PandaDock’s empirical scoring function ranks 8th of 25 methods evaluated, ahead of every AutoDock Vina and Vinardo configuration tested, while the GNN scores below Vina, consistent with the within-target ceiling identified on SAIR.
Abstract
We present PandaDock, an open-source molecular docking platform implementing flexible-ligand conformational search with analytic gradients, a precomputed affinity grid engine, specialized modules for induced-fit, metal-coordination and tethered docking, and an SE(3)-equivariant graph neural network scoring function trained at scale. Ligand flexibility is represented as a torsion tree and pose parameters are optimized by Monte Carlo with Metropolis acceptance refined by L-BFGS, with rotational gradients obtained in closed form through the derivative of the SO(3) exponential map rather than by finite differences. Affinity grids are built by a blocked neighbor-selection scheme that is exact and 5.6–9.7× faster than dense evaluation, and may be cached across ligands sharing a receptor and site, reducing a six-ligand series from 29.3 s to 10.4 s. On 814 protein–ligand complexes spanning 14 target families, PandaDock recovers a pose within 2 Å of the crystal geometry in 33.7% of cases at rank 1 and in 57.0% of cases within the returned ensemble. The GNN scoring function is trained on 741,706 co-folded complexes from SAIR under target-disjoint splits, reaching a Pearson r of 0.407 on 90,219 held-out complexes and transferring to 202 independent crystal structures with measured Ki, Kd, IC50 or EC50 at r = 0.467. We report the model against three controls, a target-mean predictor, a ligand-descriptor-only baseline, and within-target correlations, and document both where it performs and where it does not, including its unsuitability for pose rescoring. On an independent 30-compound series against a single GABAA receptor target, PandaDock’s empirical scoring function ranks 8th of 25 methods evaluated, ahead of every AutoDock Vina and Vinardo configuration tested, while the GNN scores below Vina, consistent with the within-target ceiling identified on SAIR. At full scale on the PDBbind v2020 refined set (n = 4,640, native crystal poses), the fully independent SAIR model reaches r = 0.531, and a dedicated model trained on PDBbind alone under a target-disjoint split reaches r = 0.690 on its own held-out test complexes – the strongest evidence in this work that PandaDock’s affinity predictions generalize. PandaDock is distributed under an open-source license at https://github.com/pritampanda15/PandaDock with a complete command-line interface and a reproducible benchmarking harness.
This study constructed a pH-responsive P-TN/SF@Fe-Cur composite coating that demonstrated significant anti-infective, anti-inflammatory, antioxidant, pro-angiogenic, and pro-osteogenic effects in rat subcutaneous infection and femoral defect models.
ProteinReasoner is developed, a multimodal generative protein foundation model that sequentially connects amino acid sequence, evolutionary constraints and three-dimensional structure within a shared autoregressive architecture and suggests a general route towards reasoning across interdependent representations in other scientific domains.
Chaozhong Liu, Linlin Chao, Shaomin Ji et al.· bioRxiv· 1 citation
Due to its importance and wide adoption, wheat cultivation is promptly required to shift towards sustainable practices, reducing the dependency on chemical components. Among bio-based solutions aimed at securing the sustainability of wheat cultivation, biostimulants offer a versatile platform of eco-friendly tools assuring sustainability and profitability. Microalgae present a concrete example of a biostimulant source due to their richness in metabolites and high value products. Therefore, this study evaluated the biostimulant potential of eleven eco-extracts prepared from soil-isolated microalgae strains. Eco-extracts applied via soil drench at low dose (0.1 g/L) were investigated for their biostimulant effects on wheat growth, physiology, yield, and quality under controlled conditions. Results demonstrated significant ameliorations in treated plants as compared to the control, with no phytoinhibitory effects. Remarkable enhancements were notable in growth parameters such as shoot and root lengths (+40-70%), physiological traits such as total chlorophyll and stomatal conductance (+7-52%), yield components in the example of grain number per spike and thousand grain weight (+17-103%), and grain quality namely protein and polyphenol content (+2-fold to 4-fold). Similarly, phosphorus accumulation and uptake were significantly improved, while soil physicochemical status was ameliorated, indicating enhanced fertility. Multivariate analysis and composite index ranking marked Chlorella sp. GA18, Chlorella sp. GA65, Scenedesmus sp. GA69, and Chlorococcum sp. GA63 as eco-extracts with consistent performances across all plant traits. These findings highlighted the promising potential of integrating microalgae-based eco-friendly extracts in sustainable wheat cultivation.
