Biology subjects

Torres, M. D. T.

Publications and source records attributed to Torres, M. D. T..

18 recordsLinked to original sources

bioRxiv2026

Designing antimicrobials with programmable mechanism and safety

Antimicrobial peptides (AMPs) are a promising solution to antimicrobial resistance, yet generative models for their design cannot control the physicochemical properties and motifs that shape activity and selectivity. Here, we present OmegAMP, a conditional diffusion framework controlling net charge, mean hydrophobicity, and sequence length, supporting de novo, analog, and motif-guided design. Across 204 wet-lab characterized peptides, de novo generation yielded antimicrobials with broad activity against multidrug-resistant Gram-negative isolates. Analog generation converted six inactive prototypes into antimicrobials, with the prototype determining each analog's membrane-disruption mode and mammalian-cell safety. Motif-guided analog generation preserved lipopolysaccharide engagement of active prototypes, and a redesigned non-antimicrobial leucine zipper acquired antimicrobial activity while retaining DNA-perturbing character in vitro. In murine skin and thigh infection models, leads reduced bacterial burden, with a motif-guided DNA-perturbing lead matching the fluoroquinolone control systemically. OmegAMP opens a programmable route to new peptide antibiotics whose mechanism and safety follow from the chosen prototype.

bioinformatics↗

bioRxiv2026

Ancient human mitochondrial genomes encode antimicrobial peptides

Mitochondria are bacteria-derived organelles that coordinate major innate immune pathways, but whether mitochondrial genomes themselves encode direct antimicrobial functions is underexplored. Here, we test the hypothesis that ancient human mitochondrial DNA is not only an evolutionary record, but also contains encrypted peptide sequences with the capacity to contribute to host defense. Because mitochondria descend from a bacterial endosymbiont and retain bacterial-like molecular features, we reasoned that their compact genomes might preserve sequence fragments capable of engaging bacterial-like membranes or bacterial physiology. We mined 2,025 ancient human mitochondrial genomes using a computational pipeline that couples ORF extraction and deep learning, identifying 65 candidate peptides that we term mitochondrins. We synthesized 38 candidates and experimentally validated 14 as antimicrobials against clinically relevant Gram-negative and Gram-positive bacteria. Active mitochondrins were not defined by length, charge, or helicity alone; instead, potency depended on precise hydrophobic-cationic patterning, with nested peptide families revealing how single motif-level changes can switch activity on or off. Mechanistic assays showed that mitochondrins span multiple antibacterial modalities, from strong membrane disruption to potent activity with limited membrane perturbation, suggesting noncanonical or multi-step killing mechanisms. Several peptides displayed low cytotoxicity toward human cells, and one representative mitochondrin reduced bacterial burden in a murine skin abscess model. These findings provide a biochemical basis for the hypothesis that mitochondrial genomes may contribute to innate immunity.

bioengineering↗

bioRxiv2026

Peptide structural plasticity is predictable from sequence and environment

Many peptides often do not have a single dominant structure. Instead, many remain disordered in water and fold when they encounter membranes or other chemical environments, a property that underlies diverse biological functions but is difficult to predict. Here we introduce ApexFold, a machine-learning frame-work that predicts how peptide secondary structure change across environments. ApexFold uses peptide sequence and features together with physicochemical descriptors of the surrounding medium to estimate the fractions of helical, {beta}-like and disordered structure expected in each condition. Trained on circular-dichroism measurements from 1,187 peptides assayed in water, co-solvents and membrane-mimicking micelles, ApexFold predicted solvent-induced structural shifts in independent peptide panels and outperformed static structure predictors that return a single conformation. These results show that peptide structural plasticity can be learned from sequence and environment, providing a way to prioritize peptides and experimental conditions before synthesis and structural characterization.

bioengineering↗

bioRxiv2026

Modification-aware AI enables terminal chemical modifications for peptide design and discovers potent antimicrobials

