Journal of Chemical Information and Modeling 最新文献

Accurate prediction of RNA tertiary structure remains a central challenge in structural biology, yet existing computational approaches face fundamental limitations arising from the ruggedness of the RNA free-energy landscape and the scarcity of experimentally resolved structures. Here we present RNADaemon, a framework that formulates RNA tertiary structure prediction as a Markov Decision Process and trains a Soft Actor-Critic agent to apply adaptive external force-field biases that steer all-atom molecular dynamics toward native-like conformations to minimize the eRMSD metric. Trained on 479 monomeric RNA structures and evaluated on 14 test cases from CASP16, RNA-Puzzles, and the PDB, the agent trains stably, approaches SimRNA and FARFAR2 in median RMSD, and recovers the global fold of most reference structures. However, performance remains markedly inferior to that of AlphaFold 3 and trRosettaRNA. We identify the scalar Bellman error as a fundamental information bottleneck that currently limits the performance of the agent. To our knowledge, this is the first application of continuous-action deep reinforcement learning (RL) with all-atom force fields to RNA tertiary structure prediction. This study establishes a benchmark for future comparisons and provides diagnostic insights for RL-guided RNA structure modeling.

Peptide self-assembly is a ubiquitous molecular phenomenonin whichshort amino acid sequences spontaneously organize into diverse nanostructures.These assemblies exhibit distinct morphologies closely linked to theirbiological functions and potential applications, making them attractivecandidates for biomaterials in drug delivery, regenerative medicine,and diagnostics. However, designing and predicting peptide sequenceswith specific self-assembled morphologies remains highly challengingdue to the complex interplay of noncovalent interactions, includinghydrogen bonding, hydrophobic effects, and π–πstacking. Although deep learning has enabled accurate prediction ofpeptide self-assembly propensity, rational de novo design of peptides with targeted assembly behavior remains largelyunexplored. In this study, we propose Diff-SelfA-PepGSI, a novel pipelinefor the morphology-specific design of self-assembling peptides. Thisthree-stage framework comprises: (i) generation, in which a diffusion-basedgenerative model produces candidate self-assembling peptide sequences;(ii) screening, in which pretrained protein language models extractdeep semantic features and a deep discriminative network performssequence optimization and property screening; and (iii) identification,in which a dual-branch structure extracts features and a dedicatedclassifier identifies the specific nanostructures formed. By integratingsequence generation, predictive screening, and morphology identification,this workflow establishes a proof-of-concept de novo design pipeline that links peptide sequences directly to their targetmorphologies. Diff-SelfA-PepGSI demonstrates superior performancecompared to state-of-the-art models in both screening and identificationtasks. Experimental validation preliminarily demonstrates the feasibilityof the de novo design pipeline, successfully generatingself-assembling peptides such as LAPFLA. Under the reported experimentalconditions, 4 of 11 generated candidates (36.4%) exhibited the targetmorphology predicted by the model. Within the challenging contextof de novo morphology-specific peptide design, thissuccess rate supports the potential of Diff-SelfA-PepGSI as an earlystage self-assembling peptide generation platform.