Gurpreet Singh
Gurpreet Singh has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Lakshminarayanan Samavedham
National University of Singapore
2 shared publications - Subhi J. Al’aRef
Division of Cardiology, Department of Internal Medicine, University of Arkansas for Medical Sciences, Little Rock, AR 72205, USA
2 shared publications Ahmed Essaghir
GSK , Rixensart, Belgium
1 shared publicationAlexander Hudson
GSK , Siena, Italy
1 shared publicationAlexander R van Rosendael
Dalio Institute of Cardiovascular Imaging, Weill Cornell Medicine and NewYork-Presbyterian Hospital , New York, NY, USA
1 shared publicationAlexander R. van Rosendael
Affiliation Department of Cardiology, Leiden University Medical Center, Leiden, The Netherlands
1 shared publication
Latest Publications
- 1 February 2022
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 38 (7) , 2062-2063
TMQuery: a database of precomputed template modeling scores for assessment of protein structural similarity
Summary: Comparisons of protein structures are critical for developing novel protein designs, annotating protein functions and predicting protein structure. The template modeling score (TM-score) is a widely used but computationally expensive measure of protein similarity that is applicable to a wide variety of structural biology problems. We introduce TMQuery—a continuously updated database containing over eight billion pre-computed TM-score values for every pair of proteins in the Protein Data Bank, allowing researchers to quickly query and download TM-scores via a web interface. Availability and implementation: Publicly available at https://tmquery.gsk.com/.
- 1 February 2022
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 38 (7) , 2062-2063
TMQuery: a database of precomputed template modeling scores for assessment of protein structural similarity
Summary: Comparisons of protein structures are critical for developing novel protein designs, annotating protein functions and predicting protein structure. The template modeling score (TM-score) is a widely used but computationally expensive measure of protein similarity that is applicable to a wide variety of structural biology problems. We introduce TMQuery—a continuously updated database containing over eight billion pre-computed TM-score values for every pair of proteins in the Protein Data Bank, allowing researchers to quickly query and download TM-scores via a web interface. Availability and implementation: Publicly available at https://tmquery.gsk.com/.
- Open Access
- 30 September 2020
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (9) , e0239934
Comparing a novel machine learning method to the Friedewald formula and Martin-Hopkins equation for low-density lipoprotein estimation
Low-density lipoprotein cholesterol (LDL-C) is a target for cardiovascular prevention. Contemporary equations for LDL-C estimation have limited accuracy in certain scenarios (high triglycerides [TG], very low LDL-C). We derived a novel method for LDL-C estimation from the standard lipid profile using a machine learning (ML) approach utilizing random forests (the Weill Cornell model). We compared its correlation to direct LDL-C with the Friedewald and Martin-Hopkins equations for LDL-C estimation. The study cohort comprised a convenience sample of standard lipid profile measurements (with the directly measured components of total cholesterol [TC], high-density lipoprotein cholesterol [HDL-C], and TG) as well as chemical-based direct LDL-C performed on the same day at the New York-Presbyterian Hospital/Weill Cornell Medicine (NYP-WCM). Subsequently, an ML algorithm was used to construct a model for LDL-C estimation. Results are reported on the held-out test set, with correlation coefficients and absolute residuals used to assess model performance. Between 2005 and 2019, there were 17,500 lipid profiles performed on 10,936 unique individuals (4,456 females; 40.8%) aged 1 to 103. Correlation coefficients between estimated and measured LDL-C values were 0.982 for the Weill Cornell model, compared to 0.950 for Friedewald and 0.962 for the Martin-Hopkins method. The Weill Cornell model was consistently better across subgroups stratified by LDL-C and TG values, including TG >500 and LDL-C <70. An ML model was found to have a better correlation with direct LDL-C than either the Friedewald formula or Martin-Hopkins equation, including in the setting of elevated TG and very low LDL-C.