Antimicrobial resistance (AMR) is an escalating global health threat, intensifying the urgent need for novel antibiotics. Here, we introduce Termini, a generative machine learning (ML) framework that integrates peptide generation, classification, and regression modules to systematically identify potent antimicrobial peptides (AMPs). A key feature of this pipeline is its explicit design of both N- and C-terminal modifications, combined with predictive modeling across 15 bacterial species. We experimentally validated the framework against 11 pathogenic species, representing the broadest spectrum of testing reported to date in such a study. We synthesized and tested 120 peptides (including 60 unique amino acid sequences) with and without terminal modifications. Remarkably, 111 of these peptides (92.5%) demonstrated antimicrobial activity in vitro. Comparative analyses demonstrated that terminal modifications substantially enhanced antimicrobial potency. Furthermore, the lead candidates identified through in vitro screening exhibited robust anti-infective efficacy in subsequent in vivo experiments, confirming their therapeutic potential. Collectively, these results highlight the high hit rate, biological relevance, and translational promise of this integrative, modification-aware AI framework for next-generation antimicrobial peptide development.

microbiology↗

bioRxiv2025

Proteasome-derived antimicrobial peptides discovered via deep learning

Recent computational discoveries have identified numerous bioactive peptides within the human proteome, as well as across the broader tree of life, which were previously unrecognized for their roles in host immunity. These findings have led us to propose the "cross-talk hypothesis", suggesting that many molecules, such as proteins and peptides, traditionally viewed as extraneous to immune function may in fact actively contribute to immunity. Building on our earlier studies, which uncovered proteasome-derived peptides with putative antimicrobial activity in the human proteome, here we systematically interrogated the proteasome, a large protein complex responsible for degrading and recycling damaged or surplus proteins, for additional antimicrobial peptides. Using deep learning, we systematically mined ProteasomeDB, a curated repository of proteasomal cleavage and splicing events, to predict antibiotic activity against 11 clinically relevant pathogens. This deep learning approach uncovered 59 candidate peptides ("proteasomins") with a median minimum inhibitory concentration (MIC) of [≤]64LmolLLL1. Refinement yielded 21 sequence-diverse proteasomins, which were characterized for their physicochemical properties. These peptides were enriched in cationic residues and exhibit enhanced amphiphilicity, key attributes for disrupting microbial membranes. Dimensionality reduction via UMAP further showed that proteasomins are sequence-distinct from known antimicrobial peptides, underscoring their novelty and potential for unique mechanisms of action. Moreover, comparative analyses revealed that cis- and trans-spliced proteasomins exhibit similar predicted antimicrobial activities, suggesting that critical structural determinants remain conserved irrespective of splicing modality. Collectively, these findings expand our understanding of the proteasome, underscore the extensive, previously unrecognized repertoire of innate immune peptides, and provide a promising foundation for developing innovative therapeutics to combat multidrug-resistant pathogens.

microbiology↗

bioRxiv2025

Generative latent diffusion language modeling yields anti-infective synthetic peptides

Generative artificial intelligence (AI) offers a powerful avenue for peptide design, yet this process remains challenging due to the vast sequence space, complex structure-activity relationships, and the need to balance antimicrobial potency with low toxicity. Traditional approaches often rely on trial-and-error screening and fail to efficiently navigate the immense diversity of potential sequences. Here, we introduce AMP-Diffusion, a novel latent diffusion model fine-tuned on antimicrobial peptide (AMP) sequences using embeddings from protein language models. By systematically exploring sequence space, AMP-Diffusion enables the rapid discovery of promising antibiotic candidates. We generated 50,000 candidate sequences, which were subsequently filtered and ranked using our APEX predictor model. From these, 46 top candidates were synthesized and experimentally validated. The resulting AMP-Diffusion peptides demonstrated broad-spectrum antibacterial activity, targeting clinically relevant pathogens--including multidrug-resistant strains--while exhibiting low cytotoxicity in human cell assays. Mechanistic studies revealed bacterial killing via membrane permeabilization and depolarization, and the peptides showed favorable physicochemical profiles. In preclinical mouse models of infection, lead peptides effectively reduced bacterial burdens, displaying efficacy comparable to polymyxin B and levofloxacin, with no detectable adverse effects. This study highlights the potential of AMP-Diffusion as a robust generative platform for designing novel antibiotics and bioactive peptides, offering a promising strategy to address the escalating challenge of antimicrobial resistance.

