# A copula method for modeling directional dependence of genes

- Jong-Min Kim
^{1}, - Yoon-Sung Jung
^{2}, - Engin A Sungur
^{1}, - Kap-Hoon Han
^{3}, - Changyi Park
^{4}Email author and - Insuk Sohn
^{5}

**9**:225

https://doi.org/10.1186/1471-2105-9-225

© Kim et al; licensee BioMed Central Ltd. 2008

**Received: **23 November 2007

**Accepted: **01 May 2008

**Published: **01 May 2008

## Abstract

### Background

Genes interact with each other as basic building blocks of life, forming a complicated network. The relationship between groups of genes with different functions can be represented as gene networks. With the deposition of huge microarray data sets in public domains, study on gene networking is now possible. In recent years, there has been an increasing interest in the reconstruction of gene networks from gene expression data. Recent work includes linear models, Boolean network models, and Bayesian networks. Among them, Bayesian networks seem to be the most effective in constructing gene networks. A major problem with the Bayesian network approach is the excessive computational time. This problem is due to the interactive feature of the method that requires large search space. Since fitting a model by using the copulas does not require iterations, elicitation of the priors, and complicated calculations of posterior distributions, the need for reference to extensive search spaces can be eliminated leading to manageable computational affords. Bayesian network approach produces a discretely expression of conditional probabilities. Discreteness of the characteristics is not required in the copula approach which involves use of uniform representation of the continuous random variables. Our method is able to overcome the limitation of Bayesian network method for gene-gene interaction, i.e. information loss due to binary transformation.

### Results

We analyzed the gene interactions for two gene data sets (one group is eight histone genes and the other group is 19 genes which include DNA polymerases, DNA helicase, type B cyclin genes, DNA primases, radiation sensitive genes, repaire related genes, replication protein A encoding gene, DNA replication initiation factor, securin gene, nucleosome assembly factor, and a subunit of the cohesin complex) by adopting a measure of directional dependence based on a copula function. We have compared our results with those from other methods in the literature. Although microarray results show a transcriptional co-regulation pattern and do not imply that the gene products are physically interactive, this tight genetic connection may suggest that each gene product has either direct or indirect connections between the other gene products. Indeed, recent comprehensive analysis of a protein interaction map revealed that those histone genes are physically connected with each other, supporting the results obtained by our method.

### Conclusion

The results illustrate that our method can be an alternative to Bayesian networks in modeling gene interactions. One advantage of our approach is that dependence between genes is not assumed to be linear. Another advantage is that our approach can detect directional dependence. We expect that our study may help to design artificial drug candidates, which can block or activate biologically meaningful pathways. Moreover, our copula approach can be extended to investigate the effects of local environments on protein-protein interactions. The copula mutual information approach will help to propose the new variant of ARACNE (Algorithm for the Reconstruction of Accurate Cellular Networks): an algorithm for the reconstruction of gene regulatory networks.

## Background

Genes interact with each other as basic building blocks of life, forming a complicated network. The relationship between groups of genes with different functions can be represented as gene networks. Recent developments in microarray technology revolutionized research in the life sciences, allowing researchers to measure tens of thousands of genes simultaneously [1, 2]. With the deposition of huge microarray data sets in public domains, study on gene networking is now possible. Reconstructing gene networks from the microarray data will facilitate cellular function dissection at the molecular level. Hence the study will have a profound impact on biomedical research, ranging from cancer research to disease prevention [3].

There has been an increasing interest in the reconstruction of gene networks from gene expression data. Recent works include linear models [4, 5], Boolean network models [6], and Bayesian networks [3, 7–10]. Bayesian networks seem to be very effective in the construction of gene networks. They can incorporate prior knowledge from biology into their models and handle missing data effectively. In particular, dynamic Bayesian networks can learn a gene network from time-course gene expressions. As noted in [9], a major problem with Bayesian networks is the computation problem. Our motivation is to overcome this limitation of Bayesian networks in gene interactions. For this purpose, we introduce a simple method for constructing gene networks based on copulas. Note that copulas can model a variety of interactions.

