Search

Drug-target binding affinity (DTA) prediction is an essential step in drug discovery. Drug-target protein binding occurs at specific regions between the protein and drug, rather than the entire protein and drug. However, existing deep-learning DTA prediction methods do not consider the interactions between drug substructures and protein sub-sequences. This work proposes GraphATT-DTA, a DTA prediction model that constructs the essential regions for determining interaction affinity between compounds and proteins, modeled with an attention mechanism for interpretability. We make the model consider the local-to-global interactions with the attention mechanism between compound and protein. As a result, GraphATT-DTA shows an improved prediction of DTA performance and interpretability compared with state-of-the-art models. The model is trained and evaluated with the Davis dataset, the human kinase dataset; an external evaluation is achieved with the independently proposed human kinase dataset from the BindingDB dataset.

Antimicrobial resistance is a growing health concern. Antimicrobial peptides (AMPs) disrupt harmful microorganisms by non-specific mechanisms, making it difficult for microbes to develop resistance. Accordingly, they are promising alternatives to traditional antimicrobial drugs. In this study, we developed an improved AMP classification model, called AMP-BERT. We propose a deep learning model with a fine-tuned BERT architecture designed to extract structural/functional information from input peptides and identify each input as AMP or non-AMP. We compared the performance of our proposed model and other machine/deep learning-based methods. Our model, AMP-BERT, yielded the best prediction results among all models evaluated with our curated external dataset. In addition, we utilized the attention mechanism in BERT to implement an interpretable feature analysis and determine the specific residues in known AMPs that contribute to peptide structure and antimicrobial function. The results show that AMP-BERT can capture the structural properties of peptides for model learning, enabling the prediction of AMPs or non-AMPs from input sequences. AMP-BERT is expected to contribute to the identification of candidate AMPs for functional validation and drug development. The code and dataset for the fine-tuning of AMP-BERT is publicly available at https://github.com/GIST-CSBL/AMP-BERT. This article is protected by copyright. All rights reserved.

Background Genome-wide studies of DNA methylation across the epigenetic landscape provide insights into the heterogeneity of pluripotent embryonic stem cells (ESCs). Differentiating into embryonic somatic and germ cells, ESCs exhibit varying degrees of pluripotency, and epigenetic changes occurring in this process have emerged as important factors explaining stem cell pluripotency. Results Here, using paired scBS-seq and scRNA-seq data of mice, we constructed a machine learning model that predicts degrees of pluripotency for mouse ESCs. Since the biological activities of non-CpG markers have yet to be clarified, we tested the predictive power of CpG and non-CpG markers, as well as a combination thereof, in the model. Through rigorous performance evaluation with both internal and external validation, we discovered that a model using both CpG and non-CpG markers predicted the pluripotency of ESCs with the highest prediction performance (0.956 AUC, external test). The prediction model consisted of 16 CpG and 33 non-CpG markers. The CpG and most of the non-CpG markers targeted depletions of methylation and were indicative of cell pluripotency, whereas only a few non-CpG markers reflected accumulations of methylation. Additionally, we confirmed that there exists the differing pluripotency between individual developmental stages, such as E3.5 and E6.5, as well as between induced mouse pluripotent stem cell (iPSC) and somatic cell. Conclusions In this study, we investigated CpG and non-CpG methylation in relation to mouse stem cell pluripotency and developed a model thereon that successfully predicts the pluripotency of mouse ESCs.

Artificial intelligence (AI) has been recognized as a powerful technique that can accelerate drug discovery during the hit compound identification step. However, most simple deep learning models have been used for naive pre-filtering as the prediction result cannot be interpreted. Recently, our group developed a new deep learning model (Highlight on Target Sequence; HoTS) that can predict binding regions in a target protein sequence based on patterns learned from interactions between a target protein sequence and a ligand. In this study, we searched for new binding regions of the P2X3 receptor (P2X3R) using HoTS, and suggested a novel putative binding site of P2X3R by a cavity search on the predicted binding regions. The novel putative binding site was employed to generate pharmacophore features, and combinations of pharmacophore features were validated as queries. Two separate virtual screenings using the optimized pharmacophore query Q12 with docking-based scoring and HoTS-based prediction of ligand interactions enabled the initial selection of the compound library for in vitro screening. The screening of each set of 500 compounds from the two approaches (HoTS interaction prediction and Pharmacophore-LibDock cascade) resulted in the identification of 10 (HoTS-1 - 10) and 6 compounds (PD-1 - 6) with low micromolar IC

The identification of efficient and sensitive biomarkers for non-invasive tests is one of the major challenges in cancer diagnosis. To address this challenge, metabolomics is widely applied for identifying biomarkers that detect abnormal changes in cancer patients. Canine mammary tumors exhibit physiological characteristics identical to those in human breast cancer and serve as a useful animal model to conduct breast cancer research. Here, we aimed to provide a reliable large-scale metabolite dataset collected from dogs with mammary tumors, using proton nuclear magnetic resonance spectroscopy. We identified 55 metabolites in urine samples from 20 benign, 87 malignant, and 49 healthy control subjects. This dataset provides details of mammary tumor-specific metabolites in dogs and insights into cancer-specific metabolic alterations that share similar molecular characteristics.

