K-mer Frequency Research Articles

FindGSEP: Estimating genome size of polyploid species using k-mer frequencies.

estimating genome size using k-mer frequencies, which plays a fundamental role in designing genome sequencing and analysis projects, has remained challenging for polyploid species, i.e., ploidy p > 2. To address this, we introduce findGSEP, which is designed based on iterative curve fitting of k-mer frequencies. Precisely, it firstly disentangles up to p normal distributions by analyzing k-mer frequencies in whole genome sequencing of the focal species. Secondly, it computes the sizes of genomic regions related to 1∼p (homologous) chromosome(s) using each respective curve fitting, from which it infers the full polyploid and average haploid genome size. findGSEP can handle any level of ploidy p, and infer more accurate genome size than other well-known tools, as shown by tests using simulated and real genomic sequencing data of various species including octoploids. findGSEP was implemented as a web server, which is freely available at http://146.56.237.198:3838/findGSEP/. Also, findGSEP was implemented as an R package for parallel processing of multiple samples. Source code and tutorial on its installation and usage is available at https://github.com/sperfu/findGSEP. Supplementary data are available at Bioinformatics online.

Efficient Storage and Analysis of Genomic Data: A k-mer Frequency Mapping and Image Representation Method.

k-mer frequencies are crucial for understanding DNA sequence patterns and structure, with applications in motif discovery, genome classification, and short read assembly. However, the exponential increase in the dimension of frequency tables with increasing k-mer length poses storage challenges. In this study, we present a novel method for compressing k-mer data without information loss, aiming to optimize storage and analysis processes. We employed Chaos Game Representation (CGR) to map k-mers to coordinates and used these components to generate raster images of k-mers. The CGR maps were partitioned and labeled based on substrings, with each substring mapped to a subframe, creating a fractal-like structure. The entire k-mer frequency set of each genomic sequence was represented as a single image, with each pixel corresponding to a specific k-mer and its occurrence. This approach reduced file size by up to 16-fold compared to plain text and 3-fold compared to binary format. Furthermore, we demonstrated the feasibility of performing alignment-free similarity analyses on images derived from k-mer frequencies of whole genome sequences from 14 plant species. Our results highlight the potential of this method as a fast and efficient tool for accessing, processing, and analyzing large biological sequence datasets, enabling the retrieval of k-mer frequencies and image reconstruction.

Prediction of Antibiotic Susceptibility in E. coli Isolates Using Machine Learning.

Antimicrobial resistance (AMR) poses a significant global health threat, resulting in 4.96 million deaths in 2019, with projections reaching 10 million by 2050. This resistance, primarily due to the overuse of antibiotics, complicates the treatment of infections caused by various microorganisms, including the gram-negative bacterium Escherichia coli. Traditional culture-based methods for detecting AMR are slow and imprecise, hindering timely clinical decision-making. In contrast, whole genome sequencing offers a faster, more accurate alternative for AMR detection. A novel machine learning study leveraging whole genomic sequencing data to predict the phenotypic susceptibility of Escherichia coli to ciprofloxacin is presented. Using a novel dataset of 256 bacterial genomes and related susceptibility data, features were generated based on AMRFinderPlus findings and k-mer frequencies. The machine learning models, Random Forest and XGBoost, were evaluated using a five-fold cross-validation approach. Results showed that combining AMRFinderPlus and k-mer frequency features could achieve more than 90% accuracy using the XGBoost gradient boosting model. These findings suggest that the best results may be achieved using reference-free features combined with known gene markers.

