were made by the CoMFA09 and CoMSIA09 models based on the Hypo09 alignment model. The predictive r(2)(pred) values of 0.56 and 0.56 were derived from the CoMFA09 and CoMSIA09 models, respectively. The CoMFA09 and CoMSIA09 models also had a satisfied predication accuracy of 77.78% and 80%, and the goodness of hit test score of 0.675 and 0.699, respectively. These results indicate that our combination approach could effectively identify diverse B-Raf inhibitors and predict the activity.

An Automatic Bleeding-Rank System for Transurethral Resection of the Prostate Surgery Videos Using Machine Learning.

Benign prostatic hyperplasia (BPH) is the main cause of lower urinary tract symptoms (LUTS) in aging males. Transurethral resection of the prostate (TURP) surgery is performed by a cystoscope passing through the urethra and scraping off the prostrate piece by piece through a cutting loop. Although TURP is a minimally invasive procedure, bleeding is still the most common complication. Therefore, the evaluation, monitoring, and prevention of interop bleeding during TURP are very important issues. The main idea of this study is to rank bleeding levels during TURP surgery from videos. Generally, to judge bleeding level by human eyes from surgery videos is a difficult task, which requires sufficient experienced urologists. In this study, machine learning-based ranking algorithms are proposed to efficiently evaluate the ranking of blood levels. Based on the visual clarity of the surgical field, the four ranking of blood levels, including score 0: excellent; score 1: acceptable; score 2: slightly bad; and 3: bad, were identified by urologists who have sufficient experience in TURP surgery. The results of extensive experiments show that the revised accuracy can achieve 90, 89, 90, and 91%, respectively. Particularly, the results reveal that the proposed methods were capable of classifying the ranking of bleeding level accurately and efficiently reducing the burden of urologists.

The Chinese Mandarin Version of the Crisis Triage Rating Scale for Taiwanese with Mental Illness to Compulsory Hospitalization.

BACKGROUND: A controversial issue of the need to protect human rights and ensure public safety still remains a conflict in Taiwan. The purpose of this study was to translate the Crisis Triage Rating Scale to Chinese Mandarin (CMCTRS). METHOD: A cross-sectional design with convenient sampling was employed in this study. The CMCTRS was tested on 302 Taiwanese individuals with mental illness who were admitted to the emergency room (ER) of a psychiatric center. A higher score indicated a greater need for mandatory psychiatric admission. Psychiatrists rated the patients' status according to three scale criteria and six action plans of recommendations. RESULTS: Five specialists evaluated the content validity index to be 0.8. A total of 210 participants (69.5%) were deemed suitable for compulsory hospitalization or admission for observation in ER. The optimal cut-off score was 8, with a Youden Index of 1.46, a sensitivity of 0.748, and a specificity of 0.712 in deciding the need for hospitalization or observation. CONCLUSIONS: The CMCTRS exhibited an acceptable criterion validity with psychiatrists in a population of 302 patients at the ER of a psychiatric center. A cut-off point of 8 is recommended for determining hospitalization or a minimum 24 h stay at emergency for observation.

Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure.

BACKGROUND: Early identification of critically ill neonates with poor outcomes can optimize therapeutic strategies. We aimed to examine whether machine learning (ML) methods can improve mortality prediction for neonatal intensive care unit (NICU) patients on intubation for respiratory failure. METHODS: A total of 1734 neonates with respiratory failure were randomly divided into training (70%, n = 1214) and test (30%, n = 520) sets. The primary outcome was the probability of NICU mortality. The areas under the receiver operating characteristic curves (AUCs) of several ML algorithms were compared with those of the conventional neonatal illness severity scoring systems including the NTISS and SNAPPE-II. RESULTS: For NICU mortality, the random forest (RF) model showed the highest AUC (0.939 (0.921-0.958)) for the prediction of neonates with respiratory failure, and the bagged classification and regression tree model demonstrated the next best results (0.915 (0.891-0.939)). The AUCs of both models were significantly better than the traditional NTISS (0.836 (0.800-0.871)) and SNAPPE-II scores (0.805 (0.766-0.843)). The superior performances were confirmed by higher accuracy and F1 score and better calibration, and the superior and net benefit was confirmed by decision curve analysis. In addition, Shapley additive explanation (SHAP) values were utilized to explain the RF prediction model. CONCLUSIONS: Machine learning algorithms increase the accuracy and predictive ability for mortality of neonates with respiratory failure compared with conventional neonatal illness severity scores. The RF model is suitable for clinical use in the NICU, and clinicians can gain insights and have better communication with families in advance.

