Predicting Phage Host Interactions Across Taxonomic Levels: A Systematic Review and Meta-Analysis for Microbial Ecology

The prediction of phage-host interactions is key for several applications in biotechnology, medicine, and microbial ecology. Wide studies in machine learning tools have allowed the exploration of these interactions across multiple taxonomic levels. A systematic review and meta-analysis were conducted on 570 records retrieved from PubMed, Scopus, and Web of Science. Eleven studies were selected for the meta-analysis, encompassing 61 datasets. Precision across taxonomic levels (Domain, Phylum, Class, Order, Family, Genus, Species) was evaluated for several prediction tools. Statistical tests, including the Shapiro-Wilk and ANOVA tests, were used. A mixed-effects meta-regression model was used to examine the impact of taxonomic subgroups on the prediction of the proportion of Correctly Predicted PHIs. The results indicated significant variability in the performance of prediction tools across taxonomic levels. Domain-level predictions exhibited near-perfect Proportion of Correctly Predicted PHIs (0.99), whereas finer resolutions (Family and Order) showed considerable variability, with average precision values of 0.682 and 0.775, respectively. The mixed-effects meta-regression analysis revealed that Family and Species taxonomic subgroups were associated with significant reductions in the prediction Proportion of Correctly Predicted PHIs with effect sizes of -0.1464 and -0.1944, respectively. Residual heterogeneity was negligible, indicating that the moderators adequately explained the variability in prediction precision. This study highlights the importance of selecting the appropriate prediction tool based on the desired taxonomic resolution. The findings emphasize the need for further refinement of prediction algorithms, particularly at the Family and Species levels, where tools exhibit the most variability.