Skip to main content

Table 2 List of features used in the classifiers, types of their values, and source of data

From: ISOWN: accurate somatic mutation identification in the absence of normal tissue controls

Features

Type of value

Internal or external

Number of distinct values

COSMIC_CNT

Integer

External database

Numeric

ExAC

Boolean

External database

2

dbSNP

Boolean

External database

2

Mutation assessor

Categorical

External database

5

PolyPhen-2

Categorical

External database

3

Sequence context

Categorical

Human genome

64

Sample frequency (SF)

Double

Internal data

Numeric

Variant allele frequency

Double

Internal data

Numeric

Flanking regions

Double

Internal data

Numeric

Substitution pattern

Categorical

Internal data

6