microbiology↗

bioRxiv2025

Improving functional protein generation via foundation model-derived latent space likelihood optimization

A variety of deep generative models have been adopted to perform de novo functional protein generation. Compared to 3D protein design, sequence-based generation methods, which aim to generate amino acid sequences with desired functions, remain a major approach for functional protein generation due to the abundance and quality of protein sequence data, as well as the relatively low modeling complexity for training. Although these models are typically trained to match protein sequences from the training data, exact matching of every amino acid is not always essential. Certain amino acid changes (e.g., mismatches, insertions, and deletions) may not necessarily lead to functional changes. This suggests that maximizing the training data likelihood beyond the amino acid sequence space could yield better generative models. Pre-trained protein large language models (PLMs) like ESM2 can encode protein sequences into a latent space, potentially serving as functional validators. We propose training functional protein sequence generative models by simultaneously optimizing the likelihood of training data in both the amino acid sequence space and the latent space derived from a PLM. This training scheme can also be viewed as a knowledge distillation approach that dynamically re-weights samples during training. We applied our method to train GPT- like models (i.e., autoregressive transformers) for antimicrobial peptide (AMP) and malate dehydrogenase (MDH) generation tasks. Computational experiments confirmed that our method outperformed various deep generative models (e.g., generative adversarial net, variational autoencoder, and GPT model without the proposed training strategy) on these tasks, demonstrating the effectiveness of our multi-likelihood optimization strategy.

bioinformatics↗

bioRxiv2025

Key-cutting machine: A novel optimization framework for tailored protein and peptide design

Computational protein and peptide design is emerging as a transformative framework for engineering macromolecules with precise structures and functions, offering innovative solutions in medicine, biotechnology, and materials science. However, current methods predominantly rely on generative models, which are expensive to train and inflexible to modify. Here, we introduce the Key-Cutting Machine (KCM), a novel optimization-based platform that iteratively leverages structure prediction to match desired backbone geometries. KCM requires only a single GPU and enables seamless incorporation of user-defined requirements into the objective function, circumventing the high retraining costs typical of generative models while allowing straightforward assessment of measurable properties. By employing an Estimation of Distribution Algorithm, KCM optimizes sequences based on geometric, physicochemical, and energetic criteria. We benchmarked its performance on -helices, {beta}-sheets, and unstructured regions, demonstrating precise backbone geometry design. As a proof of concept, we applied KCM to antimicrobial peptide (AMP) design by using a template AMP as the "key", yielding a candidate with potent in vitro activity against multiple bacterial strains and efficacy in a murine infection model. KCM thus emerges as a robust tool for de novo protein and peptide design, offering a flexible paradigm for replicating and extending the structure-function relationships of existing templates.

bioengineering↗

bioRxiv2024

Design of multimodal antibiotics against intracellular infections using deep learning

The rise of antimicrobial resistance has rendered many treatments ineffective, posing serious public health challenges. Intracellular infections are particularly difficult to treat since conventional antibiotics fail to neutralize pathogens hidden within human cells. However, designing molecules that penetrate human cells with preserved antimicrobial activity has historically been a major challenge. Here, we introduce ApexDuo, a multimodal artificial intelligence (AI) model for generating peptides with both cell- penetrating and antimicrobial properties. From a library of 50 million AI-generated compounds, we selected and characterized several candidates. Our lead, Turingcin-46, penetrated mammalian cells and reduced intracellular Staphylococcus aureus and Listeria monocytogenes. In mouse models of skin abscess and peritonitis, Turingcin-46 reduced bacterial loads by up to two orders of magnitude. In sum, ApexDuo generated multimodal peptide antibiotics, opening new avenues for designing molecules with more than one function.