- 30 September 2020
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (9) , e0239934
Open AccessComparing a novel machine learning method to the Friedewald formula and Martin-Hopkins equation for low-density lipoprotein estimation
Low-density lipoprotein cholesterol (LDL-C) is a target for cardiovascular prevention. Contemporary equations for LDL-C estimation have limited accuracy in certain scenarios (high triglycerides [TG], very low LDL-C). We derived a novel method for LDL-C estimation from the standard lipid profile using a machine learning (ML) approach utilizing random forests (the Weill Cornell model). We compared its correlation to direct LDL-C with the Friedewald and Martin-Hopkins equations for LDL-C estimation. The study cohort comprised a convenience sample of standard lipid profile measurements (with the directly measured components of total cholesterol [TC], high-density lipoprotein cholesterol [HDL-C], and TG) as well as chemical-based direct LDL-C performed on the same day at the New York-Presbyterian Hospital/Weill Cornell Medicine (NYP-WCM). Subsequently, an ML algorithm was used to construct a model for LDL-C estimation. Results are reported on the held-out test set, with correlation coefficients and absolute residuals used to assess model performance. Between 2005 and 2019, there were 17,500 lipid profiles performed on 10,936 unique individuals (4,456 females; 40.8%) aged 1 to 103. Correlation coefficients between estimated and measured LDL-C values were 0.982 for the Weill Cornell model, compared to 0.950 for Friedewald and 0.962 for the Martin-Hopkins method. The Weill Cornell model was consistently better across subgroups stratified by LDL-C and TG values, including TG >500 and LDL-C <70. An ML model was found to have a better correlation with direct LDL-C than either the Friedewald formula or Martin-Hopkins equation, including in the setting of elevated TG and very low LDL-C.
- 12 September 2019
- Published by Oxford University Press (OUP) in European Heart Journal
- Vol. 41 (3) , 359-367
Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry
Symptom-based pretest probability scores that estimate the likelihood of obstructive coronary artery disease (CAD) in stable chest pain have moderate accuracy. We sought to develop a machine learning (ML) model, utilizing clinical factors and the coronary artery calcium score (CACS), to predict the presence of obstructive CAD on coronary computed tomography angiography (CCTA). The study screened 35 281 participants enrolled in the CONFIRM registry, who underwent ≥64 detector row CCTA evaluation because of either suspected or previously established CAD. A boosted ensemble algorithm (XGBoost) was used, with data split into a training set (80%) on which 10-fold cross-validation was done and a test set (20%). Performance was assessed of the (1) ML model (using 25 clinical and demographic features), (2) ML + CACS, (3) CAD consortium clinical score, (4) CAD consortium clinical score + CACS, and (5) updated Diamond-Forrester (UDF) score. The study population comprised of 13 054 patients, of whom 2380 (18.2%) had obstructive CAD (≥50% stenosis). Machine learning with CACS produced the best performance [area under the curve (AUC) of 0.881] compared with ML alone (AUC of 0.773), CAD consortium clinical score (AUC of 0.734), and with CACS (AUC of 0.866) and UDF (AUC of 0.682), P < 0.05 for all comparisons. CACS, age, and gender were the highest ranking features. A ML model incorporating clinical features in addition to CACS can accurately estimate the pretest likelihood of obstructive CAD on CCTA. In clinical practice, the utilization of such an approach could improve risk stratification and help guide downstream management.
- 12 September 2019
- Published by Oxford University Press (OUP) in European Heart Journal
- Vol. 41 (3) , 359-367
Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry
Symptom-based pretest probability scores that estimate the likelihood of obstructive coronary artery disease (CAD) in stable chest pain have moderate accuracy. We sought to develop a machine learning (ML) model, utilizing clinical factors and the coronary artery calcium score (CACS), to predict the presence of obstructive CAD on coronary computed tomography angiography (CCTA). The study screened 35 281 participants enrolled in the CONFIRM registry, who underwent ≥64 detector row CCTA evaluation because of either suspected or previously established CAD. A boosted ensemble algorithm (XGBoost) was used, with data split into a training set (80%) on which 10-fold cross-validation was done and a test set (20%). Performance was assessed of the (1) ML model (using 25 clinical and demographic features), (2) ML + CACS, (3) CAD consortium clinical score, (4) CAD consortium clinical score + CACS, and (5) updated Diamond-Forrester (UDF) score. The study population comprised of 13 054 patients, of whom 2380 (18.2%) had obstructive CAD (≥50% stenosis). Machine learning with CACS produced the best performance [area under the curve (AUC) of 0.881] compared with ML alone (AUC of 0.773), CAD consortium clinical score (AUC of 0.734), and with CACS (AUC of 0.866) and UDF (AUC of 0.682), P < 0.05 for all comparisons. CACS, age, and gender were the highest ranking features. A ML model incorporating clinical features in addition to CACS can accurately estimate the pretest likelihood of obstructive CAD on CCTA. In clinical practice, the utilization of such an approach could improve risk stratification and help guide downstream management.
