APLpred: A machine learning-based tool for accurate prediction and characterization of asparagine peptide lyases using sequence-derived optimal features.

Asparagine peptide lyase (APL) is among the seven groups of proteases, also known as proteolytic enzymes, which are classified according to their catalytic residue. APLs are synthesized as precursors or propeptides that undergo self-cleavage through autoproteolytic reaction. At present, APLs are grouped into 10 families belonging to six different clans of proteases. Recognizing their critical roles in many biological processes including virus maturation, and virulence, accurate identification and characterization of APLs is indispensable. Experimental identification and characterization of APLs is laborious and time-consuming. Here, we developed APLpred, a novel support vector machine (SVM) based predictor that can predict APLs from the primary sequences. APLpred was developed using Boruta-based optimal features derived from seven encodings and subsequently trained using five machine learning algorithms. After evaluating each model on an independent dataset, we selected APLpred (an SVM-based model) due to its consistent performance during cross-validation and independent evaluation. We anticipate APLpred will be an effective tool for identifying APLs. This could aid in designing inhibitors against these enzymes and exploring their functions. The APLpred web server is freely available at https://procarb.org/APLpred/.

Development of a two-layer machine learning model for the forensic application of legal and illegal poppy classification based on sequence data.

Poppies are beneficial plants with a variety of applications, including medicinal, edible, ornamental, and industrial purposes. Some Papaver species are forensically significant plants because they contain opium, a narcotic substance. Internationally trafficked species of illegal poppies are being identified by DNA barcoding employing multiple markers in response to their forensic value. However, effective markers for precise species identification of legal and illegal poppies are still under discussion, with research on illegal poppies focusing on Papaver somniferum L., and species identification studies of Papaver bracteatum and Papaver setigerum DC. still lacking. As a result, in order to evaluate the performance of genetic markers and classify their DNA sequences in the genus Papaver, this study developed the first machine learning-based two-layer model, in which the first layer classifies legal and illegal poppies from the given sequence and the second layer identifies species of illegal poppies using their sequences. We constructed the dataset and investigated biological features from four markers, internal transcribed spacer 1 (ITS1), internal transcribed spacer 2 (ITS2), transfer RNA Leucine (trnL), transfer RNA Leucine - transfer RNA Phenylalanine intergenic spacer (trnL-trnF intergenic spacer) and their combination, using four machine learning algorithms, K-nearest neighbor (KNN), Naïve Bayes (NB), extreme gradient boost (XGBoost) and Random Forest (RF). According to our findings, for Layer 1 to classify legal and illegal poppies, KNN-based models using combined ITS region achieved the greatest performance of accuracy 0.846 and 0.889 using training and test sets, respectively. Additionally, for Layer 2 to identify illegal poppy species, KNN-based models using combined ITS region achieved the best performance of 0.833 and 1.000 for using training and test sets, respectively. To validate the model, the combined ITS region, which includes ITS 1 and 2 sequences, from blind poppy samples were used as a case study, with the Layer 1 correctly classifying legal and illegal poppies with over 0.830 accuracy. Layer 2 correctly identified P. setigerum DC., however, only one of the three P. somniferum L. species was accurately identified. Nevertheless, our research shows that machine learning can be used to classify and identify legal and illegal poppy species using DNA barcodes which can then be used as an efficient and effective forensic tool for improved law enforcement and a safer society.

Toxic effects of fragmented polyethylene terephthalate particles on the marine rotifer Brachionus koreanus: Based on ingestion and egestion assay, in vivo toxicity test, and multi-omics analysis.