synthetic biology↗

bioRxiv2024

Venomics AI: a computational exploration of global venoms for antibiotic discovery

The relentless emergence of antibiotic-resistant pathogens, particularly Gram-negative bacteria, highlights the urgent need for novel therapeutic interventions. Drug-resistant infections account for approximately 5 million deaths annually, yet the antibiotic development pipeline has largely stagnated. Venoms, representing a remarkably diverse reservoir of bioactive molecules, remain an underexploited source of potential antimicrobials. Venom-derived peptides, in particular, hold promise for antibiotic discovery due to their evolutionary diversity and unique pharmacological profiles. In this study, we mined comprehensive global venomics datasets to identify new antimicrobial candidates. Using machine learning, we explored 16,123 venom proteins, generating 40,626,260 venom-encrypted peptides (VEPs). Using APEX, a deep learning model combining a peptide-sequence encoder with neural networks for antimicrobial activity prediction, we identified 386 VEPs structurally and functionally distinct from known antimicrobial peptides. Our analyses showed that these VEPs possess high net charge and elevated hydrophobicity, characteristics conducive to bacterial membrane disruption. Structural studies revealed considerable conformational flexibility, with many VEPs transitioning to -helical conformations in membrane-mimicking environments, indicative of their antimicrobial potential. Of the 58 VEPs selected for experimental validation, 53 displayed potent antimicrobial activity. Mechanistic assays indicated that VEPs primarily exert their effects through bacterial membrane depolarization, mirroring AMP-like mechanisms. In vivo studies using a mouse model of Acinetobacter baumannii infection demonstrated that lead VEPs significantly reduced bacterial burdens without notable toxicity. This study highlights the value of venoms as a resource for new antibiotics. By integrating computational approaches and experimental validation, venom-derived peptides emerge as promising candidates to combat the global challenge of antibiotic resistance.

bioengineering↗

bioRxiv2024

A generative artificial intelligence approach for antibiotic optimization

Antimicrobial resistance (AMR) poses a critical global health threat, underscoring the urgent need for innovative antibiotic discovery strategies. While recent advances in peptide design have yielded numerous antimicrobial agents, optimizing these molecules experimentally remains challenging due to unpredictable and resource-intensive trial-and-error approaches. Here, we introduce APEX Generative Optimization (APEXGO), a generative artificial intelligence (AI) framework that integrates a transformer-based variational autoencoder with Bayesian optimization to design and optimize antimicrobial peptides. Unlike traditional supervised learning approaches that screen fixed databases of existing molecules, APEXGO generates entirely novel peptide sequences through arbitrary modifications of template peptides, representing a paradigm shift in peptide design and antibiotic discovery. Our framework introduces a new peptide variational autoencoder with design and diversity constraints to maintain similarity to specific templates while enabling sequence innovation. This work represents the first in vitro and in vivo experimental validation of generative Bayesian optimization in any setting. Using ten de-extinct peptides as templates, APEXGO generated optimized derivatives with enhanced antimicrobial properties. We synthesized 100 of these optimized peptides and conducted comprehensive in vitro characterizations, including assessments of antimicrobial activity, mechanism of action, secondary structure, and cytotoxicity. Notably, APEXGO achieved an outstanding 85% ground-truth experimental hit rate and a 72% success rate in enhancing antimicrobial activity against clinically relevant Gram-negative pathogens, outperforming previously reported methods for antibiotic discovery and optimization. In preclinical mouse models of Acinetobacter baumannii infection, several AI-optimized molecules--most notably derivatives of mammuthusin-3 and mylodonin-2--exhibited potent anti-infective activity comparable to or exceeding that of polymyxin B, a widely used last-resort antibiotic. These findings highlight the potential of APEXGO as a novel generative AI approach for peptide design and antibiotic optimization, offering a powerful tool to accelerate antibiotic discovery and address the escalating challenge of AMR.