Adverse drug-drug interaction (DDI) is a major concern to polypharmacy due to its unexpected adverse side effects and must be identified at an early stage of drug discovery and development. Many computational methods have been proposed for this purpose, but most require specific types of information, or they have less concern in interpretation on underlying genes. We propose a deep learning-based framework for DDI prediction with drug-induced gene expression signatures so that the model can provide the expression level of interpretability for DDIs. The model engineers dynamic drug features using a gating mechanism that mimics the co-administration effects by imposing attention to genes. Also, each side-effect is projected into a latent space through translating embedding. As a result, the model achieved an AUC of 0.889 and an AUPR of 0.915 in unseen interaction prediction, which is competitively very accurate and outperforms other state-of-the-art methods. Furthermore, it can predict potential DDIs with new compounds not used in training. In conclusion, using drug-induced gene expression signatures followed by gating and translating embedding can increase DDI prediction accuracy while providing model interpretability. The source code is available on GitHub (https://github.com/GIST-CSBL/DeSIDE-DDI).

Identifying drug–target interactions (DTIs) is important for drug discovery. However, searching all drug–target spaces poses a major bottleneck. Therefore, recently many deep learning models have been proposed to address this problem. However, the developers of these deep learning models have neglected interpretability in model construction, which is closely related to a model’s performance. We hypothesized that training a model to predict important regions on a protein sequence would increase DTI prediction performance and provide a more interpretable model. Consequently, we constructed a deep learning model, named Highlights on Target Sequences (HoTS), which predicts binding regions (BRs) between a protein sequence and a drug ligand, as well as DTIs between them. To train the model, we collected complexes of protein–ligand interactions and protein sequences of binding sites and pretrained the model to predict BRs for a given protein sequence–ligand pair via object detection employing transformers. After pretraining the BR prediction, we trained the model to predict DTIs from a compound token designed to assign attention to BRs. We confirmed that training the BRs prediction model indeed improved the DTI prediction performance. The proposed HoTS model showed good performance in BR prediction on independent test datasets even though it does not use 3D structure information in its prediction. Furthermore, the HoTS model achieved the best performance in DTI prediction on test datasets. Additional analysis confirmed the appropriate attention for BRs and the importance of transformers in BR and DTI prediction. The source code is available on GitHub (https://github.com/GIST-CSBL/HoTS).

Understanding differences in drug responses between patients is crucial for delivering effective cancer treatment. We describe an interpretable AI model for use in predicting drug responses in cancer cells at the gene, molecular pathway, and drug level, which we have called the hierarchical network for drug response prediction with attention. We found that the model shows better accuracy in predicting drugs having efficacy against a given cell line than other state-of-the-art methods, with a root mean squared error of 1.0064, a Pearson's correlation coefficient of 0.9307, and an R2 value of 0.8647. We also confirmed that the model gives high attention to drug-target genes and cancer-related pathways when predicting a response. The validity of predicted results was proven by in vitro cytotoxicity assay. Overall, we propose that our hierarchical and interpretable AI-based model is capable of interpreting intrinsic characteristics of cancer cells and drugs for accurate prediction of cancer-drug responses.

Over a decade, as a specialized workshop in the field of text mining applied to biomedical informatics, DTMBIO (ACM international workshop on Data and Text Mining in Biomedical Informatics) has been held annually in conjunction with one of the largest data management conferences, CIKM. The purpose of DTMBIO is to foster discussions regarding the state-of-the-art applications of data and text mining on biomedical research problems. To address our purpose, we bring together researchers working on computer science and bio/medical informatics area including text mining and high throughput genomic data analysis, such as the next generation Sequencing (NGS) data. DTMBIO 2020 will help scientists navigate emerging trends and opportunities in the evolving area of informatics related techniques and problems in the context of biomedical research.

Genomic and precision medicine research has afforded notable advances in human cancer treatment, yet applicability to other species remains uncertain. Through whole-exome and transcriptome analyses of 191 spontaneous canine mammary tumors (CMTs) that exhibit the archetypal features of human breast cancers, we found a striking resemblance of genomic characteristics including frequent PIK3CA mutations (43.1%), aberrations of the PI3K-Akt pathway (61.7%), and key genes involved in cancer initiation and progression. We also identified three gene expression-based CMT subtypes, one of which segregated with basal-like human breast cancer subtypes with activated epithelial-to-mesenchymal transition, low claudin expression, and unfavorable disease prognosis. A relative lack of ERBB2 amplification and Her2-enrichment subtype in CMT denoted species-specific molecular mechanisms. Taken together, our results elucidate cross-species oncogenic signatures for a better understanding of universal and context-dependent mechanisms in breast cancer development and provide a basis for precision diagnostics and therapeutics for domestic dogs., Comparison of spontaneous canine cancers and human cancers may illuminate future therapeutic avenues. Here, genomic analyses of these tumors highlights a convergence on PI3K-Akt oncogenic pathways.

