Using Literature Based Discovery to Gain Insights Into the Metabolomic Processes of Cardiac Arrest

Henry, S.; Wijesinghe, Dayanjan S.; Myers, Aidan; McInnes, Bridget T.

doi:10.3389/frma.2021.644728

Cited by 4 publications

(5 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both Yetisgen-Yildiz and Pratt (2008) and Thilakaratne et al (2019) provide a detailed review of the existing evaluation methods for LBD. A wide variety of methods have been applied: for example Kostoff et al (2021) manually review the corresponding literature in order to validate the predicted discoveries, a method which does not necessarily apply to every kind of discovery; Smalheiser et al (2006) and Henry et al (2021) rely on large-scale collaborative studies, an approach which leads to convincing results but requires considerable effort and funding; Wren et al (2004) show that the observed/expected ratio of a relationship correlates with its strength, thus heuristics based on statistical observations can also be considered. These evaluation methods all have merits and limitations, but the most commonly used is still the replication method: given a known discovery at time t , the LBD system is provided with the literature available before time t and produces a list (often a ranked list) of relations which represent potential ‘future’ discoveries, i.e.…”

Section: State Of the Art In Lbd Evaluationmentioning

confidence: 99%

Literature-based discovery: addressing the issue of the subpar evaluation methodology

Moreau

2023

Bioinformatics

View full text Add to dashboard Cite

The author argues that the field of Literature-Based Discovery (LBD) is built on sand, due to a lack of appropriate evaluation method. The field is considered mature and a healthy number of papers are published every year. Although the evaluation issue is known for twenty years, so far it did not cause any impetus to solve or alleviate it. It does not stop novel contributions to be accepted in reputable journals, despite their often poor evaluation methodology. In fact, the evaluation issue seems to have been admitted as an idiosyncrasy of the field, something the LBD community has learned to live with. After briefly presenting the issue, the author advocates for the LBD community to seriously address it: not only by making it a scientific priority, but also by designing an editorial policy in journals such as Bioinformatics to counter the systemic biases which hinder progress on this issue.

show abstract

Section: State Of the Art In Lbd Evaluationmentioning

confidence: 99%

Literature-based discovery: addressing the issue of the subpar evaluation methodology

Moreau

2023

Bioinformatics

View full text Add to dashboard Cite

show abstract

“…Thus, the present study includes both a presentation of optimized mathematical solutions as well as changes to algorithmic and data handling frameworks to increase overall speed. Three major technical improvements were made to create SemNet version 2 (also known as SemNet 2.0): (1) a randomized approximation algorithm for estimating HeteSim scores to improve HeteSim calculation speed; (2) a re-engineered knowledge graph framework that removed reliance on Neo4j to improve metapath and feature computation speed; (3) an improved implementation of the adopted ULARA ranking algorithm.…”

Section: Improving Lbd Efficiency and Efficacy With Semnet 20mentioning

confidence: 99%

“…The field of LBD attempts to capture knowledge from biomedical text and integrate it in a way that makes discovery of new knowledge possible. In Henry et al [ 3 ], LBD techniques were used to discover lecithin-cholesterol acyltransferase (LCAT) as a proposed therapeutic target for cardiac arrest, a target that was later supported via in vivo studies. Additionally, LBD was used to identify repurposed drugs for the COVID-19 pandemic [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

“…AD was chosen due to its large degree of connectivity, multi-factorial and heterogeneous nature, and growing relevance in health care—a byproduct of increasing AD deaths and an aging global population [ 27 , 28 ]. AD is traditionally characterized by its tau and amyloid beta protein deposition in neurofibrillary tangles, brain atrophy, and eventual cognitive decline [ 3 ]. As researchers delved deeper into the disease, the breadth of risk factors across various domains, such as pharmaceuticals, antecedent disease, psychological profile, and lifestyle, has further increased overall complexity of AD investigation [ 27 , 29 , 30 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimizations for Computing Relatedness in Biomedical Heterogeneous Information Networks: SemNet 2.0

Kirkpatrick

Onyeze

Kartchner

et al. 2022

BDCC

View full text Add to dashboard Cite

Literature-based discovery (LBD) summarizes information and generates insight from large text corpuses. The SemNet framework utilizes a large heterogeneous information network or “knowledge graph” of nodes and edges to compute relatedness and rank concepts pertinent to a user-specified target. SemNet provides a way to perform multi-factorial and multi-scalar analysis of complex disease etiology and therapeutic identification using the 33+ million articles in PubMed. The present work improves the efficacy and efficiency of LBD for end users by augmenting SemNet to create SemNet 2.0. A custom Python data structure replaced reliance on Neo4j to improve knowledge graph query times by several orders of magnitude. Additionally, two randomized algorithms were built to optimize the HeteSim metric calculation for computing metapath similarity. The unsupervised learning algorithm for rank aggregation (ULARA), which ranks concepts with respect to the user-specified target, was reconstructed using derived mathematical proofs of correctness and probabilistic performance guarantees for optimization. The upgraded ULARA is generalizable to other rank aggregation problems outside of SemNet. In summary, SemNet 2.0 is a comprehensive open-source software for significantly faster, more effective, and user-friendly means of automated biomedical LBD. An example case is performed to rank relationships between Alzheimer’s disease and metabolic co-morbidities.

show abstract

“…On the other hand, a hypothesis can also be generated from sequencing results first and then be validated by literature mining. For example, Henry et al [ 19 ] analyzed the metabolites from cardiac arrest patients via ultra-high-performance liquid chromatography coupled with high-resolution tandem mass spectrometry. Lecithin cholesterol-acyltransferase (LCAT) was found to be significantly changed, which was then combined with the term ‘cardiac arrest’ as input to a text-mining system for co-occurrence association.…”

Section: Literature Mining Of Noncoding Rnamentioning

confidence: 99%

Literature Mining of Disease Associated Noncoding RNA in the Omics Era

Jian

2022

Molecules

View full text Add to dashboard Cite

Noncoding RNAs (ncRNA) are transcripts without protein-coding potential that play fundamental regulatory roles in diverse cellular processes and diseases. The application of deep sequencing experiments in ncRNA research have generated massive omics datasets, which require rapid examination, interpretation and validation based on exiting knowledge resources. Thus, text-mining methods have been increasingly adapted for automatic extraction of relations between an ncRNA and its target or a disease condition from biomedical literature. These bioinformatics tools can also assist in more complex research, such as database curation of candidate ncRNAs and hypothesis generation with respect to pathophysiological mechanisms. In this concise review, we first introduced basic concepts and workflow of literature mining systems. Then, we compared available bioinformatics tools tailored for ncRNA studies, including the tasks, applicability, and limitations. Their powerful utilities and flexibility are demonstrated by examples in a variety of diseases, such as Alzheimer’s disease, atherosclerosis and cancers. Finally, we outlined several challenges from the viewpoints of both system developers and end users. We concluded that the application of text-mining techniques will booster disease-associated ncRNA discoveries in the biomedical literature and enable integrative biology in the current omics era.

show abstract

Using Literature Based Discovery to Gain Insights Into the Metabolomic Processes of Cardiac Arrest

Cited by 4 publications

References 78 publications

Literature-based discovery: addressing the issue of the subpar evaluation methodology

Literature-based discovery: addressing the issue of the subpar evaluation methodology

Optimizations for Computing Relatedness in Biomedical Heterogeneous Information Networks: SemNet 2.0

Literature Mining of Disease Associated Noncoding RNA in the Omics Era

Contact Info

Product

Resources

About