microbiology↗

bioRxiv2024

Discovery of antibiotics in the archaeome using deep learning

Antimicrobial resistance (AMR) is one of the greatest threats facing humanity, making the need for new antibiotics more critical than ever. While most antibiotics have traditionally been derived from bacteria and fungi, archaea--a distinct and underexplored domain of life--offer a largely untapped reservoir for antibiotic discovery. In this study, we leveraged deep learning to systematically explore the archaeome, uncovering promising new candidates for combating AMR. By mining 233 archaeal proteomes, we identified 12,623 molecules with potential antimicrobial activity. These newly discovered peptide compounds, termed archaeasins, exhibit unique compositional features that differentiate them from traditional antimicrobial peptides, including a distinct amino acid profile. We synthesized 80 archaeasins, 93% of which demonstrated antimicrobial activity in vitro. Notably, in vivo validation identified archaeasin-73 as a lead candidate, significantly reducing bacterial loads in mouse infection models, with effectiveness comparable to established antibiotics like polymyxin B. Our findings highlight the immense potential of archaea as a resource for developing next-generation antibiotics.

microbiology↗

bioRxiv2024

Dual quorum-sensing control of purine biosynthesis drives pathogenic fitness of Enterococcus faecalis

Enterococcus faecalis is a resident of the human gut, though upon translocation to the blood or body tissues, it can be pathogenic. Here we discover and characterize two peptide-based quorum-sensing systems that transcriptionally modulate de novo purine biosynthesis in E. faecalis. Using a comparative genomic analysis, we find that most enterococcal species do not encode this system; E. moraviensis, E. haemoperoxidus and E. caccae, three species that are closely related to E. faecalis, encode one of the two systems, and only E. faecalis encodes both systems. We show that these systems are important for the intracellular survival of E. faecalis within macrophages and for the fitness of E. faecalis in a murine wound infection model. Taken together, we combine comparative genomics, microbiological, bacterial genetics, transcriptomics, targeted proteomics and animal model experiments to describe a paired quorum sensing mechanism that directly influences central metabolism and impacts the pathogenicity of E. faecalis.

microbiology↗

bioRxiv2024

Peptides from non-immune proteins target infections through antimicrobial and immunomodulatory properties

Encrypted peptides have been recently described as a new class of antimicrobial molecules. They have been proposed to play a role in host immunity and as alternatives to conventional antibiotics. Intriguingly, many of these peptides are found embedded in proteins unrelated to the immune system, suggesting that immunological responses may extend beyond traditional host immunity proteins. To test this idea, here we synthesized and tested representative peptides derived from non-immune proteins for their ability to exert antimicrobial and immunomodulatory properties. Our experiments revealed that most of the tested peptides from non-immune proteins, derived from structural proteins as well as proteins from the nervous and visual systems, displayed potent in vitro antimicrobial activity. These molecules killed bacterial pathogens by targeting their membrane, and those originating from the same region of the body exhibited synergistic effects when combined. Beyond their antimicrobial properties, nearly 90% of the peptides tested exhibited immunomodulatory effects, modulating inflammatory mediators such as IL-6, TNF-, and MCP-1. Moreover, eight of the peptides identified, collagenin 3 and 4, zipperin-1 and 2, and immunosin-2, 3, 12, and 13, displayed anti-infective efficacy in two different preclinical mouse models, reducing bacterial infections by up to four orders of magnitude. Altogether, our results support the hypothesis that peptides from non-immune proteins may play a role in host immunity. These results potentially expand our notion of the immune system to include previously unrecognized proteins and peptides that may be activated upon infection to confer protection to the host.

microbiology↗

bioRxiv2023

Molecular de-extinction of antibiotics enabled by deep learning

Molecular de-extinction is an emerging field that aims to resurrect molecules to solve present-day problems such as antibiotic resistance. Here, we introduce a deep learning approach called Antibiotic Peptide de-Extinction (APEX) to mine the proteomes of all available extinct organisms (the "extinctome") searching for encrypted peptide (EP) antibiotics. APEX mined a total of 10,311,899 EPs and identified 37,176 sequences predicted to have broad-spectrum antimicrobial activity, 11,035 of which were not found in extant organisms. Chemical synthesis and experimental validation yielded archaic EPs (AEPs) with activity against dangerous bacterial pathogens. Most peptides killed bacteria by depolarizing their cytoplasmic membrane, contrary to known antimicrobial peptides, which target the outer membrane. Notably, lead peptides, including those derived from the woolly mammoth, ancient sea cow, giant sloth, and extinct giant elk, exhibited anti-infective activity in preclinical mouse models. We propose molecular de-extinction, accelerated by deep learning, as a framework for discovering therapeutic molecules.