Microplastics (MPs) are a major concern in marine ecosystem because MPs are persistent and ubiquitous in oceans and are easily consumed by marine biota. Although many studies have reported the toxicity of MPs to marine biota, the toxicity of environmentally relevant types of MPs is little understood. We investigated the toxic effects of fragmented polyethylene terephthalate (PET) MP, one of the most abundant MPs in the ocean, on the marine rotifer Brachionus koreanus at the individual and molecular level. No significant rotifer mortality was observed after exposure to PET MPs for 24 and 48 h. The ingestion and egestion assays showed that rotifers readily ingested PET MPs in the absence of food but not when food was supplied; thus, there were also no chronic effects of PET MPs. In contrast, intracellular reactive oxygen species levels and glutathione S-transferase activity in rotifers were significantly increased by PET MPs. Transcriptomic and metabolomic analyses revealed that genes and metabolites related to energy metabolism and immune processes were significantly affected by PET MPs in a concentration-dependent manner. Although acute toxicity of PET MPs was not observed, PET MPs are potentially toxic to the antioxidant system, immune system, and energy metabolism in rotifers.

Identification of Gluconacetobacter xylinus LYP25 and application to bacterial cellulose production in biomass hydrolysate with acetic acid.

Bacterial cellulose (BC) is a remarkable biomacromolecule with potential applications in food, biomedical, and other industries. However, the low economic feasibility of BC production processes hinders its industrialization. In our previous work, we obtained candidate strains with improved BC production through random mutations in Gluconacetobacter. In this study, the molecular identification of LYP25 strain with significantly improved productivity, the development of chestnut pericarp (CP) hydrolysate medium, and its application in BC fermentation were performed for cost-effective BC production process. As a result, the mutant strain was identified as Gluconacetobacter xylinus. The CP hydrolysate (CPH) medium contained 30 g/L glucose with 0.4 g/L acetic acid, whereas other candidates known to inhibit fermentation were not detected. Although acetic acid is generally known as a fermentation inhibitor, it improves the BC production by G. xylinus when present within about 5 g/L in the medium. Fermentation of G. xylinus LYP25 in CPH medium resulted in 17.3 g/L BC, a 33 % improvement in production compared to the control medium, and BC from the experimental and control groups had similar physicochemical properties. Finally, the overall process of BC production from biomass was evaluated and our proposed platform showed the highest yield (17.9 g BC/100 g biomass).

Deep learning-based image classification of turtles imported into Korea.

Although turtles play a key role in maintaining healthy and balanced environments, these are endangered due to global trade to meet the high demand for food, medicine, and pets in Asia. In addition, imported non-native turtles have been controlled as alien invasive species in various countries, including Korea. Therefore, a rapid and accurate classification of imported turtles is needed to conserve and detect those in native ecosystems. In this study, eight Single Shot MultiBox Detector (SSD) models using different backbone networks were used to classify 36 imported turtles in Korea. The images of these species were collected from Google and were identified using morphological features. Then, these were divided into 70% for training, 15% for validation, and 15% for test sets. In addition, data augmentation was applied to the training set to prevent overfitting. Among the eight models, the Resnet18 model showed the highest mean Average Precision (mAP) at 88.1% and the fastest inference time at 0.024 s. The average correct classification rate of 36 turtles in this model was 82.8%. The results of this study could help in management of the turtle trade, specifically in improving detection of alien invasive species in the wild.

Comparative transcriptome analysis of two Daphnia galeata genotypes displaying contrasting phenotypic variation induced by fish kairomones in the same environment of the Han River, Korea.

