The human SKOV3 ovarian carcinoma cell line [14], which does not express LHR, was chosen as a negative control in this study. The cells were stably transfected to express about 12,000 LHRs per cell, and the hormone binding affinity (K_d) of human chorionic gonadotropin (CG) was 0.3 nM [14]. Human LH and CG were obtained from Dr. A.F. Parlow (National Hormone and Peptide Program, Torrance, CA). Total RNA was extracted from the cells following the same protocol described elsewhere [14], [15] and then subjected to microarray analysis using the Almac Diagnostic Ovarian Cancer DSA™ research tool (Durham, NC). Detailed procedures can be found at http://www.almacgroup.com. The tailored ovarian-cancer array measures over 100,000 transcripts on one chip, including those solely expressed in ovary and large numbers of novel ones that are not included in other standard microarrays (e.g. tissue or disease-specific splice variants, inherent antisense transcripts, and non-coding RNA obtained by the in-house sequencing analysis at Almac). The comparison of the array content between DSA and others can be found at http://www.almacgroup.com/wp-content/uploads/Ovarian_Cancer_DSA_techsheet2.pdf. Expression profiling was done on the control SKOV3 cells, the LHR+ SKOV3 cells, and the LHR+ cells incubated with LH for 1, 4, 8, and 20 hours [14], respectively, with three replicates for each of these six variable groups. All data is MIAME compliant and the raw data has been deposited in the GEO database with accession number GSE27328.

Since the ovarian DSA is a high-density platform including only perfect match (PM) probes, the transcript expression was computed using the PM-only normalization algorithm designed by Almac Diagnostics (http://csbl.bmb.uga.edu/~juancui/Publications/OvCan2011/PMonlyQC-documentation.pdf), which is similar to MAS5 (Affymetrix). Transcripts with the maximum intensity among all 18 samples lower than 10 were removed due to the extremely low signal-to-noise ratio, and the geometric mean expression of each transcript was calculated from the triplicates in each group. Through statistical analyses with ANOVA and Mann-Whitney test, only genes with a differential expression change of more than 1.5-fold, with the P-value< = 0.05 adjusted for multiple test by R package, were accepted for further analysis.

MiRanda [26] and TargetScan [27] were used for predicting the microRNA targets from the complete human genome. In addition, the Spearman's rank Rho coefficient between expression levels of the microRNA and their targets was calculated based on the following. Given X_i and Y_i with i = 1..n representing the expression profiles of microRNA and mRNA, where n = 6 represents six distinct cellular states in order of LHR−, LHR+,LH1, LH4, LH8 and LH20. The expression level was then converted to ranks x_i, and y_i, respectively. The difference, d_i = x_i−y_i, between the ranks of each observation was calculated, and the coefficient is given by , where rho>0, rho<0 and rho = 0 represent a positive, negative or no regulatory effect between microRNA and mRNA. Given the Null hypothesis H₀ that x_i and y_i are independent, a two-tailed test was conducted where the p-value is given as . Those correlated pairs with modestly relaxed significance (|rho|>0.8, p-value< = 0.05) were the focus for further analysis.

Out of 132 microRNAs that were selectively profiled on the array, 65 were identified to exhibit differential expression. Among them, 17 are differential in LHR+ SKOV3 cells vs LHR- SKOV3 cells, i.e. negative control, including six upregulated (miR-101-1, -101-2, -199b, -559, -573 and -7-3) and 11 downregulated (miR-103-2, -200c, -151, -29c, -301b, -548a2, -552, -561, -566, -613 and -642) (Table S1a). Following incubation with LH, 57 microRNAs were differentially expressed, including the most highly expressed microRNAs, miR-21, -200c, -593, -103-1 and -124-3 (Table S1b).

The details of microRNA information were obtained from miRBase [28]. Of the 65 microRNAs, 19 are overlapping with intergenic regions, 45 are overlapping with introns and one with an exon, while 34 were found on the reverse strand (Table S2). Gene loci were then obtained from Ensemble (hg18). Figure 1 shows the mapping of microRNAs to the human genome. According to the microRNA clusters annotation in miRBase, i.e. neighboring microRNAs within the pre-defined distance of 10 kb, seven clusters were identified due to their inclusion of at least one differentially expressed microRNA, namely miR-93, -301b, -200c, -425, -29, -449b and -30e. Table S2 shows the impacted regions with the differentially expressed microRNAs within a less restricted distance range. Some of the differentially expressed microRNAs have been aligned to fragile sites of the human genome where the genomic variants were evidently associated with certain types of cancer [29], [30]. For example, the loss of 11p15 (covering miR-210) is found in ovarian cancer [31] and 17q23 (covering miR-301a and miR-21) is amplified in breast cancer [32], as well as those reported in [33], [34]. It should be noted that the SKOV3 cancer cells may have already undergone some copying abnormalities, such as the amplification of miR-21 and the loss of miR-210, which may contribute to the observed gene expression level in the control cancer cells. Although this cannot be determined from the present data, our question here, instead, is whether or not LH induces further transcriptional regulation on any of these microRNAs.

Through the same differential analysis, we have identified 2,210 up-regulated and 4,297 down-regulated mRNAs in LHR+ SKOV3 cells, respectively. The expression change distribution is given in Figure 2. These genes are intimately involved in cell division, DNA replication and transcription, while the genes involved with carbohydrate transport/metabolism and lipid metabolism are only reflected by down-regulated genes. During the 20 h exposure to LH, a total of 14,903 mRNAs exhibited elevated expression at one of the time points, which extend the above functions to posttranslational modification, RNA processing and modification, intracellular trafficking and secretion, signal transduction mechanisms and coenzyme metabolism, while 10,389 mRNAs were down-regulated, reflecting the cellular defense mechanism. The enriched pathway analysis shows that LHR expression in SKOV3 cells may have a positive impact on cellular gap junctions and relevant growth signaling pathways, while moderately suppressing apoptosis, mismatch repair and the Ras-Independent pathway in NK cell-mediated cytotoxicity, which is overall an advantage to cell growth. LH, subsequently, regulated gene expression involved in the cell cycle, p53 and VEGF signaling, gap junction, immune responses and the complement and coagulation cascades, as well as on a few metabolic pathways. The transcriptome expression analysis reflects those pathway alterations that support the phenotypes observed in our previous study [14], as well as many others [15].

Inference of microRNA function can be approached by investigating the proteins and RNAs associated with the biological processes in which their mRNA targets are involved. The following strategy was adopted to first predict the potential mRNA target(s) for each microRNA. Spearman correlation analysis was performed between the expression of 65 differentially expressed microRNAs associated with LHR expression and activation and the expression of 60,860 well-annotated mRNAs across all sample groups (Materials and Methods). Among all possible microRNA-mRNA pairs, significant correlations were detected using (|rho|>0.8, P-value<0.05), which includes 62,150 and 931,009 pairs of negative and positive correlations, respectively. Figure 3 shows the distribution of the rho coefficient of both experimental and predicted microRNA/mRNA pairs against all calculated pairs, which indicates the significance of the interactions.

We then examined those pairs of particular interest, with the mRNAs differentially expressed in the LHR+ SKOV3 cells, i.e. LHR+ and the same with LH incubation for 1, 4, 8 and20 h, since our focus is on those that respond to LHR expression and activation. In total, 19,105 negatively and 211,893 positively correlated pairs are included, involving 19,154 unique mRNAs. Figures 4A and 4B illustrate the top correlated pairs from each group, most of which have not yet been experimentally validated. Interestingly, more positively correlated microRNA-mRNA pairs than negatively correlated pairs were observed for all microRNAs with the exception of nine, miR-181B2, miR-582, miR-497, miR-559, miR-561, miR-101-1, miR-187, miR-572 and miR-301A (Figure 5). The prevalence of high correlations may indicate that the microRNA is intronic or upstream to the correlated gene since they may share the same regulatory element and be transcribed together, and thus do tend to predict physically proximate pairs. The highly negative correlations are expected to indicate possible biochemically important interactions.

We further examined the expressions between microRNA and their host genes, which are generally concordant [35]. Among the 65 differentially expressed microRNAs, 13 intronic ones were observed that are highly or moderately correlated with their host genes, such as mir-555/ASH1L, mir-22/C17orf93, mir-198/FSTL1, mir-561/GULP1 and mir-564/KIF15, 18 poorly correlated and four negatively correlated with their host genes (Table S3). One possible explanation for the poor correlations is that the microRNAs may have their own regulatory elements rather than sharing the same with their host genes. To confirm this possibility, one can search for the transcriptional features in flanking sequences of microRNA precursors such as transcription start sites (TSS), CpG islands and transcription factor binding sites (TFBS), compared to the same analysis on the host genes. The very few observed negative correlations may be attributable to the interference by the diverse expression of splice variants of the same gene measured in this study. Of course, one cannot exclude the possibility that some microRNAs may regulate their host gene through the mRNA degradation machinery.

To ensure that the microRNA-correlated genes are direct targets instead of downstream genes, two popular programs, MiRanda [26] and TargetScan [27], were applied to predict miRNA targets. 584 genes were predicted as potential targets of the 65 microRNAs (see detailed list in Table S4). Although not all predicted pairs possess high correlations, it does show a trend that the percentage of predicted pairs decreased as the coefficients increase along its distribution. With the cutoffs used above, only 155 genes were retained as high-confident ones, i.e. negatively correlated with microRNA and differentially expressed, for functional analysis.

For each microRNA, the function and pathway enrichment analysis was performed on its gene targets in order to infer the main function of the miRNA. From Table S1, it is indicated, for example, that miR-199b-5p participates in angiogenesis, nucleotide excision repair, the PDGF signaling pathway, the cadherin/Wnt/integrin signaling pathway, apoptosis and the MAPK signaling pathway, according to its regulation of the transcription/translation regulator and signaling transducer proteins enriched in its target gene set. MiR-101 is also involved in the Wnt/MAPK/cadherin signaling pathway, as well as hypertrophic cardiomyopathy (HCM), melanogenesis, the metabotropic glutamate receptor group III pathway and ubiquitin-mediated proteolysis. In addition, it may also regulate to some extent the mRNA for cyclic AMP (cAMP)-specific phosphodiesterase 4D (PDE4D), which was found to be highly up-regulated by LH in LHR+ cells [15]. MiR-29c is shown to mainly regulate ECM-receptor interaction, focal adhesion, collagen α chains and the integrin signaling pathway. The main regulation of miR-129 is that of angiogenesis, the Wnt signaling pathway, transcription regulation and cell junction. It is noteworthy that several of the microRNAs have the potential to regulate various tyrosine and serine/threonine kinases.

To further elucidate the microRNA regulation involved in LH-treated cancer cells, 70 experimentally validated targets of the 65 differentially expressed microRNAs were examined according to the miRecords database [36] (Table S1). Some of these genes were differentially expressed in the response to LH binding to LHR+ cancer cells, including those involved in the regulation of cell migration and proliferation (such as IRS1, IRS2, IL6R, TPM1, GLI1, BMPR2 and GRN), cell surface receptor-linked signal transduction (SOCS5 and RAF1), anti-apoptosis (FAS, MCL1 and SGK3) and transcription regulation (DNMT3B, GLI1 and EZH2), as shown in Table 1. Six genes exhibited highly correlated expression to their microRNAs (|rho|> = 0.7), including IRS1, IRS2 and RAF1 to miR-7-1, SGK3 and MTAP to miR-21 and GRN to miR-659. The negatively correlated microRNA/mRNA pairs are of more interest in reflecting a direct interaction. It is indicated from the expression changes that LH may impose a moderate positive regulation of cell proliferation, nucleotide metabolic process and cell surface receptor-linked signal transduction, and a negative regulation of apoptosis on ovarian cancer cells, in terms of the gene regulation through miR-7-1, miR-21 and miR-659. We also examined 54 oncogenes and tumor suppressor genes derived from literature sources [30], [37] (Table S5). As listed in Table 2, only six genes have experimental or predicted information. All the predicted targets are up-regulated except one: up-regulation of miR-21 and down-regulation of its target TPM1, a tumor suppressor gene. This may suggest a role of miR-21 in inhibiting apoptosis and consequently inferring a positive impact of LH on cancer development. Up-regulation of NF1, RB1 and SUFU shows a negative effect on cancer growth, consistent with our previous report [14].