MGCN-PolyA: An Integrated Computational Framework for Predicting Poly(A) Signals with Multiscale-gated Convolutional Networks

Background: The accurate recognition of the polyadenylation signal (PAS) from DNA sequences is essential for understanding gene transcriptional regulation. A variety of machine learning-based computational methods have been developed to predict PAS in recent years; however, their performance and their generalization ability are unsatisfactory. It is highly desirable to design more preferable computational approaches for PAS prediction. Methods: In this work, we developed an integrated framework MGCN-PolyA for PAS prediction across four species, including Homo sapiens, Bos taurus, Mus musculus, and Drosophila melanogaster. MGCN-Poly(A) benefits from the diversity of feature engineering and the effectiveness of the model architecture. We combined features from different perspectives, such as word embedding, One-hot encoding, K-mer frequency, and Enhanced Nucleic Acid Composition (ENAC), which complement each other and provide rich and comprehensive information for model learning. In model architecture, MGCN-Poly(A) leverages a two-channel multi-scale gated convolutional network to effectively learn high-level feature representations at different scales, and then combines the statistical features to predict PAS using random forest algorithm. These designs not only speed up network training, but also improves the generalization ability Results: The benchmarking experiments on the independent test datasets demonstrate that MGCNPolyA outperforms other state-of-the-art algorithms in identifying PAS. MGCN-PolyA has the highest accuracy on all test datasets, and its excellent performance on cross-species validation also demonstrates the robustness of our model. Conclusion: Extracting features from different perspectives is important for PAS recognition, and the integration of DNNs and shallow machine learning algorithms can improve the model performance.

TransGINmer: Identifying viral sequences from metagenomes with self-attention and Graph Isomorphism Network

Viruses, abundant across diverse environments, play pivotal roles in microbial ecosystems and impact human health. Traditional virus studies are limited by their reliance on culture cultivation, which has been mitigated by metagenomics. It obtains nucleotide sequences of all microorganisms from the environment samples through the next-generation sequencing technology. This advancement prompts the need for efficient viral identification methods. To identify viruses accurately and quickly, We propose TransGINmer, a novel deep learning model to identify viral sequences directly from metagenomes. It encodes sequences by a k-mer frequency embedding model, constructs graphs from significant codon token correlations, and classifies them using graph isomorphism neural networks. In comparative tests against some SOTA methods DeepVirFinder, VirSorter2 and PhaMer on the testing dataset, the Amazon River dataset, the Sharon dataset and the CAMI Strain dataset, TransGINmer demonstrates superior accuracy, sensitivity, specificity, and AUC values, showcasing its potential as a robust tool for viral identification from metagenomes. TransGINmer is freely available at Github (https://github.com/xizhilangcc/TransGINmer).

An alignment- and reference-free strategy using k-mer present pattern for population genomic analyses

ABSTRACT Pangenomes are replacing single reference genomes to capture all variants within a species or clade, but their analysis predominantly leverages graph-based methods that require multiple high-quality genomes and computationally intensive multiple-genome alignments. K-mer decomposition is an alternative to graph-based pangenomes. However, how to directly use k-mers for the population genetic analyses is unknown. Here, we developed a novel strategy that uses the variants of k-mer count in the genome for population analyses. To test the effectivity of this method, we compared it directly to the SNP-based method on the analysis of population structure and genetic diversity of 267 Saccharomyces cerevisiae strains within two simulated datasets and a real sequence dataset. The population structure identified with k-mers recapitulates that obtained using SNPs, indicating the effectiveness of k-mer-based approach, and higher genetic diversity within real dataset supported k-mers contained more genetic variants. Based on k-mer frequency, we found not only SNP but also some insertion/deletion and horizontal gene transfer (HGT) fragments related to the adaptive evolution of S. cerevisiae. Our study creates a framework for the alignment- and reference-free (ARF) method in population genetic analyses, which will be more pronounced in the species with no complete genome or highly diverged species.