Although natural compounds have provided a wealth of leads and clues in drug development, the process of identifying their pharmacological effects is still a challenging task. Over the last decade, many in vitro screening methods have been developed to identify the pharmacological effects of natural compounds, but they are still costly processes with low productivity. Therefore, in silico methods, primarily based on molecular information, have been proposed. However, large-scale analysis is rarely considered, since many natural compounds do not have molecular structure and target protein information. Empirical knowledge of medicinal plants can be used as a key resource to solve the problem, but this information is not fully exploited and is used only as a preliminary tool for selecting plants for specific diseases. Here, we introduce a novel method to identify pharmacological effects of natural compounds from herbal medicine based on phenotype-oriented network analysis. In this study, medicinal plants with similar efficacy were clustered by investigating hierarchical relationships between the known efficacy of plants and 5,021 phenotypes in the phenotypic network. We then discovered significantly enriched natural compounds in each plant cluster and mapped the averaged pharmacological effects of the plant cluster to the natural compounds. This approach allows us to predict unexpected effects of natural compounds that have not been found by molecular analysis. When applied to verified medicinal compounds, our method successfully identified their pharmacological effects with high specificity and sensitivity.

Two major transcriptional regulators of carbon metabolism in bacteria are Cra and CRP. CRP is considered to be the main mediator of catabolite repression. Unlike for CRP, available in vivo DNA binding information of Cra is scarce. Here we generate and integrate ChIP-exo and RNA-seq data to identify 39 binding sites for Cra and 97 regulon genes that are regulated by Cra in Escherichia coli. An integrated metabolic-regulatory network was formed by including experimentally-derived regulatory information and a genome-scale metabolic network reconstruction. Applying analysis methods of systems biology to this integrated network showed that Cra enables the optimal bacterial growth on poor carbon sources by redirecting and repressing the glycolysis flux, by activating the glyoxylate shunt pathway, and by activating the respiratory pathway. In these regulatory mechanisms, the overriding regulatory activity of Cra over CRP is fundamental. Thus, elucidation of interacting transcriptional regulation of core carbon metabolism in bacteria by two key transcription factors was possible by combining genome-wide experimental measurement and simulation with a genome-scale metabolic model.

Combinations of natural products have been used as important sources of disease treatments. Existing databases contain information about prescriptions, herbs, and compounds and their relationships with phenotypes, but they do not have information on the use of combinations of natural product compounds. In this paper, we identified large-scale associations between natural product combinations and phenotypes by applying an association rule mining technique to integrated information on herbal medicine, combination drugs, functional foods, molecular compounds, and target genes. The rationale behind this approach is that natural products commonly found in medicinal multicomponent mixtures have statistically significant associations with the therapeutic effects of the multicomponent mixtures. Based on a molecular network analysis and an external literature validation, we show that the inferred associations are valuable information for identifying medicinal combinations of natural products since they have statistically significant closeness proximity in the molecular layer and have much experimental evidence. All results are available through the workbench site at http://biosoft.kaist.ac.kr/coconut to facilitate the investigation of the medicinal use of natural products and their combinations.

Mass spectrometry (MS) data are used to analyze biological phenomena based on chemical species. However, these data often contain unexpected duplicate records and missing values due to technical or biological factors. These 'dirty data' problems increase the difficulty of performing MS analyses because they lead to performance degradation when statistical or machine-learning tests are applied to the data. Thus, we have developed missing values preprocessor (MVP), an open-source software for preprocessing data that might include duplicate records and missing values. MVP uses the property of MS data in which identical chemical species present the same or similar values for key identifiers, such as the mass-to-charge ratio and intensity signal, and forms cliques via graph theory to process dirty data. We evaluated the validity of the MVP process via quantitative and qualitative analyses and compared the results from a statistical test that analyzed the original and MVP-applied data. This analysis showed that using MVP reduces problems associated with duplicate records and missing values. We also examined the effects of using unprocessed data in statistical tests and examined the improved statistical test results obtained with data preprocessed using MVP.

DNA methylation patterns have been shown to change throughout the normal aging process. Several studies have found epigenetic aging markers using age predictors, but these studies only focused on blood-specific or tissue-common methylation patterns. Here, we constructed nine tissue-specific age prediction models using methylation array data from normal samples. The constructed models predict the chronological age with good performance (mean absolute error of 5.11 years on average) and show better performance in the independent test than previous multi-tissue age predictors. We also compared tissue-common and tissue-specific aging markers and found that they had different characteristics. Firstly, the tissue-common group tended to contain more positive aging markers with methylation values that increased during the aging process, whereas the tissue-specific group tended to contain more negative aging markers. Secondly, many of the tissue-common markers were located in Cytosine-phosphate-Guanine (CpG) island regions, whereas the tissue-specific markers were located in CpG shore regions. Lastly, the tissue-common CpG markers tended to be located in more evolutionarily conserved regions. In conclusion, our prediction models identified CpG markers that capture both tissue-common and tissue-specific characteristics during the aging process.