In statistical literature, the general way to describe dependence between correlated random variables is to use copulas [11]. Copulas are multivariate distribution functions whose one-dimensional margins are uniform on the [0, 1] interval [12]. Copulas are useful for constructing joint distributions, especially with nonnormal random variables. The design, features, and some implementation details of the R package copula can be easily extended in multivariate modeling in many fields [13]. In finance, copula functions are adopted to handle the interaction between the markets and risk factors in a flexible way [14]. In biology, a gaussian copula has been applied in quantitative trait linkage. Copulas play an important role in developing a unified likelihood framework to analyze discrete, continuous, and censored traits [15]. In principle, copulas can be used to model the joint distributions of any discrete or continuous gene and even mixed continuous and discrete genes. In [16], several measures of directional dependence in regression based on copula functions were proposed. Recently, a sieve maximum likelihood estimation procedure for semiparametric multivariate copula models has been proposed in [17]. The proposed estimation achieved efficiency gains in finite samples, especially when prior information of the marginal distribution is incorporated. In this paper, we adopt a measure of directional dependence to investigate the gene interactions for yeast cell cycle data. One advantage of our approach is that dependence between genes is not assumed to be linear. Moreover, our approach can detect directional dependence. Hence our approach can provide valuable biological information on the presence of directional dependence between genes.

## Results and Discussion

Estimates of *α, β, θ* and proportions of variation for the directional dependence at Group I

FGM type | Normal Type | ||||||||
---|---|---|---|---|---|---|---|---|---|

Interacting genes | AIC | $\widehat{\alpha}$ | $\widehat{\beta}$ | $\widehat{\theta}$ | ${\rho}_{C}^{2}$ | ${\rho}_{U\to V}^{(2)}$ | ${\rho}_{V\to U}^{(2)}$ | $\stackrel{\_}{{\theta}_{\ast}}$ | ${\rho}_{norm}^{2}$ |

HHT1 vs HHT2 | -33.5084 | 1.0152 | 1.0199 | 1.0772 | 0.1048 | 0.1048 | 0.1048 | 0.832 | 0.67143 |

HHT1 vs HHF1 | -32.9113 | 1.0152 | 1.0222 | 1.0772 | 0.1044 | 0.1044 | 0.1044 | 0.062 | 0.00350 |

HHT1 vs HHF2 | -34.7051 | 1.0152 | 1.0229 | 1.0772 | 0.1042 | 0.1043 | 0.1043 | 0.163 | 0.02428 |

HHT1 vs HTA1 | -34.7998 | 1.0152 | 1.0162 | 1.0772 | 0.1054 | 0.1054 | 0.1054 | 0.243 | 0.05411 |

HHT1 vs HTA2 | -34.0483 | 1.0152 | 1.0218 | 1.0772 | 0.1044 | 0.1045 | 0.1045 | 0.135 | 0.01664 |

HHT1 vs HTB1 | -34.0410 | 1.0152 | 1.0105 | 1.0567 | 0.1064 | 0.1064 | 0.1064 | 0.387 | 0.13831 |

HHT1 vs HTB2 | -31.1447 | 1.0152 | 1.0234 | 1.0772 | 0.1042 | 0.1042 | 0.1042 | 0.217 | 0.04310 |

HHT2 vs HHF1 | -29.5856 | 1.0199 | 1.0199 | 1.0964 | 0.1039 | 0.1040 | 0.1040 | 0.389 | 0.13976 |

HHT2 vs HHF2 | -34.4365 | 1.0199 | 1.0229 | 1.0966 | 0.1034 | 0.1035 | 0.1035 | 0.752 | 0.54199 |

HHT2 vs HTA1 | -32.8950 | 1.0199 | 1.0162 | 1.0814 | 0.1046 | 0.1046 | 0.1046 | 0.745 | 0.53143 |

HHT2 vs HTA2 | -32.3277 | 1.0199 | 1.0218 | 1.0966 | 0.1036 | 0.1037 | 0.1037 | 0.968 | 0.93103 |

HHT2 vs HTB1 | -32.6642 | 1.0199 | 1.0105 | 1.0567 | 0.1056 | 0.1056 | 0.1056 | 0.037 | 0.00124 |