BACKGROUND: Phenotypic plasticity is a crucial adaptive mechanism that enables organisms to modify their traits in response to changes in their environment. Predator-induced defenses are an example of phenotypic plasticity observed across a wide range of organisms, from single-celled organisms to vertebrates. In addition to morphology and behavior, these responses also affect life-history traits. The crustacean Daphnia galeata is a suitable model organism for studying predator-induced defenses, as it exhibits life-history traits changes under predation risk. To get a better overview of their phenotypic plasticity under predation stress, we conducted RNA sequencing on the transcriptomes of two Korean Daphnia galeata genotypes, KE1, and KB11, collected in the same environment. RESULTS: When exposed to fish kairomones, the two genotypes exhibited phenotypic variations related to reproduction and growth, with opposite patterns in growth-related phenotypic variation. From both genotypes, a total of 135,611 unigenes were analyzed, of which 194 differentially expressed transcripts (DETs) were shared among the two genotypes under predation stress, which showed consistent, or inconsistent expression patterns in both genotypes. Prominent DETs were related to digestion and reproduction and consistently up-regulated in both genotypes, thus associated with changes in life-history traits. Among the inconsistent DETs, transcripts encode vinculin (VINC) and protein obstructor-E (OBST-E), which are associated with growth; these may explain the differences in life-history traits between the two genotypes. In addition, genotype-specific DETs could explain the variation in growth-related life-history traits between genotypes, and could be associated with the increased body length of genotype KE1. CONCLUSIONS: The current study allows for a better understanding of the adaptation mechanisms related to reproduction and growth of two Korean D. galeata genotypes induced by predation stress. However, further research is necessary to better understand the specific mechanisms by which the uncovered DETs are related with the observed phenotypic variation in each genotype. In the future, we aim to unravel the precise adaptive mechanisms underlying predator-induced responses.

Pathway-dependent toxic interaction between polystyrene microbeads and methylmercury on the brackish water flea Diaphanosoma celebensis: Based on mercury bioaccumulation, cytotoxicity, and transcriptomic analysis.

Given their worldwide distribution and toxicity to aquatic organisms, methylmercury (MeHg) and microplastics (MP) are major pollutants in marine ecosystems. Although they commonly co-exist in the ocean, information on their toxicological interactions is limited. Therefore, to understand the toxicological interactions between MeHg and MP (6-µm polystyrene), we investigated the bioaccumulation of MeHg, its cytotoxicity, and transcriptomic modulation in the brackish water flea Diaphanosoma celebensis following single and combined exposure to MeHg and MP. After single exposure to MeHg for 48-h, D. celebensis showed high Hg accumulation (34.83 ± 0.40 µg/g dw biota) and cytotoxicity, which was reduced upon co-exposure to MP. After transcriptomic analysis, 2, 253, and 159 differentially expressed genes were detected in the groups exposed to MP, MeHg, and MeHg+MP, respectively. Genes related to metabolic pathways and the immune system were significantly affected after MeHg exposure, but the effect of MeHg on these pathways was alleviated by MP co-exposure. However, MeHg and MP exhibited synergistic effects on the expression of gene related to DNA replication. These findings suggest that MP can reduce the toxicity of MeHg but that their toxicological interactions differ depending on the molecular pathway.

A case study on DNA barcoding for pet food mislabeling in South Korea.

Due to the close relationship between pets and humans, pet owners are highly invested in proper diets for their pets. Even though pet food mislabeling is concerning, there are few studies on this topic. This study investigated pet food mislabeling in South Korea's market based on DNA barcoding. In total, 10 pet food products were purchased, and 200 sequences of the partial Cytochrome c oxidase subunit 1 (COI) gene were generated from clones of the samples. The obtained sequences were compared to available public databases to identify species present in the ingredients. The data analyses showed that the labeled species were consistent with species detected by COI sequences in 6 of the products. However, the expected species were not detected in 4 products, revealing possible mislabeling in these samples. Our findings indicated that DNA barcoding might represent a promising tool to detect pet food mislabeling.

Analysis of the complete mitogenome of Daphnia galeata from the Han River, South Korea: structure comparison and control region evolution.

