ezGeno: an automatic model selection package for genomic data analysis.

MOTIVATION: To facilitate the process of tailor-making a deep neural network for exploring the dynamics of genomic DNA, we have developed a hands-on package called ezGeno. ezGeno automates the search process of various parameters and network structures and can be applied to any kind of 1D genomic data. Combinations of multiple abovementioned 1D features are also applicable. RESULTS: For the task of predicting TF binding using genomic sequences as the input, ezGeno can consistently return the best performing set of parameters and network structure, as well as highlight the important segments within the original sequences. For the task of predicting tissue-specific enhancer activity using both sequence and DNase feature data as the input, ezGeno also regularly outperforms the hand-designed models. Furthermore, we demonstrate that ezGeno is superior in efficiency and accuracy compared to the one-layer DeepBind model and AutoKeras, an open-source AutoML package. AVAILABILITY AND IMPLEMENTATION: The ezGeno package can be freely accessed at https://github.com/ailabstw/ezGeno. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Genome-wide association study reveals ethnicity-specific SNPs associated with ankylosing spondylitis in the Taiwanese population.

BACKGROUND: Ankylosing spondylitis (AS) is an autoimmune disease affecting mainly spine and sacroiliac joints and adjacent soft tissues. Genome-wide association studies (GWASs) are used to evaluate genetic associations and to predict genetic risk factors that determine the biological basis of disease susceptibility. We aimed to explore the race-specific SNP susceptibility of AS in Taiwanese individuals and to investigate the association between HLA-B27 and AS susceptibility SNPs in Taiwan. METHODS: Genotyping data were collected from a medical center participating in the Taiwan Precision Medicine Initiative (TPMI) in the northern district of Taiwan. We designed a case-control study to identify AS susceptibility SNPs through GWAS. We searched the genome browser to find the corresponding susceptibility genes and used the GTEx database to confirm the regulation of gene expression. A polygenic risk score approach was also applied to evaluate the genetic variants in the prediction of developing AS. RESULTS: The results showed that the SNPs located on the sixth chromosome were related to higher susceptibility in the AS group. There was no overlap between our results and the susceptibility SNPs found in other races. The 12 tag SNPs located in the MHC region that were found through the linkage disequilibrium method had higher gene expression. Furthermore, Taiwanese people with HLA-B27 positivity had a higher proportion of minor alleles. This might be the reason that the AS prevalence is higher in Taiwan than in other countries. We developed AS polygenic risk score models with six different methods in which those with the top 10% polygenic risk had a fivefold increased risk of developing AS compared to the remaining group with low risk. CONCLUSION: A total of 147 SNPs in the Taiwanese population were found to be statistically significantly associated with AS on the sixth pair of chromosomes and did not overlap with previously published sites in the GWAS Catalog. Whether those genes mapped by AS-associated SNPs are involved in AS and what the pathogenic mechanism of the mapped genes is remain to be further studied.

De novo motif discovery facilitates identification of interactions between transcription factors in Saccharomyces cerevisiae.

MOTIVATION: Gene regulation involves complicated mechanisms such as cooperativity between a set of transcription factors (TFs). Previous studies have used target genes shared by two TFs as a clue to infer TF-TF interactions. However, this task remains challenging because the target genes with low binding affinity are frequently omitted by experimental data, especially when a single strict threshold is employed. This article aims at improving the accuracy of inferring TF-TF interactions by incorporating motif discovery as a fundamental step when detecting overlapping targets of TFs based on ChIP-chip data. RESULTS: The proposed method, simTFBS, outperforms three naïve methods that adopt fixed thresholds when inferring TF-TF interactions based on ChIP-chip data. In addition, simTFBS is compared with two advanced methods and demonstrates its advantages in predicting TF-TF interactions. By comparing simTFBS with predictions based on the set of available annotated yeast TF binding motifs, we demonstrate that the good performance of simTFBS is indeed coming from the additional motifs found by the proposed procedures. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Disseminated zygomycosis caused by Cunninghamella bertholletiae in patient with hematological malignancy and review of published case reports.

Cunninghamella bertholletiae is an unusual opportunistic pathogen belonging to the class Zygomycetes, order Mucorales, and the family Cunninghamellaceae. It has been identified with increased frequency in immunocompromised patients, especially those with hematological malignancy. Clinical infection by this fungus is almost always devastating. We report a fatal case of disseminated zygomycosis due to Cunninghamella bertholletiae in an acute myeloid leukemia patient without chemotherapy. We also reviewed the cases of Cunninghamella bertholletiae infection reported in these 20 years. These cases highlight the high mortality rate and rapid progression associated with this opportunistic fungal infection in immunocompromised patients.

Panic Attack Prediction Using Wearable Devices and Machine Learning: Development and Cohort Study.

BACKGROUND: A panic attack (PA) is an intense form of anxiety accompanied by multiple somatic presentations, leading to frequent emergency department visits and impairing the quality of life. A prediction model for PAs could help clinicians and patients monitor, control, and carry out early intervention for recurrent PAs, enabling more personalized treatment for panic disorder (PD). OBJECTIVE: This study aims to provide a 7-day PA prediction model and determine the relationship between a future PA and various features, including physiological factors, anxiety and depressive factors, and the air quality index (AQI). METHODS: We enrolled 59 participants with PD (Diagnostic and Statistical Manual of Mental Disorders, 5th edition, and the Mini International Neuropsychiatric Interview). Participants used smartwatches (Garmin Vívosmart 4) and mobile apps to collect their sleep, heart rate (HR), activity level, anxiety, and depression scores (Beck Depression Inventory [BDI], Beck Anxiety Inventory [BAI], State-Trait Anxiety Inventory state anxiety [STAI-S], State-Trait Anxiety Inventory trait anxiety [STAI-T], and Panic Disorder Severity Scale Self-Report) in their real life for a duration of 1 year. We also included AQIs from open data. To analyze these data, our team used 6 machine learning methods: random forests, decision trees, linear discriminant analysis, adaptive boosting, extreme gradient boosting, and regularized greedy forests. RESULTS: For 7-day PA predictions, the random forest produced the best prediction rate. Overall, the accuracy of the test set was 67.4%-81.3% for different machine learning algorithms. The most critical variables in the model were questionnaire and physiological features, such as the BAI, BDI, STAI, MINI, average HR, resting HR, and deep sleep duration. CONCLUSIONS: It is possible to predict PAs using a combination of data from questionnaires and physiological and environmental data.