Studies of naturally occurring cancers in dogs, which share many genetic and environmental factors with humans, provide valuable information as a comparative model for studying the mechanisms of human cancer pathogenesis. While individual and small-scale studies of canine cancers are underway, more generalized multi-omics studies have not been attempted due to the lack of large-scale and well-controlled genomic data. Here, we produced reliable whole-exome and whole-transcriptome sequencing data of 197 canine mammary cancers and their matched controls, annotated with rich clinical and biological features. Our dataset provides useful reference points for comparative analysis with human cancers and for developing novel diagnostic and therapeutic technologies for cancers in pet dogs., Design Type(s)disease state design • transcription profiling design • parallel group designMeasurement Type(s)transcription profiling assay • exomeTechnology Type(s)RNA sequencing • DNA sequencingFactor Type(s)breed • age • experimental condition • diagnosisSample Characteristic(s)Canis lupus familiaris • tissue Machine-accessible metadata file describing the reported data (ISA-Tab format)

Background Drug repositioning, also known as drug repurposing, defines new indications for existing drugs and can be used as an alternative to drug development. In recent years, the accumulation of large volumes of information related to drugs and diseases has led to the development of various computational approaches for drug repositioning. Although herbal medicines have had a great impact on current drug discovery, there are still a large number of herbal compounds that have no definite indications. Results In the present study, we constructed a computational model to predict the unknown pharmacological effects of herbal compounds using machine learning techniques. Based on the assumption that similar diseases can be treated with similar drugs, we used four categories of drug-drug similarity (e.g., chemical structure, side-effects, gene ontology, and targets) and three categories of disease-disease similarity (e.g., phenotypes, human phenotype ontology, and gene ontology). Then, associations between drug and disease were predicted using the employed similarity features. The prediction models were constructed using classification algorithms, including logistic regression, random forest and support vector machine algorithms. Upon cross-validation, the random forest approach showed the best performance (AUC = 0.948) and also performed well in an external validation assessment using an unseen independent dataset (AUC = 0.828). Finally, the constructed model was applied to predict potential indications for existing drugs and herbal compounds. As a result, new indications for 20 existing drugs and 31 herbal compounds were predicted and validated using clinical trial data. Conclusions The predicted results were validated manually confirming the performance and underlying mechanisms – for example, irinotecan as a treatment for neuroblastoma. From the prediction, herbal compounds were considered to be drug candidates for related diseases which is important to be further developed. The proposed prediction model can contribute to drug discovery by suggesting drug candidates from herbal compounds which have potentials but few were studied. Electronic supplementary material The online version of this article (10.1186/s12859-019-2811-8) contains supplementary material, which is available to authorized users.

Accurate genome-wide detection of somatic mutations with low variant allele frequency (VAF, Somatic mutations of low allele frequencies are often difficult to detect. Here, the authors develop RePlow, a computational method that leverages technical replication for detecting low-level somatic mutations using next-generation sequencing.

A voltage-gated potassium channel encoded by the human ether-à-go-go-related gene (hERG) regulates cardiac action potential, and it is involved in cardiotoxicity with compounds that inhibit its activity. Therefore, the screening of hERG channel blockers is a mandatory step in the drug discovery process. The screening of hERG blockers by using conventional methods is inefficient in terms of cost and efforts. This has led to the development of many in silico hERG blocker prediction models. However, constructing a high-performance predictive model with interpretability on hERG blockage by certain compounds is a major obstacle. In this study, we developed the first, attention-based, interpretable model that predicts hERG blockers and captures important hERG-related compound substructures. To do that, we first collected various datasets, ranging from public databases to publicly available private datasets, to train and test the model. Then, we developed a precise and interpretable hERG blocker prediction model by using deep learning with a self-attention approach that has an appropriate molecular descriptor, Morgan fingerprint. The proposed prediction model was validated, and the validation result showed that the model was well-optimized and had high performance. The test set performance of the proposed model was significantly higher than that of previous fingerprint-based conventional machine learning models. In particular, the proposed model generally had high accuracy and F1 score thereby, representing the model's predictive reliability. Furthermore, we interpreted the calculated attention score vectors obtained from the proposed prediction model and demonstrated the important structural patterns that are represented in hERG blockers. In summary, we have proposed a powerful and interpretable hERG blocker prediction model that can reduce the overall cost of drug discovery by accurately screening for hERG blockers and suggesting hERG-related substructures.

Figure S1. Data distribution of the training dataset. Figure S2. Performance comparison in cross-validation with different feature aggregation method. Figure S3. Prediction ability for drug repositioning. (PDF 303 kb)

Table S1. Performance of prediction models in cross-validation. Table S2. Performance of prediction models in external validation. (PDF 51 kb)

Identification of drug-target interactions (DTIs) plays a key role in drug discovery. The high cost and labor-intensive nature of in vitro and in vivo experiments have highlighted the importance of in silico-based DTI prediction approaches. In several computational models, conventional protein descriptors have been shown to not be sufficiently informative to predict accurate DTIs. Thus, in this study, we propose a deep learning based DTI prediction model capturing local residue patterns of proteins participating in DTIs. When we employ a convolutional neural network (CNN) on raw protein sequences, we perform convolution on various lengths of amino acids subsequences to capture local residue patterns of generalized protein classes. We train our model with large-scale DTI information and demonstrate the performance of the proposed model using an independent dataset that is not seen during the training phase. As a result, our model performs better than previous protein descriptor-based models. Also, our model performs better than the recently developed deep learning models for massive prediction of DTIs. By examining pooled convolution results, we confirmed that our model can detect binding sites of proteins for DTIs. In conclusion, our prediction model for detecting local residue patterns of target proteins successfully enriches the protein features of a raw protein sequence, yielding better prediction results than previous approaches. Our code is available at https://github.com/GIST-CSBL/DeepConv-DTI., Author summary Drugs work by interacting with target proteins to activate or inhibit a target’s biological process. Therefore, identification of DTIs is a crucial step in drug discovery. However, identifying drug candidates via biological assays is very time and cost consuming, which introduces the need for a computational prediction approach for the identification of DTIs. In this work, we constructed a novel DTI prediction model to extract local residue patterns of target protein sequences using a CNN-based deep learning approach. As a result, the detected local features of protein sequences perform better than other protein descriptors for DTI prediction and previous models for predicting PubChem independent test datasets. That is, our approach of capturing local residue patterns with CNN successfully enriches protein features from a raw sequence.

