Lamurias, A., Tibo, A., Hose, K., Albertsen, M., & Nielsen, T. D. (2023). Graph Neural Networks for Metagenomic Binning. In The 2023 ICML Workshop on Computational Biology. Accepted Submissions. 40th International Conference on Machine Learning (ICML 2023), Honolulu, United States of America (the). ICML compbio workshop. https://doi.org/10.34726/5406
E192-02 - Forschungsbereich Databases and Artificial Intelligence
-
Erschienen in:
The 2023 ICML Workshop on Computational Biology. Accepted Submissions
-
Datum (veröffentlicht):
2023
-
Veranstaltungsname:
40th International Conference on Machine Learning (ICML 2023)
-
Veranstaltungszeitraum:
23-Jul-2023 - 29-Jul-2023
-
Veranstaltungsort:
Honolulu, Vereinigte Staaten von Amerika
-
Umfang:
7
-
Verlag:
ICML compbio workshop
-
Peer Reviewed:
Ja
-
Keywords:
Graph Neural Networks; Metagenomic Binning; Assembly Graph; Explore; Microbial communities; Environment; DNA sequencing technologies; Deep Learning; real-world datasets; Wastewater Treatment Plant (WWTP); Data Science; Bioinformatics
en
Abstract:
Most methods for metagenomic binning relysolely on the local properties of the individual contigs. Because of this, these techniques are unable to take advantage of the connections between contigs as established by the assembly graph. In this paper, we explore Graph Neural Networks (GNNs) to leverage the assembly graph when learning contig representations for metagenomic binning. We applied four different types of GNN architectures, comparing their results on real and synthetic datasets, demonstrating encouraging results and, therefore, a promising research direction to pursue and explore.
CC BY-NC-ND 4.0