- 1 May 2018
- Published by Elsevier in Clinical Imaging
- Vol. 49, VII-IX
Artificial intelligence in clinical imaging: An introduction
- 1 May 2018
- Published by Elsevier in Clinical Imaging
- Vol. 49, VII-IX
Artificial intelligence in clinical imaging: An introduction
- 1 January 2016
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 49 (7) , 990-995
Machine Learning-Based Framework for Multi-Class Diagnosis of Neurodegenerative Diseases: A Study on Parkinson’s Disease
- 1 January 2016
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 49 (7) , 990-995
Machine Learning-Based Framework for Multi-Class Diagnosis of Neurodegenerative Diseases: A Study on Parkinson’s Disease
- 26 March 2013
- Published by Wiley in Journal of Mass Spectrometry
- Vol. 48 (4) , 465-477
Mass spectrometry based lipid(ome) analyzer and molecular platform: a new software to interpret and analyze electrospray and/or matrix‐assisted laser desorption/ionization mass spectrometric data of lipids: a case study from Mycobacterium tuberculosis
Mass Spectrometry based Lipid(ome) Analyzer and Molecular Platform (MS‐LAMP) is a new software capable of aiding in interpreting electrospray ionization (ESI) and/or matrix‐assisted laser desorption/ionization (MALDI) mass spectrometric data of lipids. The graphical user interface (GUI) of this standalone programme is built using Perl::Tk. Two databases have been developed and constituted within MS‐LAMP, on the basis of Mycobacterium tuberculosis (M. tb) lipid database (www.mrl.colostate.edu) and that of Lipid Metabolites and Pathways Strategy Consortium (LIPID MAPS; www.lipidmaps.org).Different types of queries entered through GUI would interrogate with a chosen database. The queries can be molecular mass(es) or mass‐to‐charge (m/z) value(s) and molecular formula. LIPID MAPS identifier also can be used to search but not for M. tb lipids. Multiple choices have been provided to select diverse ion types and lipids. Satisfying to input parameters, a glimpse of various lipid categories and their population distribution can be viewed in the output. Additionally, molecular structures of lipids in the output can be seen using ChemSketch (www.acdlabs.com), which has been linked to the programme. Furthermore, a version of MS‐LAMP for use in Linux operating system is separately available, wherein PyMOL can be used to view molecular structures that result as output from General Lipidome MS‐LAMP.The utility of this software is demonstrated using ESI mass spectrometric data of lipid extracts of M. tb grown under two different pH (5.5 and 7.0) conditions. Copyright © 2013 John Wiley & Sons, Ltd.
- 26 March 2013
- Published by Wiley in Journal of Mass Spectrometry
- Vol. 48 (4) , 465-477
Mass spectrometry based lipid(ome) analyzer and molecular platform: a new software to interpret and analyze electrospray and/or matrix‐assisted laser desorption/ionization mass spectrometric data of lipids: a case study from Mycobacterium tuberculosis
Mass Spectrometry based Lipid(ome) Analyzer and Molecular Platform (MS‐LAMP) is a new software capable of aiding in interpreting electrospray ionization (ESI) and/or matrix‐assisted laser desorption/ionization (MALDI) mass spectrometric data of lipids. The graphical user interface (GUI) of this standalone programme is built using Perl::Tk. Two databases have been developed and constituted within MS‐LAMP, on the basis of Mycobacterium tuberculosis (M. tb) lipid database (www.mrl.colostate.edu) and that of Lipid Metabolites and Pathways Strategy Consortium (LIPID MAPS; www.lipidmaps.org).Different types of queries entered through GUI would interrogate with a chosen database. The queries can be molecular mass(es) or mass‐to‐charge (m/z) value(s) and molecular formula. LIPID MAPS identifier also can be used to search but not for M. tb lipids. Multiple choices have been provided to select diverse ion types and lipids. Satisfying to input parameters, a glimpse of various lipid categories and their population distribution can be viewed in the output. Additionally, molecular structures of lipids in the output can be seen using ChemSketch (www.acdlabs.com), which has been linked to the programme. Furthermore, a version of MS‐LAMP for use in Linux operating system is separately available, wherein PyMOL can be used to view molecular structures that result as output from General Lipidome MS‐LAMP.The utility of this software is demonstrated using ESI mass spectrometric data of lipid extracts of M. tb grown under two different pH (5.5 and 7.0) conditions. Copyright © 2013 John Wiley & Sons, Ltd.