From Protein Sequence to Protein Function via Multi-Label Linear Discriminant Analysis

Abstract

Sequence describes the primary structure of a protein, which contains important structural, characteristic, and genetic information and thereby motivates many sequence-based computational approaches to infer protein function. Among them, feature-base approaches attract increased attention because they make prediction from a set of transformed and more biologically meaningful sequence features. However, original features extracted from sequence are usually of high dimensionality and often compromised by irrelevant patterns, therefore dimension reduction is necessary prior to classification for efficient and effective protein function prediction. A protein usually performs several different functions within an organism, which makes protein function prediction a multi-label classification problem. In machine learning, multi-label classification deals with problems where each object may belong to more than one class. As a well-known feature reduction method, linear discriminant analysis (LDA) has been successfully applied in many practical applications. It, however, by nature is designed for single-label classification, in which each object can belong to exactly one class. Because directly applying LDA in multi-label classification causes ambiguity when computing scatters matrices, we apply a new Multi-label Linear Discriminant Analysis (MLDA) approach to address this problem and meanwhile preserve powerful classification capability inherited from classical LDA. We further extend MLDA by l-normalization to overcome the problem of over-counting data points with multiple labels. In addition, we incorporate biological network data using Laplacian embedding into our method, and assess the reliability of predicted putative functions. Extensive empirical evaluations demonstrate promising results of our methods.

Deep Robust Framework for Protein Function Prediction using Variable-Length Protein Sequences

“…Proposed ProtVecGen-Plus based framework achieved an average F1-score of 54.65 ± 0.15 and 65.91 ± 0.10 for BP and MF respectively. This is a significant improvement over existing state-of-the-art MLDA features [18] based model with corresponding average F1-score of 51.66 ± 0.09 and 62.31 ± 0.09 respectively. However, the hybrid model outperformed all with an average F1-score of 56.68 ± 0.13 and 67.12 ± 0.10 for BP and MF respectively.…”

“…• Hybrid approach: The classification model based on ProtVecGen-Plus features is combined with another model based on MLDA features [18] to produce even better results.…”

“…Most existing approaches to protein function prediction such as ProLanGo [3], DeepGo [4] and MLDA [18], rely upon complete protein sequences for predicting functions. Nevertheless, the functionality of a protein is the consequence of a relatively small functional subsequence present within the protein sequence [17]; this sub-sequence can be considered as a latent pattern.…”

“…These include analyzing protein sequences [2], [3], [4], [5], protein structures [6], [7], [8] and protein-protein interaction (PPI) networks [9], [10]. Other approaches are hybrid in the sense that they combine two or more of these three approaches [4], [14], [15], [18]. However, the availability of protein structures and protein interaction networks is much more limited (restricted to a few organisms only) than for protein sequences.…”

“…Feature based approaches transform raw protein sequences into discriminative features for efficient characterization of new proteins based on machine learning techniques. These approaches frequently use n-mers for the construction of the sequence vector for a protein [18], [24]. Apart from n-mers, PSSM (Position Specific Scoring Matrix) features are also used for functional annotation [2].…”