Estimation of melting temperature of molecular cocrystals using artificial neural network model

Rama Krishna Gamidi, Åke C. Rasmuson

Research output: Contribution to journalArticlepeer-review

Abstract

A quantitative structure−activity relationship model has been constructed by artificial neural networks for estimation of melting temperature (Tm) of molecular cocrystals (CCs). On the basis of a literature analysis using SciFinder and Cambridge Structural Database softwares, a database has been created of CCs for four active pharmaceutical ingredients, namely, caffeine, theophylline (THP), nicotinamide (NA), and isonicotinamide (INA). In total, of 61 CCs were included: 14-CAF, 9-THP, 29-INA, and 9-NA. A good correlation was obtained with ANNs to quantify the Tm of the CCs with respect to various coformers. The training process was completed with an average relative error of 2.38%, whereas the relative error for the validation set was 2.89%.

Original languageEnglish
Pages (from-to)175-182
Number of pages8
JournalCrystal Growth and Design
Volume17
Issue number1
DOIs
Publication statusPublished - 4 Jan 2017

Fingerprint

Dive into the research topics of 'Estimation of melting temperature of molecular cocrystals using artificial neural network model'. Together they form a unique fingerprint.

Cite this