ARAX: a graph-based modular reasoning tool for translational biomedicine.

MOTIVATION: With the rapidly growing volume of knowledge and data in biomedical databases, improved methods for knowledge-graph-based computational reasoning are needed in order to answer translational questions. Previous efforts to solve such challenging computational reasoning problems have contributed tools and approaches, but progress has been hindered by the lack of an expressive analysis workflow language for translational reasoning and by the lack of a reasoning engine-supporting that language-that federates semantically integrated knowledge-bases. RESULTS: We introduce ARAX, a new reasoning system for translational biomedicine that provides a web browser user interface and an application programming interface (API). ARAX enables users to encode translational biomedical questions and to integrate knowledge across sources to answer the user's query and facilitate exploration of results. For ARAX, we developed new approaches to query planning, knowledge-gathering, reasoning and result ranking and dynamically integrate knowledge providers for answering biomedical questions. To illustrate ARAX's application and utility in specific disease contexts, we present several use-case examples. AVAILABILITY AND IMPLEMENTATION: The source code and technical documentation for building the ARAX server-side software and its built-in knowledge database are freely available online (https://github.com/RTXteam/RTX). We provide a hosted ARAX service with a web browser interface at arax.rtx.ai and a web API endpoint at arax.rtx.ai/api/arax/v1.3/ui/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

RTX-KG2: a system for building a semantically standardized knowledge graph for translational biomedicine.

BACKGROUND: Biomedical translational science is increasingly using computational reasoning on repositories of structured knowledge (such as UMLS, SemMedDB, ChEMBL, Reactome, DrugBank, and SMPDB in order to facilitate discovery of new therapeutic targets and modalities. The NCATS Biomedical Data Translator project is working to federate autonomous reasoning agents and knowledge providers within a distributed system for answering translational questions. Within that project and the broader field, there is a need for a framework that can efficiently and reproducibly build an integrated, standards-compliant, and comprehensive biomedical knowledge graph that can be downloaded in standard serialized form or queried via a public application programming interface (API). RESULTS: To create a knowledge provider system within the Translator project, we have developed RTX-KG2, an open-source software system for building-and hosting a web API for querying-a biomedical knowledge graph that uses an Extract-Transform-Load approach to integrate 70 knowledge sources (including the aforementioned core six sources) into a knowledge graph with provenance information including (where available) citations. The semantic layer and schema for RTX-KG2 follow the standard Biolink model to maximize interoperability. RTX-KG2 is currently being used by multiple Translator reasoning agents, both in its downloadable form and via its SmartAPI-registered interface. Serializations of RTX-KG2 are available for download in both the pre-canonicalized form and in canonicalized form (in which synonyms are merged). The current canonicalized version (KG2.7.3) of RTX-KG2 contains 6.4M nodes and 39.3M edges with a hierarchy of 77 relationship types from Biolink. CONCLUSION: RTX-KG2 is the first knowledge graph that integrates UMLS, SemMedDB, ChEMBL, DrugBank, Reactome, SMPDB, and 64 additional knowledge sources within a knowledge graph that conforms to the Biolink standard for its semantic layer and schema. RTX-KG2 is publicly available for querying via its API at arax.rtx.ai/api/rtxkg2/v1.2/openapi.json . The code to build RTX-KG2 is publicly available at github:RTXteam/RTX-KG2 .

Evaluating robustness of a generalized linear model when applied to electronic health record data accessed using an Open API.

The Integrated Clinical and Environmental Exposures Service (ICEES) provides open regulatory-compliant access to clinical data, including electronic health record data, that have been integrated with environmental exposures data. While ICEES has been validated in the context of an asthma use case and several other use cases, the regulatory constraints on the ICEES open application programming interface (OpenAPI) result in data loss when using the service for multivariate analysis. In this study, we investigated the robustness of the ICEES OpenAPI through a comparative analysis, in which we applied a generalized linear model (GLM) to the OpenAPI data and the constraint-free source data to examine factors predictive of asthma exacerbations. Consistent with previous studies, we found that the main predictors identified by both analyses were sex, prednisone, race, obesity, and airborne particulate exposure. Comparison of GLM model fit revealed that data loss impacts model quality, but only with select interaction terms. We conclude that the ICEES OpenAPI supports multivariate analysis, albeit with potential data loss that users should be aware of.

