Combining lipidomics and machine learning to measure clinical lipids in dried blood spots

Abstract

Introduction Blood-based sample collection is a challenge, and dried blood spots (DBS) represent an attractive alternative. However, for DBSs to be an alternative to venous blood it is important that these samples are able to deliver comparable associations with clinical outcomes. To explore this we looked to see if lipid profile data could be used to predict the concentration of triglyceride, HDL, LDL and total cholesterol in DBSs using markers identified in plasma. Objectives To determine if DBSs can be used as an alternative to venous blood in both research and clinical settings, and to determine if machine learning could predict 'clinical lipid' concentration from lipid profile data. Methods Lipid profiles were generated from plasma (n = 777) and DBS (n = 835) samples. Random forest was applied to identify and validate panels of lipid markers in plasma, which were translated into the DBS cohort to provide robust measures of the four 'clinical lipids'. Results In plasma samples panels of lipid markers were identified that could predict the concentration of the 'clinical lipids' with correlations between estimated and measured triglyceride, HDL, LDL and total cholesterol of 0.920, 0.743, 0.580 and 0.424 respectively. When translated into DBS samples, correlations of 0.836, 0.591, 0.561 and 0.569 were achieved for triglyceride, HDL, LDL and total cholesterol. Conclusion DBSs represent an alternative to venous blood, however further work is required to improve the combined lipidomics and machine learning approach to develop it for use in health monitoring.

Non-Lethal Blood Sampling of Fish in the lab and Field With Methods for Dried Blood Plasma Spot Omic Analyses

“…have had reduced recovery and sensitivity from DBSs when compared with wet plasma ( Lakshmy et al, 2012 ; Samuelsson et al, 2015 ; Corso et al, 2016 ). A study by Snowden et al (2020) identified 71% of the lipids found in wet plasma in dried blood spots, which is similar to our results with the PF DPSs in the present study. Additionally, lipid concentrations could be corrected with the use of internal standards, as was done by Snowden et al (2020) .…”

“…A study by Snowden et al (2020) identified 71% of the lipids found in wet plasma in dried blood spots, which is similar to our results with the PF DPSs in the present study. Additionally, lipid concentrations could be corrected with the use of internal standards, as was done by Snowden et al (2020) . Overall, lipid analysis of dried blood and plasma spots shows promise and could be used with field blood samples, without requiring large plasma volumes or cold storage.…”

Artificial intelligence for proteomics and biomarker discovery

“…This may be because of low sample sizes, lack of interpretability, and general lack of sufficient reference, training, and validation data. Proof of concept ML applications using lipidomics datasets have emerged, for instance for prediction of T2D status (Ho et al, 2020) and to predict clinical lipid concentration from lipid profile data using dried blood spots (Snowden et al, 2020).…”

A pipeline for making 31P NMR accessible for small- and large-scale lipidomics studies

“…Lipidomics is of increasing importance in studies of living systems as phospholipids, triglycerides and sterols have various roles in metabolic disease, growth, infection and the structure of biological systems [1][2][3][4][5][6][7][8][9][10][11][12]. Lipidomics is complementary to approaches such as proteomics and transcriptomics, and relatively quick to acquire and therefore cost effective.…”