AI Medical Compendium Journal:
Nature communications

Showing 1 to 10 of 854 articles

An AI-assisted fluorescence microscopic system for screening mitophagy inducers by simultaneous analysis of mitophagic intermediates.

Nature communications
Mitophagy, the selective autophagic elimination of mitochondria, is essential for maintaining mitochondrial quality and cell homeostasis. Impairment of mitophagy flux, a process involving multiple sequential intermediates, is implicated in the onset ...

Prime editor with rational design and AI-driven optimization for reverse editing window and enhanced fidelity.

Nature communications
Prime editing (PE) is a precise tool for introducing genetic mutations in eukaryotes. Extending the efficient editing scope and mitigating undesired byproducts are possible. We introduce reverse PE (rPE), a SpCas9-directed variant that enabled DNA ed...

A soft robotic total artificial hybrid heart.

Nature communications
End-stage heart failure is a deadly disease. Current total artificial hearts (TAHs) carry high mortality and morbidity and offer low quality of life. To overcome current biocompatibility issues, we propose the concept of a soft robotic, hybrid (pumpi...

Concept transfer of synaptic diversity from biological to artificial neural networks.

Nature communications
Recent developments in artificial neural networks have drawn inspiration from biological neural networks, leveraging the concept of the artificial neuron to model the learning abilities of biological nerve cells. However, while neuroscience has provi...

Performance of deep-learning-based approaches to improve polygenic scores.

Nature communications
Polygenic scores, which estimate an individual's genetic propensity for a disease or trait, have the potential to become part of genomic healthcare. Neural-network based deep-learning has emerged as a method of intense interest to model complex, nonl...

Machine learning-powered activatable NIR-II fluorescent nanosensor for in vivo monitoring of plant stress responses.

Nature communications
Real-time monitoring of plant stress signaling molecules is crucial for early disease diagnosis and prevention. However, existing methods are often invasive and lack sensitivity, rendering them inadequate for continuous monitoring of subtle plant str...

Assessing and improving reliability of neighbor embedding methods: a map-continuity perspective.

Nature communications
Visualizing high-dimensional data is essential for understanding biomedical data and deep learning models. Neighbor embedding methods, such as t-SNE and UMAP, are widely used but can introduce misleading visual artifacts. We find that the manifold le...

DeepDTAGen: a multitask deep learning framework for drug-target affinity prediction and target-aware drugs generation.

Nature communications
Identifying novel drugs that can interact with target proteins is a highly challenging, time-consuming, and costly task in drug discovery and development. Numerous machine learning-based models have recently been utilized to accelerate the drug disco...

Bayesian deep-learning structured illumination microscopy enables reliable super-resolution imaging with uncertainty quantification.

Nature communications
The objective of optical super-resolution imaging is to acquire reliable sub-diffraction information on bioprocesses to facilitate scientific discovery. Structured illumination microscopy (SIM) is acknowledged as the optimal modality for live-cell su...

scMODAL: a general deep learning framework for comprehensive single-cell multi-omics data alignment with feature links.

Nature communications
Recent advancements in single-cell technologies have enabled comprehensive characterization of cellular states through transcriptomic, epigenomic, and proteomic profiling at single-cell resolution. These technologies have significantly deepened our u...