SUMMARY: Knowledge graphs are increasingly being used to integrate heterogeneous biomedical knowledge and data. General-purpose graph database management systems such as Neo4j are often used to host and search knowledge graphs, but such tools come with overhead and leave biomedical-specific standards compliance and reasoning to the user. Interoperability across biomedical knowledge bases and reasoning systems necessitates the use of standards such as those adopted by the Biomedical Data Translator consortium. We present PloverDB, a comprehensive software platform for hosting and efficiently serving biomedical knowledge graphs as standards-compliant web application programming interfaces. In addition to fundamental back-end knowledge reasoning tasks, PloverDB automatically handles entity resolution, exposure of standardized metadata and test data, and multiplexing of knowledge graphs, all in a single platform designed specifically for efficient query answering and ease of deployment. PloverDB increases data accessibility and utility by allowing data providers to quickly serve their biomedical knowledge graphs as standards-compliant web services. AVAILABILITY AND IMPLEMENTATION: PloverDB's source code and technical documentation are publicly available under an MIT License at github:RTXteam/PloverDB, archived on Zenodo at doi:10.5281/zenodo.15454600.

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.

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 .

Supervised and Unsupervised ML algorithms are widely used over graphs. They use the structural properties of the data to deliver effective results. It is known that the same information can be represented under various graph structures. Thus, these algorithms may be effective on some structural variations of the data and ineffective on others. One would like to have an algorithm that is effective and generalizes to all structural variations of a data graph. We define the concept of structural generalizability for algorithms over graphs. We focus on the problem of similarity search, which is a popular task and the building block of many ML algorithms on graphs, and propose a structurally generalizable similarity search algorithm. As this algorithm may require users to specify features in a rather complex language, we modify this algorithm so that it requires only simple guidance from the user. Our extensive empirical study show that our algorithms are structurally generalizable while being efficient and more effective than current algorithms.

BACKGROUND: Multiple studies have shown the utility of transcriptome-wide RNA-seq profiles as features for machine learning-based prediction of response to chemotherapy in cancer. While tumor transcriptome profiles are publicly available for thousands of tumors for many cancer types, a relatively modest number of tumor profiles are clinically annotated for response to chemotherapy. The paucity of labeled examples and the high dimension of the feature data limit performance for predicting therapeutic response using fully-supervised classification methods. Recently, multiple studies have established the utility of a deep neural network approach, the variational autoencoder (VAE), for generating meaningful latent features from original data. Here, we report the first study of a semi-supervised approach using VAE-encoded tumor transcriptome features and regularized gradient boosted decision trees (XGBoost) to predict chemotherapy drug response for five cancer types: colon, pancreatic, bladder, breast, and sarcoma. RESULTS: We found: (1) VAE-encoding of the tumor transcriptome preserves the cancer type identity of the tumor, suggesting preservation of biologically relevant information; and (2) as a feature-set for supervised classification to predict response-to-chemotherapy, the unsupervised VAE encoding of the tumor's gene expression profile leads to better area under the receiver operating characteristic curve and area under the precision-recall curve classification performance than the original gene expression profile or the PCA principal components or the ICA components of the gene expression profile, in four out of five cancer types that we tested. CONCLUSIONS: Given high-dimensional "omics" data, the VAE is a powerful tool for obtaining a nonlinear low-dimensional embedding; it yields features that retain biological patterns that distinguish between different types of cancer and that enable more accurate tumor transcriptome-based prediction of response to chemotherapy than would be possible using the original data or their principal components.

BACKGROUND: We previously reported on CERENKOV, an approach for identifying regulatory single nucleotide polymorphisms (rSNPs) that is based on 246 annotation features. CERENKOV uses the xgboost classifier and is designed to be used to find causal noncoding SNPs in loci identified by genome-wide association studies (GWAS). We reported that CERENKOV has state-of-the-art performance (by two traditional measures and a novel GWAS-oriented measure, AVGRANK) in a comparison to nine other tools for identifying functional noncoding SNPs, using a comprehensive reference SNP set (OSU17, 15,331 SNPs). Given that SNPs are grouped within loci in the reference SNP set and given the importance of the data-space manifold geometry for machine-learning model selection, we hypothesized that within-locus inter-SNP distances would have class-based distributional biases that could be exploited to improve rSNP recognition accuracy. We thus defined an intralocus SNP "radius" as the average data-space distance from a SNP to the other intralocus neighbors, and explored radius likelihoods for five distance measures. RESULTS: We expanded the set of reference SNPs to 39,083 (the OSU18 set) and extracted CERENKOV SNP feature data. We computed radius empirical likelihoods and likelihood densities for rSNPs and control SNPs, and found significant likelihood differences between rSNPs and control SNPs. We fit parametric models of likelihood distributions for five different distance measures to obtain ten log-likelihood features that we combined with the 248-dimensional CERENKOV feature matrix. On the OSU18 SNP set, we measured the classification accuracy of CERENKOV with and without the new distance-based features, and found that the addition of distance-based features significantly improves rSNP recognition performance as measured by AUPVR, AUROC, and AVGRANK. Along with feature data for the OSU18 set, the software code for extracting the base feature matrix, estimating ten distance-based likelihood ratio features, and scoring candidate causal SNPs, are released as open-source software CERENKOV2. CONCLUSIONS: Accounting for the locus-specific geometry of SNPs in data-space significantly improved the accuracy with which noncoding rSNPs can be computationally identified.