bioengineering↗

bioRxiv2023

Human gut metagenomic mining reveals an untapped source of peptide antibiotics

Drug-resistant bacteria are outpacing traditional antibiotic discovery efforts. Here, we computationally mined 444,054 families of putative small proteins from 1,773 human gut metagenomes, identifying 323 peptide antibiotics encoded in small open reading frames (smORFs). To test our computational predictions, 78 peptides were synthesized and screened for antimicrobial activity in vitro, with 59% displaying activity against either pathogens or commensals. Since these peptides were unique compared to previously reported antimicrobial peptides, we termed them smORF-encoded peptides (SEPs). SEPs killed bacteria by targeting their membrane, synergized with each other, and modulated gut commensals, indicating that they may play a role in reconfiguring microbiome communities in addition to counteracting pathogens. The lead candidates were anti-infective in both murine skin abscess and deep thigh infection models. Notably, prevotellin-2 from Prevotella copri presented activity comparable to the commonly used antibiotic polymyxin B. We report the discovery of hundreds of peptide sequences in the human gut.

bioengineering↗

bioRxiv2022

Molecular de-extinction of ancient antimicrobial peptides enabled by machine learning

Molecular de-extinction could offer new avenues for drug discovery by reintroducing bioactive molecules that are no longer encoded by extant organisms. To prospect for antimicrobial peptides encrypted as subsequences of extinct and extant human proteins, we introduce the panCleave random forest model for proteome-wide cleavage site prediction. Our model outperformed multiple protease-specific cleavage site classifiers for three modern human caspases, despite its pan-protease design. Antimicrobial activity was observed in vitro for modern and archaic protein fragments identified with panCleave. Lead peptides were tested for mechanism of action, resistance to proteolysis, and anti-infective efficacy in two pre-clinical mouse models. These results suggest that machine learning-based encrypted peptide prospection can identify stable, nontoxic antimicrobial peptides. Moreover, we establish molecular de-extinction through paleoproteome mining as a framework for antibacterial drug discovery. HighlightsO_LIMachine learning guides bioinspired prospection for encrypted antimicrobial peptides. C_LIO_LIModern and extinct human proteins harbor antimicrobial subsequences. C_LIO_LIAncient encrypted peptides display in vitro and in vivo activity with low host toxicity. C_LIO_LIPaleoproteome mining offers a new framework for antibiotic discovery. C_LI

bioengineering↗

bioRxiv2021

Autonomous treatment of bacterial infections in vivo using antimicrobial micro- and nanomachines

The increasing resistance of bacteria to existing antibiotics constitutes a major public health threat globally. Most current antibiotic treatments are hindered by poor delivery to the infection site, leading to undesired off-target effects and drug resistance development and spread. Here, we describe micro- and nanomachines that effectively and autonomously deliver antibiotic payloads to the target area. The active motion and antimicrobial activity of the silica-based robots are driven by catalysis of the enzyme urease and antimicrobial peptides, respectively. These antimicrobial machines show micromolar bactericidal activity in vitro against different Gram-positive and Gram-negative pathogenic bacterial strains and act by rapidly depolarizing their membrane. Finally, they demonstrated autonomous anti-infective efficacy in vivo in a clinically relevant abscess infection mouse model. In summary, our machines combine navigation, catalytic conversion, and bactericidal capacity to deliver antimicrobial payloads to specific infection sites. This technology represents a much-needed tool to direct therapeutics to their target to help combat drug-resistant infections.

bioengineering↗