A disease network-based deep learning approach for characterizing melanoma

---

Authors

Xin Lai¹

1. Tampere University

Conference / event

The German Conference on Bioinformatics 2023, September 2023 (Hamburg, Germany)

Poster summary

In cutaneous melanoma, genomic aberrations influence prognosis. We developed a method that combines genomics with a disease network and deep learning for patient classification to assess the impact of genomic features. The model's community clusters condense genomics into a score profile, revealing three subtypes with distinct survival outcomes. Machine learning ranked the impact of genomic features on scores, with top features providing insights into mutations, interactions, and pathways such as signaling and immune response. This network-based AI approach provides personalized prognostic scores for melanoma.

Keywords

Melanoma, Artifical intelligence, Systems medicine, Deep learning, TCGA, Network medicine

Research areas

Bioinformatics and Genomics, Medicine

References

1. Lai X, Zhou JF, Wessely A, Heppt M, Maier A, Berking C, Vera J, Zhang L. International Journal of Cancer. 2022; 150(6): 1029-1044. DOI: 10.1002/ijc.33860.

Funding

No data provided

Supplemental files

No data provided

Additional information

Competing interests

No competing interests were disclosed.

Data availability statement

The datasets generated during and / or analyzed during the current study are available elsewhere (e.g., repository).
doi.org/10.5281/zenodo.5556063

Creative Commons license

Copyright © 2024 Lai. This is an open access work distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.