Identifying Critical State of Complex Diseases by Single-Sample-Based Hidden Markov Model

mNFE: microbiome network flow entropy for detecting pre-disease states of type 1 diabetes

In the development of Type 1 diabetes (T1D), there are critical states just before drastic changes, and identifying these pre-disease states may predict T1D or provide crucial early-warning signals. Unlike gene expression data, gut microbiome data can be collected noninvasively from stool samples. Gut microbiome sequencing data contain different levels of phylogenetic information that can be utilized to detect the tipping point or critical state in a reliable manner, thereby providing accurate and effective early-warning signals. However, it is still difficult to detect the critical state of T1D based on gut microbiome data due to generally non-significant differences between healthy and critical states. To address this problem, we proposed a new method - microbiome network flow entropy (mNFE) based on a single sample from each individual - for detecting the critical state before seroconversion and abrupt transitions of T1D at various taxonomic levels. The numerical simulation validated the robustness of mNFE under different noise levels. Furthermore, based on real datasets, mNFE successfully identified the critical states and their dynamic network biomarkers (DNBs) at different taxonomic levels. In addition, we found some high-frequency species, which are closely related to the unique clinical characteristics of autoantibodies at the four levels, and identified some non-differential 'dark species' play important roles during the T1D progression. mNFE can robustly and effectively detect the pre-disease states at various taxonomic levels and identify the corresponding DNBs with only a single sample for each individual. Therefore, our mNFE method provides a new approach not only for T1D pre-disease diagnosis or preventative treatment but also for preventative medicine of other diseases by gut microbiome.

Dynamic modelling and tristability analysis of misfolded α-synuclein degraded via autophagy in Parkinson's disease

The widely-accepted hallmark pathology of Parkinson's disease (PD) is the presence of Lewy bodies with characteristic abnormal aggregated α-synuclein (αSyn). Growing physiological evidence suggests that there is a pivotal role for the autophagy-lysosome pathway (ALP) in the clearance of misfolded αSyn (αSyn∗). This work establishes a mathematical model for αSyn∗ degradation through the ALP. Qualitative simulations are used to uncover the tristable behavior of αSyn∗, i.e., the lower, medium, and upper steady states, which correspond to the healthy, critical, and disease stages of PD, respectively. Time series and codimension-1 bifurcation analysis suggest that the system shows tristability dynamics. Furthermore, variations in the key parameters influence the tristable dynamic behavior, and the distribution of tristable regions is exhibited more comprehensively in codimension-2 bifurcation diagrams. In addition, robustness analysis demonstrates that tristability is a robust property of the system. These results may be valuable in therapeutic strategies for the prevention and treatment of PD.

Dynamics of a model for the degradation mechanism of aggregated α-synuclein in Parkinson's disease

Accumulation of the misfolded synaptic protein α-synuclein (αSyn^*) is a hallmark of neurodegenerative disease in Parkinson's disease (PD). Recent studies suggest that the autophagy lysosome pathway (ALP) including both the Beclin1-associated and mTOR-signaling pathways is involved in the αSyn^* clearance mechanism. In this study, a mathematical model is proposed for the degradation of αSyn^* by ALP with the crosstalk element of mTOR. Using codimension-1 bifurcation analysis, the tri-stability of αSyn^* is surveyed under three different stress signals and, in addition, consideration is given to the regulatory mechanisms for the Beclin1- and mTOR-dependent rates on αSyn^* degradation using the codimension-1 and-2 bifurcation diagrams. It was found that, especially under internal and external oxidative stresses (S ₁), the bistable switch of the aggregation of αSyn^* can be transformed from an irreversible to a reversible condition through the ALP degradation pathways. Furthermore, the robustness of the tri-stable state for the stress S ₁ to the parameters related to mTOR-mediated ALP was probed. It was confirmed that mTOR-mediated ALP is important for maintaining the essential dynamic features of the tri-stable state. This study may provide a promising avenue for conducting further experiments and simulations of the degradation mechanism of dynamic modeling in PD.

Autism detection based on multiple time scale model

OBJECTIVE

Current autism clinical detection relies on doctor observation and filling of clinical scales, which is subjective and easily misdetection. Existing autism research of functional magnetic resonance imaging (fMRI) over-compresses the time-scale information and has poor generalization ability. This study extracts multiple time scale brain features of fMRI, providing objective detection.

APPROACH

We first use least absolute shrinkage and selection operator (LASSO) to build a sparse network and extract features with a time scale of 1. Then, we use hidden markov model (HMM) to extract features that describe the dynamic changes of the brain, with a time scale of 2. Additionally, to analyze the features of the potential network activity of autism from a higher time scale, we use long short-term memory (LSTM) to construct an auto-encoder to re-encode the original data and extract the features of the at a higher time scale, with a time scale of T, and T is the time length of fMRI. We use Recursive Feature Elimination (RFE) for feature selection for three different time scale features, merge them into multiple time scale features, and finally use one-dimensional convolution neural network (1DCNN) for classification.