Daphnia galeata is an important plankton in aquatic ecosystems. As a widely distributed species, D. galeata has been found throughout the Holarctic region. Understanding the genetic diversity and evolution of D. galeata requires the accumulation of genetic information from different locations. Even though the mitochondrial genome (mitogenome) sequence of D. galeata has already been reported, little is known about the evolution of its mitochondrial control region. In this study, D. galeata samples were collected from the Han River on the Korean Peninsula and its partial nd2 gene was sequenced for haplotype network analysis. This analysis showed that four clades of D. galeata were present in the Holarctic region. Moreover, the D. galeata examined in this study belonged to clade D and was specific to South Korea. The mitogenome of D. galeata from the Han River showed similar gene content and structure compared to sequences reported from Japan. Furthermore, the structure of control region of the Han River was similar to those of Japanese clones and differed substantially from European clone. Finally, a phylogenetic analysis based on the amino acid sequences of 13 protein-coding genes (PCGs) indicated that D. galeata from the Han River formed a cluster with clones collected from Lakes Kasumigaura, Shirakaba, and Kizaki in Japan. The differences in control region structure and stem and loop structure reflect the different evolutionary directions of the mitogenomes from Asian and European clones. These findings improve our understanding of the mitogenome structure and genetic diversity of D. galeata.

PRR-HyPred: A two-layer hybrid framework to predict pattern recognition receptors and their families by employing sequence encoded optimal features.

Pattern recognition receptors (PRRs) recognize distinct features on the surface of pathogens or damaged cells and play key roles in the innate immune system. PRRs are divided into various families, including Toll-like receptors, retinoic acid-inducible gene-I-like receptors, nucleotide oligomerization domain-like receptors, and C-type lectin receptors. As these are implicated in host health and several diseases, their accurate identification is indispensable for their functional characterization and targeted therapeutic approaches. Here, we construct PRR-HyPred, a novel two-layer hybrid framework in which the first layer predicts whether a given sequence is PRR or non-PRR using a support vector machine, and in the second, the predicted PRR sequence is assigned to a specific family using a random forest-based classifier. Based on a 10-fold cross-validation test, PRR-HyPred achieved 83.4 % accuracy in the first layer and 95 % in the second, with Matthew's correlation coefficient values of 0.639 and 0.816, respectively. This is the first study that can simultaneously predict and classify PRRs into specific families. PRR-HyPred is available as a web portal at https://procarb.org/PRRHyPred/. We hope that it could be a valuable tool for the large-scale prediction and classification of PRRs and subsequently facilitate future studies.

GPApred: The first computational predictor for identifying proteins with LPXTG-like motif using sequence-based optimal features.

The cell surface proteins of gram-positive bacteria are involved in many important biological functions, including the infection of host cells. Owing to their virulent nature, these proteins are also considered strong candidates for potential drug or vaccine targets. Among the various cell surface proteins of gram-positive bacteria, LPXTG-like proteins form a major class. These proteins have a highly conserved C-terminal cell wall sorting signal, which consists of an LPXTG sequence motif, a hydrophobic domain, and a positively charged tail. These surface proteins are targeted to the cell envelope by a sortase enzyme via transpeptidation. A variety of LPXTG-like proteins have been experimentally characterized; however, their number in public databases has increased owing to extensive bacterial genome sequencing without proper annotation. In the absence of experimental characterization, identifying and annotating these sequences is extremely challenging. Therefore, in this study, we developed the first machine learning-based predictor called GPApred, which can identify LPXTG-like proteins from their primary sequences. Using a newly constructed benchmark dataset, we explored different classifiers and five feature encodings and their hybrids. Optimal features were derived using the recursive feature elimination method, and these features were then trained using a support vector machine algorithm. The performance of different models was evaluated using independent datasets, and a final model (GPApred) was selected based on consistency during cross-validation and independent assessment. GPApred can be an effective tool for predicting LPXTG-like sequences and can be further employed for functional characterization or drug targeting. Availability: https://procarb.org/gpapred/.

Comparative Transcriptome Analysis of Eriocheir sinensis from Wild Habitats in Han River, Korea.

