Predicting metabolic pathways of small molecules and enzymes based on interaction information of chemicals and proteins

Gtie-Rt: A comprehensive graph learning model for predicting drugs targeting metabolic pathways in human

Drugs often target specific metabolic pathways to produce a therapeutic effect. However, these pathways are complex and interconnected, making it challenging to predict a drug's potential effects on an organism's overall metabolism. The mapping of drugs with targeting metabolic pathways in the organisms can provide a more complete understanding of the metabolic effects of a drug and help to identify potential drug-drug interactions. In this study, we proposed a machine learning hybrid model Graph Transformer Integrated Encoder (GTIE-RT) for mapping drugs to target metabolic pathways in human. The proposed model is a composite of a Graph Convolution Network (GCN) and transformer encoder for graph embedding and attention mechanism. The output of the transformer encoder is then fed into the Extremely Randomized Trees Classifier to predict target metabolic pathways. The evaluation of the GTIE-RT on drugs dataset demonstrates excellent performance metrics, including accuracy (>95%), recall (>92%), precision (>93%) and F1-score (>92%). Compared to other variants and machine learning methods, GTIE-RT consistently shows more reliable results.

A Novel Multi-Scale Graph Neural Network for Metabolic Pathway Prediction

Predicting the metabolic pathway classes of compounds in the human body is an important problem in drug research and development. For this purpose, we propose a Multi-Scale Graph Neural Network framework, named MSGNN. The framework includes a subgraph encoder, a feature encoder and a global feature processor, and a graph augmentation strategy is adopted. The subgraph encoder is responsible for extracting the local structural features of the compound, the feature encoder learns the characteristics of the atoms, and the global feature processor processes the information from the pre-training model and the two molecular fingerprints, while the graph augmentation strategy is to expand the train set through a scientific and reasonable method. The experiment result illustrates that the accuracy, precision, recall and F1 metrics of MSGNN reach 98.17%, 94.18%, 94.43% and 94.30%, respectively, which is superior to the similar models we have known. In addition, the ablation experiment demonstrates the indispensability of MSGNN modules.

MVML-MPI: Multi-View Multi-Label Learning for Metabolic Pathway Inference

Development of robust and effective strategies for synthesizing new compounds, drug targeting and constructing GEnome-scale Metabolic models (GEMs) requires a deep understanding of the underlying biological processes. A critical step in achieving this goal is accurately identifying the categories of pathways in which a compound participated. However, current machine learning-based methods often overlook the multifaceted nature of compounds, resulting in inaccurate pathway predictions. Therefore, we present a novel framework on Multi-View Multi-Label Learning for Metabolic Pathway Inference, hereby named MVML-MPI. First, MVML-MPI learns the distinct compound representations in parallel with corresponding compound encoders to fully extract features. Subsequently, we propose an attention-based mechanism that offers a fusion module to complement these multi-view representations. As a result, MVML-MPI accurately represents and effectively captures the complex relationship between compounds and metabolic pathways and distinguishes itself from current machine learning-based methods. In experiments conducted on the Kyoto Encyclopedia of Genes and Genomes pathways dataset, MVML-MPI outperformed state-of-the-art methods, demonstrating the superiority of MVML-MPI and its potential to utilize the field of metabolic pathway design, which can aid in optimizing drug-like compounds and facilitating the development of GEMs. The code and data underlying this article are freely available at https://github.com/guofei-tju/MVML-MPI. Contact:  jtang@cse.sc.edu, guofei@csu.edu.com or wuxi_dyj@csj.uestc.edu.cn.

Prediction of plant secondary metabolic pathways using deep transfer learning

BACKGROUND

Plant secondary metabolites are highly valued for their applications in pharmaceuticals, nutrition, flavors, and aesthetics. It is of great importance to elucidate plant secondary metabolic pathways due to their crucial roles in biological processes during plant growth and development. However, understanding plant biosynthesis and degradation pathways remains a challenge due to the lack of sufficient information in current databases. To address this issue, we proposed a transfer learning approach using a pre-trained hybrid deep learning architecture that combines Graph Transformer and convolutional neural network (GTC) to predict plant metabolic pathways.

RESULTS

GTC provides comprehensive molecular representation by extracting both structural features from the molecular graph and textual information from the SMILES string. GTC is pre-trained on the KEGG datasets to acquire general features, followed by fine-tuning on plant-derived datasets. Four metrics were chosen for model performance evaluation. The results show that GTC outperforms six other models, including three previously reported machine learning models, on the KEGG dataset. GTC yields an accuracy of 96.75%, precision of 85.14%, recall of 83.03%, and F1_score of 84.06%. Furthermore, an ablation study confirms the indispensability of all the components of the hybrid GTC model. Transfer learning is then employed to leverage the shared knowledge acquired from the KEGG metabolic pathways. As a result, the transferred GTC exhibits outstanding accuracy in predicting plant secondary metabolic pathways with an average accuracy of 98.30% in fivefold cross-validation and 97.82% on the final test. In addition, GTC is employed to classify natural products. It achieves a perfect accuracy score of 100.00% for alkaloids, while the lowest accuracy score of 98.42% for shikimates and phenylpropanoids.

