Mining Relationships among Multiple Entities in Biological Networks

DRACP: a novel method for identification of anticancer peptides

Background

Millions of people are suffering from cancers, but accurate early diagnosis and effective treatment are still tough for all doctors. Common ways against cancer include surgical operation, radiotherapy and chemotherapy. However, they are all very harmful for patients. Recently, the anticancer peptides (ACPs) have been discovered to be a potential way to treat cancer. Since ACPs are natural biologics, they are safer than other methods. However, the experimental technology is an expensive way to find ACPs so we purpose a new machine learning method to identify the ACPs.

Results

Firstly, we extracted the feature of ACPs in two aspects: sequence and chemical characteristics of amino acids. For sequence, average 20 amino acids composition was extracted. For chemical characteristics, we classified amino acids into six groups based on the patterns of hydrophobic and hydrophilic residues. Then, deep belief network has been used to encode the features of ACPs. Finally, we purposed Random Relevance Vector Machines to identify the true ACPs. We call this method ‘DRACP’ and tested the performance of it on two independent datasets. Its AUC and AUPR are higher than 0.9 in both datasets.

Conclusion

We developed a novel method named ‘DRACP’ and compared it with some traditional methods. The cross-validation results showed its effectiveness in identifying ACPs.

An Information Gain-based Method for Evaluating the Classification Power of Features Towards Identifying Enhancers

Background:

Enhancers are cis-regulatory elements that enhance gene expression on DNA sequences. Since most of enhancers are located far from transcription start sites, it is difficult to identify them. As other regulatory elements, the regions around enhancers contain a variety of features, which can help in enhancer recognition.

Objective:

The classification power of features differs significantly, the performances of existing methods that use one or a few features for identifying enhancer vary greatly. Therefore, evaluating the classification power of each feature can improve the predictive performance of enhancers.

Methods:

We present an evaluation method based on Information Gain (IG) that captures the entropy change of enhancer recognition according to features. To validate the performance of our method, experiments using the Single Feature Prediction Accuracy (SFPA) were conducted on each feature.

Results:

The average IG values of the sequence feature, transcriptional feature and epigenetic feature are 0.068, 0.213, and 0.299, respectively. Through SFPA, the average AUC values of the sequence feature, transcriptional feature and epigenetic feature are 0.534, 0.605, and 0.647, respectively. The verification results are consistent with our evaluation results.

Conclusion:

This IG-based method can effectively evaluate the classification power of features for identifying enhancers. Compared with sequence features, epigenetic features are more effective for recognizing enhancers.

A Mendelian Randomization Study on Infant Length and Type 2 Diabetes Mellitus Risk

OBJECTIVE

Infant length (IL) is a positively associated phenotype of type 2 diabetes mellitus (T2DM), but the causal relationship of which is still unclear. Here, we applied a Mendelian randomization (MR) study to explore the causal relationship between IL and T2DM, which has the potential to provide guidance for assessing T2DM activity and T2DM- prevention in young at-risk populations.

MATERIALS AND METHODS

To classify the study, a two-sample MR, using genetic instrumental variables (IVs) to explore the causal effect was applied to test the influence of IL on the risk of T2DM. In this study, MR was carried out on GWAS data using 8 independent IL SNPs as IVs. The pooled odds ratio (OR) of these SNPs was calculated by the inverse-variance weighted method for the assessment of the risk the shorter IL brings to T2DM. Sensitivity validation was conducted to identify the effect of individual SNPs. MR-Egger regression was used to detect pleiotropic bias of IVs.

RESULTS

The pooled odds ratio from the IVW method was 1.03 (95% CI 0.89-1.18, P = 0.0785), low intercept was -0.477, P = 0.252, and small fluctuation of ORs ranged from -0.062 ((0.966 - 1.03) / 1.03) to 0.05 ((1.081 - 1.03) / 1.03) in leave-one-out validation.

CONCLUSION

We validated that the shorter IL causes no additional risk to T2DM. The sensitivity analysis and the MR-Egger regression analysis also provided adequate evidence that the above result was not due to any heterogeneity or pleiotropic effect of IVs.