Eriocheir sinensis is an euryhaline crab found from East Asia to Europe and North America. This species can live in freshwater and seawater due to the unique physiological characteristics of their life cycle, which allows them to adapt and inhabit different habitats in a wide range of environments. Despite the wealth of studies focusing on adaptation mechanism of E. sinensis to specific environmental factors, the adaptation mechanisms to wild habitats with coexisting environmental factors are not well understood. In this study, we conducted a transcriptome analysis to investigate gene expression differences related to habitat adaptation of E. sinensis from two wild habitats with different environmental factors in the Han River, Korea. A total of 138,261 unigenes were analyzed, of which 228 were analyzed as differentially expressed genes (DEGs) between the two wild habitats. Among 228 DEGs, 110 DEGs were annotated against databases; most DEGs were involved in energy metabolism, immunity, and osmoregulation. Moreover, DEG enrichment analysis showed that upregulated genes were related to biosynthesis, metabolism, and immunity in an habitat representing relatively high salinity whereas downregulated genes were related to ion transport and hypoxia response in habitats with relatively low salinity and dissolved oxygen. The present findings can serve as foundation for future E. sinensis culture or conservation approaches in natural conditions.

Molecular phylogeny of selected dorid nudibranchs based on complete mitochondrial genome.

Dorid nudibranchs are a large group of mollusks with approximately 2,000 recorded species. Although agreement exists on the monophyletic nature of the dorid nudibranch group, the interfamily relationships of the suborder are subject to debate. Despite efforts to elucidate this issue using short molecular markers, the conclusiveness of the findings has been hindered by branching polytomy. Mitogenomes are known to be effective markers for use in phylogenetic investigations. In this study, eight mitogenomes of dorid nudibranchs were decoded and analyzed. Gene content and structure showed little change among species, reflecting the conserved mitogenomes of dorid nudibranchs. For most genes, the direction was typical for nudibranchs; nevertheless, tRNACys had an inverse direction in Cadlinidae species. Phylogenetic trees based on nucleotide and amino acid datasets revealed a relatively consistent pattern of interfamily relationships with little difference for positions of Phyllidiidae and Cadlinidae. Species of Cadlinidae were clustered together and did not form a clade with Chromododidae. Additionally, Goniodorididae was sister to Aegiridae, whereas Discodoridae was sister to Dorididae. This finding was supported by tree topology test based on mitogenome data. The results of the present study indicate that complete mitogenomes are promising markers for investigating interfamily relationships among dorid nudibranchs.

C10Pred: A First Machine Learning Based Tool to Predict C10 Family Cysteine Peptidases Using Sequence-Derived Features.

Streptococcus pyogenes, or group A Streptococcus (GAS), a gram-positive bacterium, is implicated in a wide range of clinical manifestations and life-threatening diseases. One of the key virulence factors of GAS is streptopain, a C10 family cysteine peptidase. Since its discovery, various homologs of streptopain have been reported from other bacterial species. With the increased affordability of sequencing, a significant increase in the number of potential C10 family-like sequences in the public databases is anticipated, posing a challenge in classifying such sequences. Sequence-similarity-based tools are the methods of choice to identify such streptopain-like sequences. However, these methods depend on some level of sequence similarity between the existing C10 family and the target sequences. Therefore, in this work, we propose a novel predictor, C10Pred, for the prediction of C10 peptidases using sequence-derived optimal features. C10Pred is a support vector machine (SVM) based model which is efficient in predicting C10 enzymes with an overall accuracy of 92.7% and Matthews' correlation coefficient (MCC) value of 0.855 when tested on an independent dataset. We anticipate that C10Pred will serve as a handy tool to classify novel streptopain-like proteins belonging to the C10 family and offer essential information.

Insights into the biodegradation and heavy metal resistance potential of the genus Brevibacillus through comparative genome analyses.

