Towards rapid prediction of drug-resistant cancer cell phenotypes: single cell mass spectrometry combined with machine learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Liu R
PROVIDER: S-EPMC6640148 | biostudies-literature | 2019 Jan
REPOSITORIES: biostudies-literature
Publications
Towards rapid prediction of drug-resistant cancer cell phenotypes: single cell mass spectrometry combined with machine learning.
Liu Renmeng R Zhang Genwei G Yang Zhibo Z
Chemical communications (Cambridge, England) 20190101 5
Combined single cell mass spectrometry and machine learning methods is demonstrated for the first time to achieve rapid and reliable prediction of the phenotype of unknown single cells based on their metabolomic profiles, with experimental validation. This approach can be potentially applied towards prediction of drug-resistant phenotypes prior to chemotherapy. ...[more]
Similar Datasets
Project description:When confronted with a substance of unknown identity, researchers often perform mass spectrometry on the sample and compare the observed spectrum to a library of previously collected spectra to identify the molecule. While popular, this approach will fail to identify molecules that are not in the existing library. In response, we propose to improve the library's coverage by augmenting it with synthetic spectra that are predicted from candidate molecules using machine learning. We contribute a lightweight neural network model that quickly predicts mass spectra for small molecules, averaging 5 ms per molecule with a recall-at-10 accuracy of 91.8%. Achieving high-accuracy predictions requires a novel neural network architecture that is designed to capture typical fragmentation patterns from electron ionization. We analyze the effects of our modeling innovations on library matching performance and compare our models to prior machine-learning-based work on spectrum prediction.
| S-EPMC6487538 | biostudies-literature
Project description:Neonatal dried blood spots (DBS) are routinely utilized in the clinical setting as a diagnostic tool for various genetic disorders and infectious diseases. DBS allow for minimally invasive, small volume blood collection and are stored at room temperature. Neonatal whole blood and serum samples can be important in determining genetic risk factors and predicting infantile disease; however, at the present time, limited methods exist for rapidly analyzing DBS samples for their proteomic profile, years after samples have been collected. A novel method is presented for the extraction and analysis of target proteins and peptides from neonatal DBS using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS). Extraction parameters were optimized to achieve ideal signal intensity and resolution to obtain protein identifications. Samples were extracted from filter paper with 0.1% TFA in H2O for 72 h. The extract was subjected to enzymatic digestion, spotted on an ITO-coated glass slide, and washed in order to remove salts. Analysis of extracted blood spots from ten newborns was completed. Similarities and differences in the proteomic profile of the washed extracts are presented, herein, to verify the viability of this method for analysis of dated DBS samples. This method allows for analysis of DBS samples years after collection and can be utilized to correlate diseases or disorders manifesting later in life with potential risk factors presenting in the proteomic profile of the DBS collected at time of birth.
| S-EPMC8620524 | biostudies-literature
Project description:BACKGROUND: Mass spectrometry is a key technique in proteomics and can be used to analyze complex samples quickly. One key problem with the mass spectrometric analysis of peptides and proteins, however, is the fact that absolute quantification is severely hampered by the unclear relationship between the observed peak intensity and the peptide concentration in the sample. While there are numerous approaches to circumvent this problem experimentally (e.g. labeling techniques), reliable prediction of the peak intensities from peptide sequences could provide a peptide-specific correction factor. Thus, it would be a valuable tool towards label-free absolute quantification. RESULTS: In this work we present machine learning techniques for peak intensity prediction for MALDI mass spectra. Features encoding the peptides' physico-chemical properties as well as string-based features were extracted. A feature subset was obtained from multiple forward feature selections on the extracted features. Based on these features, two advanced machine learning methods (support vector regression and local linear maps) are shown to yield good results for this problem (Pearson correlation of 0.68 in a ten-fold cross validation). CONCLUSION: The techniques presented here are a useful first step going beyond the binary prediction of proteotypic peptides towards a more quantitative prediction of peak intensities. These predictions in turn will turn out to be beneficial for mass spectrometry-based quantitative proteomics.
