Share This Author
Text mining and ontologies in biomedicine: Making sense of raw text
- I. Spasić, S. Ananiadou, J. McNaught, Anand Kumar
- Computer ScienceBriefings Bioinform.
- 1 September 2005
This paper summarises different approaches in which ontologies have been used for text-mining applications in biomedicine.
Metabolic footprinting and systems biology: the medium is the message
- D. Kell, M. Brown, H. Davey, W. Dunn, I. Spasić, S. Oliver
- BiologyNature Reviews Microbiology
- 1 July 2005
The principles, experimental approaches and scientific outcomes that have been obtained with this useful and convenient strategy to study the inner structure and behaviour of a system are reviewed.
Mass spectrometry tools and metabolite-specific databases for molecular identification in metabolomics.
The combination of accurate mass data for a large collection of metabolites, theoretical isotope abundance data and knowledge of the different ion types detected provided a greater number of electrospray mass spectrometric signals which were putatively identified and with greater confidence in the samples studied.
A model of yeast glycolysis based on a consistent kinetic characterisation of all its enzymes
A metabolome pipeline: from concept to data to knowledge
This short tutorial review and position paper seeks to set out some of the elements of “best practice” in the optimal acquisition of biological variables, and in the means by which they may be turned into reliable knowledge.
Clinical Text Data in Machine Learning: Systematic Review
The data annotation bottleneck is identified as one of the key obstacles to machine learning approaches in clinical NLP, and future research in this field would benefit from alternatives such as data augmentation and transfer learning, or unsupervised learning, which do not require data annotation.
FlexiTerm: a flexible term recognition method
- I. Spasić, R. Greenwood, A. Preece, Nick Francis, G. Elwyn
- Medicine, Computer ScienceJournal of Biomedical Semantics
- 10 October 2013
FlexiTerm is an open-source software tool for automatic term recognition that incorporates a simple term variant normalisation method and proved to be more robust than the baseline against less formally structured texts, such as those found in patient blogs or medical notes.
Selecting Text Features for Gene Name Classification: from Documents to Terms
- G. Nenadic, Simon B. Rice, I. Spasić, S. Ananiadou, B. Stapley
- Computer ScienceBioNLP@ACL
- 11 July 2003
The preliminary experiments performed have shown that using domain-specific terms can improve the performance compared to the standard bag-of-words approach, in particular for genes classified with higher confidence, and for under-represented classes.
A GC-TOF-MS study of the stability of serum and urine metabolomes during the UK Biobank sample collection and preparation protocols.
Based on this small pilot study, the UK Biobank sampling, transport and fractionation protocols are considered suitable to provide samples, which can produce scientifically robust and valid data in metabolomic studies.