CONCLUSIONS

The proposed GTC effectively captures molecular features, and achieves high performance in classifying KEGG metabolic pathways and predicting plant secondary metabolic pathways via transfer learning. Furthermore, GTC demonstrates its generalization ability by accurately classifying natural products. A user-friendly executable program has been developed, which only requires the input of the SMILES string of the query compound in a graphical interface.

Recent progress in the development of small-molecule double-locked logic gate fluorescence probes

Various bioactive substances are simultaneously involved in physiological processes, and research on the synergistic effect of them can promote the study of pathological mechanisms. To achieve this purpose, several small-molecule double-locked logic gate fluorescence probes have been developed recently. They overcome many shortcomings of the traditional "single-signal" fluorescent probes, with fluorescence that can be activated by two analytes of interest order-independently or order-dependently with one output. In this review, we summarize recently published small-molecule double-locked logic gate probes for the optical detection of two bioactive substances in living systems. We envision that this review will attract significant attention from researchers to exploit more powerful functional double-locked logic gate probes.

Predicting protein network topology clusters from chemical structure using deep learning

Comparing chemical structures to infer protein targets and functions is a common approach, but basing comparisons on chemical similarity alone can be misleading. Here we present a methodology for predicting target protein clusters using deep neural networks. The model is trained on clusters of compounds based on similarities calculated from combined compound-protein and protein-protein interaction data using a network topology approach. We compare several deep learning architectures including both convolutional and recurrent neural networks. The best performing method, the recurrent neural network architecture MolPMoFiT, achieved an F1 score approaching 0.9 on a held-out test set of 8907 compounds. In addition, in-depth analysis on a set of eleven well-studied chemical compounds with known functions showed that predictions were justifiable for all but one of the chemicals. Four of the compounds, similar in their molecular structure but with dissimilarities in their function, revealed advantages of our method compared to using chemical similarity.

MLGL-MP: a Multi-Label Graph Learning framework enhanced by pathway interdependence for Metabolic Pathway prediction

Motivation

During lead compound optimization, it is crucial to identify pathways where a drug-like compound is metabolized. Recently, machine learning-based methods have achieved inspiring progress to predict potential metabolic pathways for drug-like compounds. However, they neglect the knowledge that metabolic pathways are dependent on each other. Moreover, they are inadequate to elucidate why compounds participate in specific pathways.

Results

To address these issues, we propose a novel Multi-Label Graph Learning framework of Metabolic Pathway prediction boosted by pathway interdependence, called MLGL-MP, which contains a compound encoder, a pathway encoder and a multi-label predictor. The compound encoder learns compound embedding representations by graph neural networks. After constructing a pathway dependence graph by re-trained word embeddings and pathway co-occurrences, the pathway encoder learns pathway embeddings by graph convolutional networks. Moreover, after adapting the compound embedding space into the pathway embedding space, the multi-label predictor measures the proximity of two spaces to discriminate which pathways a compound participates in. The comparison with state-of-the-art methods on KEGG pathways demonstrates the superiority of our MLGL-MP. Also, the ablation studies reveal how its three components contribute to the model, including the pathway dependence, the adapter between compound embeddings and pathway embeddings, as well as the pre-training strategy. Furthermore, a case study illustrates the interpretability of MLGL-MP by indicating crucial substructures in a compound, which are significantly associated with the attending metabolic pathways. It is anticipated that this work can boost metabolic pathway predictions in drug discovery.

Availability and implementation

The code and data underlying this article are freely available at https://github.com/dubingxue/MLGL-MP.

Optimising the use of gene expression data to predict plant metabolic pathway memberships

Plant metabolites from diverse pathways are important for plant survival, human nutrition and medicine. The pathway memberships of most plant enzyme genes are unknown. While co-expression is useful for assigning genes to pathways, expression correlation may exist only under specific spatiotemporal and conditional contexts. Utilising > 600 tomato (Solanum lycopersicum) expression data combinations, three strategies for predicting memberships in 85 pathways were explored. Optimal predictions for different pathways require distinct data combinations indicative of pathway functions. Naive prediction (i.e. identifying pathways with the most similarly expressed genes) is error prone. In 52 pathways, unsupervised learning performed better than supervised approaches, possibly due to limited training data availability. Using gene-to-pathway expression similarities led to prediction models that outperformed those based simply on expression levels. Using 36 experimental validated genes, the pathway-best model prediction accuracy is 58.3%, significantly better compared with that for predicting annotated genes without experimental evidence (37.0%) or random guess (1.2%), demonstrating the importance of data quality. Our study highlights the need to extensively explore expression-based features and prediction strategies to maximise the accuracy of metabolic pathway membership assignment. The prediction framework outlined here can be applied to other species and serves as a baseline model for future comparisons.

