Dataset Information

CLEP: A Hybrid Data- and Knowledge- Driven Framework for Generating Patient Representations.

ABSTRACT: As machine learning and artificial intelligence increasingly attain a larger number of applications in the biomedical domain, at their core, their utility depends on the data used to train them. Due to the complexity and high dimensionality of biomedical data, there is a need for approaches that combine prior knowledge around known biological interactions with patient data. Here, we present CLEP, a novel approach that generates new patient representations by leveraging both prior knowledge and patient-level data. First, given a patient-level dataset and a knowledge graph containing relations across features that can be mapped to the dataset, CLEP incorporates patients into the knowledge graph as new nodes connected to their most characteristic features. Next, CLEP employs knowledge graph embedding models to generate new patient representations that can ultimately be used for a variety of downstream tasks, ranging from clustering to classification. We demonstrate how using new patient representations generated by CLEP significantly improves performance in classifying between patients and healthy controls for a variety of machine learning models, as compared to the use of the original transcriptomics data. Furthermore, we also show how incorporating patients into a knowledge graph can foster the interpretation and identification of biological features characteristic of a specific disease or patient subgroup. Finally, we released CLEP as an open source Python package together with examples and documentation. Availability CLEP is available to the bioinformatics community as an open source Python package at https://github.com/hybrid-kg/clep under the Apache 2.0 License. Supplementary information Supplementary data are available at Bioinformatics online.

SUBMITTER: Srinivas Bharadhwaj V

PROVIDER: S-EPMC8504642 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Hypothesis generation is a critical step in research and a cornerstone in the rare disease field. Research is most efficient when those hypotheses are based on the entirety of knowledge known to date. Systematic review articles are commonly used in biomedicine to summarize existing knowledge and contextualize experimental data. But the information contained within review articles is typically only expressed as free-text, which is difficult to use computationally. Researchers struggle to navigate, collect and remix prior knowledge as it is scattered in several silos without seamless integration and access. This lack of a structured information framework hinders research by both experimental and computational scientists. To better organize knowledge and data, we built a structured review article that is specifically focused on NGLY1 Deficiency, an ultra-rare genetic disease first reported in 2012. We represented this structured review as a knowledge graph and then stored this knowledge graph in a Neo4j database to simplify dissemination, querying and visualization of the network. Relative to free-text, this structured review better promotes the principles of findability, accessibility, interoperability and reusability (FAIR). In collaboration with domain experts in NGLY1 Deficiency, we demonstrate how this resource can improve the efficiency and comprehensiveness of hypothesis generation. We also developed a read-write interface that allows domain experts to contribute FAIR structured knowledge to this community resource. In contrast to traditional free-text review articles, this structured review exists as a living knowledge graph that is curated by humans and accessible to computational analyses. Finally, we have generalized this workflow into modular and repurposable components that can be applied to other domain areas. This NGLY1 Deficiency-focused network is publicly available at http://ngly1graph.org/. AVAILABILITY AND IMPLEMENTATION:Database URL: http://ngly1graph.org/. Network data files are at: https://github.com/SuLab/ngly1-graph and source code at: https://github.com/SuLab/bioknowledge-reviewer. CONTACT:asu@scripps.edu.

Project description:BackgroundScientists striving to unlock mysteries within complex biological systems face myriad barriers in effectively integrating available information to enhance their understanding. While experimental techniques and available data sources are rapidly evolving, useful information is dispersed across a variety of sources, and sources of the same information often do not use the same format or nomenclature. To harness these expanding resources, scientists need tools that bridge nomenclature differences and allow them to integrate, organize, and evaluate the quality of information without extensive computation.ResultsSidekick, a genomic data driven analysis and decision making framework, is a web-based tool that provides a user-friendly intuitive solution to the problem of information inaccessibility. Sidekick enables scientists without training in computation and data management to pursue answers to research questions like "What are the mechanisms for disease X" or "Does the set of genes associated with disease X also influence other diseases." Sidekick enables the process of combining heterogeneous data, finding and maintaining the most up-to-date data, evaluating data sources, quantifying confidence in results based on evidence, and managing the multi-step research tasks needed to answer these questions. We demonstrate Sidekick's effectiveness by showing how to accomplish a complex published analysis in a fraction of the original time with no computational effort using Sidekick.ConclusionsSidekick is an easy-to-use web-based tool that organizes and facilitates complex genomic research, allowing scientists to explore genomic relationships and formulate hypotheses without computational effort. Possible analysis steps include gene list discovery, gene-pair list discovery, various enrichments for both types of lists, and convenient list manipulation. Further, Sidekick's ability to characterize pairs of genes offers new ways to approach genomic analysis that traditional single gene lists do not, particularly in areas such as interaction discovery.

Project description:BackgroundTraditional government policies suggest that upstream investment in scientific research is necessary and sufficient to generate technological innovations. The expected downstream beneficial socio-economic impacts are presumed to occur through non-government market mechanisms. However, there is little quantitative evidence for such a direct and formulaic relationship between public investment at the input end and marketplace benefits at the impact end. Instead, the literature demonstrates that the technological innovation process involves a complex interaction between multiple sectors, methods, and stakeholders.DiscussionThe authors theorize that accomplishing the full process of technological innovation in a deliberate and systematic manner requires an operational-level model encompassing three underlying methods, each designed to generate knowledge outputs in different states: scientific research generates conceptual discoveries; engineering development generates prototype inventions; and industrial production generates commercial innovations. Given the critical roles of engineering and business, the entire innovation process should continuously consider the practical requirements and constraints of the commercial marketplace.The Need to Knowledge (NtK) Model encompasses the activities required to successfully generate innovations, along with associated strategies for effectively communicating knowledge outputs in all three states to the various stakeholders involved. It is intentionally grounded in evidence drawn from academic analysis to facilitate objective and quantitative scrutiny, and industry best practices to enable practical application.SummaryThe Need to Knowledge (NtK) Model offers a practical, market-oriented approach that avoids the gaps, constraints and inefficiencies inherent in undirected activities and disconnected sectors. The NtK Model is a means to realizing increased returns on public investments in those science and technology programs expressly intended to generate beneficial socio-economic impacts.

Dataset Information

CLEP: A Hybrid Data- and Knowledge- Driven Framework for Generating Patient Representations.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets