@article{SahlolKollmannsbergerEwees2020,
  author    = {Sahlol, Ahmed T. and Kollmannsberger, Philip and Ewees, Ahmed A.},
  title     = {Efficient Classification of White Blood Cell Leukemia with Improved Swarm Optimization of Deep Features},
  series = {Scientific Reports},
  volume    = {10},
  journal   = {Scientific Reports},
  number    = {1},
  doi       = {10.1038/s41598-020-59215-9},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-229398},
  year      = {2020},
  abstract  = {White Blood Cell (WBC) Leukaemia is caused by excessive production of leukocytes in the bone marrow, and image-based detection of malignant WBCs is important for its detection. Convolutional Neural Networks (CNNs) present the current state-of-the-art for this type of image classification, but their computational cost for training and deployment can be high. We here present an improved hybrid approach for efficient classification of WBC Leukemia. We first extract features from WBC images using VGGNet, a powerful CNN architecture, pre-trained on ImageNet. The extracted features are then filtered using a statistically enhanced Salp Swarm Algorithm (SESSA). This bio-inspired optimization algorithm selects the most relevant features and removes highly correlated and noisy features. We applied the proposed approach to two public WBC Leukemia reference datasets and achieve both high accuracy and reduced computational complexity. The SESSA optimization selected only 1 K out of 25 K features extracted with VGGNet, while improving accuracy at the same time. The results are among the best achieved on these datasets and outperform several convolutional network models. We expect that the combination of CNN feature extraction and SESSA feature optimization could be useful for many other image classification tasks.},
  language  = {en}
}
@article{MarquardtSolimandoKerscheretal.2021,
  author    = {Marquardt, Andr{\´e} and Solimando, Antonio Giovanni and Kerscher, Alexander and Bittrich, Max and Kalogirou, Charis and K{\"u}bler, Hubert and Rosenwald, Andreas and Bargou, Ralf and Kollmannsberger, Philip and Schilling, Bastian and Meierjohann, Svenja and Krebs, Markus},
  title     = {Subgroup-Independent Mapping of Renal Cell Carcinoma — Machine Learning Reveals Prognostic Mitochondrial Gene Signature Beyond Histopathologic Boundaries},
  series = {Frontiers in Oncology},
  volume    = {11},
  journal   = {Frontiers in Oncology},
  issn      = {2234-943X},
  doi       = {10.3389/fonc.2021.621278},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-232107},
  year      = {2021},
  abstract  = {Background: Renal cell carcinoma (RCC) is divided into three major histopathologic groups—clear cell (ccRCC), papillary (pRCC) and chromophobe RCC (chRCC). We performed a comprehensive re-analysis of publicly available RCC datasets from the TCGA (The Cancer Genome Atlas) database, thereby combining samples from all three subgroups, for an exploratory transcriptome profiling of RCC subgroups. Materials and Methods: We used FPKM (fragments per kilobase per million) files derived from the ccRCC, pRCC and chRCC cohorts of the TCGA database, representing transcriptomic data of 891 patients. Using principal component analysis, we visualized datasets as t-SNE plot for cluster detection. Clusters were characterized by machine learning, resulting gene signatures were validated by correlation analyses in the TCGA dataset and three external datasets (ICGC RECA-EU, CPTAC-3-Kidney, and GSE157256). Results: Many RCC samples co-clustered according to histopathology. However, a substantial number of samples clustered independently from histopathologic origin (mixed subgroup)—demonstrating divergence between histopathology and transcriptomic data. Further analyses of mixed subgroup via machine learning revealed a predominant mitochondrial gene signature—a trait previously known for chRCC—across all histopathologic subgroups. Additionally, ccRCC samples from mixed subgroup presented an inverse correlation of mitochondrial and angiogenesis-related genes in the TCGA and in three external validation cohorts. Moreover, mixed subgroup affiliation was associated with a highly significant shorter overall survival for patients with ccRCC—and a highly significant longer overall survival for chRCC patients. Conclusions: Pan-RCC clustering according to RNA-sequencing data revealed a distinct histology-independent subgroup characterized by strengthened mitochondrial and weakened angiogenesis-related gene signatures. Moreover, affiliation to mixed subgroup went along with a significantly shorter overall survival for ccRCC and a longer overall survival for chRCC patients. Further research could offer a therapy stratification by specifically addressing the mitochondrial metabolism of such tumors and its microenvironment.},
  language  = {en}
}
@article{MarquardtLandwehrRonchietal.2021,
  author    = {Marquardt, Andr{\´e} and Landwehr, Laura-Sophie and Ronchi, Cristina L. and di Dalmazi, Guido and Riester, Anna and Kollmannsberger, Philip and Altieri, Barbara and Fassnacht, Martin and Sbiera, Silviu},
  title     = {Identifying New Potential Biomarkers in Adrenocortical Tumors Based on mRNA Expression Data Using Machine Learning},
  series = {Cancers},
  volume    = {13},
  journal   = {Cancers},
  number    = {18},
  issn      = {2072-6694},
  doi       = {10.3390/cancers13184671},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-246245},
  year      = {2021},
  abstract  = {Simple Summary Using a visual-based clustering method on the TCGA RNA sequencing data of a large adrenocortical carcinoma (ACC) cohort, we were able to classify these tumors in two distinct clusters largely overlapping with previously identified ones. As previously shown, the identified clusters also correlated with patient survival. Applying the visual clustering method to a second dataset also including benign adrenocortical samples additionally revealed that one of the ACC clusters is more closely located to the benign samples, providing a possible explanation for the better survival of this ACC cluster. Furthermore, the subsequent use of machine learning identified new possible biomarker genes with prognostic potential for this rare disease, that are significantly differentially expressed in the different survival clusters and should be further evaluated. Abstract Adrenocortical carcinoma (ACC) is a rare disease, associated with poor survival. Several "multiple-omics" studies characterizing ACC on a molecular level identified two different clusters correlating with patient survival (C1A and C1B). We here used the publicly available transcriptome data from the TCGA-ACC dataset (n = 79), applying machine learning (ML) methods to classify the ACC based on expression pattern in an unbiased manner. UMAP (uniform manifold approximation and projection)-based clustering resulted in two distinct groups, ACC-UMAP1 and ACC-UMAP2, that largely overlap with clusters C1B and C1A, respectively. However, subsequent use of random-forest-based learning revealed a set of new possible marker genes showing significant differential expression in the described clusters (e.g., SOAT1, EIF2A1). For validation purposes, we used a secondary dataset based on a previous study from our group, consisting of 4 normal adrenal glands and 52 benign and 7 malignant tumor samples. The results largely confirmed those obtained for the TCGA-ACC cohort. In addition, the ENSAT dataset showed a correlation between benign adrenocortical tumors and the good prognosis ACC cluster ACC-UMAP1/C1B. In conclusion, the use of ML approaches re-identified and redefined known prognostic ACC subgroups. On the other hand, the subsequent use of random-forest-based learning identified new possible prognostic marker genes for ACC.},
  language  = {en}
}
@article{MarquardtKollmannsbergerKrebsetal.2022,
  author    = {Marquardt, Andr{\´e} and Kollmannsberger, Philip and Krebs, Markus and Argentiero, Antonella and Knott, Markus and Solimando, Antonio Giovanni and Kerscher, Alexander Georg},
  title     = {Visual clustering of transcriptomic data from primary and metastatic tumors — dependencies and novel pitfalls},
  series = {Genes},
  volume    = {13},
  journal   = {Genes},
  number    = {8},
  issn      = {2073-4425},
  doi       = {10.3390/genes13081335},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-281872},
  year      = {2022},
  abstract  = {Personalized oncology is a rapidly evolving area and offers cancer patients therapy options that are more specific than ever. However, there is still a lack of understanding regarding transcriptomic similarities or differences of metastases and corresponding primary sites. Applying two unsupervised dimension reduction methods (t-Distributed Stochastic Neighbor Embedding (t-SNE) and Uniform Manifold Approximation and Projection (UMAP)) on three datasets of metastases (n = 682 samples) with three different data transformations (unprocessed, log10 as well as log10 + 1 transformed values), we visualized potential underlying clusters. Additionally, we analyzed two datasets (n = 616 samples) containing metastases and primary tumors of one entity, to point out potential familiarities. Using these methods, no tight link between the site of resection and cluster formation outcome could be demonstrated, or for datasets consisting of solely metastasis or mixed datasets. Instead, dimension reduction methods and data transformation significantly impacted visual clustering results. Our findings strongly suggest data transformation to be considered as another key element in the interpretation of visual clustering approaches along with initialization and different parameters. Furthermore, the results highlight the need for a more thorough examination of parameters used in the analysis of clusters.},
  language  = {en}
}
@article{BritzMarkertWitvlietetal.2021,
  author    = {Britz, Sebastian and Markert, Sebastian Matthias and Witvliet, Daniel and Steyer, Anna Maria and Tr{\"o}ger, Sarah and Mulcahy, Ben and Kollmannsberger, Philip and Schwab, Yannick and Zhen, Mei and Stigloher, Christian},
  title     = {Structural Analysis of the Caenorhabditis elegans Dauer Larval Anterior Sensilla by Focused Ion Beam-Scanning Electron Microscopy},
  series = {Frontiers in Neuroanatomy},
  volume    = {15},
  journal   = {Frontiers in Neuroanatomy},
  issn      = {1662-5129},
  doi       = {10.3389/fnana.2021.732520},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-249622},
  year      = {2021},
  abstract  = {At the end of the first larval stage, the nematode Caenorhabditis elegans developing in harsh environmental conditions is able to choose an alternative developmental path called the dauer diapause. Dauer larvae exhibit different physiology and behaviors from non-dauer larvae. Using focused ion beam-scanning electron microscopy (FIB-SEM), we volumetrically reconstructed the anterior sensory apparatus of C. elegans dauer larvae with unprecedented precision. We provide a detailed description of some neurons, focusing on structural details that were unknown or unresolved by previously published studies. They include the following: (1) dauer-specific branches of the IL2 sensory neurons project into the periphery of anterior sensilla and motor or putative sensory neurons at the sub-lateral cords; (2) ciliated endings of URX sensory neurons are supported by both ILso and AMso socket cells near the amphid openings; (3) variability in amphid sensory dendrites among dauers; and (4) somatic RIP interneurons maintain their projection into the pharyngeal nervous system. Our results support the notion that dauer larvae structurally expand their sensory system to facilitate searching for more favorable environments.},
  language  = {en}
}
@article{PauliPaulProppertetal.2021,
  author    = {Pauli, Martin and Paul, Mila M. and Proppert, Sven and Mrestani, Achmed and Sharifi, Marzieh and Repp, Felix and K{\"u}rzinger, Lydia and Kollmannsberger, Philip and Sauer, Markus and Heckmann, Manfred and Sir{\´e}n, Anna-Leena},
  title     = {Targeted volumetric single-molecule localization microscopy of defined presynaptic structures in brain sections},
  series = {Communications Biology},
  volume    = {4},
  journal   = {Communications Biology},
  doi       = {10.1038/s42003-021-01939-z},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-259830},
  pages     = {407},
  year      = {2021},
  abstract  = {Revealing the molecular organization of anatomically precisely defined brain regions is necessary for refined understanding of synaptic plasticity. Although three-dimensional (3D) single-molecule localization microscopy can provide the required resolution, imaging more than a few micrometers deep into tissue remains challenging. To quantify presynaptic active zones (AZ) of entire, large, conditional detonator hippocampal mossy fiber (MF) boutons with diameters as large as 10 mu m, we developed a method for targeted volumetric direct stochastic optical reconstruction microscopy (dSTORM). An optimized protocol for fast repeated axial scanning and efficient sequential labeling of the AZ scaffold Bassoon and membrane bound GFP with Alexa Fluor 647 enabled 3D-dSTORM imaging of 25 mu m thick mouse brain sections and assignment of AZs to specific neuronal substructures. Quantitative data analysis revealed large differences in Bassoon cluster size and density for distinct hippocampal regions with largest clusters in MF boutons. Pauli et al. develop targeted volumetric dSTORM in order to image large hippocampal mossy fiber boutons (MFBs) in brain slices. They can identify synaptic targets of individual MFBs and measured size and density of Bassoon clusters within individual untruncated MFBs at nanoscopic resolution.},
  language  = {en}
}