The LAILAPS Search Engine: Relevance Ranking in Life Science Databases

Abstract

SummarySearch engines and retrieval systems are popular tools at a life science desktop. The manual inspection of hundreds of database entries, that reflect a life science concept or fact, is a time intensive daily work. Hereby, not the number of query results matters, but the relevance does. In this paper, we present the LAILAPS search engine for life science databases. The concept is to combine a novel feature model for relevance ranking, a machine learning approach to model user relevance profiles, ranking improvement by user feedback tracking and an intuitive and slim web user interface, that estimates relevance rank by tracking user interactions. Queries are formulated as simple keyword lists and will be expanded by synonyms. Supporting a flexible text index and a simple data import format, LAILAPS can easily be used both as search engine for comprehensive integrated life science databases and for small in-house project databases. With a set of features, extracted from each database hit in combination with user relevance preferences, a neural network predicts user specific relevance scores. Using expert knowledge as training data for a predefined neural network or using users own relevance training sets, a reliable relevance ranking of database hits has been implemented. In this paper, we present the LAILAPS system, the concepts, benchmarks and use cases. LAILAPS is public available for SWISSPROT data at

A Query Suggestion Workflow for Life Science IR-Systems

“…The training set can be derived from application case specific dictionaries. We decided to use WordNet 4 which is a lexical database and ontology data sets from the OBO foundry 5 to train the algorithm. This will train TANGO to give stronger consideration to biological words or chemical compound names.…”

“…We evaluated individual steps of the workflow using custom benchmark and example datasets. To demonstrate applicability and performance of the workflow it was implemented into the life science IR system LAILAPS [5]. A detailed benchmark is discussed based on example queries, which were taken from query logs of life science web information systems and some manually curated use cases.…”

Das Sombi-Framework zum Ermitteln geeigneter Suchfunktionen für biologische Modelldatenbasen

“…Als Ergebnis werden relevante Einträge domänenspezifisch zusammengefasst präsentiert. Eine weitere interessante Anwendung zeigt die Suchmaschine LAILAPS [12], deren Rankingmechanismus auf dem Prinzip neuronaler Netze basiert und Nutzerinteraktionen in das Ranking einfließen lässt. Die Anwendung von IR-Techniken für die Bio-Modellsuche jedoch ist eine erstmals von uns vorgeschlagene Methode [11].…”

The LAILAPS Search Engine: A Feature Model for Relevance Ranking in Life Science Databases

“…In the next sections we present the LAILAPS system as method for relevance ranking in life science databases [10]. In particular, we present the used ranking concept, the used feature model, its implementation as neural network and ranking benchmarks.…”