Limits...
Discovering time-lagged rules from microarray data using gene profile classifiers.

Gallo CA, Carballido JA, Ponzoni I - BMC Bioinformatics (2011)

Bottom Line: The outcomes have shown that GRNCOP2 outperforms the contrasted methods in terms of the proposed metrics, and that the results are consistent with previous biological knowledge.In this case, the experimentation has exhibited the soundness and scalability of the new method which inferred highly-related statistically-significant gene associations.The method was carefully validated with several publicly available data sets.

View Article: PubMed Central - HTML - PubMed

Affiliation: Laboratorio de Investigación y Desarrollo en Computación Científica (LIDeCC), Departamento de Ciencias e Ingeniería de la Computación, Universidad Nacional del Sur, Av, Alem 1253, 8000, Bahía Blanca, Argentina.

ABSTRACT

Background: Gene regulatory networks have an essential role in every process of life. In this regard, the amount of genome-wide time series data is becoming increasingly available, providing the opportunity to discover the time-delayed gene regulatory networks that govern the majority of these molecular processes.

Results: This paper aims at reconstructing gene regulatory networks from multiple genome-wide microarray time series datasets. In this sense, a new model-free algorithm called GRNCOP2 (Gene Regulatory Network inference by Combinatorial OPtimization 2), which is a significant evolution of the GRNCOP algorithm, was developed using combinatorial optimization of gene profile classifiers. The method is capable of inferring potential time-delay relationships with any span of time between genes from various time series datasets given as input. The proposed algorithm was applied to time series data composed of twenty yeast genes that are highly relevant for the cell-cycle study, and the results were compared against several related approaches. The outcomes have shown that GRNCOP2 outperforms the contrasted methods in terms of the proposed metrics, and that the results are consistent with previous biological knowledge. Additionally, a genome-wide study on multiple publicly available time series data was performed. In this case, the experimentation has exhibited the soundness and scalability of the new method which inferred highly-related statistically-significant gene associations.

Conclusions: A novel method for inferring time-delayed gene regulatory networks from genome-wide time series datasets is proposed in this paper. The method was carefully validated with several publicly available data sets. The results have demonstrated that the algorithm constitutes a usable model-free approach capable of predicting meaningful relationships between genes, revealing the time-trends of gene regulation.

Show MeSH
Precision and score values achieved by GRNCOP2 and GRNCOP. Values of precision and score metrics achieved by GRNCOP2 and GRNCOP in each of the 56 runs w.r.t. the CP-CSS. Figure 2a: yeastnet precision. Figure 2b: yeastnet score. Figure 2c: co-citation precision. Figure 2d: co-citation score. Figure 2e: GO precision.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3111372&req=5

Figure 2: Precision and score values achieved by GRNCOP2 and GRNCOP. Values of precision and score metrics achieved by GRNCOP2 and GRNCOP in each of the 56 runs w.r.t. the CP-CSS. Figure 2a: yeastnet precision. Figure 2b: yeastnet score. Figure 2c: co-citation precision. Figure 2d: co-citation score. Figure 2e: GO precision.

Mentions: As it can be observed, GRNCOP2 outperforms (on average) GRNCOP in several of the proposed metrics, whereas both algorithms perform significantly above the random selection, as expected. In particular, while GRNCOP2 is on average more precise and more specific than GRNCOP, this last one recovers on average a bigger number of the "relevant interactions" (i.e. it is more sensitive). These results may be explained by the fact that GRNCOP actually recovers on average twice the amount of the associations obtained by GRNCOP2. However, since the values in Table 3 represent the average of the 56 runs, the real picture may be misunderstood. Therefore, in order to correctly establish the behavior of each algorithm, several graphics were performed. Figures 2a to 2e depict the precision and score metrics achieved by both algorithms in each of the 56 runs w.r.t. the Coverage Percentage of the Combinatorial Search Space (namely CP-CSS), i.e., the percentage of associations returned by the methods in relation to all possible gene pair-wise combinations (see Table 2.).


