Interpreting machine learning models to investigate circadian regulation and facilitate exploration of clock function.
Ontology highlight
ABSTRACT:
SUBMITTER: Gardiner LJ
PROVIDER: S-EPMC8364196 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Tree ensemble machine learning models are increasingly used in microbiome science as they are compatible with the compositional, high-dimensional, and sparse structure of sequence-based microbiome data. While such models are often good at predicting phenotypes based on microbiome data, they only yield limited insights into how microbial taxa may be associated. We developed endoR, a method to interpret tree ensemble models. First, endoR simplifies the fitted model into a decision ensemble. Then, it extracts information on the importance of individual features and their pairwise interactions, displaying them as an interpretable network. Both the endoR network and importance scores provide insights into how features, and interactions between them, contribute to the predictive performance of the fitted model. Adjustable regularization and bootstrapping help reduce the complexity and ensure that only essential parts of the model are retained. We assessed endoR on both simulated and real metagenomic data. We found endoR to have comparable accuracy to other common approaches while easing and enhancing model interpretation. Using endoR, we also confirmed published results on gut microbiome differences between cirrhotic and healthy individuals. Finally, we utilized endoR to explore associations between human gut methanogens and microbiome components. Indeed, these hydrogen consumers are expected to interact with fermenting bacteria in a complex syntrophic network. Specifically, we analyzed a global metagenome dataset of 2203 individuals and confirmed the previously reported association between Methanobacteriaceae and Christensenellales. Additionally, we observed that Methanobacteriaceae are associated with a network of hydrogen-producing bacteria. Our method accurately captures how tree ensembles use features and interactions between them to predict a response. As demonstrated by our applications, the resultant visualizations and summary outputs facilitate model interpretation and enable the generation of novel hypotheses about complex systems.
| S-EPMC9797088 | biostudies-literature
Project description:Over the last decades, researchers have characterized a set of "clock genes" that drive daily rhythms in physiology and behavior. This arduous work has yielded results with far-reaching consequences in metabolic, psychiatric, and neoplastic disorders. Recent attempts to expand our understanding of circadian regulation have moved beyond the mutagenesis screens that identified the first clock components, employing higher throughput genomic and proteomic techniques. In order to further accelerate clock gene discovery, we utilized a computer-assisted approach to identify and prioritize candidate clock components. We used a simple form of probabilistic machine learning to integrate biologically relevant, genome-scale data and ranked genes on their similarity to known clock components. We then used a secondary experimental screen to characterize the top candidates. We found that several physically interact with known clock components in a mammalian two-hybrid screen and modulate in vitro cellular rhythms in an immortalized mouse fibroblast line (NIH 3T3). One candidate, Gene Model 129, interacts with BMAL1 and functionally represses the key driver of molecular rhythms, the BMAL1/CLOCK transcriptional complex. Given these results, we have renamed the gene CHRONO (computationally highlighted repressor of the network oscillator). Bi-molecular fluorescence complementation and co-immunoprecipitation demonstrate that CHRONO represses by abrogating the binding of BMAL1 to its transcriptional co-activator CBP. Most importantly, CHRONO knockout mice display a prolonged free-running circadian period similar to, or more drastic than, six other clock components. We conclude that CHRONO is a functional clock component providing a new layer of control on circadian molecular dynamics.
| S-EPMC3988006 | biostudies-literature
Project description:Mood disorders, including generalized anxiety disorder, are associated with disruptions in circadian rhythms and are linked to polymorphisms in circadian clock genes. Molecular mechanisms underlying these connections may be direct-via transcriptional activity of clock genes on downstream mood pathways in the brain, or indirect-via clock gene influences on the phase and amplitude of circadian rhythms which, in turn, modulate physiological processes influencing mood. Employing machine learning combined with statistical approaches, we explored clock genotype combinations that predict risk for anxiety symptoms in a deeply phenotyped population. We identified multiple novel circadian genotypes predictive of anxiety, with the PER3(rs17031614)-AG/CRY1(rs2287161)-CG genotype being the strongest predictor of anxiety risk, particularly in males. Molecular chronotyping, using clock gene expression oscillations, revealed that advanced circadian phase and robust circadian amplitudes are associated with high levels of anxiety symptoms. Further analyses revealed that individuals with advanced phases and pronounced circadian misalignment were at higher risk for severe anxiety symptoms. Our results support both direct and indirect influences of clock gene variants on mood: while sex-specific clock genotype combinations predictive of anxiety symptoms suggest direct effects on mood pathways, the mediation of PER3 effects on anxiety via diurnal preference measures and the association of circadian phase with anxiety symptoms provide evidence for indirect effects of the molecular clockwork on mood. Unraveling the complex molecular mechanisms underlying the links between circadian physiology and mood is essential to identifying the core clock genes to target in future functional studies, thereby advancing the development of non-invasive treatments for anxiety-related disorders.