HHT2 vs HTB2 | -27.7089 | 1.0199 | 1.0234 | 1.0966 | 0.1033 | 0.1034 | 0.1034 | 0.935 | 0.86317 |

HHF1 vs HHF2 | -34.9456 | 1.0222 | 1.0229 | 1.1055 | 0.1030 | 0.1031 | 0.1031 | 0.054 | 0.00265 |

HHF1 vs HTA1 | -32.8945 | 1.0222 | 1.0162 | 1.0814 | 0.1042 | 0.1043 | 0.1042 | 0.721 | 0.49612 |

HHF1 vs HTA2 | -32.4444 | 1.0222 | 1.0218 | 1.1041 | 0.1032 | 0.1033 | 0.1033 | 0.839 | 0.68354 |

HHF1 vs HTB1 | -32.2815 | 1.0222 | 1.0105 | 1.0567 | 0.1052 | 0.1052 | 0.1052 | 0.178 | 0.02896 |

HHF1 vs HTB2 | -31.6114 | 1.0222 | 1.0234 | 1.1055 | 0.1030 | 0.1030 | 0.1030 | 0.134 | 0.01639 |

HHF2 vs HTA1 | -34.6262 | 1.0229 | 1.0162 | 1.0814 | 0.1041 | 0.1041 | 0.1041 | 0.508 | 0.24056 |

HHF2 vs HTA2 | -33.2097 | 1.0229 | 1.0218 | 1.1041 | 0.1031 | 0.1032 | 0.1032 | 0.707 | 0.47617 |

HHF2 vs HTB1 | -34.9285 | 1.0229 | 1.0105 | 1.0567 | 0.1051 | 0.1051 | 0.1051 | 0.203 | 0.03770 |

HHF2 vs HTB2 | -31.5427 | 1.0229 | 1.0234 | 1.1083 | 0.1028 | 0.1029 | 0.1029 | 0.897 | 0.78898 |

HTA1 vs HTA2 | -34.1910 | 1.0162 | 1.0218 | 1.0814 | 0.1042 | 0.1043 | 0.1043 | 0.847 | 0.69754 |

HTA1 vs HTB1 | -34.5808 | 1.0162 | 1.0105 | 1.0567 | 0.1062 | 0.1063 | 0.1062 | 0.247 | 0.05591 |

HTA1 vs HTB2 | -30.5148 | 1.0162 | 1.0234 | 1.0814 | 0.1040 | 0.1040 | 0.1041 | 0.389 | 0.13976 |

HTA2 vs HTB1 | -32.2491 | 1.0218 | 1.0105 | 1.0567 | 0.1052 | 0.1053 | 0.1053 | 0.370 | 0.12628 |

HTA2 vs HTB2 | -31.1265 | 1.0218 | 1.0234 | 1.1041 | 0.1030 | 0.1031 | 0.1031 | 0.256 | 0.06009 |

HTB1 vs HTB2 | -30.8025 | 1.0218 | 1.0234 | 1.1004 | 0.1032 | 0.1032 | 0.1033 | 0.729 | 0.50774 |

Note that the measures of dependence ${\rho}_{C}^{2}$, ${\rho}_{U\to V}^{(2)}$, and ${\rho}_{V\to U}^{(2)}$ have different scales from usual correlation coefficient. Since Pearson's correlation coefficient is based on the assumption of normality and linearity of random variables *X* and *Y*, the range of Pearson's correlation is usually wider than that of our measures of directional dependence. Furthermore, Pearson's correlation coefficient depends on random variables *X* and *Y*, while the measures of directional dependence depend on the joint function of their cumulative distribution functions. Therefore, depending on the copula function adopted, the scales of the measures can be different. Also, when we use the uniform distribution or exponential distribution for the transformation of the marginal cumulative distribution functions of *X* and *Y*, the measure of dependence can be smaller than Pearson's Correlation coefficient. For a comparison of the measure of dependence of our FGM copula model, we used the normal copula model which is one of the representative copula models. If we look at the FGM type and Normal type in Table 1 and [see Additional file 1], we find that depending on the gene data pair, the measures of dependence using the normal copula has more variation then the measures of dependence using our proposed FGM copula. In light of these facts, our results are valid and consistent. To support our results, we also provided the matematical derivations of our proposed FGM copula model in the method section.

