Search for: All records

Abstract Nanophotonic freeform design has the potential to push the performance of optical components to new limits, but there remains a challenge to effectively perform optimization while reliably enforcing design and manufacturing constraints. We present Neuroshaper, a framework for freeform geometric parameterization in which nanophotonic device layouts are defined using an analytic neural network representation. Neuroshaper serves as a qualitatively new way to perform