Predicting biological pathways of chemical compounds with a profile-inspired approach

BACKGROUND

Assignment of chemical compounds to biological pathways is a crucial step to understand the relationship between the chemical repertory of an organism and its biology. Protein sequence profiles are very successful in capturing the main structural and functional features of a protein family, and can be used to assign new members to it based on matching of their sequences against these profiles. In this work, we extend this idea to chemical compounds, constructing a profile-inspired model for a set of related metabolites (those in the same biological pathway), based on a fragment-based vectorial representation of their chemical structures.

RESULTS

We use this representation to predict the biological pathway of a chemical compound with good overall accuracy (AUC 0.74-0.90 depending on the database tested), and analyzed some factors that affect performance. The approach, which is compared with equivalent methods, can in addition detect those molecular fragments characteristic of a pathway.

CONCLUSIONS

The method is available as a graphical interactive web server http://csbg.cnb.csic.es/iFragMent .

Identification of Carcinogenic Chemicals with Network Embedding and Deep Learning Methods

Background:

Cancer is the second leading cause of human death in the world. To date, many factors have been confirmed to be the cause of cancer. Among them, carcinogenic chemicals have been widely accepted as the important ones. Traditional methods for detecting carcinogenic chemicals are of low efficiency and high cost.

Objective:

The aim of this study was to design an efficient computational method for the identification of carcinogenic chemicals.

Methods:

A new computational model was proposed for detecting carcinogenic chemicals. As a data-driven model, carcinogenic and non-carcinogenic chemicals were obtained from Carcinogenic Potency Database (CPDB). These chemicals were represented by features extracted from five chemical networks, representing five types of chemical associations, via a network embedding method, Mashup. Obtained features were fed into a powerful deep learning method, recurrent neural network, to build the model.

Results:

The jackknife test on such model provided the F-measure of 0.971 and AUROC of 0.971.

Conclusion:

The proposed model was quite effective and was superior to the models with traditional machine learning algorithms, classic chemical encoding schemes or direct usage of chemical associations.

iMPTCE-Hnetwork: A Multilabel Classifier for Identifying Metabolic Pathway Types of Chemicals and Enzymes with a Heterogeneous Network

Metabolic pathway is an important type of biological pathways. It produces essential molecules and energies to maintain the life of living organisms. Each metabolic pathway consists of a chain of chemical reactions, which always need enzymes to participate in. Thus, chemicals and enzymes are two major components for each metabolic pathway. Although several metabolic pathways have been uncovered, the metabolic pathway system is still far from complete. Some hidden chemicals or enzymes are not discovered in a certain metabolic pathway. Besides the traditional experiments to detect hidden chemicals or enzymes, an alternative pipeline is to design efficient computational methods. In this study, we proposed a powerful multilabel classifier, called iMPTCE-Hnetwork, to uniformly assign chemicals and enzymes to metabolic pathway types reported in KEGG. Such classifier adopted the embedding features derived from a heterogeneous network, which defined chemicals and enzymes as nodes and the interactions between chemicals and enzymes as edges, through a powerful network embedding algorithm, Mashup. The popular RAndom k-labELsets (RAKEL) algorithm was employed to construct the classifier, which incorporated the support vector machine (polynomial kernel) as the basic classifier. The ten-fold cross-validation results indicated that such a classifier had good performance with accuracy higher than 0.800 and exact match higher than 0.750. Several comparisons were done to indicate the superiority of the iMPTCE-Hnetwork.

A deep learning architecture for metabolic pathway prediction

MOTIVATION

Understanding the mechanisms and structural mappings between molecules and pathway classes are critical for design of reaction predictors for synthesizing new molecules. This article studies the problem of prediction of classes of metabolic pathways (series of chemical reactions occurring within a cell) in which a given biochemical compound participates. We apply a hybrid machine learning approach consisting of graph convolutional networks used to extract molecular shape features as input to a random forest classifier. In contrast to previously applied machine learning methods for this problem, our framework automatically extracts relevant shape features directly from input SMILES representations, which are atom-bond specifications of chemical structures composing the molecules.

RESULTS

Our method is capable of correctly predicting the respective metabolic pathway class of 95.16% of tested compounds, whereas competing methods only achieve an accuracy of 84.92% or less. Furthermore, our framework extends to the task of classification of compounds having mixed membership in multiple pathway classes. Our prediction accuracy for this multi-label task is 97.61%. We analyze the relative importance of various global physicochemical features to the pathway class prediction problem and show that simple linear/logistic regression models can predict the values of these global features from the shape features extracted using our framework.

