Abstract
The bottleneck for taking full advantage of metabolomics data is often the availability, awareness, and usability of analysis tools. Software tools specifically designed for metabolomics data are being developed at an increasing rate, with hundreds of available tools already in the literature. Many of these tools are open-source and freely available but are very diverse with respect to language, data formats, and stages in the metabolomics pipeline. To help mitigate the challenges of meeting the increasing demand for guidance in choosing analytical tools and coordinating the adoption of best practices for reproducibility, we have designed and built the MSCAT (Metabolomics Software CATalog) database of metabolomics software tools that can be sustainably and continuously updated. This database provides a survey of the landscape of available tools and can assist researchers in their selection of data analysis workflows for metabolomics studies according to their specific needs. We used machine learning (ML) methodology for the purpose of semi-automating the identification of metabolomics software tool names within abstracts. MSCAT searches the literature to find new software tools by implementing a Named Entity Recognition (NER) model based on a neural network model at the sentence level composed of a character-level convolutional neural network (CNN) combined with a bidirectional long-short-term memory (LSTM) layer and a conditional random fields (CRF) layer. The list of potential new tools (and their associated publication) is then forwarded to the database maintainer for the curation of the database entry corresponding to the tool. The end-user interface allows for filtering of tools by multiple characteristics as well as plotting of the aggregate tool data to monitor the metabolomics software landscape.
Highlights
The need to list and categorize software tools used in different phases of data analysis is recognized in the metabolomics and bioinformatics communities [1,2,3,4,5]
When applied against a dataset from the second, broader PubMed query, the convolutional neural network (CNN)-long short-term memory (LSTM)-conditional random fields (CRF) model performs with an F1 of 63.5% while using only the CRF layer performs with an F1 score of 45%
The database and its associated web interfaces are hosted at the Metabolomics Workbench website [47], an international repository for the metabolomics community
Summary
The need to list and categorize software tools used in different phases of data analysis is recognized in the metabolomics and bioinformatics communities [1,2,3,4,5] Technological advances, both in instrumentation and computation, have allowed for more comprehensive and sensitive measurements of metabolites. The diversity of applications is matched by a diversity of instrumental approaches, experimental designs, as well as the expansion of statistical and computational methods applied to the growing amount of generated and curated data from metabolomics studies This translates to a large, complex, and expanding collection of software tools used in metabolomics [1,9,10,11,12,13,14,15,16,17,18,19,20,21,22]. Further software tool characteristics (OS, programming language, version, user interface type, etc.) are curated to ensure “findability” of software and to be compatible with a simple software ontology (https://github.com/allysonlister/swo, accessed on 20 September 2021)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
