Abstract
BackgroundThe clustering of data produced by liquid chromatography coupled to mass spectrometry analyses (LC-MS data) has recently gained interest to extract meaningful chemical or biological patterns. However, recent instrumental pipelines deliver data which size, dimensionality and expected number of clusters are too large to be processed by classical machine learning algorithms, so that most of the state-of-the-art relies on single pass linkage-based algorithms.ResultsWe propose a clustering algorithm that solves the powerful but computationally demanding kernel k-means objective function in a scalable way. As a result, it can process LC-MS data in an acceptable time on a multicore machine. To do so, we combine three essential features: a compressive data representation, Nyström approximation and a hierarchical strategy. In addition, we propose new kernels based on optimal transport, which interprets as intuitive similarity measures between chromatographic elution profiles.ConclusionsOur method, referred to as CHICKN, is evaluated on proteomics data produced in our lab, as well as on benchmark data coming from the literature. From a computational viewpoint, it is particularly efficient on raw LC-MS data. From a data analysis viewpoint, it provides clusters which differ from those resulting from state-of-the-art methods, while achieving similar performances. This highlights the complementarity of differently principle algorithms to extract the best from complex LC-MS data.
Highlights
The clustering of data produced by liquid chromatography coupled to mass spectrometry analyses (LC-MS data) has recently gained interest to extract mean‐ ingful chemical or biological patterns
Liquid chromatography coupled to mass spectrometry (LC-MS) constitute a technological pipeline that has become ubiquitous in various omics investigations, such as proteomics, lipidomics and metabolomics
We focused on k-means objective function, for two reasons: First, until recently, it was considered by the proteomics community as non-applicable to data as big as LC-MS data [7], while recent theoretical progresses have made this scaling-up possible [44]; Second, k-means can be reformulated to fit the reproducing kernel Hilbert space theory [45], which provides new opportunities to define similarity measures that capture the biochemical specificities of LC-MS data
Summary
The clustering of data produced by liquid chromatography coupled to mass spectrometry analyses (LC-MS data) has recently gained interest to extract mean‐ ingful chemical or biological patterns. The MS throughput has continuously improved, leading to unprecedented data volume production To date, processing these gigabytes of low level MS signals has become a challenge on its own, for a trade-off between contradictory objectives is sought: On the one hand, one needs to save memory and computational time with efficient encoding, compression and signal cleaning methods [1]. One needs to avoid too important preprocessing that systematically smoothes signals of lower magnitudes, as it is well-established that interesting biological patterns can be found near the noise level [2] To face this challenge, a recent and efficient investigation path has been to apply cluster analysis to LC-MS data. As each cluster contains similar data elements, it facilitates the extraction of repetitive but small biological patterns
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
