bioRxiv ScienceSearch

Biology subjects

Sakellaropoulos, T.

Publications and source records attributed to Sakellaropoulos, T..

2 recordsLinked to original sources

Qualitative modeling of signaling networks in replicative senescence by selecting optimal node and arc sets

Signaling networks are an important tool of modern systems biology and drug development. Here, we present a new methodology to qualitatively model signaling networks by combining experimental data and prior knowledge about protein connectivity. Unlike other methods, our approach does not focus solely on selecting which reactions are involved but also on whether a protein is present. This allows the user to model more complicated experiments and incorporate more knowledge into the model. To demonstrate the capabilities of our method we compared the signaling networks of young and replicative senescent human primary HFL-1 fibroblasts, whose differences are expected to be due mainly to changes in the expression of the proteins rather than the reactions involved. The resulting networks indicate that, compared to young cells, aged cells are not as responsive to insulin stimulation and activate pathways that establish and maintain senescence.\n\nAuthor summaryCells have developed a complex network of biochemical reactions to monitor their environment and react to changes. Although multiple pathways, tuned to identify specific stimuli, have been discovered, it is generally understood that the signaling process typically involves multiple pathways and is context depended. Consequently, reconstructing the signaling network utilized by cells at any given moment is not a trivial task. In this article, we report on a novel logic-based method for identifying signaling network by combining experimental data with prior knowledge about the connectivity of the involved proteins. Unlike other methods proposed so far, our method uses data to evaluate the presence or absence of reactions and proteins alike. We reconstructed and compared the signaling network of human primary HFL-1 fibroblasts as they undergo replicative senescence in the presence of 6 different stimuli. The resulting networks indicate that, compared to young cells, senescent cells are not responsive to insulin stimulation and activate pathways that are known to establish and maintain senescence.

systems biology

Classification and Mutation Prediction from Non-Small Cell Lung Cancer Histopathology Images using Deep Learning

Visual analysis of histopathology slides of lung cell tissues is one of the main methods used by pathologists to assess the stage, types and sub-types of lung cancers. Adenocarcinoma and squamous cell carcinoma are two most prevalent sub-types of lung cancer, but their distinction can be challenging and time-consuming even for the expert eye. In this study, we trained a deep learning convolutional neural network (CNN) model (inception v3) on histopathology images obtained from The Cancer Genome Atlas (TCGA) to accurately classify whole-slide pathology images into adenocarcinoma, squamous cell carcinoma or normal lung tissue. Our method slightly outperforms a human pathologist, achieving better sensitivity and specificity, with [~]0.97 average Area Under the Curve (AUC) on a held-out population of whole-slide scans. Furthermore, we trained the neural network to predict the ten most commonly mutated genes in lung adenocarcinoma. We found that six of these genes - STK11, EGFR, FAT1, SETBP1, KRAS and TP53 - can be predicted from pathology images with an accuracy ranging from 0.733 to 0.856, as measured by the AUC on the held-out population. These findings suggest that deep learning models can offer both specialists and patients a fast, accurate and inexpensive detection of cancer types or gene mutations, and thus have a significant impact on cancer treatment.

cancer biology