Towards an ontology-based recommender system for relevant bioinformatics workflows

Abstract

Background: With the large and diverse type of biological data, bioinformatic solutions are being more complex and computationally intensive. New specialized data skills need to be acquired by researchers in order to follow this development. Workflow Management Systems rise as an efficient way to automate tasks through abstract models in order to assist users during their problem solving tasks. However, current solutions could have several problems in reusing the developed models for given tasks. The large amount of heterogenous data and the lack of knowledge in using bioinformatics tools could mislead the users during their analyses. To tackle this issue, we propose an ontology-based workflow-mining framework generating semantic models of bioinformatic best practices in order to assist scientists. To this end, concrete workflows are extracted from scientific articles and then mined using a rich domain ontology.Results: In this study, we explore the specific topics of phylogenetic analyses. We annotated more than 300 recent articles using different ontological concepts and relations. Relative supports (frequencies) of discovered workflow components in texts show interesting results of relevant resources currently used in the different phylogenetic analysis steps. Mining concrete workflows from texts lead us to discover abstract but relevant patterns of the best combinations of tools, parameters and input data for specific phylogenetic problems.Conclusions: Extracted patterns would make workflows more intuitive and easy to be reused in similar situations. This could provide a stepping-stone into the identification of best practices and pave the road to a recommender system.

The role of metadata in reproducible computational research

“…However, methods sections and other free-text supplementals are notoriously poor and unreliable examples of reproducible computational research, as evidenced by the Amgen findings and numerous reproduction studies. A number of text mining efforts have sought to extract details of the software used in analyses directly from methods sections for purposes of survey 173 , 174 and recommendation 175 using natural language processing (NLP). The ProvCaRe database and web application extend this to both computational and clinical findings by using a wide-ranging corpus of provenance terms and extending existing PROV-O ontology.…”

Provenance-and machine learning-based recommendation of parameter values in scientific workflows

“…For each new component used in the composition of workflow, new components are recommended. Halioui, Valtchev & Diallo (2016) , uses Natural Language Processing combined with specific ontologies in the field of Bioinformatics to extract concrete workflows from works in the literature. After the reconstruction of concrete workflows , tool combinations patterns, its parameters, and input data used in these workflows are extracted.…”

FReeP: towards parameter recommendation in scientific workflows using preference learning

“…Particularly, in [Mukherjee et al 2003], Preference Learning is also used to leverage the recommendation. Regarding recommendation in workflows, Halioui [Halioui et al 2016] combined natural language processing with ontologies to recommend searching keywords. In [Soomro et al 2015], a pattern-based recommendation approach was built to suggest workflows composition.…”