The ovarian cancer oncobiome

Abstract

Humans and other mammals are colonized by microbial agents across the kingdom which can represent a unique microbiome pattern. Dysbiosis of the microbiome has been associated with pathology including cancer. We have identified a microbiome signature unique to ovarian cancers, one of the most lethal malignancies of the female reproductive system, primarily because of its asymptomatic nature during the early stages in development. We screened ovarian cancer samples along with matched, and non-matched control samples using our pan-pathogen array (PathoChip), combined with capture-next generation sequencing. The results show a distinct group of viral, bacterial, fungal and parasitic signatures of high significance in ovarian cases. Further analysis shows specific viral integration sites within the host genome of tumor samples, which may contribute to the carcinogenic process. The ovarian cancer microbiome signature provides insights for the development of targeted therapeutics against ovarian cancers.

Keywords: microbiome; next generation sequencing; oncobiome; ovarian cancer; pathochip.

Figure 1. Viral signatures detected in ovarian, matched and non-matched controls

(A) Molecular signatures of viral groups detected in ovarian cancer, with the total hybridization signal for each viral groups (sum of average hybridization signal for all the representative families in the group) represented according to descending order as a bar graph and prevalence of the same as dots. (B) The percentage of tumorigenic viral signatures detected in the ovarian cancers are represented in a pie chart. (C) The average hybridization signal of the tumorigenic viral signatures detected in the ovarian cancers are represented in the decreasing order as a bar graph, whereas their respective prevalence are represented as dots. (D and E) The signatures of viral families detected in matched (D) and non-matched (E) controls are represented according to decreasing average hybridization signals as bar graphs, and their respective prevalence as dots. (F) Heat map of average hybridization signals for probes of Poxviruses, Retroviruses, Herpesviruses, Polyomaviruses and Papillomaviruses detected in ovarian cancers (OC), matched (MC) and non-matched (NC) controls. Heat map of average hybridization signal of both conserved and specific probes of Poxviridae are shown. Among the conserved poxviridae probes mentioned, (a) comprises the conserved probes detected significantly in the ovarian cancer versus the controls, and (b) comprises the conserved probes detected significantly in the controls versus the ovarian cancers screened. In the heat map with Herpesviridae probes, those mentioned (c) are conserved probes. All other probes in these heat maps are specific probes. (G) Venn diagram showing the number of viral families common or unique to the ovarian cancer and control samples.

Figure 2. Bacterial signatures detected in ovarian, matched and non-matched controls

(A) Bacterial signatures detected in ovarian cancers, matched and non-matched controls. The prevalence of those signatures are represented in the decreasing order as dots, and their average hybridization signal being represented as a bar graph. (B) Distribution of bacterial phyla detected in ovarian cancer, matched and non-matched controls. (C) Venn diagram showing the number of bacteria common or unique to the ovarian cancer and control samples.

Figure 3. Fungal signatures detected in ovarian, matched and non-matched controls

(A) Fungal signatures detected in ovarian cancer, matched and non-matched controls. The prevalence of those signatures are represented in the decreasing order as dots, and their average hybridization signal being represented as a bar graph. (B) Venn diagram showing the number of fungi common or unique to the ovarian cancer and control samples.

Figure 4. Parasitic signatures detected in ovarian, matched and non-matched controls

(A) Parasitic signatures detected in ovarian cancer, matched and non-matched controls. The prevalence of those signatures are represented in the decreasing order as dots, and their average hybridization signal being represented as a bar graph. (B) Venn diagram showing the number of parasites common or unique to the ovarian cancer and control samples.

Figure 5. Hierarchical clustering of ovarian cancer samples screened

Hierarachial clustering of 99 ovarian cancer samples. (A). Hierarchial clustering by R program using Euclidean distance, complete linkage and non-adjusted values. Samples marked (▪) were the samples that were screened in pools, rest were screened individually. (B). Clustering of the OSCC samples using NBClust software [CH (Calinski and Harabasz) index, Euclidean distance, complete linkage]. (C). Topological analysis using Ayasdi software, using Euclidean (L2) metric and L-infinity centrality lenses. The cancer samples that had similar detection for viral and microbial signatures formed the nodes, and those nodes are connected by an edge if the corresponding node have detection pattern in common to the first node. Each nodes are colored according to the number of samples clustered in each node.

Figure 6. Targeted MiSeq reads align to capture probe locations

Probe capture sequencing alignment is shown for individual capture pools (Capture 1-6 or, C1-6). The whole genome amplified DNA plus cDNA of the ovarian cancer samples were hybridized to a set of biotinylated probes, then captured by streptavidin beads, and used for tagmentation, library preparation and deep sequencing with paired –end 250-nt reads. The total number of MiSeq reads per capture pool for HPV18 (A) and Yaba Monkey Tumor Virus (B) are mentioned at the right end of the read coverage track. For example we obtained 302 reads for C2 capture. The miseq reads from individual capture when aligned with the metagenome of PathoChip (Chip probes) was found to cluster mostly at the capture probe regions. The genomic location are mentioned in the figure for each organism. Figure A shows the MiSeq read alignement to the HPV18 probes on the PathoChip. The probes corresponding to the HPV18 genes are mentioned. It also shows the heat map of hybridization signals of all the HPV18 probes in the PathoChip with the ovarian samples. The HPV18 probes marked (*) are the probes that were biotinylated and used for capture of the HPV18 sequences from the whole genome amplified DNA plus cDNA of the ovarian cancer samples. Figure B shows the MiSeq read alignement to the PathoChip probes for Yaba Monkey Tumor Virus. MiSeq reads aligned to the 1 capture probe used which corresponded to g52R gene of the virus.

Figure 7. Viral genomic integrations in the host chromosome

(A). Alignment of the MiSeq reads to the reference of HHV6A, showed soft-clipped regions that do not align to the corresponding viral reference sequences. These soft-clipped reads shown were then extracted from the alignment and mapped (containing sequences of potential pathogen-integrated human loci) to the human genome, which reveals the exact human and pathogen integration breakpoints. (B). Karyogram plot of virus insertion sites in human chromosomes. All the insertion sites were included. The number of insertion sites in each chromosome is mentioned in the figure before chromosome number. G-banding annotation for each chromosome is shown; gneg - Giemsa negative bands; The Giemsa positive bands have further been subdivided into gpos25, gpos50, gpos75, and gpos100 with the higher number indicating a darker stain; acen - centromeric regions; gvar - variable length heterochromatic regions; stalk - tightly constricted regions on the short arms of the acrocentric chromosomes (C). Circos plot highlighting fusion events for the viral insertions into individual human chromosomes. All the reads were taken into account and chromosome numbers are mentioned. Viral insertions for individual families are represented in the inner concentric circular tracks. The outermost track shows all the insertions taken together highlighting the karyotype of each chromosome. (D). The number of individual viral genomic insertions in human somatic chromosomes detected in the study are shown. (E) Association of host genes affected by viral genomic integrations to malignant tumor formation, analysed by Ingenuity Pathway Analysis (IPA) program that showed highly significant p- value for such association.