Melanoma Clinical Decision Support System: An Artificial Intelligence-Based Tool to Diagnose and Predict Disease Outcome in Early-Stage Melanoma Patients.

This study set out to assess the performance of an artificial intelligence (AI) algorithm based on clinical data and dermatoscopic imaging for the early diagnosis of melanoma, and its capacity to define the metastatic progression of melanoma through serological and histopathological biomarkers, enabling dermatologists to make more informed decisions about patient management. Integrated analysis of demographic data, images of the skin lesions, and serum and histopathological markers were analyzed in a group of 196 patients with melanoma. The interleukins (ILs) IL-4, IL-6, IL-10, and IL-17A as well as IFNγ (interferon), GM-CSF (granulocyte and macrophage colony-stimulating factor), TGFß (transforming growth factor), and the protein DCD (dermcidin) were quantified in the serum of melanoma patients at the time of diagnosis, and the expression of the RKIP, PIRIN, BCL2, BCL3, MITF, and ANXA5 proteins was detected by immunohistochemistry (IHC) in melanoma biopsies. An AI algorithm was used to improve the early diagnosis of melanoma and to predict the risk of metastasis and of disease-free survival. Two models were obtained to predict metastasis (including "all patients" or only patients "at early stages of melanoma"), and a series of attributes were seen to predict the progression of metastasis: Breslow thickness, infiltrating BCL-2 expressing lymphocytes, and IL-4 and IL-6 serum levels. Importantly, a decrease in serum GM-CSF seems to be a marker of poor prognosis in patients with early-stage melanomas.

Terfenadine induces apoptosis and autophagy in melanoma cells through ROS-dependent and -independent mechanisms.

Previously we found that terfenadine, an H1 histamine receptor antagonist, acts as a potent apoptosis inducer in melanoma cells through modulation of Ca(2+) homeostasis. In this report, focusing our attention on the apoptotic mechanisms activated by terfenadine, we show that this drug can potentially activate distinct intrinsic signaling pathways depending on culture conditions. Serum-deprived conditions enhance the cytotoxic effect of terfenadine and caspase-4 and -2 are activated upstream of caspase-9. Moreover, although we found an increase in ROS levels, the apoptosis was ROS independent. Conversely, terfenadine treatment in complete medium induced ROS-dependent apoptosis. Caspase-4, -2, and -9 were simultaneously activated and p73 and Noxa induction were involved. ROS inhibition prevented p73 and Noxa expression but not p53 and p21 expression, suggesting a role for Noxa in p53-independent apoptosis in melanoma cells. Finally, we found that terfenadine induced autophagy, that can promote apoptosis. These findings demonstrate the great potential of terfenadine to kill melanoma cells through different cellular signaling pathways and could contribute to define new therapeutic strategies in melanoma.

The diversity profile of TP53 is influenced by positive selection on the immediately upstream locus WDR79.

BACKGROUND/AIM: TP53 is an efficient central node in a signal transduction network that responds to minimize cancer. However, over 50% of tumors show some mutation in TP53. Thus, one might argue that this single central node network lacks robustness. Therefore, we wanted to investigate if natural selection has played a role in shaping the genomic region containing TP53. METHODS: We have analyzed the HapMap data for evidence of selection using F(ST) pairwise comparisons and the extended haplotype homozygosity test on a 200-kb region encompassing TP53. We have also resequenced 4 kb upstream TP53 in Europeans (including melanoma patients), Asians, Australian Aborigines and Africans. RESULTS: Genetic hitchhiking by a linked, positively selected allele at the nearby gene WDR79 may be partly responsible for the sequence diversity profile of TP53. It can help explain why the TP53 Arg72 allele is the major allele in Europeans even when the alternative allele, 72Pro, has been reported to offer an increased longevity after disease. CONCLUSIONS: Despite the important role of TP53, a complex interplay with other evolutionary forces, which are extrinsic to TP53 function, may have driven the genetic diversity pattern of this locus, and, as a consequence, its structure and function.

Serum markers improve current prediction of metastasis development in early-stage melanoma patients: a machine learning-based study.

Metastasis development represents an important threat for melanoma patients, even when diagnosed at early stages and upon removal of the primary tumor. In this scenario, determination of prognostic biomarkers would be of great interest. Serum contains information about the general status of the organism and therefore represents a valuable source for biomarkers. Thus, we aimed to define serological biomarkers that could be used along with clinical and histopathological features of the disease to predict metastatic events on the early-stage population of patients. We previously demonstrated that in stage II melanoma patients, serum levels of dermcidin (DCD) were associated with metastatic progression. Based on the relevance of the immune response on the cancer progression and the recent association of DCD with local and systemic immune response against cancer cells, serum DCD was analyzed in a new cohort of patients along with interleukin 4 (IL-4), IL-6, IL-10, IL-17A, interferon γ (IFN-γ), transforming growth factor-ß (TGF- ß), and granulocyte-macrophage colony-stimulating factor (GM-CSF). We initially recruited 448 melanoma patients, 323 of whom were diagnosed as stages I-II according to AJCC. Levels of selected cytokines were determined by ELISA and Luminex, and obtained data were analyzed employing machine learning and Kaplan-Meier techniques to define an algorithm capable of accurately classifying early-stage melanoma patients with a high and low risk of developing metastasis. The results show that in early-stage melanoma patients, serum levels of the cytokines IL-4, GM-CSF, and DCD together with the Breslow thickness are those that best predict melanoma metastasis. Moreover, resulting algorithm represents a new tool to discriminate subjects with good prognosis from those with high risk for a future metastasis.

