Lung cancer transcriptomes refined with laser capture microdissection

Abstract

We evaluated the importance of tumor cell selection for generating gene signatures in non-small cell lung cancer. Tumor and nontumor tissue from macroscopically dissected (Macro) surgical specimens (31 pairs from 32 subjects) was homogenized, extracted, amplified, and hybridized to microarrays. Adjacent scout sections were histologically mapped; sets of approximately 1000 tumor cells and nontumor cells (alveolar or bronchial) were procured by laser capture microdissection (LCM). Within histological strata, LCM and Macro specimens exhibited approximately 67% to 80% nonoverlap in differentially expressed (DE) genes. In a representative subset, LCM uniquely identified 300 DE genes in tumor versus nontumor specimens, largely attributable to cell selection; 382 DE genes were common to Macro, Macro with preamplification, and LCM platforms. RT-qPCR validation in a 33-gene subset was confirmatory (ρ = 0.789 to 0.964, P = 0.0013 to 0.0028). Pathway analysis of LCM data suggested alterations in known cancer pathways (cell growth, death, movement, cycle, and signaling components), among others (eg, immune, inflammatory). A unique nine-gene LCM signature had higher tumor-nontumor discriminatory accuracy (100%) than the corresponding Macro signature (87%). Comparison with Cancer Genome Atlas data sets (based on homogenized Macro tissue) revealed both substantial overlap and important differences from LCM specimen results. Thus, cell selection via LCM enhances expression profiling precision, and confirms both known and under-appreciated lung cancer genes and pathways.

Figure 1

Representative images of frozen-section specimens undergoing laser capture microdissection (LCM). The target areas are outlined with black or red laser track marks. Tumors (T) for LCM were histologically characterized by consensus of two pathologists. The precise areas to be laser-captured from each tissue section were designated by a pathologist (J.L. and C.Z.) on each scout image, and laboratory personnel followed standard protocols for LCM. For tissue scans and microscopy of nontumor (NT) alveolar areas (NTa; left column), parenchymal inflammation was common. Typical nonmalignant bronchial mucosa (NTb; middle column) is outlined for microdissection. The two tumor specimens (T; right column) are squamous cell carcinoma (top row) and adenocarcinoma (bottom row).

Figure 2

Heat maps demonstrate technical feasibility of microarray-based transcriptome analyses on LCM samples. A: Heat map of differentially expressed (DE) gene transcripts from LCM T versus NT lung specimens. A total of 850 genes with adjusted P value < 0.05 and log₂ fold change (FC) of ≥1.0 were used for this comparison. B: A similar heat map differentiates LCM adenocarcinomas from LCM squamous cell carcinomas. A total of 651 genes with adjusted P < 0.05 and log₂ FC ≥ 1.0 were used for this comparison.

Figure 3

Validation of adenocarcinoma-specific (A) and squamous cell carcinoma–specific (B) DE transcripts in Macro versus LCM specimens. A: The analysis revealed 177 T versus NT DE transcripts in common between the Macro and LCM platforms (approximately 27%), shown in the Venn diagram. Validation of T versus NT microarray-based differential expression by quantitative real-time RT-PCR (RT-qPCR) in Macro and LCM specimens. PCR-based assays of top microarray hits were evaluated using RNA-specific RT-qPCR on the same adenocarcinoma sample, as described under Materials and Methods, are shown in the graphs. The values for Macro tissue sets were concordant (ie, in the same direction, up-regulated or down-regulated) with LCM microarray values (Table 2) for the selected top microarray hits. Such concordance was also found with RT-qPCR validation, although of course the actual lists of the most dysregulated genes differed between Macro and LCM specimens. B: The analysis revealed 98 T–NT DE transcripts in common (approximately 23%) between the Macro and LCM platforms (shown in Venn diagram). Validation of squamous cell carcinoma T versus NT microarray-based differential expression by RT-qPCR in Macro and LCM specimens is shown in the graphs. Assays of top microarray hits were evaluated using an RNA-specific RT-qPCR on the same sample, as described under Materials and Methods. The values for Macro tissue sets were concordant with LCM microarray values (Table 1, Table 2, Table 3) for the selected top microarray hits. Such concordance was largely true of the LCM RT-qPCR validation for LCM microarray top hits, the two exceptions being TOP2A and BIRC5, which were up-regulated on the microarray but down-regulated in the RT-qPCR. Also, TP63 was up-regulated only 1.6-fold, albeit in the same qualitative direction as the microarray data. Again, the actual lists of the most dysregulated genes differed between Macro and LCM specimens. Data are expressed as mean FC (T versus NT) values, scaled to RNA-specific amplification of a housekeeping gene (GAPDH) (A) or to parallel RNA-specific amplification of a housekeeping transcript (β-actin) (B) not confounded by pseudogenes.

Figure 4

Correlation of differential gene expression comparing RT-qPCR with expression cDNA microarray for Macro (A) and LCM (B) samples. Spearman correlation indicates a strong relationship between the two gene-expression platforms for both types of tissue (Macro: ρ = 0.789, P = 0.0013; LCM: ρ = 0.964, P = 0.0028). Each point represents one representative gene in replicate queried by one platform in the Macro (A) or LCM (B) tissue setting.

Figure 5

Differentially expressed genes for different sample preparation procedures, from a representative subset of eight tumor–nontumor pairs for which all three tissue-sampling platform types were available: macroscopic–conventional homogenized (Macro), macroscopic–conventional homogenized small aliquot undergoing Pico preamplification (Macro–Pico) controls, and LCM samples also undergoing Pico preamplification (LCM). The corresponding gene lists, including overlap lists, are available from Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo; accession number GSE31552).