Space-efficient computation of k-mer dictionaries for large values of k

Computing k-mer frequencies in a collection of reads is a common procedure in many genomic applications. Several state-of-the-art k-mer counters rely on hash tables to carry out this task but they are often optimised for small k as a hash table keeping keys explicitly (i.e., k-mer sequences) takes O(Nkw)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$O(N\\frac{k}{w})$$\\end{document} computer words, N being the number of distinct k-mers and w the computer word size, which is impractical for long values of k. This space usage is an important limitation as analysis of long and accurate HiFi sequencing reads can require larger values of k. We propose Kaarme, a space-efficient hash table for k-mers using O(N+ukw)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$O(N+u\\frac{k}{w})$$\\end{document} words of space, where u is the number of reads. Our framework exploits the fact that consecutive k-mers overlap by k-1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$k-1$$\\end{document} symbols. Thus, we only store the last symbol of a k-mer and a pointer within the hash table to a previous one, which we can use to recover the remaining k-1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$k-1$$\\end{document} symbols. We adapt Kaarme to compute canonical k-mers as well. This variant also uses pointers within the hash table to save space but requires more work to decode the k-mers. Specifically, it takes O(σk)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$O(\\sigma ^{k})$$\\end{document} time in the worst case, σ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sigma$$\\end{document} being the DNA alphabet, but our experiments show this is hardly ever the case. The canonical variant does not improve our theoretical results but greatly reduces space usage in practice while keeping a competitive performance to get the k-mers and their frequencies. We compare canonical Kaarme to a regular hash table storing canonical k-mers explicitly as keys and show that our method uses up to five times less space while being less than 1.5 times slower. We also show that canonical Kaarme uses significantly less memory than state-of-the-art k-mer counters when they do not resort to disk to keep intermediate results.

RFGR: Repeat Finder for Complete and Assembled Whole Genomes and NGS Reads.

Repetitive DNA sequences cause genomic instability and are important genetic markers. Identification of repeats is a critical step in genome annotation and analysis. On the other hand, repeats also pose a technical challenge for genome assembly and alignment programs using NGS data. RFGR is a comprehensive tool that can find exact repetitive sequences in complete genomes and assembled genomes, as well as NGS reads of prokaryotes. For complete genomes, RFGR uses a suffix trees to find seed repeats of repetitive sequences of fixed length with indels. For assembled genomes, RFGR uses a modified Bowtie aligner to find seed repeats of exact repetitive sequences in the contigs/ scaffolds, which are then extended to maximal repeats. The repeats are classified and for repeats near a gene, RFGR reports the gene as well. For the control dataset of E. coli UTI89 and E. coli K12, RFGR reports 35,141 and 49,352 repeats, respectively. For NGS reads, RFGR uses the frequency of the repetitive k-mers to determine FASTQ reads containing repetitive sequences and removes them from the dataset. An E. coli K12 NGS dataset pre-processed using RFGR, on comparison with the original dataset, gives an improved assembly. The N50 value improves by 22.86% with a decrease in size of the assembly graph by nearly 50%. Thus, with RFGR, we achieve a better assembly with reduced computation. RFGR can be improved in terms of the length of the minimum repeat found, extending to find approximate repeats and to be applicable to Eukaryotes as well.

LPI-SKMSC: Predicting LncRNA-Protein Interactions with Segmented k-mer Frequencies and Multi-space Clustering.

Long noncoding RNAs (lncRNAs) have significant regulatory roles in gene expression. Interactions with proteins are one of the ways lncRNAs play their roles. Since experiments to determine lncRNA-protein interactions (LPIs) are expensive and time-consuming, many computational methods for predicting LPIs have been proposed as alternatives. In the LPIs prediction problem, there commonly exists the imbalance in the distribution of positive and negative samples. However, there are few existing methods that give specific consideration to this problem. In this paper, we proposed a new clustering-based LPIs prediction method using segmented k-mer frequencies and multi-space clustering (LPI-SKMSC). It was dedicated to handling the imbalance of positive and negative samples. We constructed segmented k-mer frequencies to obtain global and local features of lncRNA and protein sequences. Then, the multi-space clustering was applied to LPI-SKMSC. The convolutional neural network (CNN)-based encoders were used to map different features of a sample to different spaces. It used multiple spaces to jointly constrain the classification of samples. Finally, the distances between the output features of the encoder and the cluster center in each space were calculated. The sum of distances in all spaces was compared with the cluster radius to predict the LPIs. We performed cross-validation on 3 public datasets and LPI-SKMSC showed the best performance compared to other existing methods. Experimental results showed that LPI-SKMSC could predict LPIs more effectively when faced with imbalanced positive and negative samples. In addition, we illustrated that our model was better at uncovering potential lncRNA-protein interaction pairs.

