Identification of human circadian genes based on time course gene expression profiles by using a deep learning method

A First-in-Human Study of AMG 986, a Novel Apelin Receptor Agonist, in Healthy Subjects and Heart Failure Patients

PURPOSE

AMG 986 is a novel apelin receptor (APJ) agonist that improves cardiac contractility in animal models without adversely impacting hemodynamics. This phase 1b study evaluated the safety/tolerability, pharmacokinetics, and pharmacodynamics of AMG 986 in healthy subjects and patients with heart failure (HF).

METHODS

Healthy adults (Parts A/B) and HF patients (Part C) aged 18-85 years were randomized 3:1 to single-dose oral/IV AMG 986 or placebo (Part A); multiple-dose oral/IV AMG 986 or placebo (Part B); or escalating-dose oral AMG 986 or placebo (Part C).

PRIMARY ENDPOINT

treatment-emergent adverse events, laboratory values/vital signs/ECGs; others included AMG 986 pharmacokinetics, left ventricular (LV) function.

RESULTS

Overall, 182 subjects were randomized (AMG 986/healthy: n = 116, placebo, n = 38; AMG 986/HF: n = 20, placebo, n = 8). AMG 986 had acceptable safety profile; no clinically significant dose-related impact on safety parameters up to 650 mg/day was observed. AMG 986 exposures increased nonlinearly with increasing doses; minimal accumulation was observed. In HF with reduced ejection fraction patients, there were numerical increases in percent changes from baseline in LV ejection fraction and stroke volume by volumetric assessment with AMG 986 vs placebo (stroke volume increase not recapitulated by Doppler).

CONCLUSIONS

In healthy subjects and HF patients, short-term AMG 986 treatment was well tolerated. Consistent with this observation, clinically meaningful pharmacodynamic effects in HF patients were not observed. Changes in ejection fraction and stroke volume in HF patients suggest additional studies may be needed to better define the clinical utility and optimal dosing for this molecule.

TRIAL REGISTRATION NUMBER

ClinicalTrials.gov NCT03276728.

DATE OF REGISTRATION

September 8, 2017.

Identification of Human Cell Cycle Phase Markers Based on Single-Cell RNA-Seq Data by Using Machine Learning Methods

The cell cycle is composed of a series of ordered, highly regulated processes through which a cell grows and duplicates its genome and eventually divides into two daughter cells. According to the complex changes in cell structure and biosynthesis, the cell cycle is divided into four phases: gap 1 (G1), DNA synthesis (S), gap 2 (G2), and mitosis (M). Determining which cell cycle phases a cell is in is critical to the research of cancer development and pharmacy for targeting cell cycle. However, current detection methods have the following problems: (1) they are complicated and time consuming to perform, and (2) they cannot detect the cell cycle on a large scale. Rapid developments in single-cell technology have made dissecting cells on a large scale possible with unprecedented resolution. In the present research, we construct efficient classifiers and identify essential gene biomarkers based on single-cell RNA sequencing data through Boruta and three feature ranking algorithms (e.g., mRMR, MCFS, and SHAP by LightGBM) by utilizing four advanced classification algorithms. Meanwhile, we mine a series of classification rules that can distinguish different cell cycle phases. Collectively, we have provided a novel method for determining the cell cycle and identified new potential cell cycle-related genes, thereby contributing to the understanding of the processes that regulate the cell cycle.

Building a model for predicting metabolic syndrome using artificial intelligence based on an investigation of whole-genome sequencing

Background

The circadian system is responsible for regulating various physiological activities and behaviors and has been gaining recognition. The circadian rhythm is adjusted in a 24-h cycle and has transcriptional–translational feedback loops. When the circadian rhythm is interrupted, affecting the expression of circadian genes, the phenotypes of diseases could amplify. For example, the importance of maintaining the internal temporal homeostasis conferred by the circadian system is revealed as mutations in genes coding for core components of the clock result in diseases. This study will investigate the association between circadian genes and metabolic syndromes in a Taiwanese population.