Identifying the health benefits of phytochemicals is an essential step in drug and functional food development. While many in vitro screening methods have been developed to identify the health effects of phytochemicals, there is still room for improvement because of high cost and low productivity. Therefore, researchers have alternatively proposed in silico methods, primarily based on three types of approaches, utilizing molecular, chemical or ethnopharmacological information. Although each approach has its own strength in analyzing the characteristics of phytochemicals, previous studies have not considered them all together. Here, we apply an integrated in silico analysis to identify the potential health benefits of phytochemicals based on molecular analysis and chemical properties as well as ethnopharmacological evidence. From the molecular analysis, we found an average of 415.6 health effects for 591 phytochemicals. We further investigated ethnopharmacological evidence of phytochemicals and found that on average 129.1 (31%) of the predicted health effects had ethnopharmacological evidence. Lastly, we investigated chemical properties to confirm whether they are orally bio-available, drug available or effective on certain tissues. The evaluation results indicate that the health effects can be predicted more accurately by cooperatively considering the molecular analysis, chemical properties and ethnopharmacological evidence.

Background Identification of drug-target interactions acts as a key role in drug discovery. However, identifying drug-target interactions via in-vitro, in-vivo experiments are very laborious, time-consuming. Thus, predicting drug-target interactions by using computational approaches is a good alternative. In recent studies, many feature-based and similarity-based machine learning approaches have shown promising results in drug-target interaction predictions. A previous study showed that accounting connectivity information of drug-drug and protein-protein interactions increase performances of prediction by the concept of ‘guilt-by-association’. However, the approach that only considers directly connected nodes often misses the information that could be derived from distance nodes. Therefore, in this study, we yield global network topology information by using a random walk with restart algorithm and apply the global topology information to the prediction model. Results As a result, our prediction model demonstrates increased prediction performance compare to the ‘guilt-by-association’ approach (AUC 0.89 and 0.67 in the training and independent test, respectively). In addition, we show how weighted features by a random walk with restart yields better performances than original features. Also, we confirmed that drugs and proteins that have high-degree of connectivity on the interactome network yield better performance in our model. Conclusions The prediction models with weighted features by considering global network topology increased the prediction performances both in the training and testing compared to non-weighted models and previous a ‘guilt-by-association method’. In conclusion, global network topology information on protein-protein interaction and drug-drug interaction effects to the prediction performance of drug-target interactions. Electronic supplementary material The online version of this article (10.1186/s12859-018-2199-x) contains supplementary material, which is available to authorized users.

Figure S1. Receiver operating characteristic curve of test data with drugs and targets in training data. Figure S2. Pazopanib and its targets during a STITCH prediction. (DOCX 7851Â kb)

Table S1. Protein-Protein interactions of Q9H4B4 in Uniprot. (DOCX 14Â kb)

Figure S1. Receiver operating characteristic curve of test data with drugs and targets in training data. Figure S2. Pazopanib and its targets during a STITCH prediction. (DOCX 7851Â kb)

Table S1. Protein-Protein interactions of Q9H4B4 in Uniprot. (DOCX 14Â kb)

Supplementary methods. Describing the generation process of compound descriptors and protein descriptors. (DOCX 22Â kb)

Osteoarthritis-the most common form of age-related degenerative whole-joint disease1-is primarily characterized by cartilage destruction, as well as by synovial inflammation, osteophyte formation and subchondral bone remodelling2,3. However, the molecular mechanisms that underlie the pathogenesis of osteoarthritis are largely unknown. Although osteoarthritis is currently considered to be associated with metabolic disorders, direct evidence for this is lacking, and the role of cholesterol metabolism in the pathogenesis of osteoarthritis has not been fully investigated4-6. Various types of cholesterol hydroxylases contribute to cholesterol metabolism in extrahepatic tissues by converting cellular cholesterol to circulating oxysterols, which regulate diverse biological processes7,8. Here we show that the CH25H-CYP7B1-RORα axis of cholesterol metabolism in chondrocytes is a crucial catabolic regulator of the pathogenesis of osteoarthritis. Osteoarthritic chondrocytes had increased levels of cholesterol because of enhanced uptake, upregulation of cholesterol hydroxylases (CH25H and CYP7B1) and increased production of oxysterol metabolites. Adenoviral overexpression of CH25H or CYP7B1 in mouse joint tissues caused experimental osteoarthritis, whereas knockout or knockdown of these hydroxylases abrogated the pathogenesis of osteoarthritis. Moreover, retinoic acid-related orphan receptor alpha (RORα) was found to mediate the induction of osteoarthritis by alterations in cholesterol metabolism. These results indicate that osteoarthritis is a disease associated with metabolic disorders and suggest that targeting the CH25H-CYP7B1-RORα axis of cholesterol metabolism may provide a therapeutic avenue for treating osteoarthritis.

