PWM2Vec: An Efficient Embedding Approach for Viral Host Specification from Coronavirus Spike Sequences

Abstract

The study of host specificity has important connections to the question about the origin of SARS-CoV-2 in humans which led to the COVID-19 pandemic—an important open question. There are speculations that bats are a possible origin. Likewise, there are many closely related (corona)viruses, such as SARS, which was found to be transmitted through civets. The study of the different hosts which can be potential carriers and transmitters of deadly viruses to humans is crucial to understanding, mitigating, and preventing current and future pandemics. In coronaviruses, the surface (S) protein, or spike protein, is important in determining host specificity, since it is the point of contact between the virus and the host cell membrane. In this paper, we classify the hosts of over five thousand coronaviruses from their spike protein sequences, segregating them into clusters of distinct hosts among birds, bats, camels, swine, humans, and weasels, to name a few. We propose a feature embedding based on the well-known position weight matrix (PWM), which we call PWM2Vec, and we use it to generate feature vectors from the spike protein sequences of these coronaviruses. While our embedding is inspired by the success of PWMs in biological applications, such as determining protein function and identifying transcription factor binding sites, we are the first (to the best of our knowledge) to use PWMs from viral sequences to generate fixed-length feature vector representations, and use them in the context of host classification. The results on real world data show that when using PWM2Vec, machine learning classifiers are able to perform comparably to the baseline models in terms of predictive performance and runtime—in some cases, the performance is better. We also measure the importance of different amino acids using information gain to show the amino acids which are important for predicting the host of a given coronavirus. Finally, we perform some statistical analyses on these results to show that our embedding is more compact than the embeddings of the baseline models.

Efficient Approximate Kernel Based Spike Sequence Classification

“…Converting input data into fixed-length numerical vectors for applying different machine learning algorithms such as classification and clustering is a common practice across numerous fields like smart grid [14], [15], graph analytics [16], [17], [18], [19], [20], electromyography [21], clinical data analysis [22], network security [23], and text classification [24]. Authors in [5] use the position weight matrix-based approach to compute feature embeddings for spike sequences. Although their approach shows promising results, one drawback of their method is that it only works for aligned data.…”

“…See Figure 1 for an illustration of the SARS-CoV-2 genomic structure, including the region (the spike region) that codes the spike protein. It is hence important to use this source of information to identify different host specificity [5] and variants [4]. This motivates approaches for classifying coronavirus spike sequences to better understand the dynamics of the different variants in terms of this information.…”

“…One popular way to deal with this problem is by using arXiv:2209.04952v1 [cs.LG] 11 Sep 2022 k-mers-based approach (a substring of length k). Several alignment-based [5], [6] and alignment-free [4], [7] have been proposed recently for ML tasks such as classification and clustering. Most of these methods involved computing k-mers from the spike sequences and then computing the k-mers count to get a frequency vector (more detail about kmers is given in Section 4).…”

Benchmarking Machine Learning Robustness in Covid-19 Genome Sequence Classification

“…The PSSM2Vec embedding is based on the idea of Position Specific Scoring Matrix (PSSM), also called position weight matrix (PWM) [38,39]. For a given nucleotide sequence s, PSSM2Vec designs the PWM.…”

Accurate and Fast Clade Assignment via Deep Learning and Frequency Chaos Game Representation

“…Fast and efficient solutions to the clade assignment problem would help in tracking current and evolving strains and it is crucial for the surveillance of the pathogen. This classification problem has been attacked with machine learning approaches [3, 4, 5] using the Spike protein amino acid sequence to drive the classification step.…”