Search

BACKGROUND: Systemic inflammation is associated with survival outcomes in colon cancer. However, it is not well-known which systemic inflammatory marker is a powerful prognostic marker in patients with colon cancer. METHODS: A total of 4535 colon cancer patients were included in this study. We developed a novel prognostic index using a robust combination of seven systemic inflammation-associated blood features of the discovery set. The predictability and generality of the novel prognostic index were evaluated in the discovery, validation and replication sets. RESULTS: Among all combinations, the combination of albumin and monocyte count was the best candidate expression. The final formula of the proposed novel index is named the Prognostic Immune and Nutritional Index (PINI). The concordance index of PINI for overall and progression-free survival was the highest in the discovery, validation and replication sets compared to existing prognostic inflammatory markers. PINI was found to be a significant independent prognostic factor for both overall and progression-free survival. CONCLUSIONS: PINI is a novel prognostic index that has improved discriminatory power in colon cancer patients and appears to be superior to existing prognostic inflammatory markers. PINI can be utilised for decision-making regarding personalised treatment as the complement of the TNM staging system.

Motivation Understanding comorbidity is essential for disease prevention, treatment and prognosis. In particular, insight into which pairs of diseases are likely or unlikely to co-occur may help elucidate the potential relationships between complex diseases. Here, we introduce the use of an inter-disease interactivity network to discover/prioritize comorbidities. Specifically, we determine disease associations by accounting for the direction of effects of genetic components shared between diseases, and categorize those associations as synergistic or antagonistic. We further develop a comorbidity scoring algorithm to predict whether diseases are more or less likely to co-occur in the presence of a given index disease. This algorithm can handle networks that incorporate relationships with opposite signs. Results We finally investigate inter-disease associations among 427 phenotypes in UK Biobank PheWAS data and predict the priority of comorbid diseases. The predicted comorbidities were verified using the UK Biobank inpatient electronic health records. Our findings demonstrate that considering the interaction of phenotype associations might be helpful in better predicting comorbidity. Availability and implementation The source code and data of this study are available at https://github.com/dokyoonkimlab/DiseaseInteractiveNetwork. Supplementary information Supplementary data are available at Bioinformatics online.

BackgroundDisease complications, the onset of secondary phenotypes given a primary condition, can exacerbate the long-term severity of outcomes. However, the exact cause of many of these cross-phenotype associations is still unknown. One potential reason is shared genetic etiology—common genetic drivers may lead to the onset of multiple phenotypes. Disease-disease networks (DDNs), where nodes represent diseases and edges represent associations between diseases, can provide an intuitive way of understanding the relationships between phenotypes. Using summary statistics from a phenome-wide association study (PheWAS), we can generate a corresponding DDN where edges represent shared genetic variants between diseases. Such a network can help us analyze genetic associations across the diseasome, the landscape of all human diseases, and identify potential genetic influences for disease complications.ResultsTo improve the ease of network-based analysis of shared genetic components across phenotypes, we developed the humaN disEase phenoType MAp GEnerator (NETMAGE), a web-based tool that produces interactive DDN visualizations from PheWAS summary statistics. Users can search the map by various attributes and select nodes to view related phenotypes, associated variants, and various network statistics. As a test case, we used NETMAGE to construct a network from UK BioBank (UKBB) PheWAS summary statistic data. Our map correctly displayed previously identified disease comorbidities from the UKBB and identified concentrations of hub diseases in the endocrine/metabolic and circulatory disease categories. By examining the associations between phenotypes in our map, we can identify potential genetic explanations for the relationships between diseases and better understand the underlying architecture of the human diseasome. Our tool thus provides researchers with a means to identify prospective genetic targets for drug design, using network medicine to contribute to the exploration of personalized medicine.

