The presence of residue interaction cooperativity is revealed in various IDP condensates using atomistic molecular dynamics simulations using atomistic molecular dynamics simulations to reproduce experimental results of condensate physical properties, including saturation concentration, viscoelasticity, and interfacial...
Le Chen, Xiang-Yu Wu, Guo-Rong Hu et al.· Proceedings of the National...· 0 citations
The Domain-Aware Residual Feature Modulation Network (DARMN), a deep learning framework for dynamic inter-residue contact prediction in MDP outperforms existing dynamic contact prediction and conformational ensemble prediction models, especially in long-distance contact identification, and generalizes well to unseen MD...
Jing Xiao, Wei-Bu Wang, Yi-Bo Ma et al.· Journal of Chemical Theory a...· 0 citations
A 170M-parameter M2S model trained on about 262B OpenWebText token slots outperforms the evaluated pure-uniform SEDD, GIDD, and Neural CTMC checkpoints at every tested sampling budget, reaching generative PPL $143.3$ at 128 steps versus $183.6$ for the strongest pure-uniform baseline.
