Toward a functional annotation of the human genome using artificial transcription factors

Abstract

We have developed a novel, high-throughput approach to collecting randomly perturbed gene-expression profiles from the human genome.A human 293 cell library that stably expresses randomly chosen zinc-finger transcription factors was constructed, and the expression profile of each cell line was obtained using cDNA microarray technology.Gene expression profiles from a total of 132 cell lines were collected and analyzed by (1) a simple clustering method based on expression-profile similarity, and (2) the shortest-path analysis method. These analyses identified a number of gene groups, and further investigation revealed that the genes that were grouped together had close biological relationships. The artificial transcription factor-based random genome perturbation method thus provides a novel functional genomic tool for annotation and classification of genes in the human genome and those of many other organisms.

Figure 1

Experimental scheme. See the text for details.

Figure 2

Characterization of a ZFP-TF-activated gene expression profile. (A) A gene expression profile obtained with a ZFP-TF in two different cell lines. A ZFP activator, F2840-p65, was either stably expressed in 293 cells (left) or transiently expressed in HeLa cells (right). In both experiments, insulin was highly expressed (marked by arrows). Dots colored in red were not subjected to analysis to avoid false results due to tailing. (Bottom) Plotting of the logarithmic expression ratios of each experiment and the correlation coefficient of two experiments. (B) Time-course analysis of gene expression driven by a ZFP-TF. A 293 cell line stably expressing a ZFP activator, F475-p65, was treated with Dox for the times stated. Genes identified as primary targets are marked.

Figure 2

Characterization of a ZFP-TF-activated gene expression profile. (A) A gene expression profile obtained with a ZFP-TF in two different cell lines. A ZFP activator, F2840-p65, was either stably expressed in 293 cells (left) or transiently expressed in HeLa cells (right). In both experiments, insulin was highly expressed (marked by arrows). Dots colored in red were not subjected to analysis to avoid false results due to tailing. (Bottom) Plotting of the logarithmic expression ratios of each experiment and the correlation coefficient of two experiments. (B) Time-course analysis of gene expression driven by a ZFP-TF. A 293 cell line stably expressing a ZFP activator, F475-p65, was treated with Dox for the times stated. Genes identified as primary targets are marked.

Figure 3

Histone gene groups. Numbers in gene groups are as in Supplemental Table 2. Clustering image of each group over 132 experiments is shown.

Figure 4

IGF-2 cluster identified by SP analysis. SP group number is as in Supplemental Table 3.

Figure 5

Activation of MAGE family by the Spi-B transcription factor. (A) MAGE cluster identified by SP analysis. (B) Up-regulation of MAGE genes by Spi-B. The 293 cells were transiently transfected with either an empty vector (con) or a vector expressing Spi-B (Spi). At 48-hour post-transfection, cells were harvested and RNAs prepared for real-time PCR analysis. Results are the average of two experiments, each performed in duplicate.

Figure 5

Activation of MAGE family by the Spi-B transcription factor. (A) MAGE cluster identified by SP analysis. (B) Up-regulation of MAGE genes by Spi-B. The 293 cells were transiently transfected with either an empty vector (con) or a vector expressing Spi-B (Spi). At 48-hour post-transfection, cells were harvested and RNAs prepared for real-time PCR analysis. Results are the average of two experiments, each performed in duplicate.