Gene expression analysis using oligonucleotide arrays produced by maskless photolithography

Abstract

Microarrays containing 195,000 in situ synthesized oligonucleotide features have been created using a benchtop, maskless photolithographic instrument. This instrument, the Maskless Array Synthesizer (MAS), uses a digital light processor (DLP) developed by Texas Instruments. The DLP creates the patterns of UV light used in the light-directed synthesis of oligonucleotides. This digital mask eliminates the need for expensive and time-consuming chromium masks. In this report, we describe experiments in which we tested this maskless technology for DNA synthesis on glass surfaces. Parameters examined included deprotection rates, repetitive yields, and oligonucleotide length. Custom gene expression arrays were manufactured and hybridized to Drosophila melanogaster and mouse samples. Quantitative PCR was used to validate the gene expression data from the mouse arrays.

Figure 1

Chemical yield. A plot of the results of the stepwise yield of the NPPOC chemistry in the MAS system. Oligonucleotides with different numbers of bases were synthesized ranging from 1 to 12 bases. A biotin phosphoramidite was coupled to the end of all the oligonucleotides. Streptavidin-cy3 was added to visualize the relative amounts of free hydroxyls in each feature. The data represent the relative numbers after subtraction of background.

Figure 2

Feature size flexibility. A 2.25-μm resolution fluorescent micrograph of a hybridization of biotin labeled cRNAs from Bacillus subtilus and Escherichia coli to a custom DNA array. This scan was obtained using a 2.25-μm resolution arrayWoRx scanner from API. The array contains 195,000 features in 14 × 17.4 mm². From left to right, four different feature layouts were tested: 14-μm features separated by 3-μm gaps, 16-μm features in a checkerboard pattern, 16-μm features separated by 18-μm gaps, and 33-μm features separated by 18 μm.

Figure 3

Hybridization to 1mer to 150mers. Test of the 5′ sequence fidelity of oligonucleotides up to 150 bases long. A custom array was designed to compare the hybridization characteristics of an 18mer probe sequence (5′-AGGTCATTACAGCGAGAG-3′) synthesized on the 5′ end (solution phase) of different length oligonucleotides. On the X-axis is the length of the total oligonucleotide including the 18mer sequence. The array was hybridized to a biotin-labeled target (5′-biotinCTCTCGCTGTAATGACCT-3′) that was complementary to the 18mer probe sequence. After hybridization, the array was stained with streptavidin-cy3.

Figure 4

Hybridization to 1mer to 90mers. Plot of relative intensity from a hybridization to a custom array containing probes to 20 Drosophila genes. The perfect match value (with mismatch data subtracted) is shown. Each gene had a set of probes that ranged from 1 to 90 bases long. The array was hybridized to a biotin-labeled cRNA sample from Drosophila. After hybridization, the array was stained with streptavidin-cy3.

Figure 5

Scanner images of sections from two custom mouse arrays. (A) A custom mouse array containing 3240 genes with 20 probes per gene with mismatch controls was made and hybridized with biotin-labeled cRNA from a mouse liver sample. The features on this array were 16 μm. The array contained a total of 130,044 features. (B) Another mouse array of the same design hybridized to a mouse spleen sample.

Figure 6

Log ratio plot comparing fold change data from arrays and Taqman. The fold changes for 55 mouse genes in mouse liver and mouse spleen samples were calculated from array and Taqman data, and the log ratio of the fold changes was plotted.