A random forest model for predicting the crystallisability of organic molecules

Rajni M. Bhardwaj; Andrea Johnston; Blair F. Johnston; Alastair J. Florence

doi:10.1039/c4ce02403f

A random forest model for predicting the crystallisability of organic molecules

Rajni M. Bhardwaj, Andrea Johnston, Blair F. Johnston, Alastair J. Florence^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

22 Citations (Scopus)

103 Downloads (Pure)

Abstract

A random forest model has for the first time enabled the prediction of the crystallisability (crystals vs. no crystals) of organic molecules with ∼70% accuracy. The predictive model is based on calculated molecular descriptors and published experimental crystallisation propensities of a library of substituted acylanilides.

Original language	English
Pages (from-to)	4272-4275
Number of pages	4
Journal	CrystEngComm
Volume	17
Issue number	23
Early online date	16 Feb 2015
DOIs	https://doi.org/10.1039/c4ce02403f
Publication status	Published - 21 Jun 2015

Keywords

crystallisability
acylanilides
molecular descriptors
Machine Learning

Access to Document

10.1039/c4ce02403f

Bhardwaj-etal-CEC2015-random-forest-model-for-predicting-the-crystallisability-of-organic-moleculesAccepted author manuscript, 758 KB

Cite this

@article{4f7573285784404abede26ec2b23f819,

title = "A random forest model for predicting the crystallisability of organic molecules",

abstract = "A random forest model has for the first time enabled the prediction of the crystallisability (crystals vs. no crystals) of organic molecules with ∼70% accuracy. The predictive model is based on calculated molecular descriptors and published experimental crystallisation propensities of a library of substituted acylanilides.",

keywords = "crystallisability, acylanilides, molecular descriptors, Machine Learning",

author = "Bhardwaj, {Rajni M.} and Andrea Johnston and Johnston, {Blair F.} and Florence, {Alastair J.}",

year = "2015",

month = jun,

day = "21",

doi = "10.1039/c4ce02403f",

language = "English",

volume = "17",

pages = "4272--4275",

journal = "CrystEngComm",

issn = "1466-8033",

publisher = "Royal Society of Chemistry",

number = "23",

}

TY - JOUR

T1 - A random forest model for predicting the crystallisability of organic molecules

AU - Bhardwaj, Rajni M.

AU - Johnston, Andrea

AU - Johnston, Blair F.

AU - Florence, Alastair J.

PY - 2015/6/21

Y1 - 2015/6/21

N2 - A random forest model has for the first time enabled the prediction of the crystallisability (crystals vs. no crystals) of organic molecules with ∼70% accuracy. The predictive model is based on calculated molecular descriptors and published experimental crystallisation propensities of a library of substituted acylanilides.

AB - A random forest model has for the first time enabled the prediction of the crystallisability (crystals vs. no crystals) of organic molecules with ∼70% accuracy. The predictive model is based on calculated molecular descriptors and published experimental crystallisation propensities of a library of substituted acylanilides.

KW - crystallisability

KW - acylanilides

KW - molecular descriptors

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=84930959020&partnerID=8YFLogxK

UR - http://pubs.rsc.org/en/journals/journalissues/ce

U2 - 10.1039/c4ce02403f

DO - 10.1039/c4ce02403f

M3 - Article

AN - SCOPUS:84930959020

SN - 1466-8033

VL - 17

SP - 4272

EP - 4275

JO - CrystEngComm

JF - CrystEngComm

IS - 23

ER -

A random forest model for predicting the crystallisability of organic molecules

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Alastair Florence

Blair Johnston, Assistant Director CMAC National Facility

Cite this

A random forest model for predicting the crystallisability of organic molecules

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Profiles

Alastair Florence

Blair Johnston, Assistant Director CMAC National Facility

Cite this