| S-EPMC8975926 | biostudies-literature
Project description:Mood disorders, including depression and anxiety, affect almost one-fifth of the world's adult population and are becoming increasingly prevalent. Mutations in circadian clock genes have previously been associated with mood disorders both directly and indirectly through alterations in circadian phase, suggesting that the circadian clock influences multiple molecular pathways involved in mood. By targeting previously identified single nucleotide polymorphisms (SNPs) that have been implicated in anxiety and depressive disorders, we use a combination of statistical and machine learning techniques to investigate associations with the generalized anxiety disorder assessment (GAD-7) scores in a UK Biobank sample of 90,882 individuals. As in previous studies, we observed that females exhibited higher GAD-7 scores than males regardless of genotype. Interestingly, we found no significant effects on anxiety from individual circadian gene variants; only circadian genotypes with multiple SNP variants showed significant associations with anxiety. For both sexes, severe anxiety is associated with a 120-fold increase in odds for individuals with CRY2_AG(rs1083852)/ZBTB20_TT(rs1394593) genotypes and is associated with a near 40-fold reduction in odds for individuals with PER3-A_CG(rs228697)/ZBTB20_TT(rs1394593) genotypes. We also report several sex-specific associations with anxiety. In females, the CRY2/ZBTB20 genotype combination showed a > 200-fold increase in odds of anxiety and PER3/ZBTB20 and CRY1 /PER3-A genotype combinations also appeared as female risk factors. In males, CRY1/PER3-A and PER3-B/ZBTB20 genotype combinations were associated with anxiety risk. Mediation analysis revealed direct associations of CRY2/ZBTB20 variant genotypes with moderate anxiety in females and CRY1/PER3-A variant genotypes with severe anxiety in males. The association of CRY1/PER3-A variant genotypes with severe anxiety in females was partially mediated by extreme evening chronotype. Our results reinforce existing findings that females exhibit stronger anxiety outcomes than males, and provide evidence for circadian gene associations with anxiety, particularly in females. Our analyses only identified significant associations using two-gene combinations, underscoring the importance of combined gene effects on anxiety risk. We describe novel, robust associations between gene combinations involving the ZBTB20 SNP (rs1394593) and risk of anxiety symptoms in a large population sample. Our findings also support previous findings that the ZBTB20 SNP is an important factor in mood disorders, including seasonal affective disorder. Our results suggest that reduced expression of this gene significantly modulates the risk of anxiety symptoms through direct influences on mood-related pathways. Together, these observations provide novel links between the circadian clockwork and anxiety symptoms and identify potential molecular pathways through which clock genes may influence anxiety risk.
| S-EPMC10724169 | biostudies-literature
Project description:The mammalian circadian clock relies on the transcription factor CLOCK:BMAL1 to coordinate the rhythmic expression of 15% of the transcriptome and control the daily regulation of biological functions. The recent characterization of CLOCK:BMAL1 cistrome revealed that although CLOCK:BMAL1 binds synchronously to all of its target genes, its transcriptional output is highly heterogeneous. By performing a meta-analysis of several independent genome-wide datasets, we found that the binding of other transcription factors at CLOCK:BMAL1 enhancers likely contribute to the heterogeneity of CLOCK:BMAL1 transcriptional output. While CLOCK:BMAL1 rhythmic DNA binding promotes rhythmic nucleosome removal, it is not sufficient to generate transcriptionally active enhancers as assessed by H3K27ac signal, RNA Polymerase II recruitment, and eRNA expression. Instead, the transcriptional activity of CLOCK:BMAL1 enhancers appears to rely on the activity of ubiquitously expressed transcription factors, and not tissue-specific transcription factors, recruited at nearby binding sites. The contribution of other transcription factors is exemplified by how fasting, which effects several transcription factors but not CLOCK:BMAL1, either decreases or increases the amplitude of many rhythmically expressed CLOCK:BMAL1 target genes. Together, our analysis suggests that CLOCK:BMAL1 promotes a transcriptionally permissive chromatin landscape that primes its target genes for transcription activation rather than directly activating transcription, and provides a new framework to explain how environmental or pathological conditions can reprogram the rhythmic expression of clock-controlled genes.
| S-EPMC5771620 | biostudies-literature
Project description:BackgroundThe circadian clock and the daily rhythms it produces are crucial for human health, but are often disrupted by the modern environment. At the same time, circadian rhythms may influence the efficacy and toxicity of therapeutics and the metabolic response to food intake. Developing treatments for circadian dysfunction, as well as optimizing the daily timing of treatments for other health conditions, will require a simple and accurate method to monitor the molecular state of the circadian clock.MethodsHere we used a recently developed method called ZeitZeiger to predict circadian time (CT, time of day according to the circadian clock) from genome-wide gene expression in human blood.ResultsIn cross-validation on 498 samples from 60 individuals across three publicly available datasets, ZeitZeiger predicted CT in single samples with a median absolute error of 2.1 h. The predictor trained on all 498 samples used 15 genes, only two of which are part of the core circadian clock. By then applying ZeitZeiger to 475 additional samples from the same three datasets, we quantified how the circadian clock in the blood was affected by various perturbations to the sleep-wake and light-dark cycles. Finally, we extended ZeitZeiger (1) to handle intra-individual variation by making predictions based on multiple samples taken a known time apart, and (2) to handle inter-individual variation by personalizing predictions based on samples from the respective individual. Each of these strategies improved prediction of CT by ~20%.ConclusionsOur results are an important step towards precision circadian medicine. In addition, our generalizable extensions to ZeitZeiger may be applicable to the growing number of biological datasets that contain multiple observations per individual.
