Summary of Study ST001706

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 PR001091. The data can be accessed directly via it's Project DOI: 10.21228/M8P97V 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	ST001706
Study Title	Machine learning-enabled renal cell carcinoma status prediction using multi-platform urine-based metabolomics NMR (part-II)
Study Summary	Currently, Renal Cell Carcinoma (RCC) is identified through expensive cross-sectional imaging, frequently followed by renal mass biopsy, which is invasive and subject to sampling errors. Hence, there is a critical need for a non-invasive diagnostic assay. RCC is a disease of altered cellular metabolism with the tumor(s) in close proximity to the urine in the kidney suggesting metabolomic profiling would be an excellent choice for assay development. Here, we applied liquid chromatography-mass spectrometry (LC-MS), nuclear magnetic resonance (NMR), and machine learning (ML) for the discovery of candidate metabolic panels for RCC. The study cohort consists of 82 RCC patients and 174 healthy controls, these were separated into two sub-cohorts: model cohort and the test cohort. Discriminatory metabolic features were selected in the model cohort, using univariate, wrapper, and embedded methods of feature selection. Three ML techniques with different induction biases were used for training and hyperparameter tuning. Final assessment of RCC status prediction was made using the test cohort with the selected biomarkers and the tuned ML algorithms. A seven-metabolite panel consisting of endogenous and exogenous metabolites enabled the prediction of RCC with 88% accuracy, 94% sensitivity, and 85% specificity in the test cohort, with an AUC of 0.98.
Institute	University of Georgia
Department	Biochemistry and Molecular Biology
Laboratory	Edison Lab/Fernandez Lab
Last Name	Bifarin
First Name	Olatomiwa
Address	315 Riverbend Rd, Athens, GA 30602
Email	olatomiwa.bifarin25@uga.edu
Phone	(706) 542-4401 Lab: 1045
Submit Date	2021-02-11
Raw Data Available	Yes
Raw Data File Type(s)	fid
Analysis Type Detail	NMR
Release Date	2021-04-27
Release Version	1

Select appropriate tab below to view additional metadata details:

Project:

Project ID:	PR001091
Project DOI:	doi: 10.21228/M8P97V
Project Title:	Machine learning-enabled renal cell carcinoma status prediction using multi-platform urine-based metabolomics
Project Type:	multi-platform urine-based metabolomics
Project Summary:	Currently, Renal Cell Carcinoma (RCC) is identified through expensive cross-sectional imaging, frequently followed by renal mass biopsy, which is invasive and subject to sampling errors. Hence, there is a critical need for a non-invasive diagnostic assay. RCC is a disease of altered cellular metabolism with the tumor(s) in close proximity to the urine in the kidney suggesting metabolomic profiling would be an excellent choice for assay development. Here, we applied liquid chromatography-mass spectrometry (LC-MS), nuclear magnetic resonance (NMR), and machine learning (ML) for the discovery of candidate metabolic panels for RCC. The study cohort consists of 82 RCC patients and 174 healthy controls, these were separated into two sub-cohorts: model cohort and the test cohort. Discriminatory metabolic features were selected in the model cohort, using univariate, wrapper, and embedded methods of feature selection. Three ML techniques with different induction biases were used for training and hyperparameter tuning. Final assessment of RCC status prediction was made using the test cohort with the selected biomarkers and the tuned ML algorithms. A seven-metabolite panel consisting of endogenous and exogenous metabolites enabled the prediction of RCC with 88% accuracy, 94% sensitivity, and 85% specificity in the test cohort, with an AUC of 0.98.
Institute:	University of Georgia
Department:	Biochemistry and Molecular Biology
Laboratory:	Edison Lab
Last Name:	Bifarin
First Name:	Olatomiwa
Address:	315 Riverbend Rd, Athens, GA 30602
Email:	olatomiwa.bifarin25@uga.edu
Phone:	(706) 542-4401 Lab: 1045

Subject:

Subject ID:	SU001783
Subject Type:	Human
Subject Species:	Homo sapiens
Taxonomy ID:	9606

Factors:

Subject type: Human; Subject species: Homo sapiens (Factor headings shown in green)

mb_sample_id	local_sample_id	SampleType
SA158685	1000	-
SA158686	2000	-
SA158687	207	Control
SA158688	206	Control
SA158689	208	Control
SA158690	212	Control
SA158691	204	Control
SA158692	211	Control
SA158693	200	Control
SA158694	195	Control
SA158695	198	Control
SA158696	199	Control
SA158697	215	Control
SA158698	202	Control
SA158699	220	Control
SA158700	240	Control
SA158701	238	Control
SA158702	243	Control
SA158703	246	Control
SA158704	248	Control
SA158705	231	Control
SA158706	228	Control
SA158707	219	Control
SA158708	190	Control
SA158709	222	Control
SA158710	225	Control
SA158711	216	Control
SA158712	187	Control
SA158713	151	Control
SA158714	149	Control
SA158715	152	Control
SA158716	154	Control
SA158717	155	Control
SA158718	145	Control
SA158719	143	Control
SA158720	134	Control
SA158721	135	Control
SA158722	137	Control
SA158723	141	Control
SA158724	157	Control
SA158725	158	Control
SA158726	180	Control
SA158727	176	Control
SA158728	181	Control
SA158729	251	Control
SA158730	188	Control
SA158731	174	Control
SA158732	173	Control
SA158733	159	Control
SA158734	3	Control
SA158735	169	Control
SA158736	172	Control
SA158737	189	Control
SA158738	254	Control
SA158739	320	Control
SA158740	318	Control
SA158741	322	Control
SA158742	323	Control
SA158743	324	Control
SA158744	315	Control
SA158745	314	Control
SA158746	306	Control
SA158747	309	Control
SA158748	310	Control
SA158749	313	Control
SA158750	325	Control
SA158751	329	Control
SA158752	344	Control
SA158753	343	Control
SA158754	346	Control
SA158755	347	Control
SA158756	348	Control
SA158757	340	Control
SA158758	337	Control
SA158759	330	Control
SA158760	333	Control
SA158761	335	Control
SA158762	336	Control
SA158763	304	Control
SA158764	301	Control
SA158765	265	Control
SA158766	264	Control
SA158767	266	Control
SA158768	267	Control
SA158769	268	Control
SA158770	261	Control
SA158771	260	Control
SA158772	133	Control
SA158773	255	Control
SA158774	257	Control
SA158775	259	Control
SA158776	273	Control
SA158777	276	Control
SA158778	294	Control
SA158779	296	Control
SA158780	299	Control
SA158781	300	Control
SA158782	292	Control
SA158783	291	Control
SA158784	279	Control

Showing page 1 of 3 Results: 1 2 3 Next Showing results 1 to 100 of 258

Collection:

Collection ID:	CO001776
Collection Summary:	Urine samples were collected at the Emory University Hospital
Collection Protocol Filename:	2_Collection_protocol_RCC_FEB2021.docx
Sample Type:	Urine

Treatment:

Treatment ID:	TR001796
Treatment Summary:	There were no treatments in the study, urine samples of healthy subjects and renal cell carcinoma patients were collected.

Sample Preparation:

Sampleprep ID:	SP001789
Sampleprep Summary:	Urine’s samples were prepared for both NMR and MS experiments
Sampleprep Protocol Filename:	3_Sample_preparation_protocol_RCC_FEB2021.docx
Processing Storage Conditions:	-80℃

Analysis:

Analysis ID:	AN002779
Laboratory Name:	Edison Lab
Analysis Type:	NMR
Num Factors:	3
Num Metabolites:	50
Units:	Area Under the Curve

NMR:

NMR ID:	NM000200
Analysis ID:	AN002779
Instrument Name:	Bruker Avance lll
Instrument Type:	FT-NMR
NMR Experiment Type:	1D-1H
NMR Comments:	Analysis protocol is in 4_Analysis protocol_RCC_FEB2021 (section on NMR); detailed acquisition and processing parameters are in 5_NMRAcquisition_RCC_FEB2021.
Spectrometer Frequency:	600 MHz