Background: Recent studies have found that women with obstetric disorders are at increased risk for a variety of long-term complications. However, the underlying pathophysiology of these connections remains undetermined. A network-based view incorporating knowledge of other diseases and genetic associations will aid our understanding of the role of genetics in pregnancy-related disease complications. Methods: We built a disease–disease network (DDN) using UK Biobank (UKBB) summary data from a phenome-wide association study (PheWAS) to elaborate multiple disease associations. We also constructed egocentric DDNs, where each network focuses on a pregnancy-related disorder and its neighboring diseases. We then applied graph-based semi-supervised learning (GSSL) to translate the connections in the egocentric DDNs to pathologic knowledge. Results: A total of 26 egocentric DDNs were constructed for each pregnancy-related phenotype in the UKBB. Applying GSSL to each DDN, we obtained complication risk scores for additional phenotypes given the pregnancy-related disease of interest. Predictions were validated using co-occurrences derived from UKBB electronic health records. Our proposed method achieved an increase in average area under the receiver operating characteristic curve (AUC) by a factor of 1.35 from 55.0% to 74.4% compared to the use of the full DDN. Conclusion: Egocentric DDNs hold promise as a clinical tool for the network-based identification of potential disease complications for a variety of phenotypes.

The polygenic risk score (PRS) can help to identify individuals’ genetic susceptibility for various diseases by combining patient genetic profiles and identified single-nucleotide polymorphisms (SNPs) from genome-wide association studies. Although multiple diseases will usually afflict patients at once or in succession, conventional PRSs fail to consider genetic relationships across multiple diseases. Even multi-trait PRSs, which take into account genetic effects for more than one disease at a time, fail to consider a sufficient number of phenotypes to accurately reflect the state of disease comorbidity in a patient, or are biased in terms of the traits that are selected. Thus, we developed novel network-based comorbidity risk scores to quantify associations among multiple phenotypes from phenome-wide association studies (PheWAS). We first constructed a disease-SNP heterogeneous multi-layered network (DS-Net), which consists of a disease network (disease-layer) and SNP network (SNP-layer). The disease-layer describes the population-level interactome from PheWAS data. The SNP-layer was constructed according to linkage disequilibrium. Both layers were attached to transform the information from a population-level interactome to individual-level inferences. Then, graph-based semi-supervised learning was applied to predict possible comorbidity scores on disease-layer for each subject. The SNP-layer serves as receiving individual genotyping data in the scoring process, and the disease-layer serves as the propagated output for an individual’s multiple disease comorbidity scores. The possible comorbidity scores were combined by logistic regression, and it is denoted as netCRS. The DS-Net was constructed from UK Biobank PheWAS data, and the individual genetic profiles were collected from the Penn Medicine Biobank. As a proof-of-concept study, myocardial infarction (MI) was selected to compare netCRS with the PRS with pruning and thresholding (PRS-PT). The combined model (netCRS + PRS-PT + covariates) achieved an AUC improvement of 6.26% compared to the (PRS-PT + covariates) model. In terms of risk stratification, the combined model was able to capture the risk of MI up to approximately eight-fold higher than that of the low-risk group. The netCRS and PRS-PT complement each other in predicting high-risk groups of patients with MI. We expect that using these risk prediction models will allow for the development of prevention strategies and reduction of MI morbidity and mortality.

Clinical guidelines recommend several risk factors to identify women in early pregnancy at high risk of developing pregnancy-associated hypertension. However, these variables result in low predictive accuracy. Here, we developed a prediction model for pregnancy-associated hypertension using graph-based semi-supervised learning. This is a secondary analysis of a prospective study of healthy pregnant women. To develop the prediction model, we compared the prediction performances across five machine learning methods (semi-supervised learning with both labeled and unlabeled data, semi-supervised learning with labeled data only, logistic regression, support vector machine, and random forest) using three different variable sets: [a] variables from clinical guidelines, [b] selected important variables from the feature selection, and [c] all routine variables. Additionally, the proposed prediction model was compared with placental growth factor, a predictive biomarker for pregnancy-associated hypertension. The study population consisted of 1404 women, including 1347 women with complete follow-up (labeled data) and 57 women with incomplete follow-up (unlabeled data). Among the 1347 with complete follow-up, 2.4% (33/1347) developed pregnancy-associated HTN. Graph-based semi-supervised learning using top 11 variables achieved the best average prediction performance (mean area under the curve (AUC) of 0.89 in training set and 0.81 in test set), with higher sensitivity (72.7% vs 45.5% in test set) and similar specificity (80.0% vs 80.5% in test set) compared to risk factors from clinical guidelines. In addition, our proposed model with graph-based SSL had a higher performance than that of placental growth factor for total study population (AUC, 0.71 vs. 0.80, p

