Machine learning based prediction for peptide drift times in ion mobility spectrometry

Shah, Anuj R.; Agarwal, Khushbu; Baker, Erin; Singhal, Mudita; Mayampurath, Anoop; Ibrahim, Yehia; Kangas, Lars J.; Monroe, Matthew E.; Zhao, Rui; Belov, Mikhail E.; Anderson, Gordon A.; Smith, Richard D.

doi:10.1093/bioinformatics/btq245

Cited by 40 publications

(49 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, there are only three individual studies which have reported over 1,000 CCS values and thus would be considered large-scale surveys, 54,55,72 underscoring the fact that the reporting of quantitative ion mobility measurements is predominantly an interlaboratory initiative.…”

Section: Significant Ccs Contributionsmentioning

confidence: 99%

“…The large blue bubble in Figure 7 corresponds to the 8676 peptide cross sections published by Smith and coworkers in 2010 in support of developing theoretical methods for predicting the IM drift time based upon the primary amino acid sequence. 72 While most of the CCS values have been for tryptic peptides, there is recent and significant efforts being made in the quantitative IM analysis of structurally-interesting peptide and protein classes, including helical peptides, 174–176 metalloproteins, 177–180 intrinsically-disordered proteins, 181–184 metamorphic proteins, 185,186 amyloids, 187–194 and membrane-bound proteins and assemblies. 117,195–198 The last three years has seen a balance of cross section reporting across most of the chemical classes, including lipids and carbohydrates.…”

Section: Ccs Coverage Over Timementioning

confidence: 99%

See 1 more Smart Citation

Ion Mobility Collision Cross Section Compendium

2016

View full text Add to dashboard Cite

In this review, we focus on an important aspect of ion mobility (IM) research, namely the reporting of quantitative ion mobility measurements in the form of the gas-phase collision cross section (CCS), which has provided a common basis for comparison across different instrument platforms and offers a unique form of structural information, namely size and shape preferences of analytes in the absence of bulk solvent. This review surveys the over 24,000 CCS values reported from IM methods spanning the era between 1975 to 2015, which provides both a historical and analytical context for the contributions made thus far, as well as insight into the future directions that quantitative ion mobility measurements will have in the analytical sciences. The analysis was conducted in 2016, so CCS values reported in that year are purposely omitted. In another few years, a review of this scope will be intractable, as the number of CCS values which will be reported in the next three to five years is expected to exceed the total amount currently published in the literature.

show abstract

Section: Significant Ccs Contributionsmentioning

confidence: 99%

Section: Ccs Coverage Over Timementioning

confidence: 99%

Ion Mobility Collision Cross Section Compendium

2016

View full text Add to dashboard Cite

show abstract

“…PLSR differs from machine learning classifiers based on Bayes' theorem or support vector machines (Merkwirth et al, 2004;Arimoto et al, 2005) in that it can be used to reconstruct a continuous range of predicted values for the variable of interest, rather than simply binning it into one of two or more categories. Compared with support vector regression, PLSR is easier to implement and interpret, and it often provides similar results (Ustün et al, 2007;Shah et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

Quantifying and Predicting the Promiscuity and Isoform Specificity of Small-Molecule Cytochrome P450 Inhibitors

Nath¹,

Zientek²,

Burke³

et al. 2010

Drug Metab Dispos

View full text Add to dashboard Cite

ABSTRACT:Drug promiscuity (i.e., inhibition of multiple enzymes by a single compound) is increasingly recognized as an important pharmacological consideration in the drug development process. However, systematic studies of functional or physicochemical characteristics that correlate with drug promiscuity are handicapped by the lack of a good way of quantifying promiscuity. In this article, we present a new entropy-based index of drug promiscuity. We apply this index to two high-throughput data sets describing inhibition of cytochrome P450 isoforms by smallmolecule drugs and drug candidates, and we demonstrate how drug promiscuity or specificity can be quantified. For these drug-metabolizing enzymes, we find that there is essentially no correlation between a drug's potency and specificity. We also present an index to quantify the susceptibilities of different enzymes to inhibition by diverse substrates. Finally, we use partial least-squares regression to successfully predict isoform specificity and promiscuity of small molecules, using a set of fingerprint-based descriptors.

show abstract

“…21,22 IM-MS is a particularly useful analytical combination in that the mass spectrometry separates molecules based on their intrinsic mass, whereas ion mobility provides a complimentary separation based on molecular size and shape based on the gas-phase collision cross section (CCS). While there has been significant progress in correlating the CCS to the primary molecular structure and composition, 23–25 it is challenging to predict CCS particularly for isomeric systems. Consequently, the ability of IM-MS to separate any given isomeric system is difficult to predict without referring to empirical studies.…”

mentioning

confidence: 99%

Investigation of the Complete Suite of the Leucine and Isoleucine Isomers: Toward Prediction of Ion Mobility Separation Capabilities

2016

View full text Add to dashboard Cite

In this study we investigated 11 isomers with the molecular formula C6H13NO2 (m/z 131) to ascertain the potential of utilizing drift tube ion mobility mass spectrometry to aid in the separation of isomeric mixtures. This study of small molecules provides a detailed examination of the application of uniform field ion mobility for a narrow scope of isomers with variations in both bond coordination and stereochemistry. For small molecules, it was observed that in general constitutional isomers are more readily separated by uniform field mobility in comparison to stereoisomers such as enantiomers or diastereomers. Diastereomers exhibited differences in their collision cross section (CCS), but were unresolvable in a mixture, whereas the enantiomers studied did not exhibit statistically different CCS values. A mathematical relationship relating the CCS to resolving power was developed in order to predict the required ion mobility resolving power needed to separate the various isomer classes. For the majority of isomers evaluated in this study, a uniform field-based resolving power of 100 was predicted to be sufficient to resolve over half (ca. 60%) of all hypothetical isomer pairs, including leucine and isoleucine, whereas their stereoisomers (D- and L-forms) are predicted to be significantly more challenging, if not impossible, to separate by conventional drift tube techniques.

show abstract

Machine learning based prediction for peptide drift times in ion mobility spectrometry

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 40 publications

References 44 publications

Ion Mobility Collision Cross Section Compendium

Ion Mobility Collision Cross Section Compendium

Quantifying and Predicting the Promiscuity and Isoform Specificity of Small-Molecule Cytochrome P450 Inhibitors

Investigation of the Complete Suite of the Leucine and Isoleucine Isomers: Toward Prediction of Ion Mobility Separation Capabilities

Contact Info

Product

Resources

About