Amer Chabili, Z. Hakkoum, F. Minaoui et al.· Plant Science· 1 citation
Effective control of fluid flows is critical across transportation, energy and medicine, where it can increase lift, reduce drag, enhance mixing and attenuate noise1-3. Yet fluids are notoriously difficult to control because they involve high-dimensional, nonlinear and multiscale dynamics that resist conventional approaches4-6. Reinforcement learning has driven remarkable progress in fields such as protein folding and complex games, which have shared benchmarks and standardized environments7-10. Fluid dynamics has lacked such infrastructure, so each controller is typically tuned to a single geometry and operating condition, making progress difficult to accumulate, transfer and compare11-13. Here we introduce HydroGym, a solver-independent reinforcement learning platform providing more than 60 validated, openly available flow control environments spanning from canonical laminar flows to complex turbulent flows, with systematic progression in the Reynolds number up to Re = 4 × 105, and Mach number variations in two and three dimensions. Across these environments, agents repeatedly discover robust control principles, including boundary layer manipulation, disruption of acoustic feedback and reorganization of turbulent wakes. Critically, we demonstrate a proof of concept for zero-shot transfer, in which agents that are trained exclusively in inexpensive surrogate environments are deployed to challenging real-world scenarios such as a three-dimensional wing section. We achieve a 38% reduction in local skin friction while reducing exploration costs by four orders of magnitude compared with direct on-wing optimization. As this transfer exploits shared near-wall physics, the breadth of generalization remains open, suggesting a new pathway for research toward policy generalization across computationally prohibitive simulation environments. By offering a common, extensible foundation for reproducible research, HydroGym moves flow control from isolated case studies toward a cohesive community effort.
Christian Lagemann, Sajeda Mokbel, Miro Gondrum et al.· Nature· 1 citation
ABSTRACT Microplastics (MPs) accumulation in ecosystem and human organs poses urgent environmental and health risks, yet few enzymes efficiently degrade polyethylene terephthalate (PET) under physiological conditions. We leveraged deep learning to mine unexplored sequence space across 246 million proteins, discovering AhPETase, an evolutionarily distinct hydrolase with low homology (<50% sequence identity) to known PET‐degrading enzymes. This noncanonical biocatalyst efficiently depolymerizes PET at 37°C, outperforming all typical PETases and achieving a 7.76‐fold enhancement over IsPETase, one of the most representative mesophilic PETases. Additionally, engineered variant AhPETaseM1 retains functional activity for over 20 days under physiological conditions and can degrade post‐consumer PET MPs 34‐fold faster than recombinant human‐derived enzyme MG8 (rMG8) under equal enzyme loading. Critically, it reversed PET‐induced toxicity in human lung and colon cells, establishing the first proof‐of‐concept for enzymatic MPs detoxification.
Yuxuan Wang, Shijie He, Yuheng Chang et al.· Advancement of science· 0 citations
Recently, the application of deep learning to structural data deposited in the Protein Data Bank has enabled the reliable and accurate prediction of 3D folded structures of proteins from their sequences. However, this approach is not applicable to highly dynamic proteins, where multiple structures interconvert. Furthermore, the mechanistic details of protein folding and unfolding remain challenging to study. Herein, we present a set of data highlighting these complexities. By chemical incorporation of stereoisomeric 4-fluoroproline residues at selected sites in the sequence of a folded, multi-conformational protein ("molten-globule"), we were able to modify its structural properties that propagated to highly distinct functional features, such as modulation of ligand binding affinities or misfolding and aggregation into amyloids. Application of NMR methods, notably 19F NMR spectroscopy, provided detailed molecular insights into the observed phenomena. This study illustrates how subtle residue-localized conformational bias can affect the overall protein conformational dynamics influencing protein-protein interactions that are important for cellular functions and related to diseases.
Abir Ben Bouzayene, M. Sai, Alexis Jouin et al.· Angewandte Chemie· 0 citations