Accurate genome-wide detection of somatic mutations with low variant allele frequency (VAF

Background Drug-induced liver injury (DILI) is a critical issue in drug development because DILI causes failures in clinical trials and the withdrawal of approved drugs from the market. There have been many attempts to predict the risk of DILI based on in vivo and in silico identification of hepatotoxic compounds. In the current study, we propose the in silico prediction model predicting DILI using weighted molecular fingerprints. Results In this study, we used 881 bits of molecular fingerprint and used as features describing presence or absence of each substructure of compounds. Then, the Bayesian probability of each substructure was calculated and labeled (positive or negative for DILI), and a weighted fingerprint was determined from the ratio of DILI-positive to DILI-negative probability values. Using weighted fingerprint features, the prediction models were trained and evaluated with the Random Forest (RF) and Support Vector Machine (SVM) algorithms. The constructed models yielded accuracies of 73.8% and 72.6%, AUCs of 0.791 and 0.768 in cross-validation. In independent tests, models achieved accuracies of 60.1% and 61.1% for RF and SVM, respectively. The results validated that weighted features helped increase overall performance of prediction models. The constructed models were further applied to the prediction of natural compounds in herbs to identify DILI potential, and 13,996 unique herbal compounds were predicted as DILI-positive with the SVM model. Conclusions The prediction models with weighted features increased the performance compared to non-weighted models. Moreover, we predicted the DILI potential of herbs with the best performed model, and the prediction results suggest that many herbal compounds could have potential to be DILI. We can thus infer that taking natural products without detailed references about the relevant pathways may be dangerous. Considering the frequency of use of compounds in natural herbs and their increased application in drug development, DILI labeling would be very important. Electronic supplementary material The online version of this article (doi:10.1186/s12859-017-1638-4) contains supplementary material, which is available to authorized users.

Description of frequent appearing substructures in DILI-positive compounds (Log odds ratio: 2.5). Table S2. Description of frequent appearing substructures in DILI-positive compounds (Log odds ratio: 2). Table S3 Description of frequent appearing substructures in DILI-positive compounds (Log odds ratio: 2). (PDF 55Â kb)

Performance change by different cutoff. Figure S2. Performance change by weight values. (PDF 326Â kb)

Description of frequent appearing substructures in DILI-positive compounds (Log odds ratio: 2.5). Table S2. Description of frequent appearing substructures in DILI-positive compounds (Log odds ratio: 2). Table S3 Description of frequent appearing substructures in DILI-positive compounds (Log odds ratio: 2). (PDF 55Â kb)

Inferring novel findings from known biological knowledge is one of the ultimate goals in systems biology. However, the observation of system-level responses to a given perturbation has not been thoroughly explored due to the lack of proper large-scale inference models. We developed a novel expert system that can be applied to conventional biological networks based on the production rule system which works by transforming networks into a knowledgebase. Testing on large-scale multi-level biomedical networks confirmed the applicability of our system and revealed that hundreds of molecules are affected by the cascades of given signals, thereby activating or repressing key pathways in a cell.

Performance change by different cutoff. Figure S2. Performance change by weight values. (PDF 326Â kb)

Background Verifying the proteins that are targeted by compounds of natural herbs will be helpful to select natural herb-based drug candidates. However, this entails a great deal of effort to clarify the interaction throughout in vitro or in vivo experiments. In this light, in silico prediction of the interactions between compounds and target proteins can help ease the efforts. Results In this study, we performed in silico predictions of herbal compound target identification. First, data related to compounds, target proteins, and interactions between them are taken from the DrugBank database. Then we characterized six classes of compound-target interaction in humans including G-protein-coupled receptors (GPCRs), ion channel, enzymes, receptors, transporters, and other proteins. Also, classification-prediction models that predict the interactions between compounds and target proteins through a machine learning method were constructed using these matrices. As a result, AUC values of six classes are 0.94, 0.93, 0.90, 0.89, 0.91, and 0.76 respectively. Finally, the interactions of compounds from natural products were predicted using the constructed classification models. Furthermore, from our predicted results, we confirmed that several important disease related proteins were predicted as targets of natural herbal compounds. Conclusions We constructed classification-prediction models that predict the interactions between compounds and target proteins. The constructed models showed good prediction performances, and numbers of potential natural compounds target proteins were predicted from our results.

