A prostate cancer model build by a novel SVM-ID3 hybrid feature selection method using both genotyping and phenotype data from dbGaP

Identifying Critical States of Complex Diseases by Single-Sample Jensen-Shannon Divergence

MOTIVATION

The evolution of complex diseases can be modeled as a time-dependent nonlinear dynamic system, and its progression can be divided into three states, i.e., the normal state, the pre-disease state and the disease state. The sudden deterioration of the disease can be regarded as the state transition of the dynamic system at the critical state or pre-disease state. How to detect the critical state of an individual before the disease state based on single-sample data has attracted many researchers' attention.

METHODS

In this study, we proposed a novel approach, i.e., single-sample-based Jensen-Shannon Divergence (sJSD) method to detect the early-warning signals of complex diseases before critical transitions based on individual single-sample data. The method aims to construct score index based on sJSD, namely, inconsistency index (ICI).

RESULTS

This method is applied to five real datasets, including prostate cancer, bladder urothelial carcinoma, influenza virus infection, cervical squamous cell carcinoma and endocervical adenocarcinoma and pancreatic adenocarcinoma. The critical states of 5 datasets with their corresponding sJSD signal biomarkers are successfully identified to diagnose and predict each individual sample, and some "dark genes" that without differential expressions but are sensitive to ICI score were revealed. This method is a data-driven and model-free method, which can be applied to not only disease prediction on individuals but also targeted drug design of each disease. At the same time, the identification of sJSD signal biomarkers is also of great significance for studying the molecular mechanism of disease progression from a dynamic perspective.

Precise diagnosis of three top cancers using dbGaP data

The challenge of decoding information about complex diseases hidden in huge number of single nucleotide polymorphism (SNP) genotypes is undertaken based on five dbGaP studies. Current genome-wide association studies have successfully identified many high-risk SNPs associated with diseases, but precise diagnostic models for complex diseases by these or more other SNP genotypes are still unavailable in the literature. We report that lung cancer, breast cancer and prostate cancer as the first three top cancers worldwide can be predicted precisely via 240–370 SNPs with accuracy up to 99% according to leave-one-out and 10-fold cross-validation. Our findings (1) confirm an early guess of Dr. Mitchell H. Gail that about 300 SNPs are needed to improve risk forecasts for breast cancer, (2) reveal an incredible fact that SNP genotypes may contain almost all information that one wants to know, and (3) show a hopeful possibility that complex diseases can be precisely diagnosed by means of SNP genotypes without using phenotypical features. In short words, information hidden in SNP genotypes can be extracted in efficient ways to make precise diagnoses for complex diseases.

Building a genetic risk model for bipolar disorder from genome-wide association data with random forest algorithm

A genetic risk score could be beneficial in assisting clinical diagnosis for complex diseases with high heritability. With large-scale genome-wide association (GWA) data, the current study constructed a genetic risk model with a machine learning approach for bipolar disorder (BPD). The GWA dataset of BPD from the Genetic Association Information Network was used as the training data for model construction, and the Systematic Treatment Enhancement Program (STEP) GWA data were used as the validation dataset. A random forest algorithm was applied for pre-filtered markers, and variable importance indices were assessed. 289 candidate markers were selected by random forest procedures with good discriminability; the area under the receiver operating characteristic curve was 0.944 (0.935–0.953) in the training set and 0.702 (0.681–0.723) in the STEP dataset. Using a score with the cutoff of 184, the sensitivity and specificity for BPD was 0.777 and 0.854, respectively. Pathway analyses revealed important biological pathways for identified genes. In conclusion, the present study identified informative genetic markers to differentiate BPD from healthy controls with acceptable discriminability in the validation dataset. In the future, diagnosis classification can be further improved by assessing more comprehensive clinical risk factors and jointly analysing them with genetic data in large samples.

