Prognostic analysis for early-stage (stage I/II) melanomas is of paramount importance for customized surveillance and treatment plans. Since immune checkpoint inhibitors have recently been approved for stage IIB and IIC melanomas, prognostic tools to identify patients at high risk of recurrence have become even more critical. This study aims to assess the effectiveness of machine-learning algorithms in predicting melanoma recurrence using clinical and histopathologic features from Electronic Health Records (EHRs). We collected 1720 early-stage melanomas: 1172 from the Mass General Brigham healthcare system (MGB) and 548 from the Dana-Farber Cancer Institute (DFCI). We extracted 36 clinicopathologic features and used them to predict the recurrence risk with supervised machine-learning algorithms. Models were evaluated internally and externally: (1) five-fold cross-validation of the MGB cohort; (2) the MGB cohort for training and the DFCI cohort for testing independently. In the internal and external validations, respectively, we achieved a recurrence classification performance of AUC: 0.845 and 0.812, and a time-to-event prediction performance of time-dependent AUC: 0.853 and 0.820. Breslow tumor thickness and mitotic rate were identified as the most predictive features. Our results suggest that machine-learning algorithms can extract predictive signals from clinicopathologic features for early-stage melanoma recurrence prediction, which will enable the identification of patients that may benefit from adjuvant immunotherapy.

PMCA4 is a critical regulator of Ca2+ homeostasis in mammalian cells. While its biological and prognostic relevance in several cancer types has already been demonstrated, only preclinical investigations suggested a metastasis suppressor function in melanoma. Therefore, we studied the expression pattern of PMCA4 in human skin, nevus, as well as in primary and metastatic melanoma using immunohistochemistry. Furthermore, we analyzed the prognostic power of PMCA4 mRNA levels in cutaneous melanoma both at the non-metastatic stage as well as after PD-1 blockade in advanced disease. PMCA4 localizes to the plasma membrane in a differentiation dependent manner in human skin and mucosa, while nevus cells showed no plasma membrane staining. In contrast, primary cutaneous, choroidal and conjunctival melanoma cells showed specific plasma membrane localization of PMCA4 with a wide range of intensities. Analyzing the TCGA cohort, PMCA4 mRNA levels showed a gender specific prognostic impact in stage I–III melanoma. Female patients with high transcript levels had a significantly longer progression-free survival. Melanoma cell specific PMCA4 protein expression is associated with anaplasticity in melanoma lung metastasis but had no impact on survival after lung metastasectomy. Importantly, high PMCA4 transcript levels derived from RNA-seq of cutaneous melanoma are associated with significantly longer overall survival after PD-1 blockade. In summary, we demonstrated that human melanoma cells express PMCA4 and PMCA4 transcript levels carry prognostic information in a gender specific manner.

Pancreatic ductal adenocarcinoma (PDAC) is among the deadliest malignancies and potentially curable only with radical surgical resection at early stages. The tumor microenvironment has been shown to be central to the development and progression of PDAC. A better understanding of how early human PDAC metabolically communicates with its environment and differs from healthy pancreas could help improve PDAC diagnosis and treatment. Here we performed deep proteomic analyses from diagnostic specimens of operable, treatment-naïve PDAC patients (n=14), isolating four tissue compartments by laser-capture microdissection: PDAC lesions, tumor-adjacent but morphologically benign exocrine glands, and connective tissues neighboring each of these compartments. Protein and pathway levels were compared between compartments and with control pancreatic proteomes. Selected targets were studied immunohistochemically in the 14 patients and in additional tumor microarrays, and lipid deposition was assessed by non-linear label-free imaging (n=16). Widespread downregulation of pancreatic secretory functions was observed, which was paralleled by high cholesterol biosynthetic activity without prominent lipid storage in the neoplastic cells. Stromal compartments harbored ample blood apolipoproteins, indicating the abundant microvasculature at the time of tumor removal. The features best differentiating the tumor-adjacent exocrine tissue from healthy control pancreas were defined by upregulation of proteins related to lipid transport. Importantly, histologically benign exocrine regions harbored the most significant prognostic pathways, with proteins involved in lipid transport and metabolism, such as neutral cholesteryl ester hydrolase 1, associating with shorter survival. In conclusion, this study reveals the prognostic molecular changes in the exocrine tissue neighboring pancreatic cancer and identifies enhanced lipid transport and metabolism as its defining features.

Plasma analysis by mass spectrometry-based proteomics remains a challenge due to its large dynamic range of 10 orders in magnitude. We created a methodology for protein identification known as Wise MS Transfer (WiMT). Melanoma plasma samples from biobank archives were directly analyzed using simple sample preparation. WiMT is based on MS1 features between several MS runs together with custom protein databases for ID generation. This entails a multi-level dynamic protein database with different immunodepletion strategies by applying single-shot proteomics. The highest number of melanoma plasma proteins from undepleted and unfractionated plasma was reported, mapping >1200 proteins from >10,000 protein sequences with confirmed significance scoring. Of these, more than 660 proteins were annotated by WiMT from the resulting ~5800 protein sequences. We could verify 4000 proteins by MS1t analysis from HeLA extracts. The WiMT platform provided an output in which 12 previously well-known candidate markers were identified. We also identified low-abundant proteins with functions related to (i) cell signaling, (ii) immune system regulators, and (iii) proteins regulating folding, sorting, and degradation, as well as (iv) vesicular transport proteins. WiMT holds the potential for use in large-scale screening studies with simple sample preparation, and can lead to the discovery of novel proteins with key melanoma disease functions.

Supplementary Data from Lipid Metabolic Reprogramming Extends beyond Histologic Tumor Demarcations in Operable Human Pancreatic Cancer