With the rapid accumulation of biological datasets, machine learning methods designed to automate data analysis are urgently needed. In recent years, so-called topic models that originated from the field of natural language processing have been receiving much attention in bioinformatics because of their interpretability. Our aim was to review the application and development of topic models for bioinformatics. This paper starts with the description of a topic model, with a focus on the understanding of topic modeling. A general outline is provided on how to build an application in a topic model and how to develop a topic model. Meanwhile, the literature on application of topic models to biological data was searched and analyzed in depth. According to the types of models and the analogy between the concept of document-topic-word and a biological object (as well as the tasks of a topic model), we categorized the related studies and provided an outlook on the use of topic models for the development of bioinformatics applications. Topic modeling is a useful method (in contrast to the traditional means of data reduction in bioinformatics) and enhances researchers’ ability to interpret biological information. Nevertheless, due to the lack of topic models optimized for specific biological data, the studies on topic modeling in biological data still have a long and challenging road ahead. We believe that topic models are a promising method for various applications in bioinformatics research.

With the continuous accumulation of biological data, more and more machine learning algorithms have been introduced into the field of gene function prediction, which has great significance in decoding the secret of life. Recently, a multi-label supervised topic model named labeled latent Dirichlet allocation (LLDA) has been applied to gene function prediction, and obtained more accurate and explainable predictions than conventional methods. Nonetheless, the LLDA model is only able to construct a bag of amino acid words as a classification feature, and does not support any other features, such as hydrophobicity, which has a profound impact on gene function. To achieve more accurate probabilistic modeling of gene function, we propose a multi-label supervised topic model conditioned on arbitrary features, named Dirichlet multinomial regression LLDA (DMR-LLDA), for introducing multiple types of features into the process of topic modeling. Based on DMR framework, DMR-LLDA applies an exponential a priori construction, previously with weighted features, on the hyper-parameters of gene-topic distribution, so as to reflect the effects of extra features on function probability distribution. In the five-fold cross validation experiment of a yeast datasets, DMR-LLDA outperforms the compared model significantly. All of these experiments demonstrate the effectiveness and potential value of DMR-LLDA for predicting gene function.

Proteins are a kind of macromolecules and the main component of a cell, and thus it is the most essential and versatile material of life. The research of protein functions is of great significance in decoding the secret of life. In recent years, researchers have introduced multi-label supervised topic model such as Labeled Latent Dirichlet Allocation (Labeled-LDA) into protein function prediction, which can obtain more accurate and explanatory prediction. However, the topic-label corresponding way of Labeled-LDA is associating each label (GO term) with a corresponding topic directly, which makes the latent topics to be completely degenerated, and ignores the differences between labels and latent topics. To achieve more accurate probabilistic modeling of function label, we propose a Partially Function-to-Topic Prediction (PFTP) model for introducing the local topics subset corresponding to each function label. Meanwhile, PFTP not only supports latent topics subset within a given function label but also a background topic corresponding to a ‘fake’ function label, which represents common semantic of protein function. Related definitions and the topic modeling process of PFTP are described in this paper. In a 5-fold cross validation experiment on yeast and human datasets, PFTP significantly outperforms five widely adopted methods for protein function prediction. Meanwhile, the impact of model parameters on prediction performance and the latent topics discovered by PFTP are also discussed in this paper. All of the experimental results provide evidence that PFTP is effective and have potential value for predicting protein function. Based on its ability of discovering more-refined latent sub-structure of function label, we can anticipate that PFTP is a potential method to reveal a deeper biological explanation for protein functions.