Discovery of antimicrobial peptides targeting Acinetobacter baumannii via a pre-trained and fine-tuned few-shot learning-based pipeline
Ontology highlight
ABSTRACT:
PROVIDER: PRJNA1310317 | ENA |
REPOSITORIES: ENA
Similar Datasets
Project description:Acinetobacter baumannii, a robust Gram-negative bacterium known for inducing nosocomial infections and displaying multidrug resistance, remains a formidable challenge to combat. The limited arsenal of antimicrobial peptides targeting this pathogen underscores the need for innovative strategies. Here, we report a pioneering few-shot learning-based pipeline to identify potent antimicrobial peptides targeting A. baumannii. This pipeline effectively scans through the entire libraries of hexapeptides, heptapeptides, and octapeptides, encompassing tens of billions of candidates, despite the extreme scarcity of available training data. Comprising classification, ranking, and regression modules as an integration, each module is trained using a few-shot learning strategy involving pre-training and multiple fine-tuning steps while incorporating similar and true data fine-tuning. This methodology mitigates the potential overfitting concerns due to the small size of the training samples and then enhances the predictive capability of the pipeline. The results highlight the robustness and versatility of the methodology, demonstrating its effectiveness in discovering AMPs against A. baumannii and C. albicans, while demonstrating low off-target toxicity and negligible susceptibility to drug resistance. Additionally, the EME7(7) exhibits efficacy in controlling A. baumannii infections within a mouse pneumonia model, notably without inducing kidney injury — a contrast to the observed effects of polymyxin B. This work provides a paradigm for addressing the challenges posed by limited data availability.
2025-09-01 | GSE306268 | GEO
Project description:Analysis of expression changes upon knockdown of specific SHOT-RNAs in LNCaP cells
2024-01-29 | GSE245843 | GEO
Project description:This study introduces Ice Finder, a novel tool for quantifying crystalline ice in cryo-electron tomography, addressing a critical gap in existing methodologies. We present the first application of the meta-learning paradigm to this field, demonstrating that diverse tomographic tasks across datasets can be unified under a single meta-learning framework. By leveraging few-shot learning, our approach enhances domain generalization and adaptability to domain shifts, enabling rapid adaptation to new datasets with minimal examples. Ice Finder's performance is evaluated on a comprehensive set of in situ datasets from EMPIAR, showcasing its ease of use, fast processing capabilities, and millisecond inference times.
| S-EPMC11828963 | biostudies-literature
Project description:Understanding the neural basis of the remarkable human cognitive capacity to learn novel concepts from just one or a few sensory experiences constitutes a fundamental problem. We propose a simple, biologically plausible, mathematically tractable, and computationally powerful neural mechanism for few-shot learning of naturalistic concepts. We posit that the concepts that can be learned from few examples are defined by tightly circumscribed manifolds in the neural firing-rate space of higher-order sensory areas. We further posit that a single plastic downstream readout neuron learns to discriminate new concepts based on few examples using a simple plasticity rule. We demonstrate the computational power of our proposal by showing that it can achieve high few-shot learning accuracy on natural visual concepts using both macaque inferotemporal cortex representations and deep neural network (DNN) models of these representations and can even learn novel visual concepts specified only through linguistic descriptors. Moreover, we develop a mathematical theory of few-shot learning that links neurophysiology to predictions about behavioral outcomes by delineating several fundamental and measurable geometric properties of neural representations that can accurately predict the few-shot learning performance of naturalistic concepts across all our numerical simulations. This theory reveals, for instance, that high-dimensional manifolds enhance the ability to learn new concepts from few examples. Intriguingly, we observe striking mismatches between the geometry of manifolds in the primate visual pathway and in trained DNNs. We discuss testable predictions of our theory for psychophysics and neurophysiological experiments.
| S-EPMC9618072 | biostudies-literature
Project description:oxLDL exposed trained monocytes
| PRJNA504428 | ENA
Project description:Hydroxychloroquine inhibits trained immunity
| PRJNA670179 | ENA
Project description:We demonstrate that hydroxychloroquine inhibits trained immunity at the functional and epigenetic level and is accompanied by reduced expression of interferon-stimulated genes. Trained immunity comprises a functional adaptation induced by epigenetic reprogramming which facilitates the anti-viral innate immune response.
2020-10-21 | GSE159678 | GEO
Project description:Lassa fever outbreaks hit West African countries every year and there is still no licensed vaccine to limit the burden of this viral hemorrhagic fever. We previously developed MeV-NP, a single-shot vaccine that induces protective immunity in cynomolgus monkeys one month or more than a year before Lassa virus infection and that is able to protect against divergent viral strains. Given the limited dissemination area of Lassa virus during outbreaks and the high risk of nosocomial transmission, a vaccine that induces rapid protection could be useful to protect exposed people during outbreaks in the absence of preventive vaccination. We tested whether the time to protection could be reduced after immunization by challenging MeV pre-immune cynomolgus monkeys 16 or 8 days after a single shot of MeV-NP. None of the immunized monkeys developed disease and they rapidly controlled viral replication. Animals immunized eight days before the challenge were the best controllers, producing a strong CD8 T-cell response against the viral glycoprotein. A group of animals was also vaccinated an hour after the challenge. These animals did not develop any protective immune responses and presented the same lethal disease as the control animals. This study demonstrates that MeV-NP can induce a rapid protective immune response against Lassa fever in presence of MeV pre-existing immunity but can likely not be used as therapeutic vaccine.
2023-02-21 | GSE225258 | GEO
Project description:Expression analysis of SHOT-RNA KD in LNCaP
| PRJNA1030056 | ENA
Project description:Short utterance speaker verification (SV) in the actual application is the task of accepting or rejecting the identity claim of a speaker based on a few enrollment utterances. Traditional methods have used deep neural networks to extract speaker representations for verification. Recently, several meta-learning approaches have learned a deep distance metric to distinguish speakers within meta-tasks. Among them, a prototypical network learns a metric space that may be used to compute the distance to the prototype center of speakers, in order to classify speaker identity. We use emphasized channel attention, propagation and aggregation in TDNN (ECAPA-TDNN) to implement the necessary function for the prototypical network, which is a nonlinear mapping from the input space to the metric space for either few-shot SV task. In addition, optimizing only for speakers in given meta-tasks cannot be sufficient to learn distinctive speaker features. Thus, we used an episodic training strategy, in which the classes of the support and query sets correspond to the classes of the entire training set, further improving the model performance. The proposed model outperforms comparison models on the VoxCeleb1 dataset and has a wide range of practical applications.
| S-EPMC10280689 | biostudies-literature