Is there a role for the integral equation theory of molecular liquids in chemical informatics?

Research output: Contribution to conferenceSpeech

Abstract

We propose a fast and efficient method to compute molecular descriptors based on the Integral Equation Theory (IET) of Molecular Liquids. The new RISM-MOL-INF descriptors are obtained from solute-solvent correlation functions computed by the 1D Reference Interaction Site Model (RISM). The RISM-MOL-INF descriptors are conceptually different from those commonly used in chemical informatics, since they fingerprint solutes by the change they induce in solvent density distribution, rather than by the solute molecular structure alone. It is shown that key solvation thermodynamic and ADME properties can be predicted accurately using machine learning algorithms trained on RISM-MOL-INF descriptors only. Since they can be evaluated in a matter of minutes for most small organic and druglike molecules, the RISM-MOL-INF descriptors are suitable for medium to high-throughput in silico screening in applications such as pharmaceutical research and development. Due to the importance of solvation and desolvation effects in biological systems, we believe that the RISM-MOL-INF descriptors will find many applications in biophysical and biomedical property prediction.

Conference

Conference248th ACS National Meeting & Exposition
CountryUnited Kingdom
CitySan Francisco
Period10/08/1414/08/14
Internet address

Fingerprint

manned orbital laboratories
Integral equations
integral equations
Liquids
liquids
solutes
Solvation
interactions
solvation
machine learning
Biological systems
research and development
Learning algorithms
Molecular structure
density distribution
Learning systems
Screening
molecular structure
screening
thermodynamic properties

Keywords

  • integral equation theory
  • RISM
  • reference interaction site model
  • data mining
  • cheminformatics
  • support vector machine
  • random forest
  • solubility
  • ADMET
  • drug discovery
  • hydration free energy
  • caco-2

Cite this

Palmer, D., & Fedorov, M. (2014). Is there a role for the integral equation theory of molecular liquids in chemical informatics?. 248th ACS National Meeting & Exposition, San Francisco, United Kingdom.
@conference{d1c7f8ac6fe44370aa1e15f7af1853bb,
title = "Is there a role for the integral equation theory of molecular liquids in chemical informatics?",
abstract = "We propose a fast and efficient method to compute molecular descriptors based on the Integral Equation Theory (IET) of Molecular Liquids. The new RISM-MOL-INF descriptors are obtained from solute-solvent correlation functions computed by the 1D Reference Interaction Site Model (RISM). The RISM-MOL-INF descriptors are conceptually different from those commonly used in chemical informatics, since they fingerprint solutes by the change they induce in solvent density distribution, rather than by the solute molecular structure alone. It is shown that key solvation thermodynamic and ADME properties can be predicted accurately using machine learning algorithms trained on RISM-MOL-INF descriptors only. Since they can be evaluated in a matter of minutes for most small organic and druglike molecules, the RISM-MOL-INF descriptors are suitable for medium to high-throughput in silico screening in applications such as pharmaceutical research and development. Due to the importance of solvation and desolvation effects in biological systems, we believe that the RISM-MOL-INF descriptors will find many applications in biophysical and biomedical property prediction.",
keywords = "integral equation theory, RISM, reference interaction site model, data mining, cheminformatics, support vector machine, random forest, solubility, ADMET, drug discovery, hydration free energy, caco-2",
author = "David Palmer and Maxim Fedorov",
year = "2014",
month = "8",
day = "10",
language = "English",
note = "248th ACS National Meeting & Exposition ; Conference date: 10-08-2014 Through 14-08-2014",
url = "http://www.acs.org/content/acs/en/meetings/fall-2014.html",

}

Palmer, D & Fedorov, M 2014, 'Is there a role for the integral equation theory of molecular liquids in chemical informatics?' 248th ACS National Meeting & Exposition, San Francisco, United Kingdom, 10/08/14 - 14/08/14, .

Is there a role for the integral equation theory of molecular liquids in chemical informatics? / Palmer, David; Fedorov, Maxim.

2014. 248th ACS National Meeting & Exposition, San Francisco, United Kingdom.

Research output: Contribution to conferenceSpeech

TY - CONF

T1 - Is there a role for the integral equation theory of molecular liquids in chemical informatics?

AU - Palmer, David

AU - Fedorov, Maxim

PY - 2014/8/10

Y1 - 2014/8/10

N2 - We propose a fast and efficient method to compute molecular descriptors based on the Integral Equation Theory (IET) of Molecular Liquids. The new RISM-MOL-INF descriptors are obtained from solute-solvent correlation functions computed by the 1D Reference Interaction Site Model (RISM). The RISM-MOL-INF descriptors are conceptually different from those commonly used in chemical informatics, since they fingerprint solutes by the change they induce in solvent density distribution, rather than by the solute molecular structure alone. It is shown that key solvation thermodynamic and ADME properties can be predicted accurately using machine learning algorithms trained on RISM-MOL-INF descriptors only. Since they can be evaluated in a matter of minutes for most small organic and druglike molecules, the RISM-MOL-INF descriptors are suitable for medium to high-throughput in silico screening in applications such as pharmaceutical research and development. Due to the importance of solvation and desolvation effects in biological systems, we believe that the RISM-MOL-INF descriptors will find many applications in biophysical and biomedical property prediction.

AB - We propose a fast and efficient method to compute molecular descriptors based on the Integral Equation Theory (IET) of Molecular Liquids. The new RISM-MOL-INF descriptors are obtained from solute-solvent correlation functions computed by the 1D Reference Interaction Site Model (RISM). The RISM-MOL-INF descriptors are conceptually different from those commonly used in chemical informatics, since they fingerprint solutes by the change they induce in solvent density distribution, rather than by the solute molecular structure alone. It is shown that key solvation thermodynamic and ADME properties can be predicted accurately using machine learning algorithms trained on RISM-MOL-INF descriptors only. Since they can be evaluated in a matter of minutes for most small organic and druglike molecules, the RISM-MOL-INF descriptors are suitable for medium to high-throughput in silico screening in applications such as pharmaceutical research and development. Due to the importance of solvation and desolvation effects in biological systems, we believe that the RISM-MOL-INF descriptors will find many applications in biophysical and biomedical property prediction.

KW - integral equation theory

KW - RISM

KW - reference interaction site model

KW - data mining

KW - cheminformatics

KW - support vector machine

KW - random forest

KW - solubility

KW - ADMET

KW - drug discovery

KW - hydration free energy

KW - caco-2

UR - http://www.acs.org/content/acs/en/meetings/fall-2014.html

M3 - Speech

ER -

Palmer D, Fedorov M. Is there a role for the integral equation theory of molecular liquids in chemical informatics?. 2014. 248th ACS National Meeting & Exposition, San Francisco, United Kingdom.