An open-source k-mer based machine learning tool for fast and accurate subtyping of HIV-1 genomes

Abstract

For many disease-causing virus species, global diversity is clustered into a taxonomy of subtypes with clinical significance. In particular, the classification of infections among the subtypes of human immunodeficiency virus type 1 (HIV-1) is a routine component of clinical management, and there are now many classification algorithms available for this purpose. Although several of these algorithms are similar in accuracy and speed, the majority are proprietary and require laboratories to transmit HIV-1 sequence data over the network to remote servers. This potentially exposes sensitive patient data to unauthorized access, and makes it impossible to determine how classifications are made and to maintain the data provenance of clinical bioinformatic workflows. We propose an open-source supervised and alignment-free subtyping method (Kameris) that operates on k-mer frequencies in HIV-1 sequences. We performed a detailed study of the accuracy and performance of subtype classification in comparison to four state-of-the-art programs. Based on our testing data set of manually curated real-world HIV-1 sequences (n = 2, 784), Kameris obtained an overall accuracy of 97%, which matches or exceeds all other tested software, with a processing rate of over 1,500 sequences per second. Furthermore, our fully standalone general-purpose software provides key advantages in terms of data security and privacy, transparency and reproducibility. Finally, we show that our method is readily adaptable to subtype classification of other viruses including dengue, influenza A, and hepatitis B and C virus.

Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study

“…The k-mer value 7 is used for all the experiments. The value k = 7 achieved the highest accuracy scores for the HIV-1 subtype classification [49] and this value could be relevant for other virus related analyses. The magnitude spectra are then calculated by applying Discrete Fourier Transform (DFT) to the genomic signals [50].…”

“…It is challenging (and sometimes impossible) for alignment-based methods to compare a large number of sequences that are too different in their composition. Alignment-free methods have been used successfully in the past to address the limitations of the alignment-based methods [48][49][50][51]. The alignment-free approach is quick and can handle a large number of sequences.…”

“…Moreover, the alignment demands the sequences to be continuously homologous which is not always the case. Alignment-free methods [47][48][49][50][51] have been proposed in the past as an alternative to address the limitations of the alignment-based methods. Comparative genomics beyond alignment-based approaches have benefited from the computational power of machine learning.…”

“…Comparative genomics beyond alignment-based approaches have benefited from the computational power of machine learning. Machine learning-based alignment-free methods have also been used successfully for a variety of problems including virus classification [49][50][51]. An alignment-free approach [49] was proposed for subtype classification of HIV-1 genomes and achieved *97% classification accuracy.…”

“…Machine learning-based alignment-free methods have also been used successfully for a variety of problems including virus classification [49][50][51]. An alignment-free approach [49] was proposed for subtype classification of HIV-1 genomes and achieved *97% classification accuracy. MLDSP [50], with the use of a broad range of 1D numerical representations of DNA sequences, has also achieved very high levels of classification accuracy with viruses.…”