@inproceedings{a021ebff9318482c97e0b957d194965b,
title = "Using the Duplication-Divergence Network Model to Predict Protein-Protein Interactions",
abstract = "Interactions between proteins are key to most biological processes, but thorough testing can be costly in terms of money and time. Computational approaches for predicting such interactions are an important alternative. This study presents a novel approach to this prediction using calibrated synthetic networks as input for training a decision tree ensemble model with relevant topological information. This trained model is later used for predicting interactions on the human interactome, as a case study. Results show that deterministic metrics perform better than their stochastic counterparts, although a random forest model shows a feature combination case with comparable precision results.",
keywords = "Duplication-Divergence model, Edge Embeddings, Human Interactome, Protein Interaction Prediction",
author = "Nicol{\'a}s L{\'o}pez-Rozo and Jorge Finke and Camilo Rocha",
note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 11th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2022 ; Conference date: 08-11-2022 Through 10-11-2022",
year = "2023",
doi = "10.1007/978-3-031-21127-0_27",
language = "English",
isbn = "9783031211263",
series = "Studies in Computational Intelligence",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "322--334",
editor = "Hocine Cherifi and Mantegna, {Rosario Nunzio} and Rocha, {Luis M.} and Chantal Cherifi and Salvatore Miccich{\`e}",
booktitle = "Complex Networks and Their Applications XI - Proceedings of The 11th International Conference on Complex Networks and Their Applications",
address = "Germany",
}