| S-EPMC2600826 | biostudies-other
Project description:Sphingolipids have diverse structural and bioactive functions that play important roles in many key biological processes. Factors such as low relative abundance, varied structures, and a dynamic concentration range provide a difficult analytical challenge for sphingolipid detection. To further improve mass-spectrometry-based sphingolipid analysis, lithium adduct consolidation was implemented to decrease spectral complexity and combine signal intensities, leading to increased specificity and sensitivity. We report the use of lithium hydroxide as a base in a routine hydrolysis procedure in order to effectively remove common ionization suppressants (such as glycolipids and glycerophospholipids) and introduce a source of lithium into the sample. In conjunction, an optimized MALDI matrix system, featuring 2',4',6'-trihydroxyacetophenone (THAP) is used to facilitate lithium adduct consolidation during the MALDI process. The result is a robust and high-throughput sphingolipid detection scheme, particularly of low-abundance ceramides. Application of our developed workflow includes the detection of differentially expressed liver sphingolipid profiles from a high-fat-induced obesity mouse model. We also demonstrate the method's effectiveness in detecting various sphingolipids in brain and plasma matrices. These results were corroborated with data from UHPLC HR MS/MS and MALDI FT-ICR, verifying the efficacy of the method application. Overall, we demonstrate a high-throughput workflow for sphingolipid analysis in various biological matrices by the use of MALDI TOF and lithium adduct consolidation.
| S-EPMC7790884 | biostudies-literature
Project description:Large amounts of data are generally produced from mass spectrometry imaging (MSI) experiments in obtaining the molecular and spatial information of biological samples. Traditionally, MS images are constructed using manually selected ions, and it is very challenging to comprehensively analyze MSI results due to their large data sizes and highly complex data structures. To overcome these barriers, it is obligatory to develop advanced data analysis approaches to handle the increasingly large MSI data. In the current study, we focused on the method development of using Multivariate Curve Resolution (MCR) and Machine Learning (ML) approaches. We aimed to effectively extract the essential information present in the large and complex MSI data and enhance the metabolomic data analysis of biological tissues. Multivariate Curve Resolution-Alternating Least Squares (MCR-ALS) algorithm was used to obtain major patterns of spatial distribution and grouped metabolites with the same spatial distribution patterns. In addition, both supervised and unsupervised ML methods were established to analyze the MSI data. In the supervised ML approach, Random Forest method was selected, and the model was trained using the selected datasets based on the distribution pattern obtained from MCR-ALS analyses. In the unsupervised ML approach, both DBSCAN (Density-based Spatial Clustering of Applications with Noise) and CLARA (Clustering Large Applications) were applied to cluster the MSI datasets. It is worth noting that similar patterns of spatial distribution were discovered through MSI data analysis using MCR-ALS, supervised ML, and unsupervised ML. Our protocols of data analysis can be applied to process the data acquired using many other types of MSI techniques, and to extract the overall features present in MSI results that are intractable using traditional data analysis approaches.
| S-EPMC6176743 | biostudies-literature
Project description:The brain consists of organized ensembles of cells that exhibit distinct morphologies, cellular connectivity, and dynamic biochemistries that control the executive functions of an organism. However, the relationships between chemical heterogeneity, cell function, and phenotype are not always understood. Recent advancements in matrix-assisted laser desorption/ionization mass spectrometry have enabled the high-throughput, multiplexed chemical analysis of single cells, capable of resolving hundreds of molecules in each mass spectrum. We developed a machine learning workflow to classify single cells according to their mass spectra based on cell groups of interest (GOI), e.g., neurons vs astrocytes. Three data sets from various cell groups were acquired on three different mass spectrometer platforms representing thousands of individual cell spectra that were collected and used to validate the single cell classification workflow. The trained models achieved >80% classification accuracy and were subjected to the recently developed instance-based model interpretation framework, SHapley Additive exPlanations (SHAP), which locally assigns feature importance for each single-cell spectrum. SHAP values were used for both local and global interpretations of our data sets, preserving the chemical heterogeneity uncovered by the single-cell analysis while offering the ability to perform supervised analysis. The top contributing mass features to each of the GOI were ranked and selected using mean absolute SHAP values, highlighting the features that are specific to the defined GOI. Our approach provides insight into discriminating the chemical profiles of the single cells through interpretable machine learning, facilitating downstream analysis and validation.
