Patterns of Tumor Progression Predict Small and Tissue-Specific Tumor-Originating Niches

Abstract

The development of cancer is a multistep process in which cells increase in malignancy through progressive alterations. Such altered cells compete with wild-type cells and have to establish within a tissue in order to induce tumor formation. The range of this competition and the tumor-originating cell type which acquires the first alteration is unknown for most human tissues, mainly because the involved processes are hardly observable, aggravating an understanding of early tumor development. On the tissue scale, one observes different progression types, namely with and without detectable benign precursor stages. Human epidemiological data on the ratios of the two progression types exhibit large differences between cancers. The idea of this study is to utilize data of the ratios of progression types in human cancers to estimate the homeostatic range of competition in human tissues. This homeostatic competition range can be interpreted as necessary numbers of altered cells to induce tumor formation on the tissue scale. For this purpose, we develop a cell-based stochastic model which is calibrated with newly-interpreted human epidemiological data. We find that the number of tumor cells which inevitably leads to later tumor formation is surprisingly small compared to the overall tumor and largely depends on the human tissue type. This result points toward the existence of a tissue-specific tumor-originating niche in which the fate of tumor development is decided early and long before a tumor becomes detectable. Moreover, our results suggest that the fixation of tumor cells in the tumor-originating niche triggers new processes which accelerate tumor growth after normal tissue homeostasis is voided. Our estimate for the human colon agrees well with the size of the stem cell niche in colonic crypts. For other tissues, our results might aid to identify the tumor-originating cell type. For instance, data on primary and secondary glioblastoma suggest that the tumors originate from a cell type competing in a range of 300 - 1,900 cells.

Keywords: cancer development; cell-based stochastic model; spatial Moran model; tumor formation and progression; tumor origin.

Figure 1

Tumor progression types and patterns in the model. Wild-type cells can progress to benign tumor cells during proliferation with mutation probability u and further progress to malignant tumor cells with probability v. Wild-type and benign tumor cells neutrally compete with each other within the homeostatic range of competition which is modeled by Moran dynamics, see Figure 2. We assume that tumor cells establish within the tissue if they clonally expand to fixation in the homeostatic range of competition corresponding to the parameter N in the model. Then, a tumor will inevitably be detected either directly if N is sufficiently large or at a later time due to an altered growth behavior destroying tissue homeostasis after fixation. Correspondingly, the timescale between fixation and detection, indicated by the green interval, potentially ranges from zero to several years. The cellular dynamics lead to two distinct progression types at the tissue scale, namely sequential progression and tunneling progression. The benign tumor fraction p determines the progression pattern. A further progression from benign fixation to malignant tumor detection (dotted line in the cellular scale) or after a possible benign tumor detection (dotted line in the tissue scale) is neglected.

Figure 2

Moran dynamics with different spatial cell arrangements. In the Moran dynamics, a randomly chosen cell proliferates (blue circle) and replaces a neighboring cell which undergoes cell death (red circle). In (A), the space-free dynamics is illustrated, i.e., each cell can be replaced by any other cell. In (B), only neighboring cells can be replaced representing a one-dimensional cell arrangement.

Figure 3

Estimated tumor-originating niche sizes based on tumor progression patterns. This plot shows the benign tumor fraction in the space-free (red) and one-dimensional (blue) model as function of the tumor-originating niche size. The blue curve has been numerically evaluated, see Text S1, equation (12). The red curve represents the plot of equation (3) in Text S1. The shaded areas illustrate the regimes in which both sequential and tunneling progression are possible for the space-free and the 1D model, see Table 1. The dots indicate the estimated tumor-originating niche size, (a)–(g) indicate different tissues and the squares represent experimental data for these tissues, see Table 2.