Direct experimental support for the interactions uncovered

Interacting genes (locus name) | Our Method | PathwayAssist | Chen's method | Ref. |
---|---|---|---|---|

HTA2(YBL003C) – HTA1(YDR225W) | O | O | O | 1 |

HTA2(YBL003C) – HHT2(YNL031C) | O | O | O | 1 |

HTA2(YBL003C) – HTB2(YBL002W) | O | O | O | 1 |

HTA2(YBL003C) – HHT1(YBR010W) | O | O | O | 1 |

HTA2(YBL003C) – HHF1(YBR009C) | O | × | × | 1 |

HTA2(YBL003C) – HHF2(YNL030W) | O | × | × | 1 |

HTA2(YBL003C) – HTB1(YDR224C) | O | × | × | 1 |

HTB2(YBL002W) – HTA1(YDR225W) | O | × | × | 1 |

HTB2(YBL002W) – HHT2(YNL031C) | O | × | × | 1 |

HTB2(YBL002W) – HHT1(YBR010W) | O | × | × | 1 |

HTB2(YBL002W) – HHF1(YBR009C) | O | O | O | 1 |

HTB2(YBL002W) – HHF2(YNL030W) | O | × | × | 1 |

HTB2(YBL002W) – HTB1(YDR224C) | O | O | O | N.A. |

HHT2(YNL031C) – HTA1(YDR225W) | O | × | O | N.A. |

HHT2(YNL031C) – HHT1(YBR010W) | O | × | × | 1 |

HHT2(YNL031C) – HHF1(YBR009C) | O | × | × | 2 |

HHT2(YNL031C) – HHF2(YNL030W) | O | O | O | 1 |

HHT2(YNL031C) – HTB1(YDR224C) | O | × | × | 1 |

HHF1(YBR009C) – HTA1(YDR225W) | O | × | × | 1 |

HHF1(YBR009C) – HHT1(YBR010W) | O | O | O | 1 |

HHF1(YBR009C) – HHF2(YNL030W) | O | O | O | 4 |

HHF1(YBR009C) – HTB1(YDR224C) | O | × | × | 1 |

HHF2(YNL030W) – HTA1(YDR225W) | O | O | O | 1 |

HHF2(YNL030W) – HHT1(YBR010W) | O | O | O | 1 |

HHF2(YNL030W) – HTB1(YDR224C) | O | × | O | N.A. |

HTA1(YDR225W) – HHT1(YBR010W) | O | × | × | 1 |

HTA1(YDR225W) – HTB1(YDR224C) | O | O | O | 2,3 |

HHT1(YBR010W) – HTB1(YDR224C) | O | × | × | 1 |

Although microarray results show a transcriptional co-regulation pattern and do not imply that the gene products are physically interactive, this tight genetic connection may suggest that each gene product has either direct or indirect connections between the other gene products. Indeed, recent comprehensive analysis of a protein interaction map revealed that those histone genes are physically connected with each other [19], supporting the results obtained by our method. The findings of this study may help to design artificial drug candidates, which can block or activate biologically meaningful pathways. Furthermore, our copula approach can be extended to investigate the effects of local environments on protein-protein interactions. The copula mutual information approach will help to propose a new variant of ARACNE: an algorithm for the reconstruction of gene regulatory networks.

## Conclusion

In this paper, we presented a new methodology for analyzing gene interactions based on copula functions. Our method is shown to be useful in the construction of gene networks through the analysis of yeast cell cycle data. Our method may be able to overcome the limitation of Bayesian network method for gene-gene interaction, i.e. information loss due to binary transformation. Since a copula represents a way of extracting the dependence structure of the random variables from the joint distribution function, it is a useful approach to understanding and modeling dependent structure for random variables. In our future works on gene directional dependence, we will develop hypothesis testing for directional dependence and formulate a network construction process using false discovery rate.

