An ensemble method for prediction of phage-based therapy against bacterial infections

Viromic and Metagenomic Analyses of Commercial Spirulina Fermentations Reveal Remarkable Microbial Diversity

Commercially produced cyanobacteria preparations sold under the name spirulina are widely consumed, due to their traditional use as a nutrient-rich foodstuff and subsequent marketing as a superfood. Despite their popularity, the microbial composition of ponds used to cultivate these bacteria is understudied. A total of 19 pond samples were obtained from small-scale spirulina farms and subjected to metagenome and/or virome sequencing, and the results were analysed. A remarkable level of prokaryotic and viral diversity was found to be present in the ponds, with Limnospira sp. and Arthrospira sp. sometimes being notably scarce. A detailed breakdown of prokaryotic and viral components of 15 samples is presented. Twenty putative Limnospira sp.-infecting bacteriophage contigs were identified, though no correlation between the performance of these cultures and the presence of phages was found. The high diversity of these samples prevented the identification of clear trends in sample performance over time, between ponds or when comparing successful and failed fermentations.

A deep learning method for classification of HNSCC and HPV patients using single-cell transcriptomics

Background

Head and Neck Squamous Cell Carcinoma (HNSCC) is the seventh most highly prevalent cancer type worldwide. Early detection of HNSCC is one of the important challenges in managing the treatment of the cancer patients. Existing techniques for detecting HNSCC are costly, expensive, and invasive in nature.

Methods

In this study, we aimed to address this issue by developing classification models using machine learning and deep learning techniques, focusing on single-cell transcriptomics to distinguish between HNSCC and normal samples. Furthermore, we built models to classify HNSCC samples into HPV-positive (HPV+) and HPV-negative (HPV-) categories. In this study, we have used GSE181919 dataset, we have extracted 20 primary cancer (HNSCC) samples, and 9 normal tissues samples. The primary cancer samples contained 13 HPV- and 7 HPV+ samples. The models developed in this study have been trained on 80% of the dataset and validated on the remaining 20%. To develop an efficient model, we performed feature selection using mRMR method to shortlist a small number of genes from a plethora of genes. We also performed Gene Ontology (GO) enrichment analysis on the 100 shortlisted genes.

Results

Artificial Neural Network based model trained on 100 genes outperformed the other classifiers with an AUROC of 0.91 for HNSCC classification for the validation set. The same algorithm achieved an AUROC of 0.83 for the classification of HPV+ and HPV- patients on the validation set. In GO enrichment analysis, it was found that most genes were involved in binding and catalytic activities.

Conclusion

A software package has been developed in Python which allows users to identify HNSCC in patients along with their HPV status. It is available at https://webs.iiitd.edu.in/raghava/hnscpred/.

Prediction of peptide hormones using an ensemble of machine learning and similarity-based methods

Peptide hormones serve as genome-encoded signal transduction molecules that play essential roles in multicellular organisms, and their dysregulation can lead to various health problems. In this study, we propose a method for predicting hormonal peptides with high accuracy. The dataset used for training, testing, and evaluating our models consisted of 1174 hormonal and 1174 non-hormonal peptide sequences. Initially, we developed similarity-based methods utilizing BLAST and MERCI software. Although these similarity-based methods provided a high probability of correct prediction, they had limitations, such as no hits or prediction of limited sequences. To overcome these limitations, we further developed machine and deep learning-based models. Our logistic regression-based model achieved a maximum AUROC of 0.93 with an accuracy of 86% on an independent/validation dataset. To harness the power of similarity-based and machine learning-based models, we developed an ensemble method that achieved an AUROC of 0.96 with an accuracy of 89.79% and a Matthews correlation coefficient (MCC) of 0.8 on the validation set. To facilitate researchers in predicting and designing hormone peptides, we developed a web-based server called HOPPred. This server offers a unique feature that allows the identification of hormone-associated motifs within hormone peptides. The server can be accessed at: https://webs.iiitd.edu.in/raghava/hoppred/.

Advances in phage-host interaction prediction: in silico method enhances the development of phage therapies

Phages can specifically recognize and kill bacteria, which lead to important application value of bacteriophage in bacterial identification and typing, livestock aquaculture and treatment of human bacterial infection. Considering the variety of human-infected bacteria and the continuous discovery of numerous pathogenic bacteria, screening suitable therapeutic phages that are capable of infecting pathogens from massive phage databases has been a principal step in phage therapy design. Experimental methods to identify phage-host interaction (PHI) are time-consuming and expensive; high-throughput computational method to predict PHI is therefore a potential substitute. Here, we systemically review bioinformatic methods for predicting PHI, introduce reference databases and in silico models applied in these methods and highlight the strengths and challenges of current tools. Finally, we discuss the application scope and future research direction of computational prediction methods, which contribute to the performance improvement of prediction models and the development of personalized phage therapy.

