Optimizing machine-learning models for mutagenicity prediction through better feature selection.

Assessing a compound's mutagenicity using machine learning is an important activity in the drug discovery and development process. Traditional methods of mutagenicity detection, such as Ames test, are expensive and time and labor intensive. In this context, in silico methods that predict a compound mutagenicity with high accuracy are important. Recently, machine-learning (ML) models are increasingly being proposed to improve the accuracy of mutagenicity prediction. While these models are used in practice, there is further scope to improve the accuracy of these models. We hypothesize that choosing the right features to train the model can further lead to better accuracy. We systematically consider and evaluate a combination of novel structural and molecular features which have the maximal impact on the accuracy of models. We rigorously evaluate these features against multiple classification models (from classical ML models to deep neural network models). The performance of the models was assessed using 5- and 10-fold cross-validation and we show that our approach using the molecule structure, molecular properties, and structural alerts as feature sets successfully outperform the state-of-the-art methods for mutagenicity prediction for the Hansen et al. benchmark dataset with an area under the receiver operating characteristic curve of 0.93. More importantly, our framework shows how combining features could benefit model accuracy improvements.

Interleukin 34 (IL-34) cell-surface localization regulated by the molecular chaperone 78-kDa glucose-regulated protein facilitates the differentiation of monocytic cells.

Interleukin 34 (IL-34) constitutes a cytokine that shares a common receptor, colony-stimulating factor-1 receptor (CSF-1R), with CSF-1. We recently identified a novel type of monocytic cell termed follicular dendritic cell-induced monocytic cells (FDMCs), whose differentiation depended on CSF-1R signaling through the IL-34 produced from a follicular dendritic cell line, FL-Y. Here, we report the functional mechanisms of the IL-34-mediated CSF-1R signaling underlying FDMC differentiation. CRIPSR/Cas9-mediated knockout of the Il34 gene confirmed that the ability of FL-Y cells to induce FDMCs completely depends on the IL-34 expressed by FL-Y cells. Transwell culture experiments revealed that FDMC differentiation requires a signal from a membrane-anchored form of IL-34 on the FL-Y cell surface, but not from a secreted form, in a direct interaction between FDMC precursor cells and FL-Y cells. Furthermore, flow cytometric analysis using an anti-IL-34 antibody indicated that IL-34 was also expressed on the FL-Y cell surface. Thus, we explored proteins interacting with IL-34 in FL-Y cells. Mass spectrometry analysis and pulldown assay identified that IL-34 was associated with the molecular chaperone 78-kDa glucose-regulated protein (GRP78) in the plasma membrane fraction of FL-Y cells. Consistent with this finding, GRP78-heterozygous FL-Y cells expressed a lower level of IL-34 protein on their cell surface and exhibited a reduced competency to induce FDMC differentiation compared with the original FL-Y cells. These results indicated a novel GRP78-dependent localization and specific function of IL-34 in FL-Y cells related to monocytic cell differentiation.

systemsDock: a web server for network pharmacology-based prediction and analysis.

We present systemsDock, a web server for network pharmacology-based prediction and analysis, which permits docking simulation and molecular pathway map for comprehensive characterization of ligand selectivity and interpretation of ligand action on a complex molecular network. It incorporates an elaborately designed scoring function for molecular docking to assess protein-ligand binding potential. For large-scale screening and ease of investigation, systemsDock has a user-friendly GUI interface for molecule preparation, parameter specification and result inspection. Ligand binding potentials against individual proteins can be directly displayed on an uploaded molecular interaction map, allowing users to systemically investigate network-dependent effects of a drug or drug candidate. A case study is given to demonstrate how systemsDock can be used to discover a test compound's multi-target activity. systemsDock is freely accessible at http://systemsdock.unit.oist.jp/.

An Ultrasensitive Mechanism Regulates Influenza Virus-Induced Inflammation.

