Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2025.01.08.631726

DefensePredictor: A Machine Learning Model to Discover Novel Prokaryotic Immune Systems

DeWeirdt, P. C.·Mahoney, E. M.·Laub, M. T.
View original source ↗Export metadata ↓

Abstract

Anti-phage defense systems protect bacteria from viruses. Studying defense systems has begun to reveal the evolutionary roots of eukaryotic innate immunity and produced important biotechnologies such as CRISPR-Cas9. Dozens of new systems have been discovered by looking for systems that co-localize in genomes, but this approach cannot identify systems outside defense islands. Here, we present DefensePredictor, a machine-learning model that leverages embeddings from a protein language model to classify proteins as defensive. We applied DefensePredictor to 69 diverse E. coli strains and validated 45 previously unknown systems, with >750 additional unique proteins receiving high confidence predictions. Our model, provided as open-source software, will help comprehensively map the anti-phage defense landscape of bacteria, further reveal connections between prokaryotic and eukaryotic immunity, and accelerate biotechnology development.

Source connections

Explore related subjects

microbiologyPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

DeWeirdt, P. C., Mahoney, E. M., Laub, M. T.. 2025-01-08. DefensePredictor: A Machine Learning Model to Discover Novel Prokaryotic Immune Systems. https://doi.org/10.1101/2025.01.08.631726

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

pTRIP, a novel integration plasmid for Listeria monocytogenes

In the past decades, several tools to genetically modify the human pathogen Listeria monocytogenes were developed. Here, we constructed a new integrative plasmid system for L. monocytogenes named pTRIP, for treB insertion plasmid. pTRIP is a vector which stably integrates into the treB locus of the wild type EGD-e. This locus encodes the sole trehalose-specific EIIB and EIIC component of a phosphotransferase system. Successful integration leads to the disruption of treB and thus, to an inability of the resulting L. monocytogenes strains to grow on trehalose as sole carbon source. Due to integration through double homologous recombination, it is the first integrative system which does not require antibiotic selection pressure. To assess functionality of the pTRIP system, prfA and its native promoter region were integrated into the treB locus of a {Delta}prfA strain. Complementation was confirmed in 78% of the isolated clones, indicating successful integration of prfA into the treB locus. We further constructed derivatives of pTRIP harboring the constitutive Pp60 (pTRIP1) and the inducible Prha (pTRIP2) promoter to further expand application possibilities. Microscopic analyses confirmed the functionality of both promoter constructs and showed dose-dependent induction for Prha. pTRIP is an efficient tool for stable gene expression as well as functional studies and expands genetic modification possibilities for L. monocytogenes.

microbiology↗
bioRxiv2026

A rational design strategy and validation for protease-resistant fusion-inhibitor antiviral peptides

Peptide-based fusion inhibitors are promising pharmaceuticals in the fight against enveloped viruses relying on membrane fusion for host infection. However, peptide therapeutic applications have long been hindered by their poor stability in vivo. Here, we discovered that peptide inhibitors with the wildtype sequence of the heptad repeat 2 (HR2) domain of the SARS-CoV-2 spike protein are efficiently cleaved by Transmembrane Protease, Serine 2 (TMPRSS2), a key protease involved in the SARS-CoV-2 virus-cell fusion pathway. We then identified the corresponding cleavage sites and designed three protease-resistant peptides using ranking based on deep mutational scanning and natural occurrence. The three candidates all exhibit inhibitory activity in a cell-cell fusion assay. A high-resolution cryo-EM structure of the top candidate, HR2-NHN, bound to its HR1 target reveals the molecular basis for its potent activity. The top candidate of the cell-based screening assay significantly improved efficacy relative to the wildtype peptide when administered 12 h before infection in both an authentic virus-cell infection assay and a mouse assay. More broadly, our results suggest that the design strategies for protease-resistant peptides could be applied to a broad spectrum of other enveloped viruses and pave the way for the development of safe, prophylactic antivirals that can be administered before exposure.

microbiology↗
bioRxiv2026

Host soluble inositol phosphate signaling promotes coronavirus replication

Coronaviruses rely extensively on host pathways for replication, making host-directed therapies an attractive strategy for broad-spectrum antivirals with reduced risk of viral resistance. Here we identify the host soluble inositol phosphate pathway as a previously unrecognized dependency for coronavirus infection. Genetic or pharmacologic inhibition of several kinases in this pathway markedly suppresses replication of both alpha- and betacoronaviruses, while increasing pathway activity promotes viral replication. We developed UNC7844, a potent multi-target inhibitor of these kinases, which reduces coronavirus replication by more than four orders of magnitude in cultured cells and suppresses coronavirus infection in mice. Mechanistically, UNC7844 suppresses inositol (pyro)phosphates production, disrupts phosphoinositide homeostasis, and impairs late endosomal dynamics, blocking early post-entry steps required for viral genome release and replication. Together, our findings establish the soluble inositol (pyro)phosphate pathway as an important regulator of coronavirus infection and highlight its inhibition as a promising host-directed antiviral strategy.

microbiology↗