Methods

We performed analysis using whole-genome sequencing, read vcf files and set target circadian genes to determine if there were variants on target genes. In this study, we have investigated genetic contribution of circadian-related diseases using population-based next generation whole genome sequencing. We also used significant SNPs to create a metabolic syndrome prediction model. Logistic regression, random forest, adaboost, and neural network were used to predict metabolic syndrome. In addition, we used random forest model variables importance matrix to select 40 more significant SNPs, which were subsequently incorporated to create new prediction models and to compare with previous models. The data was then utilized for training set and testing set using five-fold cross validation. Each model was evaluated with the following criteria: area under the receiver operating characteristics curve (AUC), precision, F1 score, and average precision (the area under the precision recall curve).

Results

After searching significant variants, we used Chi-Square tests to find some variants. We found 186 significant SNPs, and four predicting models which used 186 SNPs (logistic regression, random forest, adaboost and neural network), AUC were 0.68, 0.8, 0.82, 0.81 respectively. The F1 scores were 0.412, 0.078, 0.295, 0.552, respectively. The other three models which used the 40 SNPs (logistic regression, adaboost and neural network), AUC were 0.82, 0.81, 0.81 respectively. The F1 scores were 0.584, 0.395, 0.574, respectively.

Conclusions

Circadian gene defect may also contribute to metabolic syndrome. Our study found several related genes and building a simple model to predict metabolic syndrome.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12967-022-03379-7.

The role of circadian genes in the pathogenesis of colorectal cancer

Colorectal cancer (CRC) is the third most frequent cancer in human beings and is also the major cause of death among the other gastrointestinal cancers. The exact mechanisms of CRC development in most patients remains unclear. So far, several genetically, environmental and epigenetically risk factors have been identified for CRC development. The circadian rhythm is a 24-h rhythm that drives several biologic processes. The circadian system is guided by a central pacemaker which is located in the suprachiasmatic nucleus (SCN) in the hypothalamus. Circadian rhythm is regulated by circadian clock genes, cytokines and hormones like melatonin. Disruptions in biological rhythms are known to be strongly associated with several diseases, including cancer. The role of the different circadian genes has been verified in various cancers, however, the pathways of different circadian genes in the pathogenesis of CRC are less investigated. Identification of the details of the pathways in CRC helps researchers to explore new therapies for the malignancy.

Circadian dynamics of the teleost skin immune-microbiome interface

BACKGROUND

Circadian rhythms of host immune activity and their microbiomes are likely pivotal to health and disease resistance. The integration of chronotherapeutic approaches to disease mitigation in managed animals, however, is yet to be realised. In aquaculture, light manipulation is commonly used to enhance growth and control reproduction but may have unknown negative consequences for animal health. Infectious diseases are a major barrier to sustainable aquaculture and understanding the circadian dynamics of fish immunity and crosstalk with the microbiome is urgently needed.

RESULTS

Here, using rainbow trout (Oncorhynchus mykiss) as a model, we combine 16S rRNA metabarcoding, metagenomic sequencing and direct mRNA quantification methods to simultaneously characterise the circadian dynamics of skin clock and immune gene expression, and daily changes of skin microbiota. We demonstrate daily rhythms in fish skin immune expression and microbiomes, which are modulated by photoperiod and parasitic lice infection. We identify putative associations of host clock and immune gene profiles with microbial composition. Our results suggest circadian perturbation, that shifts the magnitude and timing of immune and microbiota activity, is detrimental to fish health.

CONCLUSIONS

The substantial circadian dynamics and fish host expression-microbiome relationships we find represent a valuable foundation for investigating the utility of chronotherapies in aquaculture, and more broadly contributes to our understanding of the role of microbiomes in circadian health of vertebrates. Video Abstract.

