Automatic Classification of Staphylococci by Principal-Component Analysis and a Gradient Method

Abstract

Forty-nine strains from the species Staphylococcus aureus, S. saprophyticus, S. lactis, S. afermentans, and S. roseus were submitted to different taxometric analyses; clustering was performed by single linkage, by the unweighted pair group method, and by principal-component analysis followed by a gradient method. Results were substantially tne same with all methods. All S. aureus clustered together, sharply separated from S. roseus and S. afermentans S. lactis and S. saprophyticus fell between, with the latter nearer to S. aureus. The main purpose of this study was to in-troduce a new taxometric technique, based on principal-component analysis followed by a gradient method, and to compare it with some other methods in current use. Advantages of the new method are complete automation and therefore greater objectivity, execution of the clustering in a space of reduced dimensions in which different characters have different weights, easy recognition of taxonomically important characters, and opportunity for representing clusters in three-dimensional models; the principal disadvantage is the need for large compu-ter facilities.