Connecting the Dots between PubMed Abstracts

Abstract

BackgroundThere are now a multitude of articles published in a diversity of journals providing information about genes, proteins, pathways, and diseases. Each article investigates subsets of a biological process, but to gain insight into the functioning of a system as a whole, we must integrate information from multiple publications. Particularly, unraveling relationships between extra-cellular inputs and downstream molecular response mechanisms requires integrating conclusions from diverse publications.MethodologyWe present an automated approach to biological knowledge discovery from PubMed abstracts, suitable for “connecting the dots” across the literature. We describe a storytelling algorithm that, given a start and end publication, typically with little or no overlap in content, identifies a chain of intermediate publications from one to the other, such that neighboring publications have significant content similarity. The quality of discovered stories is measured using local criteria such as the size of supporting neighborhoods for each link and the strength of individual links connecting publications, as well as global metrics of dispersion. To ensure that the story stays coherent as it meanders from one publication to another, we demonstrate the design of novel coherence and overlap filters for use as post-processing steps.ConclusionsWe demonstrate the application of our storytelling algorithm to three case studies: i) a many-one study exploring relationships between multiple cellular inputs and a molecule responsible for cell-fate decisions, ii) a many-many study exploring the relationships between multiple cytokines and multiple downstream transcription factors, and iii) a one-to-one study to showcase the ability to recover a cancer related association, viz. the Warburg effect, from past literature. The storytelling pipeline helps narrow down a scientist's focus from several hundreds of thousands of relevant documents to only around a hundred stories. We argue that our approach can serve as a valuable discovery aid for hypothesis generation and connection exploration in large unstructured biological knowledge bases.

Semantic Interaction for Visual Analytics: Inferring Analytical Reasoning for Model Steering

“…The abstraction of a large corpus of text documents as a similarity network (the notion of similarity being induced by terms that are shared between document pairs) has been used by [36,37] in a "Storytelling algorithm" to connect seemingly unrelated documents via a path referred to by the authors as a story.…”

Storytelling in entity networks to support intelligence analysts

“…Connecting the dots: The "connecting the dots" problem is not new and has appeared before in a variety of contexts: entity networks [23], image collections [24], cellular networks [25], social networks [26], and document collections [10,27,28]. While some of these works can be adapted toward our problem context, the notion of a story in intelligence analysis often deals with relating entities sequentially such that neighboring entities share commonality, whereas the above projects typically require a stronger connecting thread through all entities, not just neighboring entities.…”

How to Understand Connections Based on Big Data: From Cliques to Flexible Granules

“…The connecting building task has been used in a variety of contexts: entity networks [5,8], image collections [6], cellular networks [2,7], social networks [4], and document collections [8,9,11]. All these research efforts focus on finding connections between objects that are apparently disjoint.…”

“…• We start with describing the semi-heuristic methods which have been proposed for solving this problem, as described, e.g., in [8,9].…”

“…The paper [9] deals with biomedical publications. The field of biomedical research has become so specialized that is no longer easy for a human specialist to trace all relevant papers -or even to find all relevant papers.…”