AVAILABILITY AND IMPLEMENTATION

https://github.com/baranwa2/MetabolicPathwayPrediction.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Relating Substructures and Side Effects of Drugs with Chemical-chemical Interactions

Background:

Drugs are very important for human life because they can provide treatment, cure, prevention, or diagnosis of different diseases. However, they also cause side effects, which can increase the risks for humans and pharmaceuticals companies. It is essential to identify drug side effects in drug discovery. To date, lots of computational methods have been proposed to predict the side effects of drugs and most of them used the fact that similar drugs always have similar side effects. However, previous studies did not analyze which substructures are highly related to which kind of side effect.

Method:

In this study, we conducted a computational investigation. In this regard, we extracted a drug set for each side effect, which consisted of drugs having the side effect. Also, for each substructure, a set was constructed by picking up drugs owing such substructure. The relationship between one side effect and one substructure was evaluated based on linkages between drugs in their corresponding drug sets, resulting in an Es value. Then, the statistical significance of Es value was measured by a permutation test.

Results and Conclusion:

A number of highly related pairs of side effects and substructures were obtained and some were extensively analyzed to confirm the reliability of the results reported in this study.

Drug Target Group Prediction with Multiple Drug Networks

Background:

Identification of drug-target interaction is essential in drug discovery. It is beneficial to predict unexpected therapeutic or adverse side effects of drugs. To date, several computational methods have been proposed to predict drug-target interactions because they are prompt and low-cost compared with traditional wet experiments.

Methods:

In this study, we investigated this problem in a different way. According to KEGG, drugs were classified into several groups based on their target proteins. A multi-label classification model was presented to assign drugs into correct target groups. To make full use of the known drug properties, five networks were constructed, each of which represented drug associations in one property. A powerful network embedding method, Mashup, was adopted to extract drug features from above-mentioned networks, based on which several machine learning algorithms, including RAndom k-labELsets (RAKEL) algorithm, Label Powerset (LP) algorithm and Support Vector Machine (SVM), were used to build the classification model.

Results and Conclusion:

Tenfold cross-validation yielded the accuracy of 0.839, exact match of 0.816 and hamming loss of 0.037, indicating good performance of the model. The contribution of each network was also analyzed. Furthermore, the network model with multiple networks was found to be superior to the one with a single network and classic model, indicating the superiority of the proposed model.

Prediction of Drug Side Effects with a Refined Negative Sample Selection Strategy

Drugs are an important way to treat various diseases. However, they inevitably produce side effects, bringing great risks to human bodies and pharmaceutical companies. How to predict the side effects of drugs has become one of the essential problems in drug research. Designing efficient computational methods is an alternative way. Some studies paired the drug and side effect as a sample, thereby modeling the problem as a binary classification problem. However, the selection of negative samples is a key problem in this case. In this study, a novel negative sample selection strategy was designed for accessing high-quality negative samples. Such strategy applied the random walk with restart (RWR) algorithm on a chemical-chemical interaction network to select pairs of drugs and side effects, such that drugs were less likely to have corresponding side effects, as negative samples. Through several tests with a fixed feature extraction scheme and different machine-learning algorithms, models with selected negative samples produced high performance. The best model even yielded nearly perfect performance. These models had much higher performance than those without such strategy or with another selection strategy. Furthermore, it is not necessary to consider the balance of positive and negative samples under such a strategy.

Inferring novel genes related to colorectal cancer via random walk with restart algorithm

Colorectal cancer (CRC) is the third most common type of cancer. In recent decades, genomic analysis has played an increasingly important role in understanding the molecular mechanisms of CRC. However, its pathogenesis has not been fully uncovered. Identification of genes related to CRC as complete as possible is an important way to investigate its pathogenesis. Therefore, we proposed a new computational method for the identification of novel CRC-associated genes. The proposed method is based on existing proven CRC-associated genes, human protein-protein interaction networks, and random walk with restart algorithm. The utility of the method is indicated by comparing it to the methods based on Guilt-by-association or shortest path algorithm. Using the proposed method, we successfully identified 298 novel CRC-associated genes. Previous studies have validated the involvement of the majority of these 298 novel genes in CRC-associated biological processes, thus suggesting the efficacy and accuracy of our method.

PathwayMap: Molecular Pathway Association with Self-Normalizing Neural Networks

Drug discovery suffers from high attrition because compounds initially deemed as promising can later show ineffectiveness or toxicity resulting from a poor understanding of their activity profile. In this work, we describe a deep self-normalizing neural network model for the prediction of molecular pathway association and evaluate its performance, showing an AUC ranging from 0.69 to 0.91 on a set of compounds extracted from ChEMBL and from 0.81 to 0.83 on an external data set provided by Novartis. We finally discuss the applicability of the proposed model in the domain of lead discovery. A usable application is available via PlayMolecule.org .

