Summary of Study ST002015
This data is available at the NIH Common Fund's National Metabolomics Data Repository (NMDR) website, the Metabolomics Workbench, https://www.metabolomicsworkbench.org, where it has been assigned Project ID PR001279. The data can be accessed directly via it's Project DOI: 10.21228/M8CX10 This work is supported by NIH grant, U2C- DK119886.
See: https://www.metabolomicsworkbench.org/about/howtocite.php
This study contains a large results data set and is not available in the mwTab file. It is only available for download via FTP as data file(s) here.
Study ID | ST002015 |
Study Title | Dysregulated Alanine as a Potential Predictive Marker of Glioma—An Insight from Untargeted HRMAS-NMR and Machine Learning Data |
Study Type | Untargeted NMR |
Study Summary | Metabolic alterations play a crucial role in glioma development and progression and can be detected even before the appearance of the fatal phenotype. We have compared the circulating metabolic fingerprints of glioma patients versus healthy controls, for the first time, in a quest to identify a panel of small, dysregulated metabolites with potential to serve as a predictive and/or diagnostic marker in the clinical settings. High-resolution magic angle spinning nuclear magnetic resonance spectroscopy (HRMAS-NMR) was used for untargeted metabolomics and data acquisition followed by a machine learning (ML) approach for the analyses of large metabolic datasets. Crossvalidation of ML predicted NMR spectral features was done by statistical methods (Wilcoxon-test) using JMP-pro16 software. Alanine was identified as the most critical metabolite with potential to detect glioma with precision of 1.0, recall of 0.96, and F1 measure of 0.98. The top 10 metabolites identified for glioma detection included alanine, glutamine, valine, methionine, N-acetylaspartate (NAA), γ-aminobutyric acid (GABA), serine, α-glucose, lactate, and arginine. We achieved 100% accuracy for the detection of glioma using ML algorithms, extra tree classifier, and random forest, and 98% accuracy with logistic regression. Classification of glioma in low and high grades was done with 86% accuracy using logistic regression model, and with 83% and 79% accuracy using extra tree classifier and random forest, respectively. The predictive accuracy of our ML model is superior to any of the previously reported algorithms, used in tissue- or liquid biopsy-based metabolic studies. The identified top metabolites can be targeted to develop early diagnostic methods as well as to plan personalized treatment strategies. |
Institute | University of the Punjab |
Department | School of Biochemistry and Biotechnology |
Laboratory | Biopharmaceuticals and Biomarkers Discovery Lab |
Last Name | Firdous |
First Name | Safia |
Address | Quaid e Azam Campus, University of the Punjab, Lahore. |
saima.ibb@pu.edu.pk | |
Phone | +924299231098 |
Submit Date | 2021-10-26 |
Num Groups | 2 |
Total Subjects | 42 |
Num Males | 25 |
Num Females | 17 |
Publications | Dysregulated Alanine as a Potential Predictive Marker of Glioma—An Insight from Untargeted HRMAS-NMR and Machine Learning Data |
Analysis Type Detail | NMR |
Release Date | 2022-06-01 |
Release Version | 1 |
Select appropriate tab below to view additional metadata details:
Project:
Project ID: | PR001279 |
Project DOI: | doi: 10.21228/M8CX10 |
Project Title: | Dysregulated Alanine as a Potential Predictive Marker of Glioma—An Insight from Untargeted HRMAS-NMR and Machine Learning Data |
