bioRxiv Science⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2022.04.18.488616

gr Predictor: a Deep-Learning Model for Predicting the Hydration Structures around Proteins

Kawama, K.·Fukushima, Y.·Ikeguchi, M.·Ohta, M.·Yoshidome, T.
View original source ↗Export metadata ↓

Abstract

Among the factors affecting biological processes such as protein folding and ligand binding, hydration, which is represented by a three-dimensional water-site-distribution-function around the protein, is crucial. The typical methods for computing the distribution functions, including molecular dynamics simulations and the three-dimensional reference interaction site model (3D-RISM) theory, require a long computation time from hours to tens of hours. Here, we propose a deep-learning model rapidly estimating the distribution functions around proteins obtained by the 3D-RISM theory from the protein 3D structure. The distribution functions predicted using our deep-learning model are in good agreement with those obtained by the 3D-RISM theory. Particularly, the coefficient of determination between the distribution function obtained by the deep-learning model and that obtained using the 3D-RISM theory is approximately 0.98. Furthermore, using a graphics processing unit (GPU), the calculation by the deep learning model is completed in less than one minute, more than 2 orders of magnitude faster than the calculation time of 3D-RISM theory. Therefore, our deep learning model provides a practical and efficient way to calculate the three-dimensional water-site-distribution-functions. The program called "gr Predictor" is available under the GNU General Public License from https://github.com/YoshidomeGroup-Hydration/gr-predictor. Table of Contents graphic O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=55 SRC="FIGDIR/small/488616v1_ufig1.gif" ALT="Figure 1"> View larger version (14K): org.highwire.dtl.DTLVardef@108b3c7org.highwire.dtl.DTLVardef@52ec18org.highwire.dtl.DTLVardef@a388borg.highwire.dtl.DTLVardef@10654ad_HPS_FORMAT_FIGEXP M_FIG C_FIG

Source connections

Explore related subjects

biophysicsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Kawama, K., Fukushima, Y., Ikeguchi, M., Ohta, M., Yoshidome, T.. 2022-04-18. gr Predictor: a Deep-Learning Model for Predicting the Hydration Structures around Proteins. https://doi.org/10.1101/2022.04.18.488616

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Design of colipids with controlled lateral distance of head group moieties for targeting strategies in the field of lipid-based nanoparticles

Lipid nanoparticles and liposomes are nanoparticle drug formulations which are firmly established in clinics. In order to expand their application and improve efficacy, surface modifications can be a key strategy, especially for cell specific targeting. Targeting can be achieved by integrating ligand functionalized lipids or lipidoids on the nanoparticle surface. In this case, not solely the targeting ligand itself, but also the structure of the whole targeting lipid/lipidoid can affect the interaction of the targeting ligand with the binding motive on cells. Especially, distal spacer structures between lipid anchor and ligand unit, often composed of polyethylene glycol chains, provide a certain distance of the ligand from the nanoparticle surface. A concept which is currently neglected is the control of the lateral distance between ligand structures on the nanoparticle. Herein we investigated the possibility to design lipidoids with a lateral spacer composed of polyethylene glycol units. We synthesized and characterized different lipidoids which provide a primary amine in the head group for possible ligand coupling. In our model lipidoids the head groups were functionalized with a paramagnetic probe to apply electron paramagnetic resonance (EPR) methods for the characterization of the lipidoid interaction with model nanoparticles, in our case liposomes. Continuous wave EPR was used to study the efficiency of the novel lipidoids to integrate into lipid bilayers of model liposomes, which was shown to depend on lipidoid structure and liposome composition. Furthermore, using double electron-electron resonance (DEER), we observed lipidoid conformational changes occurring upon integration into liposomes.

biophysics↗
bioRxiv2026

Beyond Sequence and Structure: Pretraining PLMs on Continuous Biophysical Fields

We introduce the Biophysical Transformer, a protein language model that adds continuous biophysical fields as a third pretraining signal beside sequence and structure. A Poisson-Boltzmann solver computes the electrostatic potential around each three-residue token, and the model learns to predict it from sequence alone. A rotationally invariant spherical-harmonic descriptor serves as the loss target, eliminating the need for frame alignment during training and for coordinates at inference. Against a matched, one-flag control on the FLIP Meltome thermostability benchmark, the field objective raises Spearman correlation on every trained head of both human splits.The gain on human survives residualizing dipeptide composition under two architecturally different readouts and survives removing the test proteins that overlap the pretraining corpus. No effect survives on the organism-mixed split. At 1.1M parameters, both the Biophysical Transformer and its sequence-only control exceed FLIP's one-hot CNN and untrained-ESM baselines on every split. All results rest on a single pretraining run per arm,and the current design does not separate field content from generic regularization.

biophysics↗
bioRxiv2026

An auditable harness for biomolecular dynamics simulations by AI agents

AI agents now generate biological hypotheses faster than they can be tested. Hypotheses stated at the atomic level can be examined with molecular dynamics (MD) simulations. For new questions without a reference, trust in an agent-run simulation rests on a tool-written process record, not the agent's account. Existing MD agents leave this record to the language model. Here we present MDClaw, a harness whose validating tools and directed acyclic graph (DAG) check stages before execution and record every simulation stage. On MDDataBench, which grades outputs against deposited simulations, four open-weight models with MDClaw passed all three runs on 81-100% of 31 test systems. The DAG complements this outcome check. An ablation without the DAG revealed 11 successful runs that had skipped minimization or equilibration, or simulated a different structure. MDClaw carried questions from human and AI scientists through simulation to trajectories traceable to their inputs and settings.

biophysics↗