Simon is a Senior Technical Consultant (Data and analytics) at NHS National Services Scotland. He previously worked as a Senior Lecturer at the University of Glasgow, where he made significant contributions to computational metabolomics. During his academic career, Simon pioneered the application of machine learning techniques to metabolomics data, including methods for using dependencies between metabolites to aid in identification, probabilistic methods for metabolite annotation, and the use of peak grouping to improve alignment and differential expression computation. Simon was a key developer of MS2LDA, applying topic modeling for untargeted substructure exploration in metabolomics (published in PNAS 2016). He co-authored the textbook "A First Course in Machine Learning" with Mark Girolami, now in its second edition. Simon holds a PhD in Machine Learning from the University of Bristol and was an affiliate member of Glasgow Polyomics. His expertise includes machine learning and statistical techniques for complex data, particularly in healthcare, metabolomics, and information retrieval. His publications can be found on Google Scholar.

Justin is an Assistant Professor in Computational Metabolomics at the Bioinformatics Group at Wageningen University, where he leads the Van der Hooft Computational Metabolomics Group. His research vision is to close the gap between what we can see in metabolomics and what we can actually learn from it. His group develops computational metabolomics approaches inspired by natural language processing (NLP) and genomics, including tools like MS2LDA, MS2Query, and the matchms Python framework. Justin's publications include highly-cited papers in Nature Biotechnology and PNAS. He collaborates with researchers from Wageningen University, UCSD, and the Netherlands eScience Center. His group uses the plant root microbiome and human food metabolome as prime applications, as they represent complex metabolite mixtures that, once elucidated, will boost our insights into molecular mechanisms underpinning growth, development, and health.

Joe is a Principal Bioinformatician at Metabolon, Inc. Previously, he was a Data Scientist at Glasgow Polyomics where he led the development of MS2LDAviz and GraphOmics. His PhD thesis at the University of Glasgow explored Bayesian methods and topic modeling for mass spectrometry data. Joe specializes in developing computational tools for metabolomics and multi-omics data analysis, with expertise in bioinformatics, scientific Python, machine learning, and Bayesian inference. Joe's most influential works include the PNAS 2016 paper on topic modeling for untargeted substructure exploration (386+ citations), MolNetEnhancer (Metabolites 2019, 370+ citations), and the MS2LDA.org web application (Bioinformatics 2018, 126+ citations). He has collaborated with researchers from the University of Glasgow and Wageningen University on tools for metabolomics data analysis. His publications can be found on Google Scholar.

The following people have contributed code, patches and new features—MS2LDA would not be where it is today without their help:

• Rónán Daly and Glasgow Polyomics — website hosting.
• Nicolas Elie — porting to Python 3.
• Lars Ridder — MAGMa integration.
• Stefan Verhoeven — Gensim integration.
• Yunfeng (Frank) Zhu — MS1 analysis module.
• Ong Cher Wei — ClassyFire module.
• Jonas Dietrich — core developer of the MS2LDA 2.0 modernisation effort (preprint soon).
• Rosina Torres Ortega — core developer of the MS2LDA 2.0 modernisation effort.