## Methods

For presentation, let us consider a bivariate case. All the results in this section can be generalized to a multivariate case. Consider a bivariate copula *C* : [0, 1]^{2}→ [0, 1] defined as

*C*(*u, v*) = *Pr*(*U* ≤ *u, V* ≤ *v*)

for 0 ≤ *u, v* ≤ 1 where *U* and *V* are uniform random variables. Let *X* and *Y* be random variables with marginal distribution functions *F*_{
X
}and *F*_{
Y
}. Then *F*_{
X
}(*X*) and *F*_{
Y
}(*Y*) have uniform distributions. By Sklar's Theorem, due to [21], there exits a copula *C* such that *F* (*x, y*) = *C*(*F*_{
X
}(*x*), *F*_{
Y
}(*y*)) for all *x* and *y* in the domain of *F*_{
X
}and *F*_{
Y
}, i.e. a bivariate distribution function can be represented as a function of its marginals joined by a bivariate copula. Hence different families of copula correspond to different types of dependence structure. An example is the Farlie – Gumbel – Morgenstern class defined as *uv* [1 + *θ* (1 - *u*)(1 - *v*)] with *θ* ≥ 0. See [12] for a general introduction to copulas.

Now we discuss the concept and measures of directional dependence briefly. One may consider two types of directional dependence between two random variables *U* and *V* in regression: *r*_{V|U}(*u*) = *E*[*V*|*U* = *u*] and *r*_{U|V}(*v*) = *E*[*U*|*V* = *v*] for the Rodrìguez-Lallena and Úbeda-Flores family of copula in the form of

*C*(*u, v*) = *uv* + *f*(*u*)*g*(*v*), (1)

*E*[

*V*|

*U*=

*u*] is the conditional expectation of

*V*given that

*U*=

*u*[22]. Note that a specific functional form of

*f*and

*g*determines the corresponding family of bivariate distributions of (

*U, V*). If

*f*and

*g*are different, then the copula is not symmetric, in which case the form of the regression functions for

*V*and

*U*will be different. Hence one might consider two types of directional dependence, i.e. one in the direction from

*U*to

*V*and the other in the direction from

*V*to

*U*. Since directional dependence can arise from marginal or joint behavior or both, one may consider the following general measure of directional dependence defined as

where ${\rho}_{X\to Y}^{(k)}$ is the proportion of the *k*-th central moment of *Y* explained by the regression of *Y* on *X*. For example, ${\rho}_{X\to Y}^{(2)}$ can be interpreted as the proportion of variation explained by the regression of *Y* on *X* with respect to total variation of *Y*. For more details, see [16].

Finally, let us introduce the FGM distributions and measures of directional dependence for our data analysis. We consider the following type of FGM distributions in the form of the Rodrìguez-Lallena and Úbeda-Flores copula family in (1):

*C*(*u, v*) = *uv* + *θ uv*(1 - *u*)^{
α
}(1 - *v*)^{
β
}for 0 ≤ *u, v* = 1 and *α, β* ≥ 1, (3)

*θ, α*and

*β*are parameters.

*C*(

*u, v*) defined in (3) is a copula function for

*θ*satisfying

see [23].

*X*

_{ i }and

*Y*

_{ i }be i.i.d. copies of

*X*and

*Y*for

*i*= 1, ...,

*n*. Then

*U*

_{ i }=

*F*

_{ X }(

*X*

_{ i }) and

*V*

_{ i }=

*F*

_{ Y }(

*Y*

_{ i }) are the empirical marginal distribution functions of

*F*

_{ X }and

*F*

_{ Y }. Note that

*U*

_{ i }and

*V*

_{ i }have uniform distributions on (0, 1). The empirical likelihood is

**U**= (

*U*

_{1}, ...,

*U*

_{ n })

*'*and

**V**= (

*V*

_{1}, ...,

*V*

_{ n })

*'*. From (3), the empirical likelihood function is

subject to *α, β* ≥ 1, one obtains the estimates of *α* and *β* denoted by $\widehat{\alpha}$ and $\widehat{\beta}$. Since log *L*(*θ*; **u**, **v**) is a linear function of *θ* with known $\widehat{\alpha}$ and $\widehat{\beta}$, there is no closed form solution for MLE from the partial derivative function with respect to *θ*. As an alternative, we used a grid search over the range of *θ* with *α* = $\widehat{\alpha}$ and *β* = $\widehat{\beta}$.