| S-EPMC5329904 | biostudies-literature
Project description:Predictive modeling of neuroimaging data (predictive neuroimaging) for evaluating individual differences in various behavioral phenotypes and clinical outcomes is of growing interest. However, the field is experiencing challenges regarding the interpretability of the results. Approaches to defining the specific contribution of functional connections, regions, or networks in prediction models are urgently needed, which may help explore the underlying mechanisms. In this article, we systematically review the methods and applications for interpreting brain signatures derived from predictive neuroimaging based on a survey of 326 research articles. Strengths, limitations, and the suitable conditions for major interpretation strategies are also deliberated. In-depth discussion of common issues in existing literature and the corresponding recommendations to address these pitfalls are provided. We highly recommend exhaustive validation on the reliability and interpretability of the biomarkers across multiple datasets and contexts, which thereby could translate technical advances in neuroimaging into concrete improvements in precision medicine.
| S-EPMC9880880 | biostudies-literature
Project description:Most bodily functions vary over the course of a 24h day. Circadian rhythms in body temperature, sleep-wake cycles, metabolism, and blood pressure (BP) are just a few examples. These circadian rhythms are controlled by the central clock in the suprachiasmatic nucleus (SCN) of the hypothalamus and peripheral clocks located throughout the body. Light and food cues entrain these clocks to the time of day and this synchronicity contributes to the regulation of a variety of physiological processes with effects on overall health. The kidney, brain, nervous system, vasculature, and heart have been identified through the use of mouse models and clinical trials as peripheral clock regulators of BP. The dysregulation of this circadian pattern of BP, with or without hypertension, is associated with increased risk for cardiovascular disease. The mechanism of this dysregulation is unknown and is a growing area of research. In this review, we highlight research of human and mouse circadian models that has provided insight into the roles of these molecular clocks and their effects on physiological functions. Additional tissue-specific studies of the molecular clock mechanism are needed, as well as clinical studies including more diverse populations (different races, female patients, etc.), which will be critical to fully understand the mechanism of circadian regulation of BP. Understanding how these molecular clocks regulate the circadian rhythm of BP is critical in the treatment of circadian BP dysregulation and hypertension.
| S-EPMC5910276 | biostudies-literature
Project description:The mammalian circadian clock is well-known to be important for our sleep-wake cycles, as well as other daily rhythms such as temperature regulation, hormone release or feeding-fasting cycles. Under normal conditions, these daily cyclic events follow 24 h limit cycle oscillations, but under some circumstances, more complex nonlinear phenomena, such as the emergence of chaos, or the splitting of physiological dynamics into oscillations with two different periods, can be observed. These nonlinear events have been described at the organismic and tissue level, but whether they occur at the cellular level is still unknown. Our results show that period-doubling, chaos and splitting appear in different models of the mammalian circadian clock with interlocked feedback loops and in the absence of external forcing. We find that changes in the degradation of clock genes and proteins greatly alter the dynamics of the system and can induce complex nonlinear events. Our findings highlight the role of degradation rates in determining the oscillatory behaviour of clock components, and can contribute to the understanding of molecular mechanisms of circadian dysregulation.
| S-EPMC7536064 | biostudies-literature
Project description:Machine learning (ML) is a promising methodology for classification and prediction applications in healthcare. However, this method has not been practically established for clinical data. Hyperuricemia is a biomarker of various chronic diseases. We aimed to predict uric acid status from basic healthcare checkup test results using several ML algorithms and to evaluate the performance. We designed a prediction model for hyperuricemia using a comprehensive health checkup database designed by the classification of ML algorithms, such as discrimination analysis, K-nearest neighbor, naïve Bayes (NBC), support vector machine, decision tree, and random forest classification (RFC). The performance of each algorithm was evaluated and compared with the performance of a conventional logistic regression (CLR) algorithm by receiver operating characteristic curve analysis. Of the 38,001 participants, 7705 were hyperuricemic. For the maximum sensitivity criterion, NBC showed the highest sensitivity (0.73), and RFC showed the second highest (0.66); for the maximum balanced classification rate (BCR) criterion, RFC showed the highest BCR (0.68), and NBC showed the second highest (0.66) among the various ML algorithms for predicting uric acid status. In a comparison to the performance of NBC (area under the curve (AUC) = 0.669, 95% confidence intervals (CI) = 0.669⁻0.675) and RFC (AUC = 0.775, 95% CI 0.770⁻0.780) with a CLR algorithm (AUC = 0.568, 95% CI = 0.563⁻0.571), NBC and RFC showed significantly better performance (p < 0.001). The ML model was superior to the CLR model for the prediction of hyperuricemia. Future studies are needed to determine the best-performing ML algorithms based on data set characteristics. We believe that this study will be informative for studies using ML tools in clinical research.
| S-EPMC6406925 | biostudies-literature