Table 1 Main classes of data mining approaches to gene mapping, characterised by three criteria: 1) Descriptive methods primarily aim to recognise the ancestral, shared chromosomal segments identical by descent, whereas predictive methods directly associate with the disease status

Classification

RP,[5, 6] SDA,[7] DICE,[10] MDR,[11]

SVMs [13], Association rules [9]

Predictive

Haplotype and

subject-oriented

Models interactions

Haplotype clustering

HapMiner,[16] CLADHC,[17]

Spatial clustering [18]

Descriptive

Haplotype and

subject-oriented

No interactions

Phenotype clustering

MCA [19]

Predictive

Subject-oriented

No interactions

Haplotype

patterns

HPM [20] and derivatives,[21, 22, 26–28]

TreeDT [30]

Descriptive

Haplotype-oriented

Can model few interactions