SAMPL6 logP challenge: machine learning and quantum mechanical approaches

Patel, Prajay; Kuntz, David M.; Jones, Michael R.; Brooks, Bernard R.; Wilson, Angela K.

doi:10.1007/s10822-020-00287-0

Cited by 13 publications

(8 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A variety of molecular descriptors have been exploited in MLR-based studies aiming to estimate the partition coefficient, such as parameters describing the features of the chemical groups (or the whole molecule) present in the solute, 69 holograms built for each compound, where the hologram consists of the count of each atom-type, 70 surface area and volume, 71,72 hydrophobic area and chain descriptors, 72 and QM-based electronic properties. 73 On the other hand, more complex ML methods such as RFR have been used to describe the quantitative structure-property relationships with lipophilicity. 74,75 Following these studies, MLR and RFR are used here for predicting the log P tol/w values of 252 neutral compounds that encompass a diverse range of physicochemical properties (Fig.…”

Section: Resultsmentioning

confidence: 99%

Prediction of toluene/water partition coefficients in the SAMPL9 blind challenge: assessment of machine learning and IEF-PCM/MST continuum solvation models

Zamora¹,

Viayna²,

Pinheiro³

et al. 2023

Phys. Chem. Chem. Phys.

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Prediction of toluene/water partition coefficients in the SAMPL9 blind challenge: assessment of machine learning and IEF-PCM/MST continuum solvation models

Zamora¹,

Viayna²,

Pinheiro³

et al. 2023

Phys. Chem. Chem. Phys.

View full text Add to dashboard Cite

show abstract

“…A vertical solvation method has been shown to be an effective method to predict log P o/w as part of the SAMPL5 34 and SAMPL6 competitions when combined with more rigorous quantum mechanical methods, e.g., DLPNO-CCSD(T), or ab initio composite approaches, for example, the correlation consistent Composite Approach (ccCA). 35,36 The vertical solvation method is shown as eqn (1),…”

Section: Methodsmentioning

confidence: 99%

“…DFT and DLPNO-Solv-ccCA. The Stampede2 supercomputer was used to perform subsequent calculations using density functional theory (DFT) with the correlation consistent basis sets 50 and DLPNO-Solv-ccCA, 35 a variant of the correlation consistent Composite Approach (ccCA) [51][52][53] that targets solvated properties for larger organic molecules, with ORCA 5.0.3 to widen the scope of investigation with more available resources. The recommended cc-pV(n+d)Z basis sets were used for all S and Cl atoms.…”

Section: Methodsmentioning

confidence: 99%

Integrating multiscale and machine learning approaches towards the SAMPL9 log P challenge

Draper,

Waterman,

Dannatt

et al. 2024

Phys. Chem. Chem. Phys.

Self Cite

View full text Add to dashboard Cite

show abstract

“…hydrophobic area and chain descriptors [73], and QM-based electronic properties [74]. On the other hand, more complex ML methods such as RFR have been used to describe the quantitative structure-property relationships with lipophilicity [75,76].…”

Section: Prediction Of Logptol/w By Mlr and Rfr Modelsmentioning

confidence: 99%

Prediction of Toluene/Water Partition Coefficient in the SAMPL9 Blind Challenge: Assessment of Machine Learning and IEF-PCM/MST Continuum Solvation Models

Zamora

Viayna

Pinheiro

et al. 2023

Preprint

View full text Add to dashboard Cite

In recent years the use of partition systems other than the widely used biphasic n-octanol/water has received increased attention to gain insight into the molecular features that dictate the lipophilicity of compounds. Thus, the difference between n-octanol/water and toluene/water partition coefficients has proven to be a valuable descriptor to study the propensity of molecules to form intramolecular hydrogen bonds and exhibit chameleon-like properties that modulate solubility and permeability. In this context, this study reports the experimental toluene/water partition coefficients (logPtol/w) for a series of 16 drugs that were selected as an external test set in the framework of the Statistical Assessment of the Modeling of Proteins and Ligands (SAMPL) blind challenge. This external set has been used by the computational community to calibrate their methods in the current edition (SAMPL9) of this contest. Furthermore, the study also investigates the performance of two computational strategies for the prediction of logPtol/w. The first relies on the development of two machine learning (ML) models, which are built up by combining the selection of 11 molecular descriptors in conjunction with either multiple linear regression (MLR) and random forest regression (RFR) models to target a dataset of 252 experimental logPtol/w values. The second consists of the parametrization of the IEF-PCM/MST continuum solvation model from B3LYP/6-31G(d) calculations to predict the solvation free energies of 163 compounds in toluene and benzene. The performance of the ML and IEF-PCM/MST models has been calibrated against external test sets, including the compounds that define the SAMPL9 logPtol/w challenge. The results are used to discuss the merits and weaknesses of the two computational approaches.

show abstract

SAMPL6 logP challenge: machine learning and quantum mechanical approaches

Cited by 13 publications

References 54 publications

Prediction of toluene/water partition coefficients in the SAMPL9 blind challenge: assessment of machine learning and IEF-PCM/MST continuum solvation models

Prediction of toluene/water partition coefficients in the SAMPL9 blind challenge: assessment of machine learning and IEF-PCM/MST continuum solvation models

Integrating multiscale and machine learning approaches towards the SAMPL9 log P challenge

Prediction of Toluene/Water Partition Coefficient in the SAMPL9 Blind Challenge: Assessment of Machine Learning and IEF-PCM/MST Continuum Solvation Models

Contact Info

Product

Resources

About