K-mer Frequency Encoding Model for Cable Defect Identification: A Combination of Non-Destructive Testing Approach with Artificial Intelligence

This paper describes a non-destructive detection method for identifying cable defects using K-mer frequency encoding. The detection methodology combines magnetic leakage detection equipment with artificial intelligence for precise identification. The cable defect identification process includes cable signal acquisition, K-mer frequency encoding, and artificial intelligence-based identification. A magnetic leakage detection device detects signals via sensors and records their corresponding positions to obtain cable signals. The K-mer frequency encoding method consists of several steps, including cable signal normalization, the establishment of K-mer frequency encoding, repeated sampling of cable signals, and conversion for comparison to derive the K-mer frequency. The K-mer frequency coding method has advantages in data processing and repeated sampling. In the identification step of the artificial intelligence identification model, an autoencoder model is used as the algorithm, and the K-mer frequency coding method is used to introduce artificial parameters. Proper adjustments of these parameters are required for optimal cable defect identification performance in various applications and usage scenarios. Experiment results show that the proposed K-mer frequency encoding method is effective, with a cable identification accuracy rate of 91% achieved through repeated sampling.

GeneToCN: an alignment-free method for gene copy number estimation directly from next-generation sequencing reads

Genomes exhibit large regions with segmental copy number variation, many of which include entire genes and are multiallelic. We have developed a computational method GeneToCN that counts the frequencies of gene-specific k-mers in FASTQ files and uses this information to infer copy number of the gene. We validated the copy number predictions for amylase genes (AMY1, AMY2A, AMY2B) using experimental data from digital droplet PCR (ddPCR) on 39 individuals and observed a strong correlation (R = 0.99) between GeneToCN predictions and experimentally determined copy numbers. An additional validation on FCGR3 genes showed a higher concordance for FCGR3A compared to two other methods, but reduced accuracy for FCGR3B. We further tested the method on three different genomic regions (SMN, NPY4R, and LPA Kringle IV-2 domain). Predicted copy number distributions of these genes in a set of 500 individuals from the Estonian Biobank were in good agreement with the previously published studies. In addition, we investigated the possibility to use GeneToCN on sequencing data generated by different technologies by comparing copy number predictions from Illumina, PacBio, and Oxford Nanopore data of the same sample. Despite the differences in variability of k-mer frequencies, all three sequencing technologies give similar predictions with GeneToCN.

Deep flanking sequence engineering for efficient promoter design using DeepSEED

Designing promoters with desirable properties is essential in synthetic biology. Human experts are skilled at identifying strong explicit patterns in small samples, while deep learning models excel at detecting implicit weak patterns in large datasets. Biologists have described the sequence patterns of promoters via transcription factor binding sites (TFBSs). However, the flanking sequences of cis-regulatory elements, have long been overlooked and often arbitrarily decided in promoter design. To address this limitation, we introduce DeepSEED, an AI-aided framework that efficiently designs synthetic promoters by combining expert knowledge with deep learning techniques. DeepSEED has demonstrated success in improving the properties of Escherichia coli constitutive, IPTG-inducible, and mammalian cell doxycycline (Dox)-inducible promoters. Furthermore, our results show that DeepSEED captures the implicit features in flanking sequences, such as k-mer frequencies and DNA shape features, which are crucial for determining promoter properties.