Genome-Wide Association Study of Lithium-Induced Dry Mouth in Bipolar I Disorder.

Dry mouth is a rather common unpleasant adverse drug reaction (ADR) to lithium treatment in bipolar disorders that often lead to poor adherence or early dropout. The aim of this study was to identify the genetic variants of dry mouth associated with lithium treatment in patients with bipolar I (BPI) disorder. In total, 1242 BPI patients who had ever received lithium treatment were identified by the Taiwan Bipolar Consortium for this study. The proportions of patients who experienced impaired drug compliance during lithium medication were comparable between those only with dry mouth and those with any other ADR (86% and 93%, respectively). Dry mouth appeared to be the most prevalent (47.3%) ADR induced by lithium treatment. From the study patients, 921 were included in a genome-wide association study (GWAS), and replication was conducted in the remaining 321 patients. The SNP rs10135918, located in the immunoglobulin heavy chain locus (IGH), showed the strongest associations in the GWAS (p = 2.12 × 10-37) and replication groups (p = 6.36 × 10-13) (dominant model) for dry mouth with a sensitivity of 84.9% in predicting dry mouth induced by lithium. Our results may be translated into clinical recommendation to help identify at-risk individuals for early identification and management of dry mouth, which will improve medication adherence.

Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit.

BACKGROUND: preterm and critically ill neonates often experience clinically suspected sepsis during their prolonged hospitalization in the neonatal intensive care unit (NICU), which can be the initial sign of final adverse outcomes. Therefore, we aimed to utilize machine learning approaches to predict neonatal in-hospital mortality through data-driven learning. METHODS: a total of 1095 neonates who experienced clinically suspected sepsis in a tertiary-level NICU in Taiwan between August 2017 and July 2020 were enrolled. Clinically suspected sepsis was defined based on clinical features and laboratory criteria and the administration of empiric antibiotics by clinicians. The variables used for analysis included patient demographics, clinical features, laboratory data, and medications. The machine learning methods used included deep neural network (DNN), k-nearest neighbors, support vector machine, random forest, and extreme gradient boost. The performance of these models was evaluated using the area under the receiver operating characteristic curve (AUC). RESULTS: the final in-hospital mortality of this cohort was 8.2% (90 neonates died). A total of 765 (69.8%) and 330 (30.2%) patients were randomly assigned to the training and test sets, respectively. Regarding the efficacy of the single model that most accurately predicted the outcome, DNN exhibited the greatest AUC (0.923, 95% confidence interval [CI] 0.953-0.893) and the best accuracy (95.64%, 95% CI 96.76-94.52%), Cohen's kappa coefficient value (0.74, 95% CI 0.79-0.69) and Matthews correlation coefficient value (0.75, 95% CI 0.80-0.70). The top three most influential variables in the DNN importance matrix plot were the requirement of ventilator support at the onset of suspected sepsis, the feeding conditions, and intravascular volume expansion. The model performance was indistinguishable between the training and test sets. CONCLUSIONS: the DNN model was successfully established to predict in-hospital mortality in neonates with clinically suspected sepsis, and the machine learning algorithm is applicable for clinicians to gain insights and have better communication with families in advance.

Feature amplified voting algorithm for functional analysis of protein superfamily.