*U*to

*V*and from

*V*to

*U*are given as

where *Beta*(·,·) is the beta function defined by $Beta(a,b)={\displaystyle {\int}_{0}^{1}{t}^{a-1}}{(1-t)}^{b-1}$ for *a, b* > 0.

*k*= 2, we have

*ρ*

_{ c }, is

*ρ*. The relation is

We consider a parameterized copula which has *θ*_{*} *ϕ*(Φ^{-1} (*u*), Φ^{-1} (*v*); *α θ*_{*}) instead of *θ uv*(1 - *u*)^{
α
}(1 - *v*)^{
β
}at (3).

The form is as follows:*C*(*u, v*) = *uv* + *θ*_{*} *ϕ*(Φ^{-1} (*u*), Φ^{-1} (*v*); *α θ*_{*}) for 0 ≤ *u, v* ≤ 1,

*θ*

_{*}is a parameter,

*α*satisfies the following relation

We use Akaike's information criterion (AIC) [24] for copula defined as

*AIC* = -2 log *L* (*θ*; **u**, **v**) + 2*υ*,

where *υ* is the number of parameters of the model provided in [25]. Akaike developed a decision-making strategy based on the Kullback-Leibler information measure, arguing that his measure provides a natural criterion for ordering alternative statistical models for data [24]. Instead of comparing plots or p-values for the methods, in the case of the parametric approach of maximum likelihood, we can compare the value of the negative log-likelihood functions. The value of AIC contains the information which estimator fits better. The lower the AIC, the better the model.

## Declarations

### Acknowledgements

We are grateful to anonymous reviewers for their valuable comments. This research was supported by the Korea Research Foundation Grant funded by Korean Government (MOEHRD, Basic Research Promotion Fund) (KRF-2005-070-C00020).