The human colorectal carcinoma cell line (Caco-2) is a commonly used in-vitro test that predicts the absorption potential of orally administered drugs. In-silico prediction methods, based on the Caco-2 assay data, may increase the effectiveness of the high-throughput screening of new drug candidates. However, previously developed in-silico models that predict the Caco-2 cellular permeability of chemical compounds use handcrafted features that may be dataset-specific and induce over-fitting problems. Deep Neural Network (DNN) generates high-level features based on non-linear transformations for raw features, which provides high discriminant power and, therefore, creates a good generalized model. We present a DNN-based binary Caco-2 permeability classifier. Our model was constructed based on 663 chemical compounds with in-vitro Caco-2 apparent permeability data. Two hundred nine molecular descriptors are used for generating the high-level features during DNN model generation. Dropout regularization is applied to solve the over-fitting problem and the non-linear activation. The Rectified Linear Unit (ReLU) is adopted to reduce the vanishing gradient problem. The results demonstrate that the high-level features generated by the DNN are more robust than handcrafted features for predicting the cellular permeability of structurally diverse chemical compounds in Caco-2 cell lines.

Evolution results from molecular-level changes in an organism, thereby producing novel phenotypes and, eventually novel species. However, changes in a single gene can lead to significant changes in biomolecular networks through the gain and loss of many molecular interactions. Thus, significant insights into microbial evolution have been gained through the analysis and comparison of reconstructed metabolic networks. However, challenges remain from reconstruction incompleteness and the inability to experiment with evolution on the timescale necessary for new species to arise. Despite these challenges, experimental laboratory evolution of microbes has provided some insights into the cellular objectives underlying evolution, under the constraints of nutrient availability and the use of mechanisms that protect cells from extreme conditions.

Understanding altered metabolism is an important issue because altered metabolism is often revealed as a cause or an effect in pathogenesis. It has also been shown to be an important factor in the manipulation of an organism's metabolism in metabolic engineering. Unfortunately, it is not yet possible to measure the concentration levels of all metabolites in the genome-wide scale of a metabolic network; consequently, a method that infers the alteration of metabolism is beneficial. The present study proposes a computational method that identifies genome-wide altered metabolism by analyzing functional units of KEGG pathways. As control of a metabolic pathway is accomplished by altering the activity of at least one rate-determining step enzyme, not all gene expressions of enzymes in the pathway demonstrate significant changes even if the pathway is altered. Therefore, we measure the alteration levels of a metabolic pathway by selectively observing expression levels of significantly changed genes in a pathway. The proposed method was applied to two strains of Saccharomyces cerevisiae gene expression profiles measured in very high-gravity (VHG) fermentation. The method identified altered metabolic pathways whose properties are related to ethanol and osmotic stress responses which had been known to be observed in VHG fermentation because of the high sugar concentration in growth media and high ethanol concentration in fermentation products. With the identified altered pathways, the proposed method achieved best accuracy and sensitivity rates for the Red Star (RS) strain compared to other three related studies (gene-set enrichment analysis (GSEA), significance analysis of microarray to gene set (SAM-GS), reporter metabolite), and for the CEN.PK 113-7D (CEN) strain, the proposed method and the GSEA method showed comparably similar performances.

The concentrations and catalytic activities of enzymes control metabolic rates. Previous studies have focused on enzyme concentrations because there are no genome-wide techniques used for the measurement of enzyme activity. We propose a method for evaluating the significance of enzyme activity by integrating metabolic network topologies and genome-wide microarray gene expression profiles. We quantified the enzymatic activity of reactions and report the 388 significant reactions in five perturbation datasets. For the 388 enzymatic reactions, we identified 70 that were significantly regulated (P-value < 0.001). Thirty-one of these reactions were part of anaerobic metabolism, 23 were part of low-pH aerobic metabolism, 8 were part of high-pH anaerobic metabolism, 3 were part of low-pH aerobic reactions, and 5 were part of high-pH anaerobic metabolism. [BMB reports 2008; 41(8): 609-614]

Figure S1. Selection of prognostic candidate-genes based on log-rank test. Table S1. The prediction of patientsâ outcome based on log-rank test according to varied correlation thresholds. Table S2. The gene list of module 1 including previously defined prognostic factor. (DOCX 179 kb)

Verifying the proteins that are targeted by compounds of natural herbs will help select natural herb-based drug candidates. However, this entails a great deal of effort to clarify the interaction throughout in vitro or in vivo experiments. In this light, in silico prediction of the interactions between compounds and target proteins can help ease the efforts.In this study, data related to compounds, target proteins, and interactions between them are taken from DrugBank [1]. Then we characterized six classes of compound-target interaction networks in humans including G-protein-coupled receptors (GPCRs), ion channel, enzymes, receptors, transporters, and other proteins. We then calculated the structural similarity matrix between compounds - as well as the protein sequence similarity matrix between target proteins - and established drug-target interaction. Also, classification-prediction models that predict the interactions between compounds and target proteins through a machine leaning method were constructed using these matrices. As a result, AUC values of six classes are 0.94, 0.93, 0.90, 0.89, 0.91, and 0.76 respectively. Finally, the interactions of compounds from natural products were predicted using the constructed classification models.

