Prediction of Critical Temperatures and Pressures of Industrially Important Organic Compounds from Molecular Structure

• Published in: Journal of Chemical Information and Computer Sciences Vol. 38; no. 4; pp. 639 - 645
• Main Authors: Turner, Brian E, Costello, Chandra L, Jurs, Peter C
• Format: Journal Article
• Language: English
• Published: American Chemical Society 01.07.1998
• Subjects: Chemical structures; Computerized information storage and retrieval; Quantitative structure activity relationships; Similarity measures
• ISSN: 0095-2338; 1549-960X; 1520-5142
• DOI: 10.1021/ci9800054

Quantitative−structure property relationships methods are used to develop mathematical models to predict critical temperatures and pressures of a diverse set of organic compounds taken from the Design Institute for Physical Property Data (DIPPR) database. Each compound is represented with calculated molecular structure descriptors that encode its topological, electronic, geometrical, and other features. Subsets of descriptors are selected with simulated annealing and genetic algorithms. Models to predict the critical properties are constructed using multiple linear regression analysis and computational neural networks with errors comparable to the experimental errors of the critical property data.