Use of Laplacian Heat Diffusion Algorithm to Infer Novel Genes With Functions Related to Uveitis

Uveitis is the inflammation of the uvea and is a serious eye disease that can cause blindness for middle-aged and young people. However, the pathogenesis of this disease has not been fully uncovered and thus renders difficulties in designing effective treatments. Completely identifying the genes related to this disease can help improve and accelerate the comprehension of uveitis. In this study, a new computational method was developed to infer potential related genes based on validated ones. We employed a large protein–protein interaction network reported in STRING, in which Laplacian heat diffusion algorithm was applied using validated genes as seed nodes. Except for the validated ones, all genes in the network were filtered by three tests, namely, permutation, association, and function tests, which evaluated the genes based on their specialties and associations to uveitis. Results indicated that 59 inferred genes were accessed, several of which were confirmed to be highly related to uveitis by literature review. In addition, the inferred genes were compared with those reported in a previous study, indicating that our reported genes are necessary supplements.

Non-small-cell lung cancer pathological subtype-related gene selection and bioinformatics analysis based on gene expression profiles

Lung cancer is one of the most common malignant diseases and a major threat to public health on a global scale. Non-small-cell lung cancer (NSCLC) has a higher degree of malignancy and a lower 5-year survival rate compared with that of small-cell lung cancer. NSCLC may be mainly divided into two pathological subtypes, adenocarcinoma and squamous cell carcinoma. The aim of the present study was to identify disease genes based on the gene expression profile and the shortest path analysis of weighted functional protein association networks with the existing protein-protein interaction data from the Search Tool for the Retrieval of Interacting Genes. The gene expression profile (GSE10245) was downloaded from the National Center for Biotechnology Information Gene Expression Omnibus database, including 40 lung adenocarcinoma and 18 lung squamous cell carcinoma tissues. A total of 8 disease genes were identified using Naïve Bayesian Classifier based on the Maximum Relevance Minimum Redundancy feature selection method following preprocessing. An additional 21 candidate genes were selected using the shortest path analysis with Dijkstra's algorithm. The AURKA and SLC7A2 genes were selected three and two times in the shortest path analysis, respectively. All those genes participate in a number of important pathways, such as oocyte meiosis, cell cycle and cancer pathways with Kyoto Encyclopedia of Genes and Genomes pathway enrichment analysis. The present findings may provide novel insights into the pathogenesis of NSCLC and enable the development of novel therapeutic strategies. However, further investigation is required to confirm these findings.

A network-based method using a random walk with restart algorithm and screening tests to identify novel genes associated with Menière's disease

As a chronic illness derived from hair cells of the inner ear, Menière’s disease (MD) negatively influences the quality of life of individuals and leads to a number of symptoms, such as dizziness, temporary hearing loss, and tinnitus. The complete identification of novel genes related to MD would help elucidate its underlying pathological mechanisms and improve its diagnosis and treatment. In this study, a network-based method was developed to identify novel MD-related genes based on known MD-related genes. A human protein-protein interaction (PPI) network was constructed using the PPI information reported in the STRING database. A classic ranking algorithm, the random walk with restart (RWR) algorithm, was employed to search for novel genes using known genes as seed nodes. To make the identified genes more reliable, a series of screening tests, including a permutation test, an interaction test and an enrichment test, were designed to select essential genes from those obtained by the RWR algorithm. As a result, several inferred genes, such as CD4, NOTCH2 and IL6, were discovered. Finally, a detailed biological analysis was performed on fifteen of the important inferred genes, which indicated their strong associations with MD.

Identifying and Analyzing Novel Epilepsy-Related Genes Using Random Walk with Restart Algorithm

As a pathological condition, epilepsy is caused by abnormal neuronal discharge in brain which will temporarily disrupt the cerebral functions. Epilepsy is a chronic disease which occurs in all ages and would seriously affect patients' personal lives. Thus, it is highly required to develop effective medicines or instruments to treat the disease. Identifying epilepsy-related genes is essential in order to understand and treat the disease because the corresponding proteins encoded by the epilepsy-related genes are candidates of the potential drug targets. In this study, a pioneering computational workflow was proposed to predict novel epilepsy-related genes using the random walk with restart (RWR) algorithm. As reported in the literature RWR algorithm often produces a number of false positive genes, and in this study a permutation test and functional association tests were implemented to filter the genes identified by RWR algorithm, which greatly reduce the number of suspected genes and result in only thirty-three novel epilepsy genes. Finally, these novel genes were analyzed based upon some recently published literatures. Our findings implicate that all novel genes were closely related to epilepsy. It is believed that the proposed workflow can also be applied to identify genes related to other diseases and deepen our understanding of the mechanisms of these diseases.