Influenza viruses present major challenges to public health, evident by the 2009 influenza pandemic. Highly pathogenic influenza virus infections generally coincide with early, high levels of inflammatory cytokines that some studies have suggested may be regulated in a strain-dependent manner. However, a comprehensive characterization of the complex dynamics of the inflammatory response induced by virulent influenza strains is lacking. Here, we applied gene co-expression and nonlinear regression analysis to time-course, microarray data developed from influenza-infected mouse lung to create mathematical models of the host inflammatory response. We found that the dynamics of inflammation-associated gene expression are regulated by an ultrasensitive-like mechanism in which low levels of virus induce minimal gene expression but expression is strongly induced once a threshold virus titer is exceeded. Cytokine assays confirmed that the production of several key inflammatory cytokines, such as interleukin 6 and monocyte chemotactic protein 1, exhibit ultrasensitive behavior. A systematic exploration of the pathways regulating the inflammatory-associated gene response suggests that the molecular origins of this ultrasensitive response mechanism lie within the branch of the Toll-like receptor pathway that regulates STAT1 phosphorylation. This study provides the first evidence of an ultrasensitive mechanism regulating influenza virus-induced inflammation in whole lungs and provides insight into how different virus strains can induce distinct temporal inflammation response profiles. The approach developed here should facilitate the construction of gene regulatory models of other infectious diseases.

Software for systems biology: from tools to integrated platforms.

Understanding complex biological systems requires extensive support from software tools. Such tools are needed at each step of a systems biology computational workflow, which typically consists of data handling, network inference, deep curation, dynamical simulation and model analysis. In addition, there are now efforts to develop integrated software platforms, so that tools that are used at different stages of the workflow and by different researchers can easily be used together. This Review describes the types of software tools that are required at different stages of systems biology research and the current options that are available for systems biology researchers. We also discuss the challenges and prospects for modelling the effects of genetic changes on physiology and the concept of an integrated platform.

Disease severity is associated with differential gene expression at the early and late phases of infection in nonhuman primates infected with different H5N1 highly pathogenic avian influenza viruses.

UNLABELLED: Occasional transmission of highly pathogenic avian H5N1 influenza viruses to humans causes severe pneumonia with high mortality. To better understand the mechanisms via which H5N1 viruses induce severe disease in humans, we infected cynomolgus macaques with six different H5N1 strains isolated from human patients and compared their pathogenicity and the global host responses to the virus infection. Although all H5N1 viruses replicated in the respiratory tract, there was substantial heterogeneity in their replicative ability and in the disease severity induced, which ranged from asymptomatic to fatal. A comparison of global gene expression between severe and mild disease cases indicated that interferon-induced upregulation of genes related to innate immunity, apoptosis, and antigen processing/presentation in the early phase of infection was limited in severe disease cases, although interferon expression was upregulated in both severe and mild cases. Furthermore, coexpression analysis of microarray data, which reveals the dynamics of host responses during the infection, demonstrated that the limited expression of these genes early in infection led to a failure to suppress virus replication and to the hyperinduction of genes related to immunity, inflammation, coagulation, and homeostasis in the late phase of infection, resulting in a more severe disease. Our data suggest that the attenuated interferon-induced activation of innate immunity, apoptosis, and antigen presentation in the early phase of H5N1 virus infection leads to subsequent severe disease outcome. IMPORTANCE: Highly pathogenic avian H5N1 influenza viruses sometimes transmit to humans and cause severe pneumonia with ca. 60% lethality. The continued circulation of these viruses poses a pandemic threat; however, their pathogenesis in mammals is not fully understood. We, therefore, investigated the pathogenicity of six H5N1 viruses and compared the host responses of cynomolgus macaques to the virus infection. We identified differences in the viral replicative ability of and in disease severity caused by these H5N1 viruses. A comparison of global host responses between severe and mild disease cases identified the limited upregulation of interferon-stimulated genes early in infection in severe cases. The dynamics of the host responses indicated that the limited response early in infection failed to suppress virus replication and led to hyperinduction of pathological condition-related genes late in infection. These findings provide insight into the pathogenesis of H5N1 viruses in mammals.