Discovering time-lagged rules from microarray data using gene profile classifiers.

Gallo CA, Carballido JA, Ponzoni I - BMC Bioinformatics (2011)

Precision and score values achieved by GRNCOP2 and GRNCOP. Values of precision and score metrics achieved by GRNCOP2 and GRNCOP in each of the 56 runs w.r.t. the CP-CSS. Figure 2a: yeastnet precision. Figure 2b: yeastnet score. Figure 2c: co-citation precision. Figure 2d: co-citation score. Figure 2e: GO precision.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3111372&req=5

Figure 2: Precision and score values achieved by GRNCOP2 and GRNCOP. Values of precision and score metrics achieved by GRNCOP2 and GRNCOP in each of the 56 runs w.r.t. the CP-CSS. Figure 2a: yeastnet precision. Figure 2b: yeastnet score. Figure 2c: co-citation precision. Figure 2d: co-citation score. Figure 2e: GO precision.
Mentions: As it can be observed, GRNCOP2 outperforms (on average) GRNCOP in several of the proposed metrics, whereas both algorithms perform significantly above the random selection, as expected. In particular, while GRNCOP2 is on average more precise and more specific than GRNCOP, this last one recovers on average a bigger number of the "relevant interactions" (i.e. it is more sensitive). These results may be explained by the fact that GRNCOP actually recovers on average twice the amount of the associations obtained by GRNCOP2. However, since the values in Table 3 represent the average of the 56 runs, the real picture may be misunderstood. Therefore, in order to correctly establish the behavior of each algorithm, several graphics were performed. Figures 2a to 2e depict the precision and score metrics achieved by both algorithms in each of the 56 runs w.r.t. the Coverage Percentage of the Combinatorial Search Space (namely CP-CSS), i.e., the percentage of associations returned by the methods in relation to all possible gene pair-wise combinations (see Table 2.).

Bottom Line: The outcomes have shown that GRNCOP2 outperforms the contrasted methods in terms of the proposed metrics, and that the results are consistent with previous biological knowledge.In this case, the experimentation has exhibited the soundness and scalability of the new method which inferred highly-related statistically-significant gene associations.The method was carefully validated with several publicly available data sets.

View Article: PubMed Central - HTML - PubMed

Affiliation: Laboratorio de Investigación y Desarrollo en Computación Científica (LIDeCC), Departamento de Ciencias e Ingeniería de la Computación, Universidad Nacional del Sur, Av, Alem 1253, 8000, Bahía Blanca, Argentina.

ABSTRACT

Background: Gene regulatory networks have an essential role in every process of life. In this regard, the amount of genome-wide time series data is becoming increasingly available, providing the opportunity to discover the time-delayed gene regulatory networks that govern the majority of these molecular processes.

Results: This paper aims at reconstructing gene regulatory networks from multiple genome-wide microarray time series datasets. In this sense, a new model-free algorithm called GRNCOP2 (Gene Regulatory Network inference by Combinatorial OPtimization 2), which is a significant evolution of the GRNCOP algorithm, was developed using combinatorial optimization of gene profile classifiers. The method is capable of inferring potential time-delay relationships with any span of time between genes from various time series datasets given as input. The proposed algorithm was applied to time series data composed of twenty yeast genes that are highly relevant for the cell-cycle study, and the results were compared against several related approaches. The outcomes have shown that GRNCOP2 outperforms the contrasted methods in terms of the proposed metrics, and that the results are consistent with previous biological knowledge. Additionally, a genome-wide study on multiple publicly available time series data was performed. In this case, the experimentation has exhibited the soundness and scalability of the new method which inferred highly-related statistically-significant gene associations.

Conclusions: A novel method for inferring time-delayed gene regulatory networks from genome-wide time series datasets is proposed in this paper. The method was carefully validated with several publicly available data sets. The results have demonstrated that the algorithm constitutes a usable model-free approach capable of predicting meaningful relationships between genes, revealing the time-trends of gene regulation.

Show MeSH