From: Neural networks for genetic epidemiology: past, present, and future
Publication | Input | Output | Hidden Layer | |||
---|---|---|---|---|---|---|
 | Type | Coding | Type | Coding | Number Layers | Number Nodes |
Bhat et al. 1999 | Binary | 0 = absence of allele | Binary | 1/0/0 = unaffected | 1 | 15 |
 |  | 1 = presence of allele |  | 0/1/0 = mildly affected |  |  |
 |  |  |  | 0/0/1 = severely affected |  |  |
Bush et al 2005 | Discrete | -1, -1 = 1/1 genotype | Binary | 0 = unaffected | GP evolved | |
 |  | 0, + 2 = 1/2 genotype |  | 1 = affected |  |  |
 |  | +1, -1 = 2/2 genotype |  |  |  |  |
Costello et al. 2003 | Dicrete | Varied | Binary | 0 = unaffected | Multiple variations | |
 |  |  |  | 1 = affected |  |  |
Curtis et al. 2001 | Discrete | 0 = AA genotype | Binary | 0 = unaffected | 2 | 3 |
 |  | 1 = AB genotype |  | 1 = affected |  |  |
 |  | 2 = BB genotype |  |  |  |  |
Curtis 2007 | Discrete | 0 = AA genotype | Binary | 0 = unaffected | 2 | 3 |
 |  | 1 = AB genotype |  | 1 = affected |  |  |
 |  | 2 = BB genotype |  |  |  |  |
Giachino et al 2007 | Discrete and Continuous | Categorical values of genotypes and clinical features | Binary | 0 = unaffected | 1 | unknown |
 |  |  |  | 1 = affected |  |  |
Li et al. 1999 | Discrete | IBD sharing | Binary | 0/1 = concordant or not | Multiple variations | |
 |  | +1= shared allele |  | 0/1 = affected or unaffected |  |  |
 |  | -1 = unshared allele |  |  |  |  |
 |  | 0 = uninformative |  |  |  |  |
Lin et al 2006 | Discrete | Categories of genotype combinations | Binary | 0 = non-response | Multiple variations | |
 |  |  |  | 1 = response |  |  |
Lucek and Ott 1997 | Binary | 0 = absence of allele | Binary | 4 nodes for each trait (20 total nodes) | 1 | 70 |
 |  | 1 = presence of allele |  | 0 = quantitative trait off |  |  |
 |  |  |  | 1 = quantitative trait on |  |  |
Lucek et al. 1998 | Discrete | IBD sharing | Binary | +1,+1 = target output | 1 | √220 |
 |  | +1= shared allele |  | 0, +1 = noise |  |  |
 |  | -1 = unshared allele |  |  |  |  |
 |  | 0 = uninformative |  |  |  |  |
Marinov and Weeks 2001 | Discrete | IBD sharing | Binary | +1,+1 = target output | 1 | √220 |
 |  | +1= shared allele |  | 0, +1 = noise |  |  |
 |  | -1 = unshared allele |  |  |  |  |
 |  | 0 = uninformative |  |  |  |  |
Matchenko-Shimko and Dube 2006 | Discrete | Three combinations of possible allele combinations, transformed to a 0–1 range | Binary | 0 = control | Multiple variations | |
 |  |  |  | 1 = case |  |  |
Motsinger et al (2006a) | Discrete | -1, -1 = 1/1 genotype | Binary | 0 = unaffected | GP Evolved | |
 |  | 0, + 2 = 1/2 genotype |  | 1 = affected |  |  |
 |  | +1, -1 = 2/2 genotype |  |  |  |  |
Motsinger et al (2006b) | Discrete | -1, -1 = 1/1 genotype | Binary | 0 = unaffected | GE Evolved | |
 |  | 0, + 2 = 1/2 genotype |  | 1 = affected |  |  |
 |  | +1, -1 = 2/2 genotype |  |  |  |  |
North et al 2003 | Discrete | 0 = AA genotype | Binary | 0 = unaffected | Multiple Variations | |
 |  | 1 = AB genotype |  | 1 = affected |  |  |
 |  | 2 = BB genotype |  |  |  |  |
Ott 2001 | Discrete | -1, -1 = 1/1 genotype | Binary | 0 = unaffected | NA | |
 |  | 0, +2 = 1/2 genotype |  | 1 = affected |  |  |
 |  | +1, -1 = 2/2 genotype |  |  |  |  |
Pankratz et al. 2001 | Discrete | IBD sharing | Binary | 1/1 = affected/affected | 1 | 4 |
 |  | +1 = shared allele |  | 0/1 = affected/unaffected |  |  |
 |  | -1 = unshared allele |  |  |  |  |
 |  | 0 = uninformative |  |  |  |  |
Penco et al 2005 | Discrete | Categories of allele combinations at each genotype | Binary | 0 = unaffected | Multiple variations, including and evolutionary process | |
 |  |  |  | 1 = affected |  |  |
Pociot et al. 2004 | Discrete | Number of categories per sliding window | Binary | 0 = unaffected | Multiple variations | |
 |  |  |  | 1 = affected |  |  |
Ritchie et al. 2003 | Discrete | -1, -1 = 1/1 genotype | Binary | 0 = unaffected | GP evolved | |
 |  | 0, + 2 = 1/2 genotype |  | 1 = affected |  |  |
 |  | +1, -1 = 2/2 genotype |  |  |  |  |
Saccone et al. 1999 | Discrete | IBD sharing | Binary | 1/1 = affected/affected | 18 variations | |
 |  | +1= shared allele |  | 0/1 = affected/unaffected |  |  |
 |  | -1 = unshared allele |  |  |  |  |
 |  | 0 = uninformative |  |  |  |  |
Serretti and Smeraldi 2004 | Discrete | SERPR*l/l = 1 | Binary | 0 = nonresponse | 1 | 7 |
 |  | SERPR*l/s = 2 |  | 1 = response |  |  |
 |  | SERPR*s/s = 2 |  |  |  |  |
 |  | TPH*C/C = 1 |  |  |  |  |
 |  | TPH*C/A = 2 |  |  |  |  |
 |  | TPH*A/A = 2 |  |  |  |  |
Shoemaker et al. 2001 | Varied | Varied | Binary | 0 = unaffected | 1 | unknown |
 |  |  |  | 1 = affected |  |  |
Tomita et al 2004 | Discrete | Homozygous for major allele = (0.1, 0.1) | Binary | 0.9 = case | Multiple variations | |
 |  | Heterozygous = (0.1, 0.9) |  | 0.1 = control |  |  |
 |  | Homozygous for minor allele = (0.9, 0.9) |  |  |  |  |
Zandi et al. 2001 | Contin. | Pedigree-specific NPL scores | Binary | 1,1 = case pedigree | 15 variations | |
 |  |  |  | 1,0 = control pedigree |  |  |