With well over one thousand specialized biological databases in use today, the task of automatically identifying novel, relevant data for such databases is increasingly important. In this paper, we describe practical machine learning approaches for identifying MEDLINE documents and Swiss-Prot/TrEMBL protein records, for incorporation into a specialized biological database of transport proteins named TCDB. We show that both learning approaches outperform rules created by hand by a human expert. As one of the first case studies involving two different approaches to updating a deployed database, both the methods compared and the results will be of interest to curators of many specialized databases.
BackgroundAccuracy of document retrieval from MEDLINE for gene queries is crucially important for many applications in bioinformatics. We explore five information retrieval-based methods to rank documents retrieved by PubMed gene queries for the human genome. The aim is to rank relevant documents higher in the retrieved list. We address the special challenges faced due to ambiguity in gene nomenclature: gene terms that refer to multiple genes, gene terms that are also English words, and gene terms that have other biological meanings.ResultsOur two baseline ranking strategies are quite similar in performance. Two of our three LocusLink-based strategies offer significant improvements. These methods work very well even when there is ambiguity in the gene terms. Our best ranking strategy offers significant improvements on three different kinds of ambiguities over our two baseline strategies (improvements range from 15.9% to 17.7% and 11.7% to 13.3% depending on the baseline). For most genes the best ranking query is one that is built from the LocusLink (now Entrez Gene) summary and product information along with the gene names and aliases. For others, the gene names and aliases suffice. We also present an approach that successfully predicts, for a given gene, which of these two ranking queries is more appropriate.ConclusionWe explore the effect of different post-retrieval strategies on the ranking of documents returned by PubMed for human gene queries. We have successfully applied some of these strategies to improve the ranking of relevant documents in the retrieved sets. This holds true even when various kinds of ambiguity are encountered. We feel that it would be very useful to apply strategies like ours on PubMed search results as these are not ordered by relevance in any way. This is especially so for queries that retrieve a large number of documents.
Web navigation plays an important role in exploring public interconnected data sources such as life science data. A navigational query in the life science graph produces a result graph which is a layered directed acyclic graph (DAG). Traversing the result paths in this graph reaches a target object set (TOS). The challenge for ranking the target objects is to provide recommendations that reflect the relative importance of the retrieved object, as well as its relevance to the specific query posed by the scientist. We present a metric layered graph PageRank (lgPR) to rank target objects based on the link structure of the result graph. LgPR is a modification of PageRank; it avoids random jumps to respect the path structure of the result graph. We also outline a metric layered graph ObjectRank (lgOR) which extends the metric ObjectRank to layered graphs. We then present an initial evaluation of lgPR. We perform experiments on a real-world graph of life sciences objects from NCBI and report on the ranking distribution produced by lgPR. We compare lgPR with PageRank. In order to understand the characteristics of lgPR, an expert compared the Top K target objects (publications in the PubMed source) produced by lgPR and a word-based ranking method that uses text features extracted from an external source (such as Entrez Gene) to rank publications.
The availability of large-scale data on the Web motivates the development of automatic algorithms to analyze topics and to identify relationships between topics.Various approaches have been proposed in the literature. Most focus on specific topics, mainly those representing people, with little attention to topics of other kinds. They given topics of interest, as part of the 2007 TREC Expert Search task.Overall, our results show that topic profiles provide a strong foundation for exploring different topics and for mining relationships between topics using web data.Our approach can be applied to a wide range of web knowledge discovery problems, in contrast to existing approaches that are mostly designed for specific problems. Abstract Approved:Thesis Supervisor
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.