MOTIVATION: The position-weight matrix (PWM) is a useful representation of a transcription factor binding site (TFBS) sequence pattern because the PWM can be estimated from a small number of representative TFBS sequences. However, because the PWM probability model assumes independence between individual nucleotide positions, the PWMs for some TFs poorly discriminate binding sites from non-binding-sites that have similar sequence content. Since the local three-dimensional DNA structure ('shape') is a determinant of TF binding specificity and since DNA shape has a significant sequence-dependence, we combined DNA shape-derived features into a TF-generalized regulatory score and tested whether the score could improve PWM-based discrimination of TFBS from non-binding-sites. RESULTS: We compared a traditional PWM model to a model that combines the PWM with a DNA shape feature-based regulatory potential score, for accuracy in detecting binding sites for 75 vertebrate transcription factors. The PWM+shape model was more accurate than the PWM-only model, for 45% of TFs tested, with no significant loss of accuracy for the remaining TFs. AVAILABILITY AND IMPLEMENTATION: The shape-based model is available as an open-source R package at that is archived on the GitHub software repository at https://github.com/ramseylab/regshape/. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Histone acetylation (HAc) is associated with open chromatin, and HAc has been shown to facilitate transcription factor (TF) binding in mammalian cells. In the innate immune system context, epigenetic studies strongly implicate HAc in the transcriptional response of activated macrophages. We hypothesized that using data from large-scale sequencing of a HAc chromatin immunoprecipitation assay (ChIP-Seq) would improve the performance of computational prediction of binding locations of TFs mediating the response to a signaling event, namely, macrophage activation. RESULTS: We tested this hypothesis using a multi-evidence approach for predicting binding sites. As a training/test dataset, we used ChIP-Seq-derived TF binding site locations for five TFs in activated murine macrophages. Our model combined TF binding site motif scanning with evidence from sequence-based sources and from HAc ChIP-Seq data, using a weighted sum of thresholded scores. We find that using HAc data significantly improves the performance of motif-based TF binding site prediction. Furthermore, we find that within regions of high HAc, local minima of the HAc ChIP-Seq signal are particularly strongly correlated with TF binding locations. Our model, using motif scanning and HAc local minima, improves the sensitivity for TF binding site prediction by approximately 50% over a model based on motif scanning alone, at a false positive rate cutoff of 0.01. AVAILABILITY: The data and software source code for model training and validation are freely available online at http://magnet.systemsbiology.net/hac.

BACKGROUND: High throughput sequencing has become an increasingly important tool for biological research. However, the existing software systems for managing and processing these data have not provided the flexible infrastructure that research requires. RESULTS: Existing software solutions provide static and well-established algorithms in a restrictive package. However as high throughput sequencing is a rapidly evolving field, such static approaches lack the ability to readily adopt the latest advances and techniques which are often required by researchers. We have used a loosely coupled, service-oriented infrastructure to develop SeqAdapt. This system streamlines data management and allows for rapid integration of novel algorithms. Our approach also allows computational biologists to focus on developing and applying new methods instead of writing boilerplate infrastructure code. CONCLUSION: The system is based around the Addama service architecture and is available at our website as a demonstration web application, an installable single download and as a collection of individual customizable services.

Macrophages are versatile immune cells that can detect a variety of pathogen-associated molecular patterns through their Toll-like receptors (TLRs). In response to microbial challenge, the TLR-stimulated macrophage undergoes an activation program controlled by a dynamically inducible transcriptional regulatory network. Mapping a complex mammalian transcriptional network poses significant challenges and requires the integration of multiple experimental data types. In this work, we inferred a transcriptional network underlying TLR-stimulated murine macrophage activation. Microarray-based expression profiling and transcription factor binding site motif scanning were used to infer a network of associations between transcription factor genes and clusters of co-expressed target genes. The time-lagged correlation was used to analyze temporal expression data in order to identify potential causal influences in the network. A novel statistical test was developed to assess the significance of the time-lagged correlation. Several associations in the resulting inferred network were validated using targeted ChIP-on-chip experiments. The network incorporates known regulators and gives insight into the transcriptional control of macrophage activation. Our analysis identified a novel regulator (TGIF1) that may have a role in macrophage activation.