Automatic classification of chromosomes by means of quadratically asymmetric statistical distributions

✍ Scribed by Gunter Ritter; Karl Gaggermeier

• Book ID: 104160403
• Publisher: Elsevier Science
• Year: 1999
• Tongue: English
• Weight: 163 KB
• Volume: 32
• Category: Article
• ISSN: 0031-3203
• DOI: 10.1016/s0031-3203(98)00131-9

✦ Synopsis

We use quadratically asymmetric distributions as introduced in Ritter [1, 2] as statistical models of human chromosomes for automatic constrained Bayesian classi"cation into their 24 classes. These distributions are able to re#ect asymmetries in the data. Moreover, we design algorithms for constrained classi"cation of cells with missing and extra chromosomes (trisomies).

Applied to the Edinburgh features of the large Copenhagen data set Cpr, the best classi"er reported here reduces the cross-validation error rate from 2.7% (classical normal model) to 1.2% with respect to chromosomes. On the average, "ve out of six cells are completely correctly classi"ed.