Identification of novel candidate drivers connecting different dysfunctional levels for lung adenocarcinoma using protein-protein interactions and a shortest path approach

Tumors are formed by the abnormal proliferation of somatic cells with disordered growth regulation under the influence of tumorigenic factors. Recently, the theory of “cancer drivers” connects tumor initiation with several specific mutations in the so-called cancer driver genes. According to the differentiation of four basic levels between tumor and adjacent normal tissues, the cancer drivers can be divided into the following: (1) Methylation level, (2) microRNA level, (3) mutation level, and (4) mRNA level. In this study, a computational method is proposed to identify novel lung adenocarcinoma drivers based on dysfunctional genes on the methylation, microRNA, mutation and mRNA levels. First, a large network was constructed using protein-protein interactions. Next, we searched all of the shortest paths connecting dysfunctional genes on different levels and extracted new candidate genes lying on these paths. Finally, the obtained candidate genes were filtered by a permutation test and an additional strict selection procedure involving a betweenness ratio and an interaction score. Several candidate genes remained, which are deemed to be related to two different levels of cancer. The analyses confirmed our assertions that some have the potential to contribute to the tumorigenesis process on multiple levels.

Investigation of the roles of trace elements during hepatitis C virus infection using protein-protein interactions and a shortest path algorithm

BACKGROUND

Hepatitis is a type of infectious disease that induces inflammation of the liver without pinpointing a particular pathogen or pathogenesis. Type C hepatitis, as a type of hepatitis, has been reported to induce cirrhosis and hepatocellular carcinoma within a very short amount of time. It is a great threat to human health. Some studies have revealed that trace elements are associated with infection with and immune rejection against hepatitis C virus (HCV). However, the mechanism underlying this phenomenon is still unclear.

METHODS

In this study, we aimed to expand our knowledge of this phenomenon by designing a computational method to identify genes that may be related to both HCV and trace element metabolic processes. The searching procedure included three stages. First, a shortest path algorithm was applied to a large network, constructed by protein-protein interactions, to identify potential genes of interest. Second, a permutation test was executed to exclude false discoveries. Finally, some rules based on the betweenness and associations between candidate genes and HCV and trace elements were built to select core genes among the remaining genes.

RESULTS

12 lists of genes, corresponding to 12 types of trace elements, were obtained. These genes are deemed to be associated with HCV infection and trace elements metabolism.

CONCLUSIONS

The analyses indicate that some genes may be related to both HCV and trace element metabolic processes, further confirming the associations between HCV and trace elements. The method was further tested on another set of HCV genes, the results indicate that this method is quite robustness.

GENERAL SIGNIFICANCE

The newly found genes may partially reveal unknown mechanisms between HCV infection and trace element metabolism. This article is part of a Special Issue entitled "System Genetics" Guest Editor: Dr. Yudong Cai and Dr. Tao Huang.

Identifying novel genes and chemicals related to nasopharyngeal cancer in a heterogeneous network

Nasopharyngeal cancer or nasopharyngeal carcinoma (NPC) is the most common cancer originating in the nasopharynx. The factors that induce nasopharyngeal cancer are still not clear. Additional information about the chemicals or genes related to nasopharyngeal cancer will promote a better understanding of the pathogenesis of this cancer and the factors that induce it. Thus, a computational method NPC-RGCP was proposed in this study to identify the possible relevant chemicals and genes based on the presently known chemicals and genes related to nasopharyngeal cancer. To extensively utilize the functional associations between proteins and chemicals, a heterogeneous network was constructed based on interactions of proteins and chemicals. The NPC-RGCP included two stages: the searching stage and the screening stage. The former stage is for finding new possible genes and chemicals in the heterogeneous network, while the latter stage is for screening and removing false discoveries and selecting the core genes and chemicals. As a result, five putative genes, CXCR3, IRF1, CDK1, GSTP1, and CDH2, and seven putative chemicals, iron, propionic acid, dimethyl sulfoxide, isopropanol, erythrose 4-phosphate, β-D-Fructose 6-phosphate, and flavin adenine dinucleotide, were identified by NPC-RGCP. Extensive analyses provided confirmation that the putative genes and chemicals have significant associations with nasopharyngeal cancer.

Identifying novel protein phenotype annotations by hybridizing protein-protein interactions and protein sequence similarities

Studies of protein phenotypes represent a central challenge of modern genetics in the post-genome era because effective and accurate investigation of protein phenotypes is one of the most critical procedures to identify functional biological processes in microscale, which involves the analysis of multifactorial traits and has greatly contributed to the development of modern biology in the post genome era. Therefore, we have developed a novel computational method that identifies novel proteins associated with certain phenotypes in yeast based on the protein-protein interaction network. Unlike some existing network-based computational methods that identify the phenotype of a query protein based on its direct neighbors in the local network, the proposed method identifies novel candidate proteins for a certain phenotype by considering all annotated proteins with this phenotype on the global network using a shortest path (SP) algorithm. The identified proteins are further filtered using both a permutation test and their interactions and sequence similarities to annotated proteins. We compared our method with another widely used method called random walk with restart (RWR). The biological functions of proteins for each phenotype identified by our SP method and the RWR method were analyzed and compared. The results confirmed a large proportion of our novel protein phenotype annotation, and the RWR method showed a higher false positive rate than the SP method. Our method is equally effective for the prediction of proteins involving in all the eleven clustered yeast phenotypes with a quite low false positive rate. Considering the universality and generalizability of our supporting materials and computing strategies, our method can further be applied to study other organisms and the new functions we predicted can provide pertinent instructions for the further experimental verifications.