Project Type: | Untargeted HRMAS NMR, Glioma |
Project Summary: | Metabolic alterations play a crucial role in glioma development and progression and can be detected even before the appearance of the fatal phenotype. We have compared the circulating metabolic fingerprints of glioma patients versus healthy controls, for the first time, in a quest to identify a panel of small, dysregulated metabolites with potential to serve as a predictive and/or diagnostic marker in the clinical settings. High-resolution magic angle spinning nuclear magnetic resonance spectroscopy (HRMAS-NMR) was used for untargeted metabolomics and data acquisition followed by a machine learning (ML) approach for the analyses of large metabolic datasets. Cross-validation of ML predicted NMR spectral features was done by statistical methods (Wilcoxon-test) using JMP-pro16 software. Alanine was identified as the most critical metabolite with potential to detect glioma with precision of 1.0, recall of 0.96, and F1 measure of 0.98. The top 10 metabolites identified for glioma detection included alanine, glutamine, valine, methionine, N-acetylaspartate (NAA), γ-aminobutyric acid (GABA), serine, α-glucose, lactate, and arginine. We achieved 100% accuracy for the detection of glioma using ML algorithms, extra tree classifier, and random forest, and 98% accuracy with logistic regression. Classification of glioma in low and high grades was done with 86% accuracy using logistic regression model, and with 83% and 79% accuracy using extra tree classifier and random forest, respectively. The predictive accuracy of our ML model is superior to any of the previously reported algorithms, used in tissue- or liquid biopsy-based metabolic studies. The identified top metabolites can be targeted to develop early diagnostic methods as well as to plan personalized treatment strategies. |
Institute: | University of the Punjab |
Department: | School of Biochemistry and Biotechnology |
Laboratory: | Biopharmaceuticals and Biomarkers Discovery Lab |
Last Name: | Firdous |
First Name: | Safia |
Address: | Quaid e Azam Campus, University of the Punjab, Lahore. |
Email: | saima.ibb@pu.edu.pk |
Phone: | +924299231098 |
Funding Source: | HEC-IRSIP, USA NIH grants: S10OD023406 and R21CA243255 |
Publications: | Dysregulated Alanine as a Potential Predictive Marker of Glioma—An Insight from Untargeted HRMAS-NMR and Machine Learning Data |
Contributors: | Safia Firdous, Rizwan Abid, Zubair Nawaz, Faisal Bukhari, Ammar Anwer, Leo L Cheng, Saima Sadaf |
Subject:
Subject ID: | SU002096 |
Subject Type: | Human |
Subject Species: | Homo sapiens |
Taxonomy ID: | 9606 |
Age Or Age Range: | 15-60 Years |
Gender: | Male and female |
Human Race: | Asian |
Human Ethnicity: | Asian |
Human Lifestyle Factors: | N/A |
Human Medications: | N/A |
Human Prescription Otc: | N/A |
Human Smoking Status: | N/A |
Human Alcohol Drug Use: | N/A |
Human Nutrition: | N/A |
Human Inclusion Criteria: | Low and High grade glioma patients confirmed by routine histopathology analysis |
Human Exclusion Criteria: | Diabetes mellitus, Hypertension, liver (hepatitis/liver cirrhosis), and Cardiovascular disease |
Species Group: | Mammals |
Factors:
Subject type: Human; Subject species: Homo sapiens (Factor headings shown in green)
mb_sample_id | local_sample_id | Class | Grade |
---|---|---|---|
SA188621 | N2 | Control | - |
