ColocAI: artificial intelligence approach to quantify co-localization between mass spectrometry images

AbstractMotivationImaging mass spectrometry (imaging MS) is a prominent technique for capturing distributions of molecules in tissue sections. Various computational methods for imaging MS rely on quantifying spatial correlations between ion images, referred to as co-localization. However, no comprehensive evaluation of co-localization measures has ever been performed; this leads to arbitrary choices and hinders method development.ResultsWe present ColocAI, an artificial intelligence approach addressing this gap. With the help of 42 imaging MS experts from 9 labs, we created a gold standard of 2210 pairs of ion images ranked by their co-localization. We evaluated existing co-localization measures and developed novel measures using tf-idf and deep neural networks. The semi-supervised deep learning Pi model and the cosine score applied after median thresholding performed the best (Spearman 0.797 and 0.794 with expert rankings respectively). We illustrate these measures by inferring co-localization properties of 10273 molecules from 3685 public METASPACE datasets.Availability and Implementationhttps://github.com/metaspace2020/[email protected]

Download Full-text

ColocML: machine learning quantifies co-localization between mass spectrometry images

Bioinformatics ◽

10.1093/bioinformatics/btaa085 ◽

2020 ◽

Vol 36 (10) ◽

pp. 3215-3224 ◽

Cited By ~ 3

Author(s):

Katja Ovchinnikova ◽

Lachlan Stuart ◽

Alexander Rakhlin ◽

Sergey Nikolenko ◽

Theodore Alexandrov

Keyword(s):

Machine Learning ◽

Mass Spectrometry ◽

Method Development ◽

Comprehensive Evaluation ◽

Imaging Mass Spectrometry ◽

Supplementary Information ◽

Spatial Correlations ◽

Document Frequency ◽

Machine Learning Approach ◽

Imaging Ms

Abstract Motivation Imaging mass spectrometry (imaging MS) is a prominent technique for capturing distributions of molecules in tissue sections. Various computational methods for imaging MS rely on quantifying spatial correlations between ion images, referred to as co-localization. However, no comprehensive evaluation of co-localization measures has ever been performed; this leads to arbitrary choices and hinders method development. Results We present ColocML, a machine learning approach addressing this gap. With the help of 42 imaging MS experts from nine laboratories, we created a gold standard of 2210 pairs of ion images ranked by their co-localization. We evaluated existing co-localization measures and developed novel measures using term frequency–inverse document frequency and deep neural networks. The semi-supervised deep learning Pi model and the cosine score applied after median thresholding performed the best (Spearman 0.797 and 0.794 with expert rankings, respectively). We illustrate these measures by inferring co-localization properties of 10 273 molecules from 3685 public METASPACE datasets. Availability and implementation https://github.com/metaspace2020/coloc. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Spatial Metabolomics and Imaging Mass Spectrometry in the Age of Artificial Intelligence

Annual Review of Biomedical Data Science ◽

10.1146/annurev-biodatasci-011420-031537 ◽

2020 ◽

Vol 3 (1) ◽

pp. 61-87 ◽

Cited By ~ 10

Author(s):

Theodore Alexandrov

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Mass Spectrometry ◽

Image Analysis ◽

Imaging Mass Spectrometry ◽

Rapid Evolution ◽

Life Sciences ◽

Imaging Data ◽

Enabling Technology ◽

Tissue Sections

Spatial metabolomics is an emerging field of omics research that has enabled localizing metabolites, lipids, and drugs in tissue sections, a feat considered impossible just two decades ago. Spatial metabolomics and its enabling technology—imaging mass spectrometry—generate big hyperspectral imaging data that have motivated the development of tailored computational methods at the intersection of computational metabolomics and image analysis. Experimental and computational developments have recently opened doors to applications of spatial metabolomics in life sciences and biomedicine. At the same time, these advances have coincided with a rapid evolution in machine learning, deep learning, and artificial intelligence, which are transforming our everyday life and promise to revolutionize biology and healthcare. Here, we introduce spatial metabolomics through the eyes of a computational scientist, review the outstanding challenges, provide a look into the future, and discuss opportunities granted by the ongoing convergence of human and artificial intelligence.

Download Full-text