Mining for novel tumor suppressor genes using a shortest path approach

Cancer, being among the most serious diseases, causes many deaths every year. Many investigators have devoted themselves to designing effective treatments for this disease. Cancer always involves abnormal cell growth with the potential to invade or spread to other parts of the body. In contrast, tumor suppressor genes (TSGs) act as guardians to prevent a disordered cell cycle and genomic instability in normal cells. Studies on TSGs can assist in the design of effective treatments against cancer. In this study, we propose a computational method to discover potential TSGs. Based on the known TSGs, a number of candidate genes were selected by applying the shortest path approach in a weighted graph that was constructed using protein-protein interaction network. The analysis of selected genes shows that some of them are new TSGs recently reported in the literature, while others may be novel TSGs.

Identifying New Candidate Genes and Chemicals Related to Prostate Cancer Using a Hybrid Network and Shortest Path Approach

Prostate cancer is a type of cancer that occurs in the male prostate, a gland in the male reproductive system. Because prostate cancer cells may spread to other parts of the body and can influence human reproduction, understanding the mechanisms underlying this disease is critical for designing effective treatments. The identification of as many genes and chemicals related to prostate cancer as possible will enhance our understanding of this disease. In this study, we proposed a computational method to identify new candidate genes and chemicals based on currently known genes and chemicals related to prostate cancer by applying a shortest path approach in a hybrid network. The hybrid network was constructed according to information concerning chemical-chemical interactions, chemical-protein interactions, and protein-protein interactions. Many of the obtained genes and chemicals are associated with prostate cancer.

A computational method for the identification of new candidate carcinogenic and non-carcinogenic chemicals

Cancer is one of the leading causes of human death. Based on current knowledge, one of the causes of cancer is exposure to toxic chemical compounds, including radioactive compounds, dioxin, and arsenic. The identification of new carcinogenic chemicals may warn us of potential danger and help to identify new ways to prevent cancer. In this study, a computational method was proposed to identify potential carcinogenic chemicals, as well as non-carcinogenic chemicals. According to the current validated carcinogenic and non-carcinogenic chemicals from the CPDB (Carcinogenic Potency Database), the candidate chemicals were searched in a weighted chemical network constructed according to chemical-chemical interactions. Then, the obtained candidate chemicals were further selected by a randomization test and information on chemical interactions and structures. The analyses identified several candidate carcinogenic chemicals, while those candidates identified as non-carcinogenic were supported by a literature search. In addition, several candidate carcinogenic/non-carcinogenic chemicals exhibit structural dissimilarity with validated carcinogenic/non-carcinogenic chemicals.

Identification of novel thyroid cancer-related genes and chemicals using shortest path algorithm

Thyroid cancer is a typical endocrine malignancy. In the past three decades, the continued growth of its incidence has made it urgent to design effective treatments to treat this disease. To this end, it is necessary to uncover the mechanism underlying this disease. Identification of thyroid cancer-related genes and chemicals is helpful to understand the mechanism of thyroid cancer. In this study, we generalized some previous methods to discover both disease genes and chemicals. The method was based on shortest path algorithm and applied to discover novel thyroid cancer-related genes and chemicals. The analysis of the final obtained genes and chemicals suggests that some of them are crucial to the formation and development of thyroid cancer. It is indicated that the proposed method is effective for the discovery of novel disease genes and chemicals.

Metabolic pathway predictions for metabolomics: a molecular structure matching approach

Metabolic pathways are composed of a series of chemical reactions occurring within a cell. In each pathway, enzymes catalyze the conversion of substrates into structurally similar products. Thus, structural similarity provides a potential means for mapping newly identified biochemical compounds to known metabolic pathways. In this paper, we present TrackSM, a cheminformatics tool designed to associate a chemical compound to a known metabolic pathway based on molecular structure matching techniques. Validation experiments show that TrackSM is capable of associating 93% of tested structures to their correct KEGG pathway class and 88% to their correct individual KEGG pathway. This suggests that TrackSM may be a valuable tool to aid in associating previously unknown small molecules to known biochemical pathways and improve our ability to link metabolomics, proteomic, and genomic data sets. TrackSM is freely available at http://metabolomics.pharm.uconn.edu/?q=Software.html .

Discovery of new candidate genes related to brain development using protein interaction information

Human brain development is a dramatic process composed of a series of complex and fine-tuned spatiotemporal gene expressions. A good comprehension of this process can assist us in developing the potential of our brain. However, we have only limited knowledge about the genes and gene functions that are involved in this biological process. Therefore, a substantial demand remains to discover new brain development-related genes and identify their biological functions. In this study, we aimed to discover new brain-development related genes by building a computational method. We referred to a series of computational methods used to discover new disease-related genes and developed a similar method. In this method, the shortest path algorithm was executed on a weighted graph that was constructed using protein-protein interactions. New candidate genes fell on at least one of the shortest paths connecting two known genes that are related to brain development. A randomization test was then adopted to filter positive discoveries. Of the final identified genes, several have been reported to be associated with brain development, indicating the effectiveness of the method, whereas several of the others may have potential roles in brain development.