Background The recent advances in human disease network have provided insights into establishing the relationships between the genotypes and phenotypes of diseases. In spite of the great progress, it yet remains as only a map of topologies between diseases, but not being able to be a pragmatic diagnostic/prognostic tool in medicine. It can further evolve from a map to a translational tool if it equips with a function of scoring that measures the likelihoods of the association between diseases. Then, a physician, when practicing on a patient, can suggest several diseases that are highly likely to co-occur with a primary disease according to the scores. In this study, we propose a method of implementing ‘n-of-1 utility’ (n potential diseases of one patient) to human disease network—the translational disease network. Results We first construct a disease network by introducing the notion of walk in graph theory to protein-protein interaction network, and then provide a scoring algorithm quantifying the likelihoods of disease co-occurrence given a primary disease. Metabolic diseases, that are highly prevalent but have found only a few associations in previous studies, are chosen as entries of the network. Conclusions The proposed method substantially increased connectivity between metabolic diseases and provided scores of co-occurring diseases. The increase in connectivity turned the disease network info-richer. The result lifted the AUC of random guessing up to 0.72 and appeared to be concordant with the existing literatures on disease comorbidity.

Background Drug repurposing has been motivated to ameliorate low probability of success in drug discovery. For the recent decade, many in silico attempts have received primary attention as a first step to alleviate the high cost and longevity. Such study has taken benefits of abundance, variety, and easy accessibility of pharmaceutical and biomedical data. Utilizing the research friendly environment, in this study, we propose a network-based machine learning algorithm for drug repurposing. Particularly, we show a framework on how to construct a drug network, and how to strengthen the network by employing multiple/heterogeneous types of data. Results The proposed method consists of three steps. First, we construct a drug network from drug-target protein information. Then, the drug network is reinforced by utilizing drug-drug interaction knowledge on bioactivity and/or medication from literature databases. Through the enhancement, the number of connected nodes and the number of edges between them become more abundant and informative, which can lead to a higher probability of success of in silico drug repurposing. The enhanced network recommends candidate drugs for repurposing through drug scoring. The scoring process utilizes graph-based semi-supervised learning to determine the priority of recommendations. Conclusions The drug network is reinforced in terms of the coverage and connections of drugs: the drug coverage increases from 4738 to 5442, and the drug-drug associations as well from 808,752 to 982,361. Along with the network enhancement, drug recommendation becomes more reliable: AUC of 0.89 was achieved lifted from 0.79. For typical cases, 11 recommended drugs were shown for vascular dementia: amantadine, conotoxin GV, tenocyclidine, cycloeucine, etc. Electronic supplementary material The online version of this article (10.1186/s12859-019-2858-6) contains supplementary material, which is available to authorized users.

