@article{KotlyarKrebsSolimandoetal.2023,
  author    = {Kotlyar, Mischa J. and Krebs, Markus and Solimando, Antonio Giovanni and Marquardt, Andr{\´e} and Burger, Maximilian and K{\"u}bler, Hubert and Bargou, Ralf and Kneitz, Susanne and Otto, Wolfgang and Breyer, Johannes and Vergho, Daniel C. and Kneitz, Burkhard and Kalogirou, Charis},
  title     = {Critical evaluation of a microRNA-based risk classifier predicting cancer-specific survival in renal cell carcinoma with tumor thrombus of the inferior vena cava},
  series = {Cancers},
  volume    = {15},
  journal   = {Cancers},
  number    = {7},
  issn      = {2072-6694},
  doi       = {10.3390/cancers15071981},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-311040},
  year      = {2023},
  abstract  = {(1) Background: Clear cell renal cell carcinoma extending into the inferior vena cava (ccRCC\(^{IVC}\)) represents a clinical high-risk setting. However, there is substantial heterogeneity within this patient subgroup regarding survival outcomes. Previously, members of our group developed a microRNA(miR)-based risk classifier — containing miR-21-5p, miR-126-3p and miR-221-3p expression — which significantly predicted the cancer-specific survival (CSS) of ccRCC\(^{IVC}\) patients. (2) Methods: Examining a single-center cohort of tumor tissue from n = 56 patients with ccRCC\(^{IVC}\), we measured the expression levels of miR-21, miR-126, and miR-221 using qRT-PCR. The prognostic impact of clinicopathological parameters and miR expression were investigated via single-variable and multivariable Cox regression. Referring to the previously established risk classifier, we performed Kaplan-Meier analyses for single miR expression levels and the combined risk classifier. Cut-off values and weights within the risk classifier were taken from the previous study. (3) Results: miR-21 and miR-126 expression were significantly associated with lymphonodal status at the time of surgery, the development of metastasis during follow-up, and cancer-related death. In Kaplan-Meier analyses, miR-21 and miR-126 significantly impacted CSS in our cohort. Moreover, applying the miR-based risk classifier significantly stratified ccRCC\(^{IVC}\) according to CSS. (4) Conclusions: In our retrospective analysis, we successfully validated the miR-based risk classifier within an independent ccRCC\(^{IVC}\) cohort.},
  language  = {en}
}
@article{MarquardtHartrampfKollmannsbergeretal.2023,
  author    = {Marquardt, Andr{\´e} and Hartrampf, Philipp and Kollmannsberger, Philip and Solimando, Antonio G. and Meierjohann, Svenja and K{\"u}bler, Hubert and Bargou, Ralf and Schilling, Bastian and Serfling, Sebastian E. and Buck, Andreas and Werner, Rudolf A. and Lapa, Constantin and Krebs, Markus},
  title     = {Predicting microenvironment in CXCR4- and FAP-positive solid tumors — a pan-cancer machine learning workflow for theranostic target structures},
  series = {Cancers},
  volume    = {15},
  journal   = {Cancers},
  number    = {2},
  issn      = {2072-6694},
  doi       = {10.3390/cancers15020392},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-305036},
  year      = {2023},
  abstract  = {(1) Background: C-X-C Motif Chemokine Receptor 4 (CXCR4) and Fibroblast Activation Protein Alpha (FAP) are promising theranostic targets. However, it is unclear whether CXCR4 and FAP positivity mark distinct microenvironments, especially in solid tumors. (2) Methods: Using Random Forest (RF) analysis, we searched for entity-independent mRNA and microRNA signatures related to CXCR4 and FAP overexpression in our pan-cancer cohort from The Cancer Genome Atlas (TCGA) database — representing n = 9242 specimens from 29 tumor entities. CXCR4- and FAP-positive samples were assessed via StringDB cluster analysis, EnrichR, Metascape, and Gene Set Enrichment Analysis (GSEA). Findings were validated via correlation analyses in n = 1541 tumor samples. TIMER2.0 analyzed the association of CXCR4 / FAP expression and infiltration levels of immune-related cells. (3) Results: We identified entity-independent CXCR4 and FAP gene signatures representative for the majority of solid cancers. While CXCR4 positivity marked an immune-related microenvironment, FAP overexpression highlighted an angiogenesis-associated niche. TIMER2.0 analysis confirmed characteristic infiltration levels of CD8+ cells for CXCR4-positive tumors and endothelial cells for FAP-positive tumors. (4) Conclusions: CXCR4- and FAP-directed PET imaging could provide a non-invasive decision aid for entity-agnostic treatment of microenvironment in solid malignancies. Moreover, this machine learning workflow can easily be transferred towards other theranostic targets.},
  language  = {en}
}
@phdthesis{Marquardt2023,
  author    = {Marquardt, Andr{\´e}},
  title     = {Machine-Learning-Based Identification of Tumor Entities, Tumor Subgroups, and Therapy Options},
  doi       = {10.25972/OPUS-32954},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-329548},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2023},
  abstract  = {Molecular genetic analyses, such as mutation analyses, are becoming increasingly important in the tumor field, especially in the context of therapy stratification. The identification of the underlying tumor entity is crucial, but can sometimes be difficult, for example in the case of metastases or the so-called Cancer of Unknown Primary (CUP) syndrome. In recent years, methylome and transcriptome utilizing machine learning (ML) approaches have been developed to enable fast and reliable tumor and tumor subtype identification. However, so far only methylome analysis have become widely used in routine diagnostics. The present work addresses the utility of publicly available RNA-sequencing data to determine the underlying tumor entity, possible subgroups, and potential therapy options. Identification of these by ML - in particular random forest (RF) models - was the first task. The results with test accuracies of up to 99\% provided new, previously unknown insights into the trained models and the corresponding entity prediction. Reducing the input data to the top 100 mRNA transcripts resulted in a minimal loss of prediction quality and could potentially enable application in clinical or real-world settings. By introducing the ratios of these top 100 genes to each other as a new database for RF models, a novel method was developed enabling the use of trained RF models on data from other sources. Further analysis of the transcriptomic differences of metastatic samples by visual clustering showed that there were no differences specific for the site of metastasis. Similarly, no distinct clusters were detectable when investigating primary tumors and metastases of cutaneous skin melanoma (SKCM). Subsequently, more than half of the validation datasets had a prediction accuracy of at least 80\%, with many datasets even achieving a prediction accuracy of - or close to - 100\%. To investigate the applicability of the used methods for subgroup identification, the TCGA-KIPAN dataset, consisting of the three major kidney cancer subgroups, was used. The results revealed a new, previously unknown subgroup consisting of all histopathological groups with clinically relevant characteristics, such as significantly different survival. Based on significant differences in gene expression, potential therapeutic options of the identified subgroup could be proposed. Concludingly, in exploring the potential applicability of RNA-sequencing data as a basis for therapy prediction, it was shown that this type of data is suitable to predict entities as well as subgroups with high accuracy. Clinical relevance was also demonstrated for a novel subgroup in renal cell carcinoma. The reduction of the number of genes required for entity prediction to 100 genes, enables panel sequencing and thus demonstrates potential applicability in a real-life setting.},
  subject      = {Maschinelles Lernen},
  language  = {en}
}