Environment and taxonomy shape the genomic signature of prokaryotic extremophiles

This study provides comprehensive quantitative evidence suggesting that adaptations to extreme temperatures and pH imprint a discernible environmental component in the genomic signature of microbial extremophiles. Both supervised and unsupervised machine learning algorithms were used to analyze genomic signatures, each computed as the k-mer frequency vector of a 500 kbp DNA fragment arbitrarily selected to represent a genome. Computational experiments classified/clustered genomic signatures extracted from a curated dataset of sim 700 extremophile (temperature, pH) bacteria and archaea genomes, at multiple scales of analysis, 1le k le 6. The supervised learning resulted in high accuracies for taxonomic classifications at 2le k le 6, and medium to medium-high accuracies for environment category classifications of the same datasets at 3le k le 6. For k=3, our findings were largely consistent with amino acid compositional biases and codon usage patterns in coding regions, previously attributed to extreme environment adaptations. The unsupervised learning of unlabelled sequences identified several exemplars of hyperthermophilic organisms with large similarities in their genomic signatures, in spite of belonging to different domains in the Tree of Life.

A fast and globally optimal solution for RNA-seq quantification.

Alignment-based RNA-seq quantification methods typically involve a time-consuming alignment process prior to estimating transcript abundances. In contrast, alignment-free RNA-seq quantification methods bypass this step, resulting in significant speed improvements. Existing alignment-free methods rely on the Expectation-Maximization (EM) algorithm for estimating transcript abundances. However, EM algorithms only guarantee locally optimal solutions, leaving room for further accuracy improvement by finding a globally optimal solution. In this study, we present TQSLE, the first alignment-free RNA-seq quantification method that provides a globally optimal solution for transcript abundances estimation. TQSLE adopts a two-step approach: first, it constructs a k-mer frequency matrix A for the reference transcriptome and a k-mer frequency vector b for the RNA-seq reads; then, it directly estimates transcript abundances by solving the linear equation ATAx = ATb. We evaluated the performance of TQSLE using simulated and real RNA-seq data sets and observed that, despite comparable speed to other alignment-free methods, TQSLE outperforms them in terms of accuracy. TQSLE is freely available at https://github.com/yhg926/TQSLE.

MT-MAG: Accurate and interpretable machine learning for complete or partial taxonomic assignments of metagenomeassembled genomes.

We propose MT-MAG, a novel machine learning-based software tool for the complete or partial hierarchically-structured taxonomic classification of metagenome-assembled genomes (MAGs). MT-MAG is alignment-free, with k-mer frequencies being the only feature used to distinguish a DNA sequence from another (herein k = 7). MT-MAG is capable of classifying large and diverse metagenomic datasets: a total of 245.68 Gbp in the training sets, and 9.6 Gbp in the test sets analyzed in this study. In addition to complete classifications, MT-MAG offers a "partial classification" option, whereby a classification at a higher taxonomic level is provided for MAGs that cannot be classified to the Species level. MT-MAG outputs complete or partial classification paths, and interpretable numerical classification confidences of its classifications, at all taxonomic ranks. To assess the performance of MT-MAG, we define a "weighted classification accuracy," with a weighting scheme reflecting the fact that partial classifications at different ranks are not equally informative. For the two benchmarking datasets analyzed (genomes from human gut microbiome species, and bacterial and archaeal genomes assembled from cow rumen metagenomic sequences), MT-MAG achieves an average of 87.32% in weighted classification accuracy. At the Species level, MT-MAG outperforms DeepMicrobes, the only other comparable software tool, by an average of 34.79% in weighted classification accuracy. In addition, MT-MAG is able to completely classify an average of 67.70% of the sequences at the Species level, compared with DeepMicrobes which only classifies 47.45%. Moreover, MT-MAG provides additional information for sequences that it could not classify at the Species level, resulting in the partial or complete classification of 95.13%, of the genomes in the datasets analyzed. Lastly, unlike other taxonomic assignment tools (e.g., GDTB-Tk), MT-MAG is an alignment-free and genetic marker-free tool, able to provide additional bioinformatics analysis to confirm existing or tentative taxonomic assignments.

