BIONIC: biological network integration using convolutions

• Published in: Nature methods Vol. 19; no. 10; pp. 1250 - 1261
• Main Authors: Forster, Duncan T., Li, Sheena C., Yashiroda, Yoko, Yoshimura, Mami, Li, Zhijian, Isuhuaylas, Luis Alberto Vega, Itto-Nakama, Kaori, Yamanaka, Daisuke, Ohya, Yoshikazu, Osada, Hiroyuki, Wang, Bo, Bader, Gary D., Boone, Charles
• Format: Journal Article
• Language: English
• Published: New York Nature Publishing Group US 01.10.2022; Nature Publishing Group
• Subjects: 631/114/1305; 631/114/2401; 631/114/2404; 631/114/2408; 631/208/191; Algorithms; Annotations; Bioinformatics; Biological Microscopy; Biological Techniques; Biology; Biomedical and Life Sciences; Biomedical Engineering/Biotechnology; Bionics; Cellular communication; Deep learning; Genome, Human; Genomes; Humans; Integration; Life Sciences; Machine learning; Molecular Sequence Annotation; Networks; Proteomics; Yeasts
• ISSN: 1548-7091; 1548-7105; 1548-7105
• DOI: 10.1038/s41592-022-01616-x

Biological networks constructed from varied data can be used to map cellular function, but each data type has limitations. Network integration promises to address these limitations by combining and automatically weighting input information to obtain a more accurate and comprehensive representation of the underlying biology. We developed a deep learning-based network integration algorithm that incorporates a graph convolutional network framework. Our method, BIONIC (Biological Network Integration using Convolutions), learns features that contain substantially more functional information compared to existing approaches. BIONIC has unsupervised and semisupervised learning modes, making use of available gene function annotations. BIONIC is scalable in both size and quantity of the input networks, making it feasible to integrate numerous networks on the scale of the human genome. To demonstrate the use of BIONIC in identifying new biology, we predicted and experimentally validated essential gene chemical–genetic interactions from nonessential gene profiles in yeast. BIONIC uses a deep learning framework for accurate and scalable integration of biological networks.