MAIN RESULTS

Compared with well-established models, our method has achieved better results. The accuracy of our method is 76.0%, and the area under the roc curve is 0.83, tested on the completely independent data, so our method has better generalization ability.

SIGNIFICANCE

This research analyzes fMRI sequences from multiple time scale to detect autism, and it also provides a new framework and research ideas for subsequent fMRI analysis.

Detecting the critical states during disease development based on temporal network flow entropy

Complex diseases progression can be generally divided into three states, which are normal state, predisease/critical state and disease state. The sudden deterioration of diseases can be viewed as a bifurcation or a critical transition. Therefore, hunting for the tipping point or critical state is of great importance to prevent the disease deterioration. However, it is still a challenging task to detect the critical states of complex diseases with high-dimensional data, especially based on an individual. In this study, we develop a new method based on network fluctuation of molecules, temporal network flow entropy (TNFE) or temporal differential network flow entropy, to detect the critical states of complex diseases on the basis of each individual. By applying this method to a simulated dataset and six real diseases, including respiratory viral infections and tumors with four time-course and two stage-course high-dimensional omics datasets, the critical states before deterioration were detected and their dynamic network biomarkers were identified successfully. The results on the simulated dataset indicate that the TNFE method is robust under different noise strengths, and is also superior to the existing methods on detecting the critical states. Moreover, the analysis on the real datasets demonstrated the effectiveness of TNFE for providing early-warning signals on various diseases. In addition, we also predicted disease deterioration risk and identified drug targets for cancers based on stage-wise data.

Single-Sample Node Entropy for Molecular Transition in Pre-deterioration Stage of Cancer

A complex disease, especially cancer, always has pre-deterioration stage during its progression, which is difficult to identify but crucial to drug research and clinical intervention. However, using a few samples to find mechanisms that propel cancer crossing the pre-deterioration stage is still a complex problem. In this study, we successfully developed a novel single-sample model based on node entropy with a priori established protein interaction network. Using this model, critical stages were successfully detected in simulation data and four TCGA datasets, indicating its sensitivity and robustness. Besides, compared with the results of the differential analysis, our results showed that most of dynamic network biomarkers identified by node entropy, such as NKD2 or DAAM1, located in upstream in many important cancer-related signaling pathways regulated intergenic signaling within pathways. We also identified some novel prognostic biomarkers such as PER2, TNFSF4, MMP13 and ENO4 using node entropy rather than expression level. More importantly, we found the switch of non-specific pathways related to DNA damage repairing was the main driven force for cancer progression. In conclusion, we have successfully developed a dynamic node entropy model based on single case data to find out tipping point and possible mechanism for cancer progression. These findings may provide new target genes in therapeutic intervention tactics.

Real-time, personalized medicine through wearable sensors and dynamic predictive modeling: a new paradigm for clinical medicine

Accurately predicting the onset and course of a disease in an individual is a major unmet challenge in medicine due to the complex and dynamic nature of disease progression. Continuous data from wearable technologies and biomarker data with a fine time resolution provide a unique opportunity to learn more about disease evolution and to usher in a new era of personalized and real-time medicine. Herein, we propose the potential of real-time, continuously measured physiological data as a noninvasive biomarker approach for detecting disease transitions, using allogeneic hematopoietic stem cell transplant (HCT) patient care as an example. Additionally, we review a recent computational technique, the landscape dynamic network biomarker method, that uses biomarker data to identify transition states in disease progression and explore how to use it with both biomarker and physiological data for earlier detection of graft-versus-host disease specifically. Throughout, we argue that increased collaboration across multiple fields is essential to realizing the full potential of wearable and biomarker data in a new paradigm of personalized and real-time medicine.

Identifying critical state of complex diseases by single-sample Kullback-Leibler divergence

Background

Developing effective strategies for signaling the pre-disease state of complex diseases, a state with high susceptibility before the disease onset or deterioration, is urgently needed because such state usually followed by a catastrophic transition into a worse stage of disease. However, it is a challenging task to identify such pre-disease state or tipping point in clinics, where only one single sample is available and thus results in the failure of most statistic approaches.

Methods

In this study, we presented a single-sample-based computational method to detect the early-warning signal of critical transition during the progression of complex diseases. Specifically, given a set of reference samples which were regarded as background, a novel index called single-sample Kullback–Leibler divergence (sKLD), was proposed to explore and quantify the disturbance on the background caused by a case sample. The pre-disease state is then signaled by the significant change of sKLD.

Results

The novel algorithm was developed and applied to both numerical simulation and real datasets, including lung squamous cell carcinoma, lung adenocarcinoma, stomach adenocarcinoma, thyroid carcinoma, colon adenocarcinoma, and acute lung injury. The successful identification of pre-disease states and the corresponding dynamical network biomarkers for all six datasets validated the effectiveness and accuracy of our method.

Conclusions

The proposed method effectively explores and quantifies the disturbance on the background caused by a case sample, and thus characterizes the criticality of a biological system. Our method not only identifies the critical state or tipping point at a single sample level, but also provides the sKLD-signaling markers for further practical application. It is therefore of great potential in personalized pre-disease diagnosis.