Summary Immune diseases have a strong genetic component with Mendelian patterns of inheritance. While the tight association has been a major understanding in the underlying pathophysiology for the category of immune diseases, the common features of these diseases remain unclear. Based on the potential commonality among immune genes, we design Gene Ranker for key gene identification. Gene Ranker is a network-based gene scoring algorithm that initially constructs a backbone network based on protein interactions. Patient gene expression networks are added into the network. An add-on process screens the networks of weighted gene co-expression network analysis (WGCNA) on the samples of immune patients. Gene Ranker is disease-specific; however, any WGCNA network that passes the screening procedure can be added on. With the constructed network, it employs the semi-supervised learning for gene scoring. Results The proposed method was applied to immune diseases. Based on the resulting scores, Gene Ranker identified potential key genes in immune diseases. In scoring validation, an average area under the receiver operating characteristic curve of 0.82 was achieved, which is a significant increase from the reference average of 0.76. Highly ranked genes were verified through retrieval and review of 27 million PubMed literatures. As a typical case, 20 potential key genes in rheumatoid arthritis were identified: 10 were de facto genes and the remaining were novel. Availability and Implementation Gene Ranker is available at http://www.alphaminers.net/GeneRanker/ Supplementary information Supplementary data are available at Bioinformatics online.

Silicon materials have been widely used as thermo-sensing layers in infrared detectors or uncooled micro-bolometers. Parameters such as a large thermal coefficient of resistance (TCR), low sheet resistance (Rs), and low 1/f noise are important for high performance of these devices. However, there is always a trade-off between these parameters. For example, the crystalline silicon materials typically exhibit low Rs and 1/f noise, and significantly low TCR, while the amorphous silicon materials generally have large TCR, and considerably high Rs and 1/f noise. Consequently, the best trade-off can be achieved by using a mixed-phase structure of silicon materials, i.e. an intermediate form between the crystalline and amorphous structures. Herein we report the important characteristics of hydrogenated mixed-phase silicon films, deposited by the plasma-enhanced chemical vapour deposition process, for infrared detectors. The films in the mixed-phase structure showed high TCR values in the range of 2–3% K–1 and moderate sheet resistances in range of 10–40 MΩ sq−1. These results indicate that the mixed-phase silicon films are potential alternatives to conventional boron doped hydrogenated amorphous and microcrystalline silicon films for use as thermo-sensing layers in infrared detectors.

Background Hearing Aids amplify sounds at certain frequencies to help patients, who have hearing loss, to improve the quality of life. Variables affecting hearing improvement include the characteristics of the patients’ hearing loss, the characteristics of the hearing aids, and the characteristics of the frequencies. Although the two former characteristics have been studied, there are only limited studies predicting hearing gain, after wearing Hearing Aids, with utilizing all three characteristics. Therefore, we propose a new machine learning algorithm that can present the degree of hearing improvement expected from the wearing of hearing aids. Methods The proposed algorithm consists of cascade structure, recurrent structure and deep network structure. For cascade structure, it reflects correlations between frequency bands. For recurrent structure, output variables in one particular network of frequency bands are reused as input variables for other networks. Furthermore, it is of deep network structure with many hidden layers. We denote such networks as cascade recurring deep network where training consists of two phases; cascade phase and tuning phase. Results When applied to medical records of 2,182 patients treated for hearing loss, the proposed algorithm reduced the error rate by 58% from the other neural networks. Conclusions The proposed algorithm is a novel algorithm that can be utilized for signal or sequential data. Clinically, the proposed algorithm can serve as a medical assistance tool that fulfill the patients’ satisfaction.

Figure S1. A snapshot of the enhanced network with 150 drugs: the solid lines represent original connections with information on shared target protein, and the dotted lines represent newly connected edges using CLASH. Red circles represent orphan drugs but linked to the network by the proposed method. (PDF 751 kb)

Additional file 2. The matlab source code for disease network construction from PPI network.

