Knowledge-Enhanced Graph Attention Network for Fact Verification

Fact verification aims to evaluate the authenticity of a given claim based on the evidence sentences retrieved from Wikipedia articles. Existing works mainly leverage the natural language inference methods to model the semantic interaction of claim and evidence, or further employ the graph structure to capture the relation features between multiple evidences. However, previous methods have limited representation ability in encoding complicated units of claim and evidences, and thus cannot support sophisticated reasoning. In addition, a limited amount of supervisory signals lead to the graph encoder could not distinguish the distinctions of different graph structures and weaken the encoding ability. To address the above issues, we propose a Knowledge-Enhanced Graph Attention network (KEGA) for fact verification, which introduces a knowledge integration module to enhance the representation of claims and evidences by incorporating external knowledge. Moreover, KEGA leverages an auxiliary loss based on contrastive learning to fine-tune the graph attention encoder and learn the discriminative features for the evidence graph. Comprehensive experiments conducted on FEVER, a large-scale benchmark dataset for fact verification, demonstrate the superiority of our proposal in both the multi-evidences and single-evidence scenarios. In addition, our findings show that the background knowledge for words can effectively improve the model performance.

FAIRSCAPE: a Framework for FAIR and Reproducible Biomedical Analytics

Results of computational analyses require transparent disclosure of their supporting resources, while the analyses themselves often can be very large scale and involve multiple processing steps separated in time. Evidence for the correctness of any analysis should include not only a textual description, but also a formal record of the computations which produced the result, including accessible data and software with runtime parameters, environment, and personnel involved. This article describes FAIRSCAPE, a reusable computational framework, enabling simplified access to modern scalable cloud-based components. FAIRSCAPE fully implements the FAIR data principles and extends them to provide fully FAIR Evidence, including machine-interpretable provenance of datasets, software and computations, as metadata for all computed results. The FAIRSCAPE microservices framework creates a complete Evidence Graph for every computational result, including persistent identifiers with metadata, resolvable to the software, computations, and datasets used in the computation; and stores a URI to the root of the graph in the result’s metadata. An ontology for Evidence Graphs, EVI (https://w3id.org/EVI), supports inferential reasoning over the evidence. FAIRSCAPE can run nested or disjoint workflows and preserves provenance across them. It can run Apache Spark jobs, scripts, workflows, or user-supplied containers. All objects are assigned persistent IDs, including software. All results are annotated with FAIR metadata using the evidence graph model for access, validation, reproducibility, and re-use of archived data and software.

Evidence Graphs: Supporting Transparent and FAIR Computation, with Defeasible Reasoning on Data, Methods and Results

Introduction: Transparency of computation is a requirement for assessing the validity of computed results and research claims based upon them; and it is essential for access to, assessment, and reuse of computational components. These components may be subject to methodological or other challenges over time. While reference to archived software and/or data is increasingly common in publications, a single machine-interpretable, integrative representation of how results were derived, that supports defeasible reasoning, has been absent. Methods: We developed the Evidence Graph Ontology, EVI, in OWL 2, with a set of inference rules, to provide deep representations of supporting and challenging evidence for computations, services, software, data, and results, across arbitrarily deep networks of computations, in connected or fully distinct processes. EVI integrates FAIR practices on data and software, with important concepts from provenance models, and argumentation theory. It extends PROV for additional expressiveness, with support for defeasible reasoning. EVI treats any com- putational result or component of evidence as a defeasible assertion, supported by a DAG of the computations, software, data, and agents that produced it. Results: We have successfully deployed EVI for very-large-scale predictive analytics on clinical time-series data. Every result may reference its own evidence graph as metadata, which can be extended when subsequent computations are executed. Discussion: Evidence graphs support transparency and defeasible reasoning on results. They are first-class computational objects, and reference the datasets and software from which they are derived. They support fully transparent computation, with challenge and support propagation. The EVI approach may be extended to include instruments, animal models, and critical experimental reagents.