Adding protein context to the human protein-protein interaction network to reveal meaningful interactions.

Interactions of proteins regulate signaling, catalysis, gene expression and many other cellular functions. Therefore, characterizing the entire human interactome is a key effort in current proteomics research. This challenge is complicated by the dynamic nature of protein-protein interactions (PPIs), which are conditional on the cellular context: both interacting proteins must be expressed in the same cell and localized in the same organelle to meet. Additionally, interactions underlie a delicate control of signaling pathways, e.g. by post-translational modifications of the protein partners - hence, many diseases are caused by the perturbation of these mechanisms. Despite the high degree of cell-state specificity of PPIs, many interactions are measured under artificial conditions (e.g. yeast cells are transfected with human genes in yeast two-hybrid assays) or even if detected in a physiological context, this information is missing from the common PPI databases. To overcome these problems, we developed a method that assigns context information to PPIs inferred from various attributes of the interacting proteins: gene expression, functional and disease annotations, and inferred pathways. We demonstrate that context consistency correlates with the experimental reliability of PPIs, which allows us to generate high-confidence tissue- and function-specific subnetworks. We illustrate how these context-filtered networks are enriched in bona fide pathways and disease proteins to prove the ability of context-filters to highlight meaningful interactions with respect to various biological questions. We use this approach to study the lung-specific pathways used by the influenza virus, pointing to IRAK1, BHLHE40 and TOLLIP as potential regulators of influenza virus pathogenicity, and to study the signalling pathways that play a role in Alzheimer's disease, identifying a pathway involving the altered phosphorylation of the Tau protein. Finally, we provide the annotated human PPI network via a web frontend that allows the construction of context-specific networks in several ways.

Software support for SBGN maps: SBGN-ML and LibSBGN.

MOTIVATION: LibSBGN is a software library for reading, writing and manipulating Systems Biology Graphical Notation (SBGN) maps stored using the recently developed SBGN-ML file format. The library (available in C++ and Java) makes it easy for developers to add SBGN support to their tools, whereas the file format facilitates the exchange of maps between compatible software applications. The library also supports validation of maps, which simplifies the task of ensuring compliance with the detailed SBGN specifications. With this effort we hope to increase the adoption of SBGN in bioinformatics tools, ultimately enabling more researchers to visualize biological knowledge in a precise and unambiguous manner. AVAILABILITY AND IMPLEMENTATION: Milestone 2 was released in December 2011. Source code, example files and binaries are freely available under the terms of either the LGPL v2.1+ or Apache v2.0 open source licenses from http://libsbgn.sourceforge.net. CONTACT: sbgn-libsbgn@lists.sourceforge.net.

Toward an integrated software platform for systems pharmacology.

Understanding complex biological systems requires the extensive support of computational tools. This is particularly true for systems pharmacology, which aims to understand the action of drugs and their interactions in a systems context. Computational models play an important role as they can be viewed as an explicit representation of biological hypotheses to be tested. A series of software and data resources are used for model development, verification and exploration of the possible behaviors of biological systems using the model that may not be possible or not cost effective by experiments. Software platforms play a dominant role in creativity and productivity support and have transformed many industries, techniques that can be applied to biology as well. Establishing an integrated software platform will be the next important step in the field.

Asking the right questions for mutagenicity prediction from BioMedical text.

Assessing the mutagenicity of chemicals is an essential task in the drug development process. Usually, databases and other structured sources for AMES mutagenicity exist, which have been carefully and laboriously curated from scientific publications. As knowledge accumulates over time, updating these databases is always an overhead and impractical. In this paper, we first propose the problem of predicting the mutagenicity of chemicals from textual information in scientific publications. More simply, given a chemical and evidence in the natural language form from publications where the mutagenicity of the chemical is described, the goal of the model/algorithm is to predict if it is potentially mutagenic or not. For this, we first construct a golden standard data set and then propose MutaPredBERT, a prediction model fine-tuned on BioLinkBERT based on a question-answering formulation of the problem. We leverage transfer learning and use the help of large transformer-based models to achieve a Macro F1 score of >0.88 even with relatively small data for fine-tuning. Our work establishes the utility of large language models for the construction of structured sources of knowledge bases directly from scientific publications.