Voting-based integration algorithm improves causal network learning from interventional and observational data: An application to cell signaling network inference.

In order to increase statistical power for learning a causal network, data are often pooled from multiple observational and interventional experiments. However, if the direct effects of interventions are uncertain, multi-experiment data pooling can result in false causal discoveries. We present a new method, "Learn and Vote," for inferring causal interactions from multi-experiment datasets. In our method, experiment-specific networks are learned from the data and then combined by weighted averaging to construct a consensus network. Through empirical studies on synthetic and real-world datasets, we found that for most of the larger-sized network datasets that we analyzed, our method is more accurate than state-of-the-art network inference approaches.

An approach for open multivariate analysis of integrated clinical and environmental exposures data.

The Integrated Clinical and Environmental Exposures Service (ICEES) provides regulatory-compliant open access to sensitive patient data that have been integrated with public exposures data. ICEES was designed initially to support dynamic cohort creation and bivariate contingency tests. The objective of the present study was to develop an open approach to support multivariate analyses using existing ICEES functionalities and abiding by all regulatory constraints. We first developed an open approach for generating a multivariate table that maintains contingencies between clinical and environmental variables using programmatic calls to the open ICEES application programming interface. We then applied the approach to data on a large cohort (N = 22,365) of patients with asthma or related conditions and generated an eight-feature table. Due to regulatory constraints, data loss was incurred with the incorporation of each successive feature variable, from a starting sample size of N = 22,365 to a final sample size of N = 4,556 (20.4%), but data loss was < 10% until the addition of the final two feature variables. We then applied a generalized linear model to the subsequent dataset and focused on the impact of seven select feature variables on asthma exacerbations, defined as annual emergency department or inpatient visits for respiratory issues. We identified five feature variables-sex, race, obesity, prednisone, and airborne particulate exposure-as significant predictors of asthma exacerbations. We discuss the advantages and disadvantages of ICEES open multivariate analysis and conclude that, despite limitations, ICEES can provide a valuable resource for open multivariate analysis and can serve as an exemplar for regulatory-compliant informatic solutions to open patient data, with capabilities to explore the impact of environmental exposures on health outcomes.

Open Application of Statistical and Machine Learning Models to Explore the Impact of Environmental Exposures on Health and Disease: An Asthma Use Case.

ICEES (Integrated Clinical and Environmental Exposures Service) provides a disease-agnostic, regulatory-compliant approach for openly exposing and analyzing clinical data that have been integrated at the patient level with environmental exposures data. ICEES is equipped with basic features to support exploratory analysis using statistical approaches, such as bivariate chi-square tests. We recently developed a method for using ICEES to generate multivariate tables for subsequent application of machine learning and statistical models. The objective of the present study was to use this approach to identify predictors of asthma exacerbations through the application of three multivariate methods: conditional random forest, conditional tree, and generalized linear model. Among seven potential predictor variables, we found five to be of significant importance using both conditional random forest and conditional tree: prednisone, race, airborne particulate exposure, obesity, and sex. The conditional tree method additionally identified several significant two-way and three-way interactions among the same variables. When we applied a generalized linear model, we identified four significant predictor variables, namely prednisone, race, airborne particulate exposure, and obesity. When ranked in order by effect size, the results were in agreement with the results from the conditional random forest and conditional tree methods as well as the published literature. Our results suggest that the open multivariate analytic capabilities provided by ICEES are valid in the context of an asthma use case and likely will have broad value in advancing open research in environmental and public health.