Exploring Integrative Analysis Using the BioMedical Evidence Graph

PURPOSE The analysis of cancer biology data involves extremely heterogeneous data sets, including information from RNA sequencing, genome-wide copy number, DNA methylation data reporting on epigenetic regulation, somatic mutations from whole-exome or whole-genome analyses, pathology estimates from imaging sections or subtyping, drug response or other treatment outcomes, and various other clinical and phenotypic measurements. Bringing these different resources into a common framework, with a data model that allows for complex relationships as well as dense vectors of features, will unlock integrated data set analysis. METHODS We introduce the BioMedical Evidence Graph (BMEG), a graph database and query engine for discovery and analysis of cancer biology. The BMEG is unique from other biologic data graphs in that sample-level molecular and clinical information is connected to reference knowledge bases. It combines gene expression and mutation data with drug-response experiments, pathway information databases, and literature-derived associations. RESULTS The construction of the BMEG has resulted in a graph containing > 41 million vertices and 57 million edges. The BMEG system provides a graph query–based application programming interface to enable analysis, with client code available for Python, Javascript, and R, and a server online at bmeg.io. Using this system, we have demonstrated several forms of cross–data set analysis to show the utility of the system. CONCLUSION The BMEG is an evolving resource dedicated to enabling integrative analysis. We have demonstrated queries on the system that illustrate mutation significance analysis, drug-response machine learning, patient-level knowledge-base queries, and pathway level analysis. We have compared the resulting graph to other available integrated graph systems and demonstrated the former is unique in the scale of the graph and the type of data it makes available.

FAIRSCAPE: A Framework for FAIR and Reproducible Biomedical Analytics

Results of computational analyses require transparent disclosure of their supporting resources, while the analyses themselves often can be very large scale and involve multiple processing steps separated in time. Evidence for the correctness of any analysis consists of accessible data and software with runtime parameters, environment, and personnel involved.Evidence graphs - a derivation of argumentation frameworks adapted to biological science - can provide this disclosure as machine-readable metadata resolvable from persistent identifiers for computationally generated graphs, images, or tables, that can be archived and cited in a publication including a persistent ID.We have built a cloud-based, computational research commons for predictive analytics on biomedical time series datasets with hundreds of algorithms and thousands of computations using a reusable computational framework we call FAIRSCAPE.FAIRSCAPE computes a complete chain of evidence on every result, including software, computations, and datasets. An ontology for Evidence Graphs, EVI (https://w3id.org/EVI), supports inferential reasoning over the evidence. FAIRSCAPE can run nested or disjoint workflows and preserves the provenance graph across them. It can run Apache Spark jobs, scripts, workflows, or user-supplied containers. All objects are assigned persistent IDs, including software. All results are annotated with FAIR metadata using the evidence graph model for access, validation, reproducibility, and re-use of archived data and software.FAIRSCAPE is a reusable computational framework, enabling simplified access to modern scalable cloud-based components. It fully implements the FAIR data principles and extends them to provide FAIR Evidence, including provenance of datasets, software and computations, as metadata for all computed results.

Exploring Integrative Analysis using the BioMedical Evidence Graph

The analysis of cancer biology data involves extremely heterogeneous datasets including information from RNA sequencing, genome-wide copy number, DNA methylation data reporting on epigenomic regulation, somatic mutations from whole-exome or whole-genome analyses, pathology estimates from imaging sections or subtyping, drug response or other treatment outcomes, and various other clinical and phenotypic measurements. Bringing these different resources into a common framework, with a data model that allows for complex relationships as well as dense vectors of features, will unlock integrative analysis. We introduce a graph database and query engine for discovery and analysis of cancer biology, called the BioMedical Evidence Graph (BMEG). The BMEG is unique from other biological data graphs in that sample level molecular information is connected to reference knowledge bases. It combines gene expression and mutation data, with drug response experiments, pathway information databases and literature derived associations. The construction of the BMEG has resulted in a graph containing over 36M vertices and 29M edges. The BMEG system provides a graph query based API to enable analysis, with client code available for Python, Javascript and R, and a server online at bmeg.io. Using this system we have developed several forms of integrated analysis to demonstrate the utility of the system. The BMEG is an evolving resource dedicated to enabling integrative analysis. We have demonstrated queries on the system that illustrate mutation significance analysis, drug response machine learning, patient level knowledge base queries and pathway level analysis. We have compared the resulting graph to other available integrated graph systems, and demonstrated that it is unique in the scale of the graph and the type of data it makes available.HighlightsData resource connected extremely diverse set of cancer data setsGraph query engine that can be easily deployed and used on new datasetsEasily installed python clientServer online at bmeg.ioSummaryThe analysis of cancer biology data involves extremely heterogeneous datasets including information. Bringing these different resources into a common framework, with a data model that allows for complex relationships as well as dense vectors of features, will unlock integrative analysis. We introduce a graph database and query engine for discovery and analysis of cancer biology, called the BioMedical Evidence Graph (BMEG). The construction of the BMEG has resulted in a graph containing over 36M vertices and 29M edges. The BMEG system provides a graph query based API to enable analysis, with client code available for Python, Javascript and R, and a server online at bmeg.io. Using this system we have developed several forms of integrated analysis to demonstrate the utility of the system.