Evaluation of classification and forecasting methods on time series gene expression data

Time series gene expression data is widely used to study different dynamic biological processes. Although gene expression datasets share many of the characteristics of time series data from other domains, most of the analyses in this field do not fully leverage the time-ordered nature of the data and focus on clustering the genes based on their expression values. Other domains, such as financial stock and weather prediction, utilize time series data for forecasting purposes. Moreover, many studies have been conducted to classify generic time series data based on trend, seasonality, and other patterns. Therefore, an assessment of these approaches on gene expression data would be of great interest to evaluate their adequacy in this domain. Here, we perform a comprehensive evaluation of different traditional unsupervised and supervised machine learning approaches as well as deep learning based techniques for time series gene expression classification and forecasting on five real datasets. In addition, we propose deep learning based methods for both classification and forecasting, and compare their performances with the state-of-the-art methods. We find that deep learning based methods generally outperform traditional approaches for time series classification. Experiments also suggest that supervised classification on gene expression is more effective than clustering when labels are available. In time series gene expression forecasting, we observe that an autoregressive statistical approach has the best performance for short term forecasting, whereas deep learning based methods are better suited for long term forecasting.

An Optimal Time for Treatment-Predicting Circadian Time by Machine Learning and Mathematical Modelling

Tailoring medical interventions to a particular patient and pathology has been termed personalized medicine. The outcome of cancer treatments is improved when the intervention is timed in accordance with the patient's internal time. Yet, one challenge of personalized medicine is how to consider the biological time of the patient. Prerequisite for this so-called chronotherapy is an accurate characterization of the internal circadian time of the patient. As an alternative to time-consuming measurements in a sleep-laboratory, recent studies in chronobiology predict circadian time by applying machine learning approaches and mathematical modelling to easier accessible observables such as gene expression. Embedding these results into the mathematical dynamics between clock and cancer in mammals, we review the precision of predictions and the potential usage with respect to cancer treatment and discuss whether the patient's internal time and circadian observables, may provide an additional indication for individualized treatment timing. Besides the health improvement, timing treatment may imply financial advantages, by ameliorating side effects of treatments, thus reducing costs. Summarizing the advances of recent years, this review brings together the current clinical standard for measuring biological time, the general assessment of circadian rhythmicity, the usage of rhythmic variables to predict biological time and models of circadian rhythmicity.

Weighing and modelling factors influencing serum cortisol and melatonin concentration among workers that are exposed to various sound pressure levels using neural network algorithm: An empirical study

BACKGROUND

Noise is one of the most common harmful agents in the workplace. Exposure to excessive noise can lead to complications such as cardiovascular disorders, disturbance of body hormones' rhythm and hearing loss. This study aimed at weighing and modelling factors influencing serum cortisol and melatonin concentrations of workers that are exposed to various sound pressure levels using neural network algorithm.

METHODOLOGY

A case-control design was adopted in the current research. The required data were collected from 75 industrial and mining firm staff members. They were assigned to three groups with equal sample sizes (25 workers). In developing the conceptual model in regard to variables that may affect workers' serum cortisol and melatonin concentration, SPL, age, weight, and height were included. The influence of SPL on serum cortisol concentration as assessed in the three shifts. Moreover, radioimmunoassay (RIA) was utilized to assess serum cortisol and melatonin concentrations. Neural network algorithm was subsequently exploited to weigh and model predictor factors. IBM SPSS Modeler 18.0 was the software program used for data analysis.

RESULTS

The average cortisol concentration values for administrative, condensing, and pelletizing units respectively were 10.24 ± 2.35, 12.15 ± 3.46, and 14.91 ± 4.16μ g d l . On the other hand, the average melatonin concentration values for administrative, condensing, and pelletizing units respectively were 37 ± 12.52, 34 ± 13.15, and 27 ± 9.54μ g d l . According to the results of the developed model for cortisol, SPL3 (32%) and age (5%) respectively had the highest and lowest impact. On the other hand, considering the model developed for melatonin, height (27%) and SPL1 (10%) were the most and least influential factors in that order. The accuracy rates of the model were also found to be 95% for cortisol and 97% for melatonin.

CONCLUSION

Comparing cortisol concentrations during various shifts revealed a significant reduction (from the beginning to the end of the shift) in all the three groups. Further, the rise of SPL would result in higher secretion of cortisol. Moreover, in all the three groups, the average serum melatonin concentration went up from the beginning to the middle of the shift and then declined to the end of the shift. Considering the accuracy rates of the models developed to predict hormones, neural network algorithm is a suitable and powerful tool for weighing and modelling factors influencing serum cortisol and melatonin concentrations.