Members of the genus Brevibacillus belonging to the familyPaenibacillaceae are Gram-positive/variable, endospore-forming, and rod-shaped bacteria that dwell in various environmental habitats. Brevibacillus spp. have a wide range of enzyme activities such as degradation of various carbohydrates, plastics, and they possess resistance against heavy metals. These characteristics make them encouraging contenders for biotechnological applications.In this work, we analyzed the reference genomes of 19Brevibacillusspecies, focusing on discovering the biodegradation and heavy metal resistance capabilities of this little studied genus from genomic data. The results indicate that several strain specific traits were identified. For example Brevibacillus halotolerans s-14, and Brevibacillus laterosporus DSM 25 have more glycoside hydrolases (GHs) compared to other carbohydrate-active enzymes, and therefore might be more suitable for biodegradation of carbohydrates. In contrast, strains such as Brevibacillus antibioticus TGS2-1, with a higher number of glycosyltransfereases (GTs) may aid in the biosynthesis of complex carbohydrates. Our results also suggest some correlation between heavy metal resistance and polyurethane degradation, thus indicating that heavy metal resistance strains (e.g. Brevibacillus reuszeri J31TS6) can be a promising source of enzymes for polyurethane degradation. These strain specific features make the members of this bacterial group potential candidates for further investigations with industrial implications. This work also represents the first exhaustive study of Brevibacillus at the genome scale.

Image Classification of Amazon Parrots by Deep Learning: A Potentially Useful Tool for Wildlife Conservation.

Parrots play a crucial role in the ecosystem by performing various roles, such as consuming the reproductive structures of plants and dispersing plant seeds. However, most are threatened because of habitat loss and commercial trade. Amazon parrots are one of the most traded and illegally traded parrots. Therefore, monitoring their wild populations and global trade is crucial for their conservation. However, monitoring wild populations is becoming more challenging because the manual analysis of large-scale datasets of images obtained from camera trap methods is labor-intensive and time consuming. Monitoring the wildlife trade is difficult because of the large quantities of wildlife trade. Amazon parrots can be difficult to identify because of their morphological similarity. Object detection models have been widely used for automatic and accurate species classification. In this study, to classify 26 Amazon parrot species, 8 Single Shot MultiBox Detector models were assessed. Among the eight models, the DenseNet121 model showed the highest mean average precision at 88.9%. This model classified the 26 Amazon parrot species at 90.7% on average. Continuous improvement of deep learning models classifying Amazon parrots may support monitoring wild populations and the global trade of these species.

Machine Learning Models for Identification and Prediction of Toxic Organic Compounds Using Daphnia magna Transcriptomic Profiles.

A wide range of environmental factors heavily impact aquatic ecosystems, in turn, affecting human health. Toxic organic compounds resulting from anthropogenic activity are a source of pollution in aquatic ecosystems. To evaluate these contaminants, current approaches mainly rely on acute and chronic toxicity tests, but cannot provide explicit insights into the causes of toxicity. As an alternative, genome-wide gene expression systems allow the identification of contaminants causing toxicity by monitoring the organisms' response to toxic substances. In this study, we selected 22 toxic organic compounds, classified as pesticides, herbicides, or industrial chemicals, that induce environmental problems in aquatic ecosystems and affect human-health. To identify toxic organic compounds using gene expression data from Daphnia magna, we evaluated the performance of three machine learning based feature-ranking algorithms (Learning Vector Quantization, Random Forest, and Support Vector Machines with a Linear kernel), and nine classifiers (Linear Discriminant Analysis, Classification And Regression Trees, K-nearest neighbors, Support Vector Machines with a Linear kernel, Random Forest, Boosted C5.0, Gradient Boosting Machine, eXtreme Gradient Boosting with tree, and eXtreme Gradient Boosting with DART booster). Our analysis revealed that a combination of feature selection based on feature-ranking and a random forest classification algorithm had the best model performance, with an accuracy of 95.7%. This is a preliminary study to establish a model for the monitoring of aquatic toxic substances by machine learning. This model could be an effective tool to manage contaminants and toxic organic compounds in aquatic systems.

Comparative analysis of complete mitochondrial genomes of three Trichoglossus species (Psittaciformes: Psittacidae).