Deep Reinforcement Learning for Data Association in Cell Tracking

Accurate target detection and association are vital for the development of reliable target tracking, especially for cell tracking based on microscopy images due to the similarity of cells. We propose a deep reinforcement learning method to associate the detected targets between frames. According to the dynamic model of each target, the cost matrix is produced by conjointly considering various features of targets and then used as the input of a neural network. The proposed neural network is trained using reinforcement learning to predict a distribution over the association solution. Furthermore, we design a residual convolutional neural network that results in more efficient learning. We validate our method on two applications: the multiple target tracking simulation and the ISBI cell tracking. The results demonstrate that our approach based on reinforcement learning techniques could effectively track targets following different motion patterns and show competitive results.

Acceptance Prediction for Answers on Online Health-care Community

BACKGROUND

With the development of e-Health, it plays a more and more important role in predicting whether a doctor's answer can be accepted by a patient through online healthcare community. Unlike the previous work which focus mainly on the numerical feature, in our framework, we combine both numerical and textual information to predict the acceptance of answers. The textual information is composed of questions posted by the patients and answers posted by the doctors. To extract the textual features from them, we first trained a sentence encoder to encode a pair of question and answer into a co-dependent representation on a held-out dataset. After that,we can use it to predict the acceptance of answers by doctors.

RESULTS

Our experimental results on the real-world dataset demonstrate that by applying our model additional features from text can be extracted and the prediction can be more accurate. That's to say, the model which take both textual features and numerical features as input performs significantly better than model which takes numerical features only on all the four metrics (Accuracy, AUC, F1-score and Recall).

CONCLUSIONS

This work proposes a generic framework combining numerical features and textual features for acceptance prediction, where textual features are extracted from text based on deep learning methods firstly and can be used to achieve a better prediction results.

TS-GOEA: a web tool for tissue-specific gene set enrichment analysis based on gene ontology

BACKGROUND

The Gene Ontology (GO) knowledgebase is the world's largest source of information on the functions of genes. Since the beginning of GO project, various tools have been developed to perform GO enrichment analysis experiments. GO enrichment analysis has become a commonly used method of gene function analysis. Existing GO enrichment analysis tools do not consider tissue-specific information, although this information is very important to current research.

RESULTS

In this paper, we built an easy-to-use web tool called TS-GOEA that allows users to easily perform experiments based on tissue-specific GO enrichment analysis. TS-GOEA uses strict threshold statistical method for GO enrichment analysis, and provides statistical tests to improve the reliability of the analysis results. Meanwhile, TS-GOEA provides tools to compare different experimental results, which is convenient for users to compare the experimental results. To evaluate its performance, we tested the genes associated with platelet disease with TS-GOEA.

CONCLUSIONS

TS-GOEA is an effective GO analysis tool with unique features. The experimental results show that our method has better performance and provides a useful supplement for the existing GO enrichment analysis tools. TS-GOEA is available at http://120.77.47.2:5678.

Attention-based recurrent neural network for influenza epidemic prediction

BACKGROUND

Influenza is an infectious respiratory disease that can cause serious public health hazard. Due to its huge threat to the society, precise real-time forecasting of influenza outbreaks is of great value to our public.

RESULTS

In this paper, we propose a new deep neural network structure that forecasts a real-time influenza-like illness rate (ILI%) in Guangzhou, China. Long short-term memory (LSTM) neural networks is applied to precisely forecast accurateness due to the long-term attribute and diversity of influenza epidemic data. We devise a multi-channel LSTM neural network that can draw multiple information from different types of inputs. We also add attention mechanism to improve forecasting accuracy. By using this structure, we are able to deal with relationships between multiple inputs more appropriately. Our model fully consider the information in the data set, targetedly solving practical problems of the Guangzhou influenza epidemic forecasting.

CONCLUSION

We assess the performance of our model by comparing it with different neural network structures and other state-of-the-art methods. The experimental results indicate that our model has strong competitiveness and can provide effective real-time influenza epidemic forecasting.