Genetic characterization of a novel organoid from human malignant giant-cell tumor.

Malignant giant-cell tumors are extremely rare bone sarcomas that transform from conventional giant-cell tumors during long periods of treatment. Owing to their rarity, no further analysis of their molecular pathogenesis exists, and thus, no standard treatment has been established. Recently, organoid culture methods have been highlighted for recapturing the tumor microenvironment, and we have applied the culture methods and succeeded in establishing patient-derived organoids (PDO) of rare sarcomas. This study aimed to investigate the genomic characteristics of our established novel organoids from human malignant giant-cell tumors. At our institute, we treated a patient with malignant giant-cell tumor. The remaining sarcoma specimens after surgical resection were cultured according to the air-liquid interface organoid-culture method. Organoids were xenografted into NOD-scid IL2Rgnull mice. The developed tumors were histologically and genomically analyzed to compare their characteristics with those of the original tumors. Genetic changes over time throughout treatment were analyzed, and the genomic status of the established organoid was confirmed. Organoids from malignant giant-cell tumors could be serially maintained using air-liquid interface organoid-culture methods. The tumors developed in xenografted NOD-scid IL2Rgnull mice. After several repetitions of the process, a patient-derived organoid line from the malignant giant-cell tumor was established. Immunohistochemical analyses and next-generation sequencing revealed that the established organoids lacked the H3-3A G34W mutation. The xenografted organoids of the malignant giant-cell tumor had phenotypes histologically and genetically similar to those of the original tumor. The established organoids were confirmed to be derived from human malignant giant-cell tumors. In summary, the present study demonstrated a novel organoid model of a malignant giant-cell tumor that was genetically confirmed to be a malignant transformed tumor. Our organoid model could be used to elucidate the molecular pathogenesis of a malignant giant-cell tumor and develop novel treatment modalities.

CTen: a web-based platform for identifying enriched cell types from heterogeneous microarray data.

BACKGROUND: Interpreting in vivo sampled microarray data is often complicated by changes in the cell population demographics. To put gene expression into its proper biological context, it is necessary to distinguish differential gene transcription from artificial gene expression induced by changes in the cellular demographics. RESULTS: CTen (cell type enrichment) is a web-based analytical tool which uses our highly expressed, cell specific (HECS) gene database to identify enriched cell types in heterogeneous microarray data. The web interface is designed for differential expression and gene clustering studies, and the enrichment results are presented as heatmaps or downloadable text files. CONCLUSIONS: In this work, we use an independent, cell-specific gene expression data set to assess CTen's performance in accurately identifying the appropriate cell type and provide insight into the suggested level of enrichment to optimally minimize the number of false discoveries. We show that CTen, when applied to microarray data developed from infected lung tissue, can correctly identify the cell signatures of key lymphocytes in a highly heterogeneous environment and compare its performance to another popular bioinformatics tool. Furthermore, we discuss the strong implications cell type enrichment has in the design of effective microarray workflow strategies and show that, by combining CTen with gene expression clustering, we may be able to determine the relative changes in the number of key cell types.CTen is available at http://www.influenza-x.org/~jshoemaker/cten/

BioPAX support in CellDesigner.

MOTIVATION: BioPAX is a standard language for representing and exchanging models of biological processes at the molecular and cellular levels. It is widely used by different pathway databases and genomics data analysis software. Currently, the primary source of BioPAX data is direct exports from the curated pathway databases. It is still uncommon for wet-lab biologists to share and exchange pathway knowledge using BioPAX. Instead, pathways are usually represented as informal diagrams in the literature. In order to encourage formal representation of pathways, we describe a software package that allows users to create pathway diagrams using CellDesigner, a user-friendly graphical pathway-editing tool and save the pathway data in BioPAX Level 3 format. AVAILABILITY: The plug-in is freely available and can be downloaded at ftp://ftp.pantherdb.org/CellDesigner/plugins/BioPAX/ CONTACT: huaiyumi@usc.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Tissue-specific subnetworks and characteristics of publicly available human protein interaction databases.

