Distance Profiles (DiP): A translationally and rotationally invariant 3D structure descriptor capturing steric properties of molecules

Baumann, Knut

doi:10.1002/1521-3838(200211)21:5<507::aid-qsar507>3.0.co;2-l

Cited by 20 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9 The second data set comprises 36 aryl sulfonamides that act as inhibitors of the endothelin receptor subtype-A (ET A ). 84 The alignment for GRID/PLS was taken from a previous study (variant based on crystal structure of BMS182874). 85 The third data set consists of 38 different PGF 2α analogues that show an antinidatory effect in either hamster or rat which is measured as a log(ED 50 )-value.…”

Section: ■ Materials and Methodsmentioning

confidence: 99%

See 1 more Smart Citation

xMaP—An Interpretable Alignment-Free Four-Dimensional Quantitative Structure–Activity Relationship Technique Based on Molecular Surface Properties and Conformer Ensembles

Dreher

Scheiber

Stiefl

et al. 2018

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

A novel alignment-free molecular descriptor called xMaP (flexible MaP descriptor) is introduced. The descriptor is the advancement of the previously published translationally and rotationally invariant three-dimensional (3D) descriptor MaP (mapping property distributions onto the molecular surface) to the fourth dimension (4D). In addition to MaP, xMaP is independent of the chosen starting conformation of the encoded molecules and is therefore entirely alignment-free. This is achieved by using ensembles of conformers, which are generated by conformational searches. This step of the procedure is similar to Hopfinger's 4D quantitative structure-activity relationship (QSAR). A five-step procedure is used to compute the xMaP descriptor. First, a conformational search for each molecule is carried out. Next, for each of the conformers an approximation to the molecular surface with equally distributed surface points is computed. Third, molecular properties are projected onto this surface. Fourth, areas of identical properties are clustered to so-called patches. Fifth, the spatial distribution of the patches is converted into an alignment-free descriptor that is based on the entire conformer ensemble. The resulting descriptor can be interpreted by superimposing the most important descriptor variables and the molecules of the data set. The most important descriptor variables are identified with chemometric regression tools. The novel descriptor was applied to several benchmark data sets and was compared to other descriptors and QSAR techniques comprising a binary fingerprint, a topological pharmacophore descriptor (Cats2D), and the field-based 3D-QSAR technique GRID/PLS which is alignment-dependent. The use of conformer ensembles renders xMaP very robust. It turns out that xMaP performs very well on (almost) all data sets and that the statistical results are comparable to GRID/PLS. In addition to that, xMaP can also be used to efficiently visualize the derived quantitative structure-activity relationships.

show abstract

Section: ■ Materials and Methodsmentioning

confidence: 99%

“…The alignment was taken from Stiefl . The second data set comprises 36 aryl sulfonamides that act as inhibitors of the endothelin receptor subtype-A (ET A ) . The alignment for GRID/PLS was taken from a previous study (variant based on crystal structure of BMS182874) .…”

Section: Materials and Methodsmentioning

confidence: 99%

xMaP—An Interpretable Alignment-Free Four-Dimensional Quantitative Structure–Activity Relationship Technique Based on Molecular Surface Properties and Conformer Ensembles

Dreher

Scheiber

Stiefl

et al. 2018

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Topological descriptors encode the connectivity of the molecule, examples of which include substructure-matching schemes and bond distance histograms such as 2D autocorrelation functions [Sliwoski et al, 2016]. Geometrical descriptors include radial distribution and 3D autocorrelation functions which calculate histograms of interatomic distances within a molecule, or encoding coefficients of the spherical harmonics which best describe the shape of the molecule [Baumann, 2002, Wang et al, 2011. Topological and geometrical descriptors are often weighted by atomic properties such as partial charge or polarizability to describe the spatial and topological distributions of these properties as well.…”

Section: Structure-based Function Prediction 121 Related Workmentioning

confidence: 99%

3D Deep Learning for Biological Function Prediction from Physical Fields

Golkov¹,

Marcin²,

Mirchev³

et al. 2017

Preprint

View full text Add to dashboard Cite

Predicting the biological function of molecules, be it proteins or drug-like compounds, from their atomic structure is an important and long-standing problem. Function is dictated by structure, since it is by spatial interactions that molecules interact with each other, both in terms of steric complementarity, as well as intermolecular forces. Thus, the electron density field and electrostatic potential field of a molecule contain the "raw fingerprint" of how this molecule can fit to binding partners. In this paper, we show that deep learning can predict biological function of molecules directly from their raw 3D approximated electron density and electrostatic potential fields. Protein function based on EC numbers is predicted from the approximated electron density field. In another experiment, the activity of small molecules is predicted with quality comparable to state-of-the-art descriptor-based methods. We propose several alternative computational models for the GPU with different memory and runtime requirements for different sizes of molecules and of databases. We also propose application-specific multi-channel data representations. With future improvements of training datasets and neural network settings in combination with complementary information sources (sequence, genomic context, expression level), deep learning can be expected to show its generalization power and revolutionize the field of molecular function prediction.

show abstract

“…In view of that, the weighted holistic invariant molecular (WHIM) method [50][51][52] put forward by Todeschini's team makes a great deal of difference from CoMFA methods, and resolves molecular-field energies by classical probes, behaving as a group of rotation-translation invariants derived from a weighted transformation of different physical variables against the steric coordinates of atoms. Since then, several other QSAM methods containing COMMA [53], EVA [54], DiP [55], etc. have also been developed with being independent of conformation alignments, but these methods suffer from the demerits of low resolution of molecular structural information, implicit physicochemical meanings and complicated calculations.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Scale Parameterization Approach of Peptides for Quantitative Sequence-Activity Models

Niu

Xia²,

Liang³

2010

PPL

View full text Add to dashboard Cite

show abstract

Distance Profiles (DiP): A translationally and rotationally invariant 3D structure descriptor capturing steric properties of molecules

Cited by 20 publications

References 28 publications

xMaP—An Interpretable Alignment-Free Four-Dimensional Quantitative Structure–Activity Relationship Technique Based on Molecular Surface Properties and Conformer Ensembles

xMaP—An Interpretable Alignment-Free Four-Dimensional Quantitative Structure–Activity Relationship Technique Based on Molecular Surface Properties and Conformer Ensembles

3D Deep Learning for Biological Function Prediction from Physical Fields

A Multi-Scale Parameterization Approach of Peptides for Quantitative Sequence-Activity Models

Contact Info

Product

Resources

About