Dataset Information

Towards early monitoring of chemotherapy-induced drug resistance based on single cell metabolomics: Combining single-probe mass spectrometry with machine learning.

ABSTRACT: Despite the presence of methods evaluating drug resistance during chemotherapies, techniques, which allow for monitoring the degree of drug resistance in early chemotherapeutic stage from single cells in their native microenvironment, are still absent. Herein, we report an analytical approach that combines single cell mass spectrometry (SCMS) based metabolomics with machine learning (ML) models to address the existing challenges. Metabolomic profiles of live cancer cells (HCT-116) with different levels (i.e., no, low, and high) of chemotherapy-induced drug resistance were measured using the Single-probe SCMS technique. A series of ML models, including random forest (RF), artificial neural network (ANN), and penalized logistic regression (LR), were constructed to predict the degrees of drug resistance of individual cells. A systematic comparison of performance was conducted among multiple models, and the method validation was carried out experimentally. Our results indicate that these ML models, especially the RF model constructed on the obtained SCMS datasets, can rapidly and accurately predict different degrees of drug resistance of live single cells. With such rapid and reliable assessment of drug resistance demonstrated at the single cell level, our method can be potentially employed to evaluate chemotherapeutic efficacy in the clinic.

SUBMITTER: Liu R

PROVIDER: S-EPMC6878984 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Towards early monitoring of chemotherapy-induced drug resistance based on single cell metabolomics: Combining single-probe mass spectrometry with machine learning.

Liu Renmeng R Sun Mei M Zhang Genwei G Lan Yunpeng Y Yang Zhibo Z

Analytica chimica acta 20190925

Despite the presence of methods evaluating drug resistance during chemotherapies, techniques, which allow for monitoring the degree of drug resistance in early chemotherapeutic stage from single cells in their native microenvironment, are still absent. Herein, we report an analytical approach that combines single cell mass spectrometry (SCMS) based metabolomics with machine learning (ML) models to address the existing challenges. Metabolomic profiles of live cancer cells (HCT-116) with different ...[more]

PMID: 31708031

Similar Datasets

Project description:BackgroundTissue imaging of treatment-induced metabolic changes is useful for optimizing cancer therapies, but commonly used methods require trade-offs between assay sensitivity and spatial resolution. Nanostructure-Initiator Mass Spectrometry imaging (NIMS) permits quantitative co-localization of drugs and treatment response biomarkers in cells and tissues with relatively high resolution. The present feasibility studies use NIMS to monitor phosphorylation of 3'-deoxy-3'-fluorothymidine (FLT) to FLT-MP in lymphoma cells and solid tumors as an indicator of drug exposure and pharmacodynamic responses.MethodsNIMS analytical sensitivity and spatial resolution were examined in cultured Burkitt's lymphoma cells treated briefly with Rapamycin or FLT. Sample aliquots were dispersed on NIMS surfaces for single cell imaging and metabolic profiling, or extracted in parallel for LC-MS/MS analysis. Docetaxel-induced changes in FLT metabolism were also monitored in tissues and tissue extracts from mice bearing drug-sensitive tumor xenografts. To correct for variations in FLT disposition, the ratio of FLT-MP to FLT was used as a measure of TK1 thymidine kinase activity in NIMS images. TK1 and tumor-specific luciferase were measured in adjacent tissue sections using immuno-fluorescence microscopy.ResultsNIMS and LC-MS/MS yielded consistent results. FLT, FLT-MP, and Rapamycin were readily detected at the single cell level using NIMS. Rapid changes in endogenous metabolism were detected in drug-treated cells, and rapid accumulation of FLT-MP was seen in most, but not all imaged cells. FLT-MP accumulation in xenograft tumors was shown to be sensitive to Docetaxel treatment, and TK1 immunoreactivity co-localized with tumor-specific antigens in xenograft tumors, supporting a role for xenograft-derived TK1 activity in tumor FLT metabolism.ConclusionsNIMS is suitable for monitoring drug exposure and metabolite biotransformation with essentially single cell resolution, and provides new spatial and functional dimensions to studies of cancer metabolism without the need for radiotracers or tissue extraction. These findings should prove useful for in vitro and pre-clinical studies of cancer metabolism, and aid the optimization of metabolism-based cancer therapies and diagnostics.

Dataset Information

Towards early monitoring of chemotherapy-induced drug resistance based on single cell metabolomics: Combining single-probe mass spectrometry with machine learning.

Publications

Towards early monitoring of chemotherapy-induced drug resistance based on single cell metabolomics: Combining single-probe mass spectrometry with machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets