A disease network‐based deep learning approach for characterizing melanoma. Issue 6 (17th November 2021)

• Record Type: Journal Article
• Authors: Lai, Xin; Zhou, Jinfei; Wessely, Anja; Heppt, Markus; Maier, Andreas; Berking, Carola; Vera, Julio; Zhang, Le
• Is Part Of: International journal of cancer. Volume 150:Issue 6(2022)
• Page Start: 1029
• Page End: 1044
• Publication Date: 2021-11-17
• Subjects: autoencoder -- disease network -- genomics -- melanoma -- neural network -- systems medicine; Cancer -- Periodicals; Cancer -- Prevention -- Periodicals; 616.994
• DOI: 10.1002/ijc.33860
• Languages: English
• ISSNs: 0020-7136

Abstract

Abstract: Multiple types of genomic variations are present in cutaneous melanoma and some of the genomic features may have an impact on the prognosis of the disease. The access to genomics data via public repositories such as The Cancer Genome Atlas (TCGA) allows for a better understanding of melanoma at the molecular level, therefore making characterization of substantial heterogeneity in melanoma patients possible. Here, we proposed an approach that integrates genomics data, a disease network, and a deep learning model to classify melanoma patients for prognosis, assess the impact of genomic features on the classification and provide interpretation to the impactful features. We integrated genomics data into a melanoma network and applied an autoencoder model to identify subgroups in TCGA melanoma patients. The model utilizes communities identified in the network to effectively reduce the dimensionality of genomics data into a patient score profile. Based on the score profile, we identified three patient subtypes that show different survival times. Furthermore, we quantified and ranked the impact of genomic features on the patient score profile using a machine‐learning technique. Follow‐up analysis of the top‐ranking features provided us with the biological interpretation of them at both pathway and molecular levels, such as their mutation and interactome profiles in melanoma and their involvement in pathways associated with signaling transduction, immune system and cell cycle. Taken together, we demonstrated the ability of the approach to identify disease subgroups using a deep learning model that captures the most relevant information of genomics data in the melanoma network. Abstract : What's new? Genomic heterogeneity in melanoma is vast. Hence, the integration of genomics data with known associations between genomic variations and melanoma prognosis could facilitate the identification of genomic features most relevant to patient outcome. Here, the authors integrate genomics data with a disease network and deep learning model for the prognostic classification of melanoma patients and assessment of impacts of genomic features on disease classification. The data suggest that deep learning models based on genomics data and disease networks can contribute to personalized prognostic assessment for melanoma patients. The generic nature of the approach suggests that it is applicable to other cancer types.