## Authors’ Affiliations

## References

- Lipshutz RJ, Morris D, Chee M, Hubbell E, Kozal MJ, Shah N, Shen N, Yang R, Fodor SPA: Using oligonucleotide probe arrays to access genetic diversity.
*Biotechniques*1995, 19: 442–447.PubMedGoogle Scholar - Schena M, Shalon D, Davis RW, Brown PO: Quantitative monitoring of gene expression patterns with a complementary DNA microarray.
*Science*1995, 270: 467–470. 10.1126/science.270.5235.467View ArticlePubMedGoogle Scholar - Chen XW, Anatha G, Wang X: An effective structure learning method for constructing gene networks.
*Bioinformatics*2006, 22: 1367–1374. 10.1093/bioinformatics/btl090View ArticlePubMedGoogle Scholar - Chen KC, Wang TY, Tseng HH, Huang CYF, Kao CY: A stochastic differential equation model for quantifying transcriptional regulartory network in Saccharomyces cerevisiae.
*Bioinformatics*2005, 21: 2883–2890. 10.1093/bioinformatics/bti415View ArticlePubMedGoogle Scholar - Deng X, Geng H, Ali H: EXAMINE: a computational approach to reconstructing gene regulartory networks.
*Biosystems*2005, 81: 125–136. 10.1016/j.biosystems.2005.02.007View ArticlePubMedGoogle Scholar - Shmulevich I, Dougherty E, Kim S, Zhang W: Probabilistic Boolean Networks: a rule-based uncertainty model for gene regulartory networks.
*Bioinformatics*2002, 18: 261–274. 10.1093/bioinformatics/18.2.261View ArticlePubMedGoogle Scholar - Bulashevska S, Eils R: Inferring genetic regulatory logic from expression data.
*Bioinformatics*2005, 21: 2706–2713. 10.1093/bioinformatics/bti388View ArticlePubMedGoogle Scholar - Li H, Lu L, Manly KF, Chesler EJ, Bao L, Wang J, Zhou M, Williams RW, Cui Y: Inferring gene transcriptional modulatory relations: a genetical genomics approach.
*Human Molecular Genetics*2005, 14: 1119–1125. 10.1093/hmg/ddi124View ArticlePubMedGoogle Scholar - Zou M, Conzen SD: A new dynamic Bayesian network (DBN) approach for identifying gene regulatory networks from time course microarray data.
*Bioinformatics*2005, 21: 71–79. 10.1093/bioinformatics/bth463View ArticlePubMedGoogle Scholar - Missal K, Cross MA, Drasdo D: Gene network inference from incomplete expression data: transcriptional control of hematopoietic commitment.
*Bioinformatics*2006, 22: 731–738. 10.1093/bioinformatics/bti820View ArticlePubMedGoogle Scholar - Sklar A: Functions de repartition a n dimensions et leurs marges.
*Publ Inst Stat Univ Paris*1959, 8: 229–231.Google Scholar - Nelsen RB:
*An Introduction to Copulas*. New York: Springer-Verlag; 1998.Google Scholar - Yan J: Enjoy the Joy of Copulas.
*Technical Report #365, Department of Statistics and Acturial Science, University of Iowa*2006.Google Scholar - Cherubini U, Luciano E, Vecchiato W:
*Copula Methods in Finance*. New York: John Wiley & Sons; 2004.View ArticleGoogle Scholar - Li M, Boehnke M, Abecasis GR, Song PXK: Quantitative Trait Linkage Analysis Using Gaussian Copulas.
*Genetics*2006, 173: 2317–2327. 10.1534/genetics.105.054650PubMed CentralView ArticlePubMedGoogle Scholar - Sungur EA: A Note on Directional Dependence in Regression Setting.
*Communications in Statistics: Theory and Methodology*2005, 34: 1957–1965. 10.1080/03610920500201228View ArticleGoogle Scholar - Chen X, Fan Y, Tsyrennikov V: Efficient Estimation of Semiparametric Multivariate Copula Models.
*Journal of the American Statistical Association*2006, 101: 1228–1240. 10.1198/016214506000000311View ArticleGoogle Scholar - Spellman PT, Sherlock G, Zhang MQ, Iyer VR, Anders K, Eisen MB, Brown PO, Botstein D, Futcher B: Comprehensive identification of cell cycle-regulated genes of the yeast Saccharomyces cerevisiae by microarray hybridization.
*Molecular Biology of the Cell*1998, 9: 3273–3297.PubMed CentralView ArticlePubMedGoogle Scholar - von Mering C, Krause R, Snel B, Cornell M, Oliver SG, Fields S, Bork P: Comparative assessment of large-scale datasets of protein-protein interactions.
*Nature*2002, 417: 399–403. 10.1038/nature750View ArticlePubMedGoogle Scholar - Nikitin A, Egorov S, Daraselia N, Mazo I: Pathway studio-the analysis and navigation of molecular networks.
*Bioinformatics*2003, 19: 2155–2157. 10.1093/bioinformatics/btg290View ArticlePubMedGoogle Scholar - Sklar A: Random variables, joint distribution functions, and copulas.
*Kybernetika (Prague)*1973, 9: 449–460.Google Scholar - Rodrìguez-Lallena JA, Úbeda Flores M: A new class of bivariate copulas.
*Statistics and Probability Letters*2004, 66: 315–325. 10.1016/j.spl.2003.09.010View ArticleGoogle Scholar - Bairamov I, Kotz S, Bekçi M: New generalized Farlie-Gumbel-Morgenstern distributions and concomitants of order statistics.
*Journal of Applied Statistics*2001, 28: 521–536. 10.1080/02664760120047861View ArticleGoogle Scholar - Akaike H: A new look at the statistical model identification.
*IEEE Transactions on Automatic Control*1974, 19: 716–723. 10.1109/TAC.1974.1100705View ArticleGoogle Scholar - Matteis RD: Fitting copula to data.
*PhD thesis*. Institute of Mathematics, University of Zurich; 2001.Google Scholar

## Copyright

This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.