Drug-induced liver injury (DILI) is one of the major factors in drug development because it causes failure in clinical trials and withdrawals from market. Though, determining the DILI potentiality is still challenging due to its low occurrences and unexpected contradicts with clinical animal studies.There have been a variety of efforts and experiments on constructing prediction models to identify compounds that cause liver toxicity. However, the discriminant power of the previous models is not confident enough. Also, studies often relies on experimental data for better accuracy which can cause data access limitation and time consuming works. Therefore, some researchers started concerning compound properties and its molecular structures.In this study, we developed a classification model using liver toxicity related compounds as training set. We acquired 192 toxin data and 187 DILI-negative drugs. We obtained toxin data related to liver toxicity from two databases; Hazardous Substances Data Bank (HSDB) [1] , Toxin and Toxin Target Database (T3DB) [2; 4]. For negative set, we used data from three previous studies which include DILI-labels.We used 18 compound properties and molecular structures as features of a classification model. We collected property information using the admetSAR website and the CDK descriptor tool. Moreover, we used the Pybel API provided by Open Babel [3] to retrieve fingerprints as structure information.In classification model construction, two machine learning algorithms, support vector machine (SVM) and random forest, were used with physicochemical properties and structure information as features. The classifiers were developed through 10-fold cross-validation and resulted in accuracy of 73% and 80% in the SVM and the random forest model respectively.

In this work, we propose a comprehensive analysis of the genomic features of the human in mutations to classify loss-of-function (LoF) and gain-of-function (GoF) mutations. Through these genetic mutations, a protein can lose its native function, or it can confer a new function. However, when a mutation occurs, it is difficult to determine whether it will result in a LoF or a GoF. Therefore, we propose a study that analyzes the human genomic features of LoF and GoF instances to find features that can be used to classify LoF and GoF mutations. In order to collect experimentally verified LoF and GoF mutational information, we obtained 816 LoF mutations and 474 GoF mutations from a literature text-mining process. Next, with data-preprocessing steps, 258 LoF and 129 GoF mutations remained for a further analysis. We analyzed the properties of these LoF and GoF mutations. Among the properties, we selected features which show different tendencies between the two groups. Finally, we implemented classifications using support vector machine, random forest, and logistic regression methods to confirm whether or not these features can identify LoF and GoF mutations. By implementing classifications with the selected features, it is demonstrated that the selected features have good discriminative power.

Natural products used in dietary supplements, complementary and alternative medicine (CAM) and conventional medicine are composites of multiple chemical compounds. These chemical compounds potentially offer an extensive source for drug discovery with accumulated knowledge of efficacy and safety. However, existing natural product related databases have drawbacks in both standardization and structuralization of information. Therefore, in this work, we construct an integrated database of natural products by mapping the prescription, herb, compound, and phenotype information to international identifiers and structuralizing the efficacy information through database integration and text-mining methods. We expect that the constructed database could serve as a fundamental resource for the natural products research.

E. coli sequence type 131 (ST131) is one of pathogens that causes resistant infections. Comparative genome analyses allow interpretations of the virulence factors of pathogens. Thus, in this study, we analysis the genomic differences between the pathogenic E. coli ST131 and the non-pathogenic E. coli K-12. In this study, we identify the genomic differences between 96 E. coli ST131 strains and the E. coli K-12 in gene elements and their non-coding regulation elements. Using next-generation whole-genome sequencing data, we investigated genetic variations of protein-coding regions and their regulation regions. After the alignment of the sequence reads, large numbers of single nucleotide variants (SNVs) were observed in the regulation and protein-coding sequences. In the regulation regions, we found strong conserved regions, in this case, ribosome binding sites. In the gene regions, we found conserved start and stop codons with the specific position varying commonly in each codon. Except for these well-conserved regions, other variations were randomly distributed in regulation regions. Even a region having well-known conserved sequences such as -10 and -35 in the promoter had a similar level of variation. In this study, we found genomic variations between the pathogenic E. coli ST 131 strain and the non-pathogenic E. coli K-12. In addition, the numbers of sequence variations were determined in both the protein-coding regions and the regulation regions. However, we found that the effects of variations on the protein-coding regions are less significant than those on the regulation regions.

Motivation: Finding somatic mutations from massively parallel sequencing data is becoming a standard process in genome-based biomedical studies. There are a number of robust methods developed for detecting somatic single nucleotide variations However, detection of somatic copy number alteration has been substantially less explored and remains vulnerable to frequently raised sampling issues: low frequency in cell population and absence of the matched control samples. Results: We developed a novel computational method SoloDel that accurately classifies low-frequent somatic deletions from germline ones with or without matched control samples. We first constructed a probabilistic, somatic mutation progression model that describes the occurrence and propagation of the event in the cellular lineage of the sample. We then built a Gaussian mixture model to represent the mixed population of somatic and germline deletions. Parameters of the mixture model could be estimated using the expectation-maximization algorithm with the observed distribution of read-depth ratios at the points of discordant-read based initial deletion calls. Combined with conventional structural variation caller, SoloDel greatly increased the accuracy in classifying somatic mutations. Even without control, SoloDel maintained a comparable performance in a wide range of mutated subpopulation size (10–70%). SoloDel could also successfully recall experimentally validated somatic deletions from previously reported neuropsychiatric whole-genome sequencing data. Availability and implementation: Java-based implementation of the method is available at http://sourceforge.net/projects/solodel/ Contact: swkim@yuhs.ac or dhlee@biosoft.kaist.ac.kr Supplementary information: Supplementary data are available at Bioinformatics online.