Efficiently Predicting Vancomycin Resistance of Enterococcus Faecium From MALDI-TOF MS Spectra Using a Deep Learning-Based Approach.

Matrix-assisted laser desorption ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) has recently become a useful analytical approach for microbial identification. The presence and absence of specific peaks on MS spectra are commonly used to identify the bacterial species and predict antibiotic-resistant strains. However, the conventional approach using few single peaks would result in insufficient prediction power without using complete information of whole MS spectra. In the past few years, machine learning algorithms have been successfully applied to analyze the MALDI-TOF MS peaks pattern for rapid strain typing. In this study, we developed a convolutional neural network (CNN) method to deal with the complete information of MALDI-TOF MS spectra for detecting Enterococcus faecium, which is one of the leading pathogens in the world. We developed a CNN model to rapidly and accurately predict vancomycin-resistant Enterococcus faecium (VREfm) samples from the whole mass spectra profiles of clinical samples. The CNN models demonstrated good classification performances with the average area under the receiver operating characteristic curve (AUROC) of 0.887 when using external validation data independently. Additionally, we employed the score-class activation mapping (CAM) method to identify the important features of our CNN models and found some discriminative signals that can substantially contribute to detecting the ion of resistance. This study not only utilized the complete information of MALTI-TOF MS data directly but also provided a practical means for rapid detection of VREfm using a deep learning algorithm.

The necessity of abdominal drainage for patients with complicated appendicitis undergoing laparoscopic appendectomy: a retrospective cohort study.

BACKGROUND: This study aimed to evaluate the necessity of abdominal drainage after laparoscopic appendectomy in patients with complicated appendicitis. METHODS: Patients with acute appendicitis undergoing laparoscopic appendectomy at two hospitals between January 2014 and December 2018 were retrospectively included. Complicated appendicitis was defined as the American Association for the Surgery of Trauma (AAST) grade ≥ II. The patients were classified according to the AAST grade and the indwelling of abdominal drainage. The postoperative surgical outcomes and recovery were compared among patient groups to evaluate the impact of abdominal drainage for patients with complicated appendicitis undergoing laparoscopic appendectomy. RESULTS: A total of 1241 patients was retrospectively included. Among them, there were 820 patients with simple appendicitis (AAST grade I) and 421 patients with complicated appendicitis (AAST grade ≥ II). For complicated appendicitis, the drainage group (N = 192) tended to harbor more overall complications, intra-abdominal abscess formation, time to resume a soft diet, and the postoperative length of hospitalization (P = 0.0000 for all). Multivariate logistic regression confirmed that abdominal drainage increased the risk of overall complications [Odds ratio (OR) 2.439; 95% confidence interval (CI) 1.597-3.726; P ≤ 0.0001] and failed to decrease the risk of intra-abdominal abscess formation (OR 1.655; 95% CI 0.487-5.616; P = 0.4193). Multivariate linear regression analysis also showed that the drainage group harbored longer postoperative length of hospitalization (Coefficients: 20.697; 95% CI 15.251-26.143; P < 0.0001) and time to resume a soft diet (Coefficients: 45.899; 95% CI 34.502-57.297; P < 0.0001). CONCLUSIONS: Abdominal drainage did not prevent overall complications in patients with complicated appendicitis; paradoxically, it delayed the convalescence. Our results discourage the routine use of abdominal drainage and suggest that abdominal drainage should be performed sparingly.

A Precision Health Service for Chronic Diseases: Development and Cohort Study Using Wearable Device, Machine Learning, and Deep Learning.

This paper presents an integrated and scalable precision health service for health promotion and chronic disease prevention. Continuous real-time monitoring of lifestyle and environmental factors is implemented by integrating wearable devices, open environmental data, indoor air quality sensing devices, a location-based smartphone app, and an AI-assisted telecare platform. The AI-assisted telecare platform provided comprehensive insight into patients' clinical, lifestyle, and environmental data, and generated reliable predictions of future acute exacerbation events. All data from 1,667 patients were collected prospectively during a 24-month follow-up period, resulting in the detection of 386 abnormal episodes. Machine learning algorithms and deep learning algorithms were used to train modular chronic disease models. The modular chronic disease prediction models that have passed external validation include obesity, panic disorder, and chronic obstructive pulmonary disease, with an average accuracy of 88.46%, a sensitivity of 75.6%, a specificity of 93.0%, and an F1 score of 79.8%. Compared with previous studies, we establish an effective way to collect lifestyle, life trajectory, and symptom records, as well as environmental factors, and improve the performance of the prediction model by adding objective comprehensive data and feature selection. Our results also demonstrate that lifestyle and environmental factors are highly correlated with patient health and have the potential to predict future abnormal events better than using only questionnaire data. Furthermore, we have constructed a cost-effective model that needs only a few features to support the prediction task, which is helpful for deploying real-world modular prediction models.