MOTIVATION: Protein-protein interaction (PPI) databases are widely used tools to study cellular pathways and networks; however, there are several databases available that still do not account for cell type-specific differences. Here, we evaluated the characteristics of six interaction databases, incorporated tissue-specific gene expression information and finally, investigated if the most popular proteins of scientific literature are involved in good quality interactions. RESULTS: We found that the evaluated databases are comparable in terms of node connectivity (i.e. proteins with few interaction partners also have few interaction partners in other databases), but may differ in the identity of interaction partners. We also observed that the incorporation of tissue-specific expression information significantly altered the interaction landscape and finally, we demonstrated that many of the most intensively studied proteins are engaged in interactions associated with low confidence scores. In summary, interaction databases are valuable research tools but may lead to different predictions on interactions or pathways. The accuracy of predictions can be improved by incorporating datasets on organ- and cell type-specific gene expression, and by obtaining additional interaction evidence for the most 'popular' proteins. CONTACT: kitano@sbi.jp SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Establishment of Organoids From Human Epithelioid Sarcoma With the Air-Liquid Interface Organoid Cultures.

Background: Although biological resources are essential for basic and preclinical research in the oncological field, those of sarcoma are not sufficient for rapid development of the treatment. So far, some sarcoma cell lines have been established, however, the success rate was low and the established sarcoma types were frequently biased. Therefore, an efficient culture method is needed to determine the various types of sarcomas. Organoid culture is a 3-dimentional culture method that enables the recapitulation of the tumor microenvironment and the success rate reported is higher than the 2-dimentional culture. The purpose of this study was to report our newly established organoids from human epithelioid sarcoma using the air-liquid interface organoid culture method. Methods: We treated 2 patients with epithelioid sarcoma in our institute. The remaining sarcoma specimens after surgical resection were embedded in collagen type 1 gels according to the air-liquid interface organoid culture method. After serial passages, we xenografted the organoids to NOD-scid IL2Rgnull (NSG) mice. Using the developed tumors, we performed histological and genomic analyses to compare the similarities and differences with the original epithelioid sarcoma from the patient. Results: Organoids from the epithelioid sarcoma could be serially cultured and maintained in collagen type 1 gels for more than 3 passages. Developed orthotopic tumor xenografts were detected in the NSG mice. After the process was repeated severally, the patient derived organoid lines from the epithelioid sarcoma were established. The established organoids showed loss of integrase interactor 1 expression with polymerase chain reaction and immunohistochemical analyses. The xenografted organoids of the epithelioid sarcoma had histologically similar phenotypes with the original tumor and genetically resembled it to some degree. Conclusions: The present study demonstrated 2 novel established organoid models of epithelioid sarcoma, and our organoid models could be used to investigate the molecular pathogenesis and develop a novel treatment.

Payao: a community platform for SBML pathway model curation.

SUMMARY: Payao is a community-based, collaborative web service platform for gene-regulatory and biochemical pathway model curation. The system combines Web 2.0 technologies and online model visualization functions to enable a collaborative community to annotate and curate biological models. Payao reads the models in Systems Biology Markup Language format, displays them with CellDesigner, a process diagram editor, which complies with the Systems Biology Graphical Notation, and provides an interface for model enrichment (adding tags and comments to the models) for the access-controlled community members. AVAILABILITY AND IMPLEMENTATION: Freely available for model curation service at http://www.payaologue.org. Web site implemented in Seaser Framework 2.0 with S2Flex2, MySQL 5.0 and Tomcat 5.5, with all major browsers supported. CONTACT: kitano@sbi.jp

PathText: a text mining integrator for biological pathway visualizations.

