Computational Intelligence - November 2015 - 61
section II. The modified method
removes the main effects from the search
as they are discovered and allows the
ACO algorithm to concentrate on combinations of SNPs with smaller marginal
effects. In detail, the ACO algorithm
runs numgen generations, the SNP snp1
with the largest amount of pheromone is
identified and all combinations of snp1
and all remaining SNPs in the dataset are
calculated. The combination with the
highest chi-squared value is recorded and
snp1 is removed from the dataset for further combinations. The ACO-Tabu
method can be described by the following algorithm.
1: repeat
2: Run the ACO algorithm numgen
generations;
3: Identify SNP with highest amount
pheromone as snp1;
4: Calculate all the combinations of
snp1 and the remaining SNPs;
5: Record the best combination;
6: Remove snp1 from the dataset;
7: until end of the run
The number of generations numgen
between the removal of SNPs has been
experimentally chosen to be 1,000.
A. Results
Table 1 Best combinations of SNPs discovered by identifier (RS number).
Chromosome number and gene name (where applicable) in parentheses.
DISeaSe
COMbINaTION
p-ValUe
T2D
rs9508846(13,hCG_1815504)=AA AND rs7901695(10,TCF7L2)=CC
8 # 10−15
T2D
rs11196205(10,TCF7L2)=GG OR rs10992923(9)=GA
3 # 10−15
T2D
rs7077039(10,TCF7L2)=TT XOR rs9783382(11)=GG
6 # 10−14
T2D
rs9508846(13,hCG_1815504)!GA AND rs7901695(10,TCF7L2)=CC
4 # 10−16
IBD
rs12242030(10)=AA AND rs17116117(11,hTR3B)=CC
2 # 10−28
IBD
rs10210302(2,ATG16L1)=CC OR rs17116117(11,hTR3B)=TC
1 # 10−30
IBD
rs7382225(6)=GG XOR rs17116117(11,hTR3B)=TC
3 # 10−27
IBD
rs2076756(16,NOD2)!GG AND rs17116117(11,hTR3B)=CC
4 # 10−31
T1D
rs3805006(3,ITPR1)=CT AND rs9270986(6,NCBI36)=AA
7 # 10−256
T1D
rs9273363(6,hLA-DQB1)=GG OR rs3805006(3,ITPR1)=CC
7 # 10−246
T1D
rs9273363(6,hLA-DQB1)=TT XOR rs7859401(9,ZNF367)=CC
6 # 10−247
T1D
rs3805006(3,ITPR1)!CC AND rs9270986(6,NCBI36)=AA
9 # 10−293
RA
rs17104722(14)=CC AND rs4718582(7,TYW1)=CC
5 # 10−103
RA
rs4718582(7,TYW1)=AG OR rs2076533(6)=AA
8 # 10−101
RA
rs4718582(7,TYW1)=AA XOR rs7295430(12)=AA
6 # 10−87
RA
rs9268403(6)!TT AND rs4718582(7,TYW1)=TT
3 # 10−104
are some other promising genes identified by the algorithm that could represent new avenues for investigation.
A sample of the best combinations
from this algorithm on the type II diabetes dataset can be seen in Table 2.
Encouragingly, despite removing the
main effects, the system is still able to
discover gene-gene interactions with
good p-values for type II diabetes. Due
to the removal of the main effects, the
resulting combinations are less wellknown in the literature and so it is more
difficult to verify their biological plausibility. However some of the SNPs from
Table 2, other than the SNPs in the
genes FTO and TCF7L2, are known to
be associated with T2D and are identified below.
The SNP with rs1481279 (combination X) is described as the most notable
signal contribution to T2D predisposition
rs4132670 TCF7L2
rs4506565 TCF7L2
rs10885409 TCF7L2
rs7901695 TCF7L2
rs7193144 FTO
rs10787472 TCF7L2
rs4074720 TCF7L2
rs11196208 TCF7L2
rs11196205 TCF7L2
rs10829495
rs12243326 TCF7L2
rs1121980 FTO
rs8050136 FTO
rs9940128 FTO
rs1241956 HIVEP3
rs7917983 TCF7L2
rs9926289 FTO
rs9309324
rs2389591 NM_001101417
rs9939609 FTO
rs10829494
rs358806 LRTM1-WNT5A
rs12999941
rs2080950 NT_034779
rs11000542_PRKG1
rs903228 ASB3
rs7932087
rs9930506 FTO
rs9422545 HOK-2, MOK2
Amount of Pheromone
Figure 6 shows a typical run of the execution of the ACO-Tabu hybrid,
removing the most significant
350
SNP at every 1,000 generations.
As would be expected, perfor300
mance drops for a time, before
climbing to another peak. Inevi250
tably over time, the overall fitness
drops as more top SNPs are
200
deleted. The first four SNPs
removed from the database are
150
present in the TCF7L2 gene and
100
the fifth is located in the wellknown FTO gene.
Over 100 runs of the algorithm of 5,000 generations each,
the number of times each SNP
that has been found at least once
is shown in Figure 7. A SNP in
the gene TCF7L2 is found in
every one of the hundred runs.
Generation
Clearly, the best two known signals, TCF7L2 and FTO, domi- FIgUre 6 Evolution of the highest amount of pheromone over 30,000 generations. Every 1,000 generations,
nate this figure. However, there the SNP with the highest amount of pheromone can be seen.
November 2015 | Ieee ComputatIoNal INtellIgeNCe magazINe
61
Table of Contents for the Digital Edition of Computational Intelligence - November 2015
Computational Intelligence - November 2015 - Cover1
Computational Intelligence - November 2015 - Cover2
Computational Intelligence - November 2015 - 1
Computational Intelligence - November 2015 - 2
Computational Intelligence - November 2015 - 3
Computational Intelligence - November 2015 - 4
Computational Intelligence - November 2015 - 5
Computational Intelligence - November 2015 - 6
Computational Intelligence - November 2015 - 7
Computational Intelligence - November 2015 - 8
Computational Intelligence - November 2015 - 9
Computational Intelligence - November 2015 - 10
Computational Intelligence - November 2015 - 11
Computational Intelligence - November 2015 - 12
Computational Intelligence - November 2015 - 13
Computational Intelligence - November 2015 - 14
Computational Intelligence - November 2015 - 15
Computational Intelligence - November 2015 - 16
Computational Intelligence - November 2015 - 17
Computational Intelligence - November 2015 - 18
Computational Intelligence - November 2015 - 19
Computational Intelligence - November 2015 - 20
Computational Intelligence - November 2015 - 21
Computational Intelligence - November 2015 - 22
Computational Intelligence - November 2015 - 23
Computational Intelligence - November 2015 - 24
Computational Intelligence - November 2015 - 25
Computational Intelligence - November 2015 - 26
Computational Intelligence - November 2015 - 27
Computational Intelligence - November 2015 - 28
Computational Intelligence - November 2015 - 29
Computational Intelligence - November 2015 - 30
Computational Intelligence - November 2015 - 31
Computational Intelligence - November 2015 - 32
Computational Intelligence - November 2015 - 33
Computational Intelligence - November 2015 - 34
Computational Intelligence - November 2015 - 35
Computational Intelligence - November 2015 - 36
Computational Intelligence - November 2015 - 37
Computational Intelligence - November 2015 - 38
Computational Intelligence - November 2015 - 39
Computational Intelligence - November 2015 - 40
Computational Intelligence - November 2015 - 41
Computational Intelligence - November 2015 - 42
Computational Intelligence - November 2015 - 43
Computational Intelligence - November 2015 - 44
Computational Intelligence - November 2015 - 45
Computational Intelligence - November 2015 - 46
Computational Intelligence - November 2015 - 47
Computational Intelligence - November 2015 - 48
Computational Intelligence - November 2015 - 49
Computational Intelligence - November 2015 - 50
Computational Intelligence - November 2015 - 51
Computational Intelligence - November 2015 - 52
Computational Intelligence - November 2015 - 53
Computational Intelligence - November 2015 - 54
Computational Intelligence - November 2015 - 55
Computational Intelligence - November 2015 - 56
Computational Intelligence - November 2015 - 57
Computational Intelligence - November 2015 - 58
Computational Intelligence - November 2015 - 59
Computational Intelligence - November 2015 - 60
Computational Intelligence - November 2015 - 61
Computational Intelligence - November 2015 - 62
Computational Intelligence - November 2015 - 63
Computational Intelligence - November 2015 - 64
Computational Intelligence - November 2015 - 65
Computational Intelligence - November 2015 - 66
Computational Intelligence - November 2015 - 67
Computational Intelligence - November 2015 - 68
Computational Intelligence - November 2015 - 69
Computational Intelligence - November 2015 - 70
Computational Intelligence - November 2015 - 71
Computational Intelligence - November 2015 - 72
Computational Intelligence - November 2015 - 73
Computational Intelligence - November 2015 - 74
Computational Intelligence - November 2015 - 75
Computational Intelligence - November 2015 - 76
Computational Intelligence - November 2015 - 77
Computational Intelligence - November 2015 - 78
Computational Intelligence - November 2015 - 79
Computational Intelligence - November 2015 - 80
Computational Intelligence - November 2015 - Cover3
Computational Intelligence - November 2015 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202311
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202308
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202305
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202302
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202211
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202208
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202205
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202202
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202111
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202108
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202105
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202102
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202011
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202008
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202005
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_202002
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201911
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201908
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201905
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201902
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201811
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201808
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201805
https://www.nxtbook.com/nxtbooks/ieee/computationalintelligence_201802
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring17
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring16
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring15
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring14
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_summer13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_spring13
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_winter12
https://www.nxtbook.com/nxtbooks/ieee/computational_intelligence_fall12
https://www.nxtbookmedia.com