| S-EPMC7374983 | biostudies-literature
Project description:Colistin resistance is one of the major threats for global public health, requiring reliable and rapid susceptibility testing methods. The aim of this study was the evaluation of a MALDI-TOF mass spectrometry (MS) peak-based assay to distinguish colistin resistant (colR) from susceptible (colS) Escherichia coli strains. To this end, a classifying algorithm model (CAM) was developed, testing three different algorithms: Genetic Algorithm (GA), Supervised Neural Network (SNN) and Quick Classifier (QC). Among them, the SNN- and GA-based CAMs showed the best performances: recognition capability (RC) of 100% each one, and cross validation (CV) of 97.62% and 100%, respectively. Even if both algorithms shared similar RC and CV values, the SNN-based CAM was the best performing one, correctly identifying 67/71 (94.4%) of the E. coli strains collected: in point of fact, it correctly identified the greatest number of colS strains (42/43; 97.7%), despite its lower ability in identifying the colR strains (15/18; 83.3%). In conclusion, although broth microdilution remains the gold standard method for testing colistin susceptibility, the CAM represents a useful tool to rapidly screen colR and colS strains in clinical practice.
| S-EPMC8623207 | biostudies-literature
Project description:LC-MS/MS-based identification of HLA-peptides is poised to provide a deep understanding of the rules underlying antigen presentation. However, a key obstacle limiting the utility of MS data is the ambiguity arising from the co-expression of multiple HLA alleles. Here, we introduce a strategy for profiling the HLA ligandome one allele at a time. By using cell lines expressing a single HLA allele, optimizing immunopurifications, and developing a novel spectral search algorithm, we identified thousands of peptides bound to 16 different HLA class I alleles. These data enabled the discovery of novel binding motifs, and an integrative analysis quantifying the contribution of factors critical to epitope presentation, such as protein cleavage and gene expression. We trained neural network prediction algorithms with our large dataset (>24,000 peptides) and outperformed algorithms trained on datasets of peptides with measured affinities. We thus demonstrate a scalable strategy for systematically learning the rules of endogenous antigen presentation.
2017-02-21 | GSE93315 | GEO
Project description:Mass spectrometry provides rapid and quantitative identification of protein species with relatively low sample consumption. The trend towards biological analysis at increasingly smaller scales, ultimately down to the volume of an individual cell, continues, and mass spectrometry with a sensitivity of a few to single molecules will be necessary. Nanoelectromechanical systems provide unparalleled mass sensitivity, which is now sufficient for the detection of individual molecular species in real time. Here, we report the first demonstration of mass spectrometry based on single biological molecule detection with a nanoelectromechanical system. In our nanoelectromechanical-mass spectrometry system, nanoparticles and protein species are introduced by electrospray injection from the fluid phase in ambient conditions into vacuum, and are subsequently delivered to the nanoelectromechanical system detector by hexapole ion optics. Precipitous frequency shifts, proportional to the mass, are recorded in real time as analytes adsorb, one by one, onto a phase-locked, ultrahigh-frequency nanoelectromechanical resonator. These first nanoelectromechanical system-mass spectrometry spectra, obtained with modest mass sensitivity from only several hundred mass adsorption events, presage the future capabilities of this approach. We also outline the substantial improvements that are feasible in the near term, some of which are unique to nanoelectromechanical system based-mass spectrometry.
| S-EPMC3846395 | biostudies-literature
Project description: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.
| S-EPMC6878984 | biostudies-literature