Background Biological system is a multi-layered structure of omics with genome, epigenome, transcriptome, metabolome, proteome, etc., and can be further stretched to clinical/medical layers such as diseasome, drugs, and symptoms. One advantage of omics is that we can figure out an unknown component or its trait by inferring from known omics components. The component can be inferred by the ones in the same level of omics or the ones in different levels. Methods To implement the inference process, an algorithm that can be applied to the multi-layered complex system is required. In this study, we develop a semi-supervised learning algorithm that can be applied to the multi-layered complex system. In order to verify the validity of the inference, it was applied to the prediction problem of disease co-occurrence with a two-layered network composed of symptom-layer and disease-layer. Results The symptom-disease layered network obtained a fairly high value of AUC, 0.74, which is regarded as noticeable improvement when comparing 0.59 AUC of single-layered disease network. If further stretched to whole layered structure of omics, the proposed method is expected to produce more promising results. Conclusion This research has novelty in that it is a new integrative algorithm that incorporates the vertical structure of omics data, on contrary to other existing methods that integrate the data in parallel fashion. The results can provide enhanced guideline for disease co-occurrence prediction, thereby serve as a valuable tool for inference process of multi-layered biological system.

Background The study on disease-disease association has been increasingly viewed and analyzed as a network, in which the connections between diseases are configured using the source information on interactome maps of biomolecules such as genes, proteins, metabolites, etc. Although abundance in source information leads to tighter connections between diseases in the network, for a certain group of diseases, such as metabolic diseases, the connections do not occur much due to insufficient source information; a large proportion of their associated genes are still unknown. One way to circumvent the difficulties in the lack of source information is to integrate available external information by using one of up-to-date integration or fusion methods. However, if one wants a disease network placing huge emphasis on the original source of data but still utilizing external sources only to complement it, integration may not be pertinent. Interpretation on the integrated network would be ambiguous: meanings conferred on edges would be vague due to fused information. Methods In this study, we propose a network based algorithm that complements the original network by utilizing external information while preserving the network’s originality. The proposed algorithm links the disconnected node to the disease network by using complementary information from external data source through four steps: anchoring, connecting, scoring, and stopping. Results When applied to the network of metabolic diseases that is sourced from protein-protein interaction data, the proposed algorithm recovered connections by 97%, and improved the AUC performance up to 0.71 (lifted from 0.55) by using the external information outsourced from text mining results on PubMed comorbidity literatures. Experimental results also show that the proposed algorithm is robust to noisy external information. Conclusion This research has novelty in which the proposed algorithm preserves the network’s originality, but at the same time, complements it by utilizing external information. Furthermore it can be utilized for original association recovery and novel association discovery for disease network.

Background In cancer prognosis research, diverse machine learning models have applied to the problems of cancer susceptibility (risk assessment), cancer recurrence (redevelopment of cancer after resolution), and cancer survivability, regarding an accuracy (or an AUC--the area under the ROC curve) as a primary measurement for the performance evaluation of the models. However, in order to help medical specialists to establish a treatment plan by using the predicted output of a model, it is more pragmatic to elucidate which variables (markers) have most significantly influenced to the resulting outcome of cancer or which patients show similar patterns. Methods In this study, a coupling approach of two sub-modules--a predictor and a descriptor--is proposed. The predictor module generates the predicted output for the cancer outcome. Semi-supervised learning co-training algorithm is employed as a predictor. On the other hand, the descriptor module post-processes the results of the predictor module, mainly focusing on which variables are more highly or less significantly ranked when describing the results of the prediction, and how patients are segmented into several groups according to the trait of common patterns among them. Decision trees are used as a descriptor. Results The proposed approach, 'predictor-descriptor,' was tested on the breast cancer survivability problem based on the surveillance, epidemiology, and end results database for breast cancer (SEER). The results present the performance comparison among the established machine leaning algorithms, the ranks of the prognosis elements for breast cancer, and patient segmentation. In the performance comparison among the predictor candidates, Semi-supervised learning co-training algorithm showed best performance, producing an average AUC of 0.81. Later, the descriptor module found the top-tier prognosis markers which significantly affect to the classification results on survived/dead patients: 'lymph node involvement', 'stage', 'site-specific surgery', 'number of positive node examined', and 'tumor size', etc. Also, a typical example of patient-segmentation was provided: the patients classified as dead were grouped into two segments depending on difference in prognostic profiles, ones with serious results with respect to the pathologic exams and the others with the feebleness of age.