BACKGROUND: Identifying the regions associated with protein function is a singularly important task in the post-genomic era. Biological studies often identify functional enzyme residues by amino acid sequences, particularly when related structural information is unavailable. In some cases of protein superfamilies, functional residues are difficult to detect by current alignment tools or evolutionary strategies when phylogenetic relationships do not parallel their protein functions. The solution proposed in this study is Feature Amplified Voting Algorithm with Three-profile alignment (FAVAT). The core concept of FAVAT is to reveal the desired features of a target enzyme or protein by voting on three different property groups aligned by three-profile alignment method. Functional residues of a target protein can then be retrieved by FAVAT analysis. In this study, the amidohydrolase superfamily was an interesting case for verifying the proposed approach because it contains divergent enzymes and proteins. RESULTS: The FAVAT was used to identify critical residues of mammalian imidase, a member of the amidohydrolase superfamily. Members of this superfamily were first classified by their functional properties and sources of original organisms. After FAVAT analysis, candidate residues were identified and compared to a bacterial hydantoinase in which the crystal structure (1GKQ) has been fully elucidated. One modified lysine, three histidines and one aspartate were found to participate in the coordination of metal ions in the active site. The FAVAT analysis also redressed the misrecognition of metal coordinator Asp57 by the multiple sequence alignment (MSA) method. Several other amino acid residues known to be related to the function or structure of mammalian imidase were also identified. CONCLUSIONS: The FAVAT is shown to predict functionally important amino acids in amidohydrolase superfamily. This strategy effectively identifies functionally important residues by analyzing the discrepancy between the sequence and functional properties of related proteins in a superfamily, and it should be applicable to other protein families.

Sorting by reversals and block-interchanges with various weight assignments.

BACKGROUND: A classical problem in studying genome rearrangements is understanding the series of rearrangement events involved in transforming one genome into another in accordance with the parsimonious principle when two genomes with the same set of genes differ in gene order. The most studied event is the reversal, but an increasing number of reports have considered reversals along with other genome rearrangement events. Some recent studies have investigated the use of reversals and block-interchanges simultaneously with a weight proportion of 1:2. However, there has been less progress towards exploring additional combinations of weights. RESULTS: In this paper, we present several approaches to examine genome rearrangement problems by considering reversals and block-interchanges together using various weight assignments. An exact algorithm for the weight proportion of 1:2 is developed, and then, its idea is extended to design approximation algorithms for other weight assignments. The results of our simulations suggest that the performance of our approximation algorithm is superior to its theoretical expectation. CONCLUSION: If the weight of reversals is no more than that of block-interchanges, our algorithm provides an acceptable solution for the transformation of two permutations. Nevertheless whether there are more tractable results for studying the two events remains open.

Long-term Use of Clozapine is Protective for Bone Density in Patients with Schizophrenia.

Low bone mineral density (BMD) prevails among patients with schizophrenia. Antipsychotics use plays an important role in BMD. Previous cross-section study suggests that clozapine treatment may benefit BMD of women with schizophrenia. However, the effect of long-term clozapine therapy on BMD remains unknown. This prospective study compared clozapine and non-clozapine antipsychotics in long-term effects on BMD among both men and women with schizophrenia. Patients with schizophrenia and age-matched healthy individuals were enrolled from two centers. All patients, including clozapine receivers and non-clozapine antipsychotics recipients, kept clinically stable with unchanged antipsychotics and doses for at least 6 months at enrollment and during the follow-up period. BMD was examined by dual-energy X-ray absorptiometer upon enrollment and at 1- or 3-year follow-up. Thorough clinical and laboratory variables were measured too. The mean BMD of patients receiving clozapine was higher than that of the non-clozapine patients at both enrollment and follow-up. Overall, the patients in the clozapine group gained BMD, while those in the non-clozapine group lost BMD after 1-3 years (p = 0.015). There was no significant difference of BMD change between clozapine-treated patients and healthy controls. Factors associated with BMD change in the clozapine group included calcium level (B = -0.607, p = 0.021) and T3 level (B = -0.077, p = 0.007). This longitudinal study suggests that long-term clozapine treatment may protect BMD compared to prolactin-raising and non-clozapine prolactin-sparing antipsychotics among patients with schizophrenia. Future prospective studies are warranted to testify whether switching from non-clozapine antipsychotics to clozapine can rescue BMD.