AI Medical Compendium Journal:
Science advances

Showing 11 to 20 of 114 articles

Massive experimental quantification allows interpretable deep learning of protein aggregation.

Science advances
Protein aggregation is a pathological hallmark of more than 50 human diseases and a major problem for biotechnology. Methods have been proposed to predict aggregation from sequence, but these have been trained and evaluated on small and biased experi...

Supervised and unsupervised learning reveal heroin-induced impairments in astrocyte structural plasticity.

Science advances
Astrocytes regulate synaptic activity across large brain territories via their complex, interconnected morphology. Emerging evidence supports the involvement of astrocytes in shaping relapse to opioid use through morphological rearrangements in the n...

Biomimetic rigid-soft finger design for highly dexterous and adaptive robotic hands.

Science advances
In dexterous robotic hand design, achieving high mobility and adaptability comparable to human hands remains an ongoing challenge. Biomimetic designs mimicking the musculoskeletal structure have shown promise yet face difficulties in preserving key k...

Encoding mechanical intelligence using ultraprogrammable joints.

Science advances
Animal bodies act as physical controllers, with their finely tuned passive mechanical responses physically "encoding" complex movements and environmental interactions. This capability allows animals to perform challenging tasks with minimal muscular ...

Topology optimization of random memristors for input-aware dynamic SNN.

Science advances
Machine learning has advanced unprecedentedly, exemplified by GPT-4 and SORA. However, they cannot parallel human brains in efficiency and adaptability due to differences in signal representation, optimization, runtime reconfigurability, and hardware...

Genome-wide methylome modeling via generative AI incorporating long- and short-range interactions.

Science advances
Using millions of methylation segments, we developed DiffuCpG, a generative artificial intelligence (AI) diffusion model designed to solve the critical challenge of missing data in high-throughput methylation technologies. DiffuCpG goes beyond conven...

Preference-based assistance optimization for lifting and lowering with a soft back exosuit.

Science advances
Wearable robotic devices have become increasingly prevalent in both occupational and rehabilitative settings, yet their widespread adoption remains inhibited by usability barriers related to comfort, restriction, and noticeable functional benefits. A...

MIST: An interpretable and flexible deep learning framework for single-T cell transcriptome and receptor analysis.

Science advances
Joint analysis of transcriptomic and T cell receptor (TCR) features at single-cell resolution provides a powerful approach for in-depth T cell immune function research. Here, we introduce a deep learning framework for single-T cell transcriptome and ...

Robust semi-automatic vessel tracing in the human retinal image by an instance segmentation neural network.

Science advances
Vasculature morphology and hierarchy are essential for blood perfusion. Human retinal circulation is an intricate vascular system emerging and remerging at the optic nerve head (ONH). Tracing retinal vascular branching from ONH can allow detailed mor...

Curriculum is more influential than haptic feedback when learning object manipulation.

Science advances
Dexterous manipulation remains an aspirational goal for autonomous robotic systems, particularly when learning to lift and rotate objects against gravity with intermittent finger contacts. We use model-free reinforcement learning to compare the effec...