SA188622 | N3 | Control | - |
SA188623 | N1 | Control | - |
SA188624 | N14 | Control | - |
SA188625 | N13 | Control | - |
SA188626 | N15 | Control | - |
SA188627 | N4 | Control | - |
SA188628 | N6 | Control | - |
SA188629 | N11 | Control | - |
SA188630 | N12 | Control | - |
SA188631 | N10 | Control | - |
SA188632 | N9 | Control | - |
SA188633 | N7 | Control | - |
SA188634 | N8 | Control | - |
SA188635 | N5 | Control | - |
SA188636 | N16 | Control | - |
SA188637 | AA1 | HGG | III |
SA188638 | GBM8 | HGG | IV |
SA188639 | GBM9 | HGG | IV |
SA188640 | GBM10 | HGG | IV |
SA188641 | GBM7 | HGG | IV |
SA188642 | GBM6 | HGG | IV |
SA188643 | GBM2 | HGG | IV |
SA188644 | GBM3 | HGG | IV |
SA188645 | GBM4 | HGG | IV |
SA188646 | GBM5 | HGG | IV |
SA188647 | GBM11 | HGG | IV |
SA188648 | GBM12 | HGG | IV |
SA188649 | GBM13 | HGG | IV |
SA188650 | GBM14 | HGG | IV |
SA188651 | GBM15 | HGG | IV |
SA188652 | GBM16 | HGG | IV |
SA188653 | GBM1 | HGG | IV |
SA188654 | PA1 | LGG | I |
SA188655 | PA4 | LGG | I |
SA188656 | PA3 | LGG | I |
SA188657 | PA2 | LGG | I |
SA188658 | DA5 | LGG | II |
SA188659 | DA1 | LGG | II |
SA188660 | DA2 | LGG | II |
SA188661 | DA3 | LGG | II |
SA188662 | DA4 | LGG | II |
Showing results 1 to 42 of 42 |
Collection:
Collection ID: | CO002089 |
Collection Summary: | Peripheral blood (3 cc) from each patient (fasting state) was collected in Li-heparin tubes, centrifuged (300× g, 10 min) to prepare plasma within an hour of collection, and preserved in sterile tubes at −80 ◦C, as 200 µL aliquots, until further analyses. |
Sample Type: | Blood (whole) |
Collection Location: | Punjab Institute of Neurosciences (PINS), Lahore, Pakistan. |
Collection Frequency: | Pre-operative |
Storage Conditions: | -80℃ |
Collection Vials: | Li-Heparin |
Treatment:
Treatment ID: | TR002108 |
Treatment Summary: | The enrolled patients underwent surgical resection of tumor after sample collection. |
Sample Preparation:
Sampleprep ID: | SP002102 |
Sampleprep Summary: | Sample was prepared by adding 10 µL plasma sample in a 4 mm zirconia rotor with 12 µL Kel-F inserts; 2 µL D2O (Sigma Aldrich, St. Louis, MO, USA) with reference trimethylsilylpropanoic acid (TSP) was added for field locking. |
Processing Storage Conditions: | On ice |
Analysis:
Analysis ID: | AN003283 |
Laboratory Name: | Martinos Center for Biomedical Imaging |
Analysis Type: | NMR |
Acquisition Date: | June 2018-January 2019 |
Software Version: | Bruker Biospin NMR System |
Operator Name: | Leo L Cheng |
Detector Type: | Topspin |
Results File: | HRMAS_NMR_data_Glioma.txt |
Units: | Peak Area |
NMR:
NMR ID: | NM000225 |
Analysis ID: | AN003283 |
Instrument Name: | Bruker Avence |
Instrument Type: | Other |
NMR Experiment Type: | Other |
NMR Comments: | Triple nucleus (1H,13C,31P) HRMAS probe |
Field Frequency Lock: | D2O |
Spectrometer Frequency: | 600MHz |
NMR Probe: | Triple nucleus (1 H, 13 C, 31 P) HRMAS probe |
NMR Solvent: | D2O |
NMR Tube Size: | 4mm |
Shimming Method: | Autoshim |
Pulse Sequence: | 90° Pulse Sequence |
Water Suppression: | PLdB9 |
Pulse Width: | 3 μs |
Power Level: | -14 dB |
Chemical Shift Ref Cpd: | TSP |
Temperature: | 4℃ |
Number Of Scans: | 256 |
Dummy Scans: | 4 |
Relaxation Delay: | 5 s |
Spectral Width: | 12 ppm |
Num Data Points Acquired: | 4096 |
Line Broadening: | 0.5Hz |
Chemical Shift Ref Std: | TSP at 0ppm, Lactate at 1.318ppm, Alanine at 1.468ppm |
Binned Increment: | 0.01 |
Binned Data Protocol File: | N A |