Prioritizing candidate diseases-related metabolites based on literature and functional similarity

Background

As the terminal products of cellular regulatory process, functional related metabolites have a close relationship with complex diseases, and are often associated with the same or similar diseases. Therefore, identification of disease related metabolites play a critical role in understanding comprehensively pathogenesis of disease, aiming at improving the clinical medicine. Considering that a large number of metabolic markers of diseases need to be explored, we propose a computational model to identify potential disease-related metabolites based on functional relationships and scores of referred literatures between metabolites. First, obtaining associations between metabolites and diseases from the Human Metabolome database, we calculate the similarities of metabolites based on modified recommendation strategy of collaborative filtering utilizing the similarities between diseases. Next, a disease-associated metabolite network (DMN) is built with similarities between metabolites as weight. To improve the ability of identifying disease-related metabolites, we introduce scores of text mining from the existing database of chemicals and proteins into DMN and build a new disease-associated metabolite network (FLDMN) by fusing functional associations and scores of literatures. Finally, we utilize random walking with restart (RWR) in this network to predict candidate metabolites related to diseases.

Results

We construct the disease-associated metabolite network and its improved network (FLDMN) with 245 diseases, 587 metabolites and 28,715 disease-metabolite associations. Subsequently, we extract training sets and testing sets from two different versions of the Human Metabolome database and assess the performance of DMN and FLDMN on 19 diseases, respectively. As a result, the average AUC (area under the receiver operating characteristic curve) of DMN is 64.35%. As a further improved network, FLDMN is proven to be successful in predicting potential metabolic signatures for 19 diseases with an average AUC value of 76.03%.

Conclusion

In this paper, a computational model is proposed for exploring metabolite-disease pairs and has good performance in predicting potential metabolites related to diseases through adequate validation. This result suggests that integrating literature and functional associations can be an effective way to construct disease associated metabolite network for prioritizing candidate diseases-related metabolites.

Identifying Alzheimer’s Disease-related miRNA Based on Semi-clustering

Background:

More and more scholars are trying to use it as a specific biomarker for Alzheimer’s Disease (AD) and mild cognitive impairment (MCI). Multiple studies have indicated that miRNAs are associated with poor axonal growth and loss of synaptic structures, both of which are early events in AD. The overall loss of miRNA may be associated with aging, increasing the incidence of AD, and may also be involved in the disease through some specific molecular mechanisms.

Objective:

Identifying Alzheimer’s disease-related miRNA can help us find new drug targets, early diagnosis.

Materials and Methods:

We used genes as a bridge to connect AD and miRNAs. Firstly, proteinprotein interaction network is used to find more AD-related genes by known AD-related genes. Then, each miRNA’s correlation with these genes is obtained by miRNA-gene interaction. Finally, each miRNA could get a feature vector representing its correlation with AD. Unlike other studies, we do not generate negative samples randomly with using classification method to identify AD-related miRNAs. Here we use a semi-clustering method ‘one-class SVM’. AD-related miRNAs are considered as outliers and our aim is to identify the miRNAs that are similar to known AD-related miRNAs (outliers).

Results and Conclusion:

We identified 257 novel AD-related miRNAs and compare our method with SVM which is applied by generating negative samples. The AUC of our method is much higher than SVM and we did case studies to prove that our results are reliable.

Prediction of Disease Comorbidity Using HeteSim Scores based on Multiple Heterogeneous Networks

Background:

Accumulating experimental studies have indicated that disease comorbidity causes additional pain to patients and leads to the failure of standard treatments compared to patients who have a single disease. Therefore, accurate prediction of potential comorbidity is essential to design more efficient treatment strategies. However, only a few disease comorbidities have been discovered in the clinic.

Objective:

In this work, we propose PCHS, an effective computational method for predicting disease comorbidity.

Materials and Methods:

We utilized the HeteSim measure to calculate the relatedness score for different disease pairs in the global heterogeneous network, which integrates six networks based on biological information, including disease-disease associations, drug-drug interactions, protein-protein interactions and associations among them. We built the prediction model using the Support Vector Machine (SVM) based on the HeteSim scores.

Results and Conclusion:

The results showed that PCHS performed significantly better than previous state-of-the-art approaches and achieved an AUC score of 0.90 in 10-fold cross-validation. Furthermore, some of our predictions have been verified in literatures, indicating the effectiveness of our method.