FHSA-SED: Two-Locus Model Detection for Genome-Wide Association Study with Harmony Search Algorithm

Motivation

Two-locus model is a typical significant disease model to be identified in genome-wide association study (GWAS). Due to intensive computational burden and diversity of disease models, existing methods have drawbacks on low detection power, high computation cost, and preference for some types of disease models.

Method

In this study, two scoring functions (Bayesian network based K2-score and Gini-score) are used for characterizing two SNP locus as a candidate model, the two criteria are adopted simultaneously for improving identification power and tackling the preference problem to disease models. Harmony search algorithm (HSA) is improved for quickly finding the most likely candidate models among all two-locus models, in which a local search algorithm with two-dimensional tabu table is presented to avoid repeatedly evaluating some disease models that have strong marginal effect. Finally G-test statistic is used to further test the candidate models.

Results

We investigate our method named FHSA-SED on 82 simulated datasets and a real AMD dataset, and compare it with two typical methods (MACOED and CSE) which have been developed recently based on swarm intelligent search algorithm. The results of simulation experiments indicate that our method outperforms the two compared algorithms in terms of detection power, computation time, evaluation times, sensitivity (TPR), specificity (SPC), positive predictive value (PPV) and accuracy (ACC). Our method has identified two SNPs (rs3775652 and rs10511467) that may be also associated with disease in AMD dataset.

Incorporation of personal single nucleotide polymorphism (SNP) data into a national level electronic health record for disease risk assessment, part 3: an evaluation of SNP incorporated national health information system of Turkey for prostate cancer

Background

A personalized medicine approach provides opportunities for predictive and preventive medicine. Using genomic, clinical, environmental, and behavioral data, the tracking and management of individual wellness is possible. A prolific way to carry this personalized approach into routine practices can be accomplished by integrating clinical interpretations of genomic variations into electronic medical records (EMRs)/electronic health records (EHRs). Today, various central EHR infrastructures have been constituted in many countries of the world, including Turkey.

Objective

As an initial attempt to develop a sophisticated infrastructure, we have concentrated on incorporating the personal single nucleotide polymorphism (SNP) data into the National Health Information System of Turkey (NHIS-T) for disease risk assessment, and evaluated the performance of various predictive models for prostate cancer cases. We present our work as a three part miniseries: (1) an overview of requirements, (2) the incorporation of SNP data into the NHIS-T, and (3) an evaluation of SNP data incorporated into the NHIS-T for prostate cancer.

Methods

In the third article of this miniseries, we have evaluated the proposed complementary capabilities (ie, knowledge base and end-user application) with real data. Before the evaluation phase, clinicogenomic associations about increased prostate cancer risk were extracted from knowledge sources, and published predictive genomic models assessing individual prostate cancer risk were collected. To evaluate complementary capabilities, we also gathered personal SNP data of four prostate cancer cases and fifteen controls. Using these data files, we compared various independent and model-based, prostate cancer risk assessment approaches.

Results

Through the extraction and selection processes of SNP-prostate cancer risk associations, we collected 209 independent associations for increased risk of prostate cancer from the studied knowledge sources. Also, we gathered six cumulative models and two probabilistic models. Cumulative models and assessment of independent associations did not have impressive results. There was one of the probabilistic, model-based interpretation that was successful compared to the others. In envirobehavioral and clinical evaluations, we found that some of the comorbidities, especially, would be useful to evaluate disease risk. Even though we had a very limited dataset, a comparison of performances of different disease models and their implementation with real data as use case scenarios helped us to gain deeper insight into the proposed architecture.

Conclusions

In order to benefit from genomic variation data, existing EHR/EMR systems must be constructed with the capability of tracking and monitoring all aspects of personal health status (genomic, clinical, environmental, etc) in 24/7 situations, and also with the capability of suggesting evidence-based recommendations. A national-level, accredited knowledge base is a top requirement for improved end-user systems interpreting these parameters. Finally, categorization using similar, individual characteristics (SNP patterns, exposure history, etc) may be an effective way to predict disease risks, but this approach needs to be concretized and supported with new studies.