BACKGROUND: The genus Trichoglossus belongs to the family Psittacidae and includes fourteen species distributed worldwide. According to the International Union for Conservation of Nature and Natural Resources (IUCN) Red List of Threatened Species, most Trichoglossus species have shown a decreasing population trend recently. In particular, Trichoglossus forsteni is listed as "Endangered" in the IUCN Red List of Threatened Species. Moreover, Trichoglossus haematodus and Trichoglossus moluccanus are one of the most traded and illegally traded parrots. However, only a few genetic studies have been conducted regarding the conservation of this genus. METHODS AND RESULTS: In the present study, complete mitochondrial genomes of three species (T. forsteni, T. haematodus, and T. moluccanus) were sequenced and compared with Trichoglossus rubritorquis, species whose mitochondrial genome is already reported. Results indicate that the complete mitochondrial genomes of the three species were similar in length (17,906 bp for T. haematodus to 17,909 bp for T. forsteni). Furthermore, the organization and order of these three mitochondrial genomes were identical, including thirteen protein-coding genes (PCGs), two ribosomal RNA genes, 22 transfer RNA genes, and two control regions (CRs) categorized into three domains containing nine conserved motifs. In addition, the genus Trichoglossus formed a well-supported monophyletic lineage. CONCLUSIONS: The results of this study may be useful for future genetic studies toward the conservation of the genus Trichoglossus.

Seasonal Diversity of Microeukaryotes in the Han River, Korea Through 18S rRNA Gene Metabarcoding.

Freshwater ecosystems contain a large diversity of microeukaryotes that play important roles in maintaining their structure. Microeukaryote communities vary in composition and abundance on the basis of temporal and environmental variables and may serve as useful bioindicators of environmental changes. In the present study, 18S rRNA metabarcoding was employed to investigate the seasonal diversity of microeukaryote communities during four seasons in the Han River, Korea. In total, 882 unique operational taxonomic units (OTUs) were detected, including various diatoms, metazoans (e.g., arthropods and rotifers), chlorophytes, and fungi. Although alpha diversity revealed insignificant differences based on seasons, beta diversity exhibited a prominent variation in the community composition as per seasons. The analysis revealed that the diversity of microeukaryotes was primarily driven by seasonal changes in the prevailing conditions of environmental water temperature and dissolved oxygen. Moreover, potential indicator OTUs belonging to diatoms and chlorophytes were associated with seasonal and environmental factors. This analysis was a preliminary study that established a continuous monitoring system using metabarcoding. This approach could be an effective tool to manage the Han River along with other freshwater ecosystems in Korea.

SortPred: The first machine learning based predictor to identify bacterial sortases and their classes using sequence-derived information.

Sortase enzymes are cysteine transpeptidases that embellish the surface of Gram-positive bacteria with various proteins thereby allowing these microorganisms to interact with their neighboring environment. It is known that several of their substrates can cause pathological implications, so researchers have focused on the development of sortase inhibitors. Currently, six different classes of sortases (A-F) are recognized. However, with the extensive application of bacterial genome sequencing projects, the number of potential sortases in the public databases has exploded, presenting considerable challenges in annotating these sequences. It is very laborious and time-consuming to characterize these sortase classes experimentally. Therefore, this study developed the first machine-learning-based two-layer predictor called SortPred, where the first layer predicts the sortase from the given sequence and the second layer predicts their class from the predicted sortase. To develop SortPred, we constructed an original benchmarking dataset and investigated 31 feature descriptors, primarily on five feature encoding algorithms. Afterward, each of these descriptors were trained using a random forest classifier and their robustness was evaluated with an independent dataset. Finally, we selected the final model independently for both layers depending on the performance consistency between cross-validation and independent evaluation. SortPred is expected to be an effective tool for identifying bacterial sortases, which in turn may aid in designing sortase inhibitors and exploring their functions. The SortPred webserver and a standalone version are freely accessible at: https://procarb.org/sortpred.