MOTIVATION: Metabolic and signaling pathways are an increasingly important part of organizing knowledge in systems biology. They serve to integrate collective interpretations of facts scattered throughout literature. Biologists construct a pathway by reading a large number of articles and interpreting them as a consistent network, but most of the models constructed currently lack direct links to those articles. Biologists who want to check the original articles have to spend substantial amounts of time to collect relevant articles and identify the sections relevant to the pathway. Furthermore, with the scientific literature expanding by several thousand papers per week, keeping a model relevant requires a continuous curation effort. In this article, we present a system designed to integrate a pathway visualizer, text mining systems and annotation tools into a seamless environment. This will enable biologists to freely move between parts of a pathway and relevant sections of articles, as well as identify relevant papers from large text bases. The system, PathText, is developed by Systems Biology Institute, Okinawa Institute of Science and Technology, National Centre for Text Mining (University of Manchester) and the University of Tokyo, and is being used by groups of biologists from these locations.

A comprehensive molecular interaction map of the budding yeast cell cycle.

With the accumulation of data on complex molecular machineries coordinating cell-cycle dynamics, coupled with its central function in disease patho-physiologies, it is becoming increasingly important to collate the disparate knowledge sources into a comprehensive molecular network amenable to systems-level analyses. In this work, we present a comprehensive map of the budding yeast cell-cycle, curating reactions from ∼600 original papers. Toward leveraging the map as a framework to explore the underlying network architecture, we abstract the molecular components into three planes--signaling, cell-cycle core and structural planes. The planar view together with topological analyses facilitates network-centric identification of functions and control mechanisms. Further, we perform a comparative motif analysis to identify around 194 motifs including feed-forward, mutual inhibitory and feedback mechanisms contributing to cell-cycle robustness. We envisage the open access, comprehensive cell-cycle map to open roads toward community-based deeper understanding of cell-cycle dynamics.

A comprehensive map of the mTOR signaling network.

The mammalian target of rapamycin (mTOR) is a central regulator of cell growth and proliferation. mTOR signaling is frequently dysregulated in oncogenic cells, and thus an attractive target for anticancer therapy. Using CellDesigner, a modeling support software for graphical notation, we present herein a comprehensive map of the mTOR signaling network, which includes 964 species connected by 777 reactions. The map complies with both the systems biology markup language (SBML) and graphical notation (SBGN) for computational analysis and graphical representation, respectively. As captured in the mTOR map, we review and discuss our current understanding of the mTOR signaling network and highlight the impact of mTOR feedback and crosstalk regulations on drug-based cancer therapy. This map is available on the Payao platform, a Web 2.0 based community-wide interactive process for creating more accurate and information-rich databases. Thus, this comprehensive map of the mTOR network will serve as a tool to facilitate systems-level study of up-to-date mTOR network components and signaling events toward the discovery of novel regulatory processes and therapeutic strategies for cancer.

LimeMap: a comprehensive map of lipid mediator metabolic pathways.

Lipid mediators are major factors in multiple biological functions and are strongly associated with disease. Recent lipidomics approaches have made it possible to analyze multiple metabolites and the associations of individual lipid mediators. Such systematic approaches have enabled us to identify key changes of biological relevance. Against this background, a knowledge-based pathway map of lipid mediators would be useful to visualize and understand the overall interactions of these factors. Here, we have built a precise map of lipid mediator metabolic pathways (LimeMap) to visualize the comprehensive profiles of lipid mediators that change dynamically in various disorders. We constructed the map by focusing on ω-3 and ω-6 fatty acid metabolites and their respective metabolic pathways, with manual curation of referenced information from public databases and relevant studies. Ultimately, LimeMap comprises 282 factors (222 mediators, and 60 enzymes, receptors, and ion channels) and 279 reactions derived from 102 related studies. Users will be able to modify the map and visualize measured data specific to their purposes using CellDesigner and VANTED software. We expect that LimeMap will contribute to elucidating the comprehensive functional relationships and pathways of lipid mediators.