AMAnD: an automated metagenome anomaly detection methodology utilizing DeepSVDD neural networks.

The composition of metagenomic communities within the human body often reflects localized medical conditions such as upper respiratory diseases and gastrointestinal diseases. Fast and accurate computational tools to flag anomalous metagenomic samples from typical samples are desirable to understand different phenotypes, especially in contexts where repeated, long-duration temporal sampling is done. Here, we present Automated Metagenome Anomaly Detection (AMAnD), which utilizes two types of Deep Support Vector Data Description (DeepSVDD) models; one trained on taxonomic feature space output by the Pan-Genomics for Infectious Agents (PanGIA) taxonomy classifier and one trained on kmer frequency counts. AMAnD's semi-supervised one-class approach makes no assumptions about what an anomaly may look like, allowing the flagging of potentially novel anomaly types. Three diverse datasets are profiled. The first dataset is hosted on the National Center for Biotechnology Information's (NCBI) Sequence Read Archive (SRA) and contains nasopharyngeal swabs from healthy and COVID-19-positive patients. The second dataset is also hosted on SRA and contains gut microbiome samples from normal controls and from patients with slow transit constipation (STC). AMAnD can learn a typical healthy nasopharyngeal or gut microbiome profile and reliably flag the anomalous COVID+ or STC samples in both feature spaces. The final dataset is a synthetic metagenome created by the Critical Assessment of Metagenome Annotation Simulator (CAMISIM). A control dataset of 50 well-characterized organisms was submitted to CAMISIM to generate 100 synthetic control class samples. The experimental conditions included 12 different spiked-in contaminants that are taxonomically similar to organisms present in the laboratory blank sample ranging from one strain tree branch taxonomic distance away to one family tree branch taxonomic distance away. This experiment was repeated in triplicate at three different coverage levels to probe the dependence on sample coverage. AMAnD was again able to flag the contaminant inserts as anomalous. AMAnD's assumption-free flagging of metagenomic anomalies, the real-time model training update potential of the deep learning approach, and the strong performance even with lightweight models of low sample cardinality would make AMAnD well-suited to a wide array of applied metagenomics biosurveillance use-cases, from environmental to clinical utility.

DCiPatho: deep cross-fusion networks for genome scale identification of pathogens.

Pathogen detection from biological and environmental samples is important for global disease control. Despite advances in pathogen detection using deep learning, current algorithms have limitations in processing long genomic sequences. Through the deep cross-fusion of cross, residual and deep neural networks, we developed DCiPatho for accurate pathogen detection based on the integrated frequency features of 3-to-7k-mers. Compared with the existing state-of-the-art algorithms, DCiPatho can be used to accurately identify distinct pathogenic bacteria infecting humans, animals and plants. We evaluated DCiPatho on both learned and unlearned pathogen species using both genomics and metagenomics datasets. DCiPatho is an effective tool for the genomic-scale identification of pathogens by integrating the frequency of k-mers into deep cross-fusion networks. The source code is publicly available at https://github.com/LorMeBioAI/DCiPatho.

Reference-Free Plant Disease Detection Using Machine Learning and Long-Read Metagenomic Sequencing.

