Figure 3 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Diagram of machine learning analysis (second filtering step in gene expression analysis) in order to obtain "potential survival genes" in Ewing sarcoma (EwS). (a) Random forest classifiers are applied to 3 public datasets (GSE63155, GSE17618, GSE63156) in 10-fold cross-validation, obtaining an area under the receiver operating characteristic curve (ROC AUC) of 0.67 to 0.87. These models yield genes that are predictive for survival for each dataset. The intersection of these 3 gene sets contains 1491 genes, which we consider as "potential survival genes" in EwS. (b) DAVID functional annotation of "potential survival genes". Thirteen terms in category UP-KEYWORDS obtained significant p-values (Benjamini adjusted p < 0.01). For each term, the number of annotated genes among the "potential survival genes" and the adjusted p-value is given.
Source publication
Background:
In Ewing sarcoma (EwS), long-term treatment effects and poor survival rates for relapsed or metastatic cases require individualization of therapy and the discovery of new treatment methods. Tumor glucose metabolic activity varies significantly between patients, and FDG-PET signals have been proposed as prognostic factors. However, the...
Contexts in source publication
Context 1
... the second filtering step, we focused on genes that are potentially linked to survival in EwS. To obtain such genes, we used a machine learning approach on three external, public EwS datasets: GSE63155, GSE17618, GSE63156 (Figure 3a). The model identified 1491 genes that were predictive in all three external datasets, denoted as "potential survival genes". ...
Context 2
... model identified 1491 genes that were predictive in all three external datasets, denoted as "potential survival genes". Functional annotation of these genes yielded phosphoprotein, alternative splicing, polymorphism, acetylation, cytoplasm, cell division, cell cycle, Golgi apparatus, DNA replication, disease mutation, mitosis, cell junction, and endoplasmic reticulum (Figure 3b). We focused on the "potential survival genes" for the correlation analysis with SUVmax. ...
Citations
... Notably, NPY5R expression was recently described as correlating with high standardized uptake value (SUV) measurements in fluorodeoxyglucose (FDG)-positron emission tomography (PET) scans of Ewing sarcoma tumors. 63 There are currently no reports describing an association with or function of SLCO5A1, PCDH17, or CDH8 in Ewing sarcoma. ...
... Y2R and Y4R stimulate Gq/11 alpha subunit dissociation to increase intracellular calcium levels and protein kinase C (PKC) activation [60]. YR signaling routes may coexist and connect with other receptor-triggered pathways turning on downstream biochemical signaling changes and leading to adaptive changes controlling cell behavior [70][71][72][73][74][75][76][77] (Figure 7). ...
Currently available data on the involvement of neuropeptide Y (NPY), peptide YY (PYY), and pancreatic polypeptide (PP) and their receptors (YRs) in cancer are updated. The structure and dynamics of YRs and their intracellular signaling pathways are also studied. The roles played by these peptides in 22 different cancer types are reviewed (e.g., breast cancer, colorectal cancer, Ewing sarcoma, liver cancer, melanoma, neuroblastoma, pancreatic cancer, pheochromocytoma, and prostate cancer). YRs could be used as cancer diagnostic markers and therapeutic targets. A high Y1R expression has been correlated with lymph node metastasis, advanced stages, and perineural invasion; an increased Y5R expression with survival and tumor growth; and a high serum NPY level with relapse, metastasis, and poor survival. YRs mediate tumor cell proliferation, migration, invasion, metastasis, and angiogenesis; YR antagonists block the previous actions and promote the death of cancer cells. NPY favors tumor cell growth, migration, and metastasis and promotes angiogenesis in some tumors (e.g., breast cancer, colorectal cancer, neuroblastoma, pancreatic cancer), whereas in others it exerts an antitumor effect (e.g., cholangiocarcinoma, Ewing sarcoma, liver cancer). PYY or its fragments block tumor cell growth, migration, and invasion in breast, colorectal, esophageal, liver, pancreatic, and prostate cancer. Current data show the peptidergic system’s high potential for cancer diagnosis, treatment, and support using Y2R/Y5R antagonists and NPY or PYY agonists as promising antitumor therapeutic strategies. Some important research lines to be developed in the future will also be suggested.
Transcription factors (TFs) regulation is required for the vast majority of biological processes in living organisms. Some diseases may be caused by improper transcriptional regulation. Identifying the target genes of TFs is thus critical for understanding cellular processes and analyzing disease molecular mechanisms. Computational approaches can be challenging to employ when attempting to predict potential interactions between TFs and target genes. In this paper, we present a novel graph model (PPRTGI) for detecting TF-target gene interactions using DNA sequence features. Feature representations of TFs and target genes are extracted from sequence embeddings and biological associations. Then, by combining the aggregated node feature with graph structure, PPRTGI uses a graph neural network with personalized PageRank to learn interaction patterns. Finally, a bilinear decoder is applied to predict interaction scores between TF and target gene nodes. We designed experiments on six datasets from different species. The experimental results show that PPRTGI is effective in regulatory interaction inference, with our proposed model achieving an area under receiver operating characteristic score of 93.87% and an area under precision-recall curves score of 88.79% on the human dataset. This paper proposes a new method for predicting TF-target gene interactions, which provides new insights into modeling molecular networks and can thus be used to gain a better understanding of complex biological systems.
ZUSAMMENFASSUNG
Mit dem nächsten Jahrzehnt kann sich die ambulante Pädiatrie im Rahmen eines tiefgreifenden Wandels auf gesellschaftliche und berufliche Veränderungen einstellen. Infektionskrankheiten behalten Ihre Bedeutung, gerade in den nächsten Jahren wird der Kinderarzt immer wieder mit den Folgeerkrankungen der Pandemie konfrontiert. Genetisch bedingte Erkrankungen von Migranten (Sichelzellkrankheiten, Thalassämien) werden weiter im Studium nicht ausreichend vermittelt, spielen aber in der Praxis eine zunehmende Rolle. Darüber hinaus sehen wir eine Zunahme von jungen Patienten mit chronischen Erkrankungen. Die Kinder- und Jugendärzte nehmen vermehrt eine Lotsen- und Beratungsfunktion ein und stehen der gesamten Familie bei Entscheidungen bei. Sozialpädiatrische Krankheitsbilder nehmen in der kinderärztlichen Praxis zu. Die notwendige interdisziplinäre Vernetzung von Allgemein- zu Spezialpädiatrie sowie zwischen ambulantem und stationärem Bereich gewinnt auch hier an Bedeutung.
Telemedizin und künstliche Intelligenz (KI) verändern den Aufgabenbereich des Kinder- und Jugendarztes. Das spezifische Fachwissen kann durch künstliche Intelligenz teilweise geleistet werden. Der Kinderarzt muss entscheiden, welche Empfehlungen und Schlussfolgerungen der KI richtig sind und welche dem Patienten in seiner individuellen Situation am besten gerecht werden. Die Telemedizin beschleunigt den Fachaustausch von Expertenwissen des Schwerpunktpädiaters mit dem Erfahrungswissen des Allgemeinpädiaters.
Um eine flächendeckende und bedarfsgerechte, patientenorientierte Versorgung gewährleisten zu können, müssen die medizinischen Ansprüche und die ärztlichen Kompetenzen schon in die Ausbildung integriert werden und die berufspolitischen Voraussetzungen für die Umsetzung gegeben sein.
