Protein-protein interaction prediction via Collective Matrix Factorization

Abstract

Abstract-Protein-protein interactions (PPI) play an important role in cellular processes and metabolic processes within a cell. An important task is to determine the existence of interactions among proteins. Unfortunately, existing biological experimental techniques are expensive, time-consuming and labor-intensive. The network structures of many such networks are sparse, incomplete and noisy, containing many false positive and false negatives. Thus, state-of-the-art methods for link prediction in these networks often cannot give satisfactory prediction results, especially when some networks are extremely sparse. Noticing that we typically have more than one PPI network available, we naturally wonder whether it is possible to 'transfer' the linkage knowledge from some existing, relatively dense networks to a sparse network, to improve the prediction performance. Noticing that a network structure can be modeled using a matrix model, in this paper, we introduce the wellknown Collective Matrix Factorization (CMF) technique to 'transfer' usable linkage knowledge from relatively dense interaction network to a sparse target network. Our approach is to establish the correspondence between a source and a target network via network similarities. We test this method on two real protein-protein interaction networks, Helicobacter pylori (as a target network) and Human (as a source network). Our experimental results show that our method can achieve higher and more robust performance as compared to some baseline methods.

Mining from protein–protein interactions

“…One relatively simple approach for estimating U and V is based on local optimization, such as the gradient descent or EM algorithms. This matrix factorization‐based approach is considered for predicting edges in a protein network, under a special machine learning setting, called transfer learning 38…”

A novel collective matrix factorization model for recommendation with fine‐grained social trust prediction

“…32 Collective matrix factorization has been widely applied to various domains including recommender systems, [33][34][35][36][37] computer vision, 38 and bioinformatics. 39 Singh and Gordon propose the first Collective matrix factorization (CMF) model to predict unobserved values of relation given two or more relation data. CMF jointly decomposes multiple relation matrices, and the factors share parameters when entities appear in multiple relations (e.g., users appear in both rating relation data and social network relation data).…”

A Survey of Transfer and Multitask Learning in Bioinformatics

“…This is equivalent to learning two tasks jointly while optimizing the following loss function: (14) Protein-protein interaction prediction is an important aspect of systems biology. Besides the work of Qi et al [46], Xu et al [47] also explored how to use multitask learning in this area via a technique known as Collective Matrix Factorization (CMF) [48]. These methods use similarities of the proteins in two interaction networks as the corresponding shared knowledge.…”