A graphic method for identification of novel glioma related genes

Glioma, as the most common and lethal intracranial tumor, is a serious disease that causes many deaths every year. Good comprehension of the mechanism underlying this disease is very helpful to design effective treatments. However, up to now, the knowledge of this disease is still limited. It is an important step to understand the mechanism underlying this disease by uncovering its related genes. In this study, a graphic method was proposed to identify novel glioma related genes based on known glioma related genes. A weighted graph was constructed according to the protein-protein interaction information retrieved from STRING and the well-known shortest path algorithm was employed to discover novel genes. The following analysis suggests that some of them are related to the biological process of glioma, proving that our method was effective in identifying novel glioma related genes. We hope that the proposed method would be applied to study other diseases and provide useful information to medical workers, thereby designing effective treatments of different diseases.

Identifying gastric cancer related genes using the shortest path algorithm and protein-protein interaction network

Gastric cancer, as one of the leading causes of cancer related deaths worldwide, causes about 800,000 deaths per year. Up to now, the mechanism underlying this disease is still not totally uncovered. Identification of related genes of this disease is an important step which can help to understand the mechanism underlying this disease, thereby designing effective treatments. In this study, some novel gastric cancer related genes were discovered based on the knowledge of known gastric cancer related ones. These genes were searched by applying the shortest path algorithm in protein-protein interaction network. The analysis results suggest that some of them are indeed involved in the biological process of gastric cancer, which indicates that they are the actual gastric cancer related genes with high probability. It is hopeful that the findings in this study may help promote the study of this disease and the methods can provide new insights to study various diseases.

A hybrid method for prediction and repositioning of drug Anatomical Therapeutic Chemical classes

In the Anatomical Therapeutic Chemical (ATC) classification system, therapeutic drugs are divided into 14 main classes according to the organ or system on which they act and their chemical, pharmacological and therapeutic properties. This system, recommended by the World Health Organization (WHO), provides a global standard for classifying medical substances and serves as a tool for international drug utilization research to improve quality of drug use. In view of this, it is necessary to develop effective computational prediction methods to identify the ATC-class of a given drug, which thereby could facilitate further analysis of this system. In this study, we initiated an attempt to develop a prediction method and to gain insights from it by utilizing ontology information of drug compounds. Since only about one-fourth of drugs in the ATC classification system have ontology information, a hybrid prediction method combining the ontology information, chemical interaction information and chemical structure information of drug compounds was proposed for the prediction of drug ATC-classes. As a result, by using the Jackknife test, the 1st prediction accuracies for identifying the 14 main ATC-classes in the training dataset, the internal validation dataset and the external validation dataset were 75.90%, 75.70% and 66.36%, respectively. Analysis of some samples with false-positive predictions in the internal and external validation datasets indicated that some of them may even have a relationship with the false-positive predicted ATC-class, suggesting novel uses of these drugs. It was conceivable that the proposed method could be used as an efficient tool to identify ATC-classes of novel drugs or to discover novel uses of known drugs.

Prediction of cancer drugs by chemical-chemical interactions

Cancer, which is a leading cause of death worldwide, places a big burden on health-care system. In this study, an order-prediction model was built to predict a series of cancer drug indications based on chemical-chemical interactions. According to the confidence scores of their interactions, the order from the most likely cancer to the least one was obtained for each query drug. The 1(st) order prediction accuracy of the training dataset was 55.93%, evaluated by Jackknife test, while it was 55.56% and 59.09% on a validation test dataset and an independent test dataset, respectively. The proposed method outperformed a popular method based on molecular descriptors. Moreover, it was verified that some drugs were effective to the 'wrong' predicted indications, indicating that some 'wrong' drug indications were actually correct indications. Encouraged by the promising results, the method may become a useful tool to the prediction of drugs indications.

Identification of age-related macular degeneration related genes by applying shortest path algorithm in protein-protein interaction network

This study attempted to find novel age-related macular degeneration (AMD) related genes based on 36 known AMD genes. The well-known shortest path algorithm, Dijkstra's algorithm, was applied to find the shortest path connecting each pair of known AMD related genes in protein-protein interaction (PPI) network. The genes occurring in any shortest path were considered as candidate AMD related genes. As a result, 125 novel AMD genes were predicted. The further analysis based on betweenness and permutation test indicates that there are 10 genes involved in the formation or development of AMD and may be the actual AMD related genes with high probability. We hope that this contribution would promote the study of age-related macular degeneration and discovery of novel effective treatments.