Surveillance for early disease detection is crucial to reduce the threat of plant diseases to food security. Metagenomic sequencing and taxonomic classification have recently been used to detect and identify plant pathogens. However, for an emerging pathogen, its genome may not be similar enough to any public genome to permit reference-based tools to identify infected samples. Also, in the case of point-of care diagnosis in the field, database access may be limited. Therefore, here we explore reference-free detection of plant pathogens using metagenomic sequencing and machine learning (ML). We used long-read metagenomes from healthy and infected plants as our model system and constructed k-mer frequency tables to test eight different ML models. The accuracy in classifying individual reads as coming from a healthy or infected metagenome were compared. Of all models, random forest (RF) had the best combination of short run-time and high accuracy (over 0.90) using tomato metagenomes. We further evaluated the RF model with a different tomato sample infected with the same pathogen or a different pathogen and a grapevine sample infected with a grapevine pathogen and achieved similar performances. ML models can thus learn features to successfully perform reference-free detection of plant diseases whereby a model trained with one pathogen-host system can also be used to detect different pathogens on different hosts. Potential and challenges of applying ML to metagenomics in plant disease detection are discussed. IMPORTANCE Climate change may lead to the emergence of novel plant diseases caused by yet unknown pathogens. Surveillance for emerging plant diseases is crucial to reduce their threat to food security. However, conventional genomic based methods require knowledge of existing plant pathogens and cannot be applied to detecting newly emerged pathogens. In this work, we explored reference-free, meta-genomic sequencing-based disease detection using machine learning. By sequencing the genomes of all microbial species extracted from an infected plant sample, we were able to train machine learning models to accurately classify individual sequencing reads as coming from a healthy or an infected plant sample. This method has the potential to be integrated into a generic pipeline for a meta-genomic based plant disease surveillance approach but also has limitations that still need to be overcome.

Clustering Highly Divergent Homologous Proteins: An Alignment‐Free Method

The comparative analysis of amino acid sequences is an important tool in molecular biology that often requires multiple sequence alignments. In comparisons between less closely related genomes, however, it becomes more difficult to accurately align protein-coding sequences, or even to identify homologous regions in different genomes. In this article, we describe an alignment-free method for the classification of homologous protein-coding regions from different genomes. This methodology was originally developed for comparing genomes within virus families, but may be adapted for other organisms. We quantify sequence homology from the overlap (intersection distance) of the k-mer (word) frequency distributions for different protein sequences. Next, we extract groups of homologous sequences from the resulting distance matrix using a combination of dimensionality reduction and hierarchical clustering methods. Finally, we demonstrate how to generate visualizations of the composition of clusters with respect to protein annotations, and by coloring protein-coding regions of genomes by cluster assignments. These provide a useful means to quickly assess the reliability of the clustering results based on the distribution of homologous genes among genomes. © 2023 Wiley Periodicals LLC. Basic Protocol 1: Data collection and processing Basic Protocol 2: Calculating k-mer distances Basic Protocol 3: Extracting clusters of homology Support Protocol: Genome plot based on clustering results.

GraphLncLoc: long non-coding RNA subcellular localization prediction using graph convolutional networks based on sequence to graph transformation.

The subcellular localization of long non-coding RNAs (lncRNAs) is crucial for understanding lncRNA functions. Most of existing lncRNA subcellular localization prediction methods use k-mer frequency features to encode lncRNA sequences. However, k-mer frequency features lose sequence order information and fail to capture sequence patterns and motifs of different lengths. In this paper, we proposed GraphLncLoc, a graph convolutional network-based deep learning model, for predicting lncRNA subcellular localization. Unlike previous studies encoding lncRNA sequences by using k-mer frequency features, GraphLncLoc transforms lncRNA sequences into de Bruijn graphs, which transforms the sequence classification problem into a graph classification problem. To extract the high-level features from the de Bruijn graph, GraphLncLoc employs graph convolutional networks to learn latent representations. Then, the high-level feature vectors derived from de Bruijn graph are fed into a fully connected layer to perform the prediction task. Extensive experiments show that GraphLncLoc achieves better performance than traditional machine learning models and existing predictors. In addition, our analyses show that transforming sequences into graphs has more distinguishable features and is more robust than k-mer frequency features. The case study shows that GraphLncLoc can uncover important motifs for nucleus subcellular localization. GraphLncLoc web server is available at http://csuligroup.com:8000/GraphLncLoc/.