Biology subjects

de la Fuente, C.

Publications and source records attributed to de la Fuente, C..

8 recordsLinked to original sources

bioRxiv2026

A Conditional Variational Autoencoder with QSAR-Guided Surrogate-Weighted Fine-Tuning and Cross-Entropy Optimization for Targeted Antimicrobial Peptide Generation

Machine Learning frameworks have emerged as a promising tool for antimicrobial peptide design; however, generative models remain limited by two persistent problems: the limited availability of experimentally validated peptides and the circular dependency of the models. In this work we present a conditional variational autoencoder pipeline that addresses both limitations through a modular architecture that combines both binary and quantitative experimental data and implements a multimodal approach to externally guide the generation. A transformer-based encoder successfully generated a discriminative 64-dimensional latent space (test AUROC 0.968, F1 0.919) separating antimicrobial from non-antimicrobial sequences. This latent representation conditions a species-specific LoRA fine-tuned ProtGPT2 decoder through a scalar gating function, which generates balanced antimicrobial peptides through two different modes; prior and perturb, depending on their generation starting points. We introduced a Surrogate Weighted Fine-Tuning (SWF) ensemble to eliminate the circular dependency and a Cross-Entropy Method to explore and exploit the latent space, leading to successful antimicrobial peptide generation. The best candidates exhibited competitive physicochemical characteristics, a mean helical fraction of 0.874 (mean pLDDT 83.7), and externally predicted efficacy evaluated by APEX.

bioinformatics↗

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

A deep reinforcement learning platform for antibiotic discovery

Antimicrobial resistance (AMR) is projected to cause up to 10 million deaths annually by 2050, underscoring the urgent need for new antibiotics. Here we present ApexAmphion, a deep-learning framework for de novo design of antibiotics that couples a 6.4-billion-parameter protein language model with reinforcement learning. The model is first fine-tuned on curated peptide data to capture antimicrobial sequence regularities, then optimised with proximal policy optimization against a composite reward that combines predictions from a learned minimum inhibitory concentration (MIC) classifier with differentiable physicochemical objectives. In vitro evaluation of 100 designed peptides showed low MIC values (nanomolar range in some cases) for all candidates (100% hit rate). Moreover, 99 our of 100 compounds exhibited broad-spectrum antimicrobial activity against at least two clinically relevant bacteria. The lead molecules killed bacteria primarily by potently targeting the cytoplasmic membrane. By unifying generation, scoring and multi-objective optimization with deep reinforcement learning in a single pipeline, our approach rapidly produces diverse, potent candidates, offering a scalable route to peptide antibiotics and a platform for iterative steering toward potency and developability within hours.

molecular biology↗

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

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↗

bioRxiv2019

Ancient DNA reconstructs the genetic legacies of pre-contact Puerto Rico communities

Indigenous peoples have occupied the island of Puerto Rico since at least 3000 B.C. Due to the demographic shifts that occurred after European contact, the origin(s) of these ancient populations, and their genetic relationship to present-day islanders, are unclear. We use ancient DNA to characterize the population history and genetic legacies of pre-contact Indigenous communities from Puerto Rico. Bone, tooth and dental calculus samples were collected from 124 individuals from three pre-contact archaeological sites: Tibes, Punta Candelero and Paso del Indio. Despite poor DNA preservation, we used target enrichment and high-throughput sequencing to obtain complete mitochondrial genomes (mtDNA) from 45 individuals and autosomal genotypes from two individuals. We found a high proportion of Native American mtDNA haplogroups A2 and C1 in the pre-contact Puerto Rico sample (40% and 44%, respectively). This distribution, as well as the haplotypes represented, support a primarily Amazonian South American origin for these populations, and mirrors the Native American mtDNA diversity patterns found in present-day islanders. Three mtDNA haplotypes from pre-contact Puerto Rico persist among Puerto Ricans and other Caribbean islanders, indicating that present-day populations are reservoirs of pre-contact mtDNA diversity. Lastly, we find similarity in autosomal ancestry patterns between pre-contact individuals from Puerto Rico and the Bahamas, suggesting a shared component of Indigenous Caribbean ancestry with close affinity to South American populations. Our findings contribute to a more complete reconstruction of pre-contact Caribbean population history and explore the role of Indigenous peoples in shaping the biocultural diversity of present-day Puerto Ricans and other Caribbean islanders.

genomics↗