A random forest model for predicting exosomal proteins using evolutionary information and motifs

Non-invasive diagnostics and therapies are crucial to prevent patients from undergoing painful procedures. Exosomal proteins can serve as important biomarkers for such advancements. In this study, we attempted to build a model to predict exosomal proteins. All models are trained, tested, and evaluated on a non-redundant dataset comprising 2831 exosomal and 2831 non-exosomal proteins, where no two proteins have more than 40% similarity. Initially, the standard similarity-based method Basic Local Alignment Search Tool (BLAST) was used to predict exosomal proteins, which failed due to low-level similarity in the dataset. To overcome this challenge, machine learning (ML) based models were developed using compositional and evolutionary features of proteins achieving an area under the receiver operating characteristics (AUROC) of 0.73. Our analysis also indicated that exosomal proteins have a variety of sequence-based motifs which can be used to predict exosomal proteins. Hence, we developed a hybrid method combining motif-based and ML-based approaches for predicting exosomal proteins, achieving a maximum AUROC of 0.85 and MCC of 0.56 on an independent dataset. This hybrid model performs better than presently available methods when assessed on an independent dataset. A web server and a standalone software ExoProPred (https://webs.iiitd.edu.in/raghava/exopropred/) have been created to help scientists predict and discover exosomal proteins and find functional motifs present in them.

Biological and bioinformatic tools for the discovery of unknown phage-host combinations

The field of microbial ecology has been transformed by metagenomics in recent decades and has culminated in vast datasets that facilitate the bioinformatic dissection of complex microbial communities. Recently, attention has turned from defining the microbiota composition to the interactions and relationships that occur between members of the microbiota. Within complex microbiota, the identification of bacteriophage-host combinations has been a major challenge. Recent developments in artificial intelligence tools to predict protein structure and function as well as the relationships between bacteria and their infecting bacteriophages allow a strategic approach to identifying and validating phage-host relationships. However, biological validation of these predictions remains essential and will serve to improve the existing predictive tools. In this review, I provide an overview of the most recent developments in both bioinformatic and experimental approaches to predicting and experimentally validating unknown phage-host combinations.

Genome analysis of triple phages that curtails MDR E. coli with ML based host receptor prediction and its evaluation

Infections by multidrug resistant bacteria (MDR) are becoming increasingly difficult to treat and alternative approaches like phage therapy, which is unhindered by drug resistance, are urgently needed to tackle MDR bacterial infections. During phage therapy phage cocktails targeting different receptors are likely to be more effective than monophages. In the present study, phages targeting carbapenem resistant clinical isolate of E. coli U1007 was isolated from Ganges River (U1G), Cooum River (CR) and Hospital waste water (M). Capsid architecture discerned using TEM identified the phage families as Podoviridae for U1G, Myoviridae for CR and Siphoviridae for M phage. Genome sequencing showed the phage genomes varied in size U1G (73,275 bp) CR (45,236 bp) and M (45,294 bp). All three genomes lacked genes encoding tRNA sequence, antibiotic resistant or virulent genes. A machine learning (ML) based multi-class classification model using Random Forest, Logistic Regression, and Decision Tree were employed to predict the host receptor targeted by receptor binding protein of all 3 phages and the best performing algorithm Random Forest predicted LPS O antigen, LamB or OmpC for U1G; FhuA, OmpC for CR phage; and FhuA, LamB, TonB or OmpF for the M phage. OmpC was validated as receptor for U1G by physiological experiments. In vivo intramuscular infection study in zebrafish showed that cocktail of dual phages (U1G + M) along with colsitin resulted in a significant 3.5 log decline in cell counts. Our study highlights the potential of ML tool to predict host receptor and proves the utility of phage cocktail to restrict E. coli U1007 in vivo.

Automating Predictive Phage Therapy Pharmacology

Viruses that infect as well as often kill bacteria are called bacteriophages, or phages. Because of their ability to act bactericidally, phages increasingly are being employed clinically as antibacterial agents, an infection-fighting strategy that has been in practice now for over one hundred years. As with antibacterial agents generally, the development as well as practice of this phage therapy can be aided via the application of various quantitative frameworks. Therefore, reviewed here are considerations of phage multiplicity of infection, bacterial likelihood of becoming adsorbed as a function of phage titers, bacterial susceptibility to phages also as a function of phage titers, and the use of Poisson distributions to predict phage impacts on bacteria. Considered in addition is the use of simulations that can take into account both phage and bacterial replication. These various approaches can be automated, i.e., by employing a number of online-available apps provided by the author, the use of which this review emphasizes. In short, the practice of phage therapy can be aided by various mathematical approaches whose implementation can be eased via online automation.