Limits...
A neural network model for constructing endophenotypes of common complex diseases: an application to male young-onset hypertension microarray data.

Lynn KS, Li LL, Lin YJ, Wang CH, Sheng SH, Lin JH, Liao W, Hsu WL, Pan WH - Bioinformatics (2009)

Bottom Line: Identification of disease-related genes using high-throughput microarray data is more difficult for complex diseases as compared with monogenic ones.We assumed that a complex disease is associated with multiple endophenotypes and can be induced by their up/downregulated gene expression patterns.We successfully constructed a three-endophenotype model for Taiwanese hypertensive males with high identification accuracy.

View Article: PubMed Central - PubMed

Affiliation: Institute of Information Sciences, Academia Sinica, Taipei, Taiwan.

ABSTRACT

Motivation: Identification of disease-related genes using high-throughput microarray data is more difficult for complex diseases as compared with monogenic ones. We hypothesized that an endophenotype derived from transcriptional data is associated with a set of genes corresponding to a pathway cluster. We assumed that a complex disease is associated with multiple endophenotypes and can be induced by their up/downregulated gene expression patterns. Thus, a neural network model was adopted to simulate the gene-endophenotype-disease relationship in which endophenotypes were represented by hidden nodes.

Results: We successfully constructed a three-endophenotype model for Taiwanese hypertensive males with high identification accuracy. Of the three endophenotypes, one is strongly protective, another is weakly protective and the third is highly correlated with developing young-onset male hypertension. Sixteen of the involved 101 genes were highly and consistently influential to the endophenotypes. Identification of SLC4A5, SLC5A10 and LDOC1 indicated that sodium/bicarbonate transport, sodium/glucose transport and cell-proliferation regulation may play important upstream roles and identification of BNIP1, APOBEC3F and LDOC1 suggested that apoptosis, innate immune response and cell-proliferation regulation may play important downstream roles in hypertension. The involved genes not only provide insights into the mechanism of hypertension but should also be considered in future gene mapping endeavors.

Show MeSH

Related in: MedlinePlus

Gene expression plot of the three endophenotypes: each vertical strip represents a subject; each horizontal strip represents a gene; the colors used to indicate expression level is illustrated at the color bar in the right-hand side. The vertical blocks between black lines denote subject subgroups defined by different endophenotypic patterns (refer to Fig. 2g and h); horizontal blocks denote endophenotypes. The ‘S1’, ‘S2’ and ‘S3’ are magnified views of GCGR expression level of the three major subject groups (indicated in the three yellow boxes).
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2666815&req=5

Figure 3: Gene expression plot of the three endophenotypes: each vertical strip represents a subject; each horizontal strip represents a gene; the colors used to indicate expression level is illustrated at the color bar in the right-hand side. The vertical blocks between black lines denote subject subgroups defined by different endophenotypic patterns (refer to Fig. 2g and h); horizontal blocks denote endophenotypes. The ‘S1’, ‘S2’ and ‘S3’ are magnified views of GCGR expression level of the three major subject groups (indicated in the three yellow boxes).

Mentions: Rothman's (1976) concept of sufficient causes provides a theoretical framework of how multiple causal pies or phenocopies of a disease dilute the effect of target genes, resulting from either genetic or environmental causes. The following example demonstrates how the significance of a gene can vary in different types of patients. We compared the expression levels of GCGR, a candidate gene for hypertension, obtained from two major case subgroups (denoted as S1 and S2 in Fig. 3) with those obtained from a major control subgroup (denoted as S3 inFig. 3). The GCGR was not significantly differentiable (P = 0.16) between S1 and S3, however, it was significantly differentiable (P = 0.03) between S2 and S3. Therefore, conventional approaches for modeling a particular disease may fail to identify potential genes when only examining gene expression profiles.Fig. 3.


A neural network model for constructing endophenotypes of common complex diseases: an application to male young-onset hypertension microarray data.

Lynn KS, Li LL, Lin YJ, Wang CH, Sheng SH, Lin JH, Liao W, Hsu WL, Pan WH - Bioinformatics (2009)

Gene expression plot of the three endophenotypes: each vertical strip represents a subject; each horizontal strip represents a gene; the colors used to indicate expression level is illustrated at the color bar in the right-hand side. The vertical blocks between black lines denote subject subgroups defined by different endophenotypic patterns (refer to Fig. 2g and h); horizontal blocks denote endophenotypes. The ‘S1’, ‘S2’ and ‘S3’ are magnified views of GCGR expression level of the three major subject groups (indicated in the three yellow boxes).
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2666815&req=5

Figure 3: Gene expression plot of the three endophenotypes: each vertical strip represents a subject; each horizontal strip represents a gene; the colors used to indicate expression level is illustrated at the color bar in the right-hand side. The vertical blocks between black lines denote subject subgroups defined by different endophenotypic patterns (refer to Fig. 2g and h); horizontal blocks denote endophenotypes. The ‘S1’, ‘S2’ and ‘S3’ are magnified views of GCGR expression level of the three major subject groups (indicated in the three yellow boxes).
Mentions: Rothman's (1976) concept of sufficient causes provides a theoretical framework of how multiple causal pies or phenocopies of a disease dilute the effect of target genes, resulting from either genetic or environmental causes. The following example demonstrates how the significance of a gene can vary in different types of patients. We compared the expression levels of GCGR, a candidate gene for hypertension, obtained from two major case subgroups (denoted as S1 and S2 in Fig. 3) with those obtained from a major control subgroup (denoted as S3 inFig. 3). The GCGR was not significantly differentiable (P = 0.16) between S1 and S3, however, it was significantly differentiable (P = 0.03) between S2 and S3. Therefore, conventional approaches for modeling a particular disease may fail to identify potential genes when only examining gene expression profiles.Fig. 3.

Bottom Line: Identification of disease-related genes using high-throughput microarray data is more difficult for complex diseases as compared with monogenic ones.We assumed that a complex disease is associated with multiple endophenotypes and can be induced by their up/downregulated gene expression patterns.We successfully constructed a three-endophenotype model for Taiwanese hypertensive males with high identification accuracy.

View Article: PubMed Central - PubMed

Affiliation: Institute of Information Sciences, Academia Sinica, Taipei, Taiwan.

ABSTRACT

Motivation: Identification of disease-related genes using high-throughput microarray data is more difficult for complex diseases as compared with monogenic ones. We hypothesized that an endophenotype derived from transcriptional data is associated with a set of genes corresponding to a pathway cluster. We assumed that a complex disease is associated with multiple endophenotypes and can be induced by their up/downregulated gene expression patterns. Thus, a neural network model was adopted to simulate the gene-endophenotype-disease relationship in which endophenotypes were represented by hidden nodes.

Results: We successfully constructed a three-endophenotype model for Taiwanese hypertensive males with high identification accuracy. Of the three endophenotypes, one is strongly protective, another is weakly protective and the third is highly correlated with developing young-onset male hypertension. Sixteen of the involved 101 genes were highly and consistently influential to the endophenotypes. Identification of SLC4A5, SLC5A10 and LDOC1 indicated that sodium/bicarbonate transport, sodium/glucose transport and cell-proliferation regulation may play important upstream roles and identification of BNIP1, APOBEC3F and LDOC1 suggested that apoptosis, innate immune response and cell-proliferation regulation may play important downstream roles in hypertension. The involved genes not only provide insights into the mechanism of hypertension but should also be considered in future gene mapping endeavors.

Show MeSH
Related in: MedlinePlus