Complex signatures of selection for the melanogenic loci TYR, TYRP1 and DCT in humans.

BACKGROUND: The observed correlation between ultraviolet light incidence and skin color, together with the geographical apportionment of skin reflectance among human populations, suggests an adaptive value for the pigmentation of the human skin. We have used Affymetrix U133a v2.0 gene expression microarrays to investigate the expression profiles of a total of 9 melanocyte cell lines (5 from lightly pigmented donors and 4 from darkly pigmented donors) plus their respective unirradiated controls. In order to reveal signatures of selection in loci with a bearing on skin pigmentation in humans, we have resequenced between 4 to 5 kb of the proximal regulatory regions of three of the most differently expressed genes, in the expectation that variation at regulatory regions might account for intraespecific morphological diversity, as suggested elsewhere. RESULTS: Contrary to our expectations, expression profiles did not cluster the cells into unirradiated versus irradiated melanocytes, or into lightly pigmented versus darkly pigmented melanocytes. Instead, expression profiles correlated with the presence of Bovine Pituitary Extract (known to contain alpha-MSH) in the media. This allowed us to differentiate between melanocytes that are synthesizing melanin and those that are not. TYR, TYRP1 and DCT were among the five most differently expressed genes between these two groups. Population genetic analyses of sequence haplotypes of the proximal regulatory flanking-regions included Tajima's D, HEW and DHEW neutrality tests analysis. These were complemented with EHH tests (among others) in which the significance was obtained by a novel approach using extensive simulations under the coalescent model with recombination. We observe strong evidence for positive selection for TYRP1 alleles in Africans and for DCT and TYRP1 in Asians. However, the overall picture reflects a complex pattern of selection, which might include overdominance for DCT in Europeans. CONCLUSION: Diversity patterns clearly evidence adaptive selection in pigmentation genes in Africans and Asians. In Europeans, the evidence is more complex, and both directional and balancing selection may be involved in light skin. As a result, different non-African populations may have acquired light skin by alternative ways, and so light skin, and perhaps dark skin too, may be the result of convergent evolution.

Cutaneous polyarteritis nodosa.

The term polyarteritis nodosa (PAN) presently includes classic systemic PAN, cutaneous PAN, and microscopic PAN (microscopic polyangeiitis). Cutaneous PAN involves the deep dermis and the panniculus, with anatomopathological findings diagnostic for arteritis. The most frequent clinical manifestation of cutaneous PAN is the presence of nodules on the lower legs, which frequently are found at different stages of development. At times, they may not leave residual changes, but generally a violaceous livedoid color or pigmentation with retiform appearance persists for months and even years. Ulceration also is a frequent complication of cutaneous PAN. Pain, arthralgias, malaise, and moderate fever are frequently associated symptoms. Histopathologically, cutaneous PAN shows a single artery involved with diagnostic inflammatory changes. The involved artery is always located in the deep dermis or in the panniculus. Inflammatory active skin nodules show a necrotizing arteritis with variable amounts of fibrinoid necrosis and leukocytoclasia, edema and inflammatory cells. The presence of focal panniculitis surrounding the involved artery is characteristic, in contrast with the more diffuse panniculitis usually found in other nodular diseases. Cutaneous PAN has a variable course, with repeated exacerbations. Salicilates relieve the pain in most instances and may be the only treatment required to improve the symptoms in patients with moderate flare-ups. A short course of corticosteroids therapy at a moderate dose is the most effective treatment to relieve the symptoms and to reduce the inflammation. Patients with an increased ASO titer should always be treated with penicillin.

H1 histamine receptor antagonists induce genotoxic and caspase-2-dependent apoptosis in human melanoma cells.

Previously, we found that the H1 histamine receptor antagonist diphenhydramine induces apoptosis in human acute T-lymphocytic leukemia cells. Since histamine has been shown to act as a growth factor in malignant melanoma cells, we decided to evaluate the in vitro effect of diphenhydramine and other H1 histamine receptor antagonists, such as terfenadine, astemizol and triprolidine on four malignant human melanoma cell lines. These antagonists were found to induce apoptotic cell death in all four melanoma cell lines. Apoptosis was determined by assessment of phosphatidylserine exposure on the surface of the cells and nuclear fragmentation. Importantly, H1 antagonist treatments did not adversely affect the viability of human melanocytes and murine fibroblasts at the same doses and duration of exposure. Treatment of melanoma cells with terfenadine induced DNA damage and caspases 2, 3, 6, 8 and 9 activation. Furthermore, the general caspase inhibitor (z-VAD-FMK) and a selective inhibitor of caspase-2 (z-VDVAD-FMK) protected melanoma cells from terfenadine-induced apoptosis. In contrast, the caspase-8 inhibitor (z-IETD-FMK) was ineffective. In addition, we found that mitochondria are involved in TEF-induced apoptosis, characterized by the dissipation of the mitochondrial transmembrane potential, the release of cytochrome c into the cytosolic compartment and caspase-9 activation. On the basis of these results we conclude that H1 histamine receptor antagonists induce apoptosis in human melanoma cells but not in normal melanocytes and embryonic murine fibroblasts; this apoptosis appears to be caspase-2-dependent and involves the mitochondrial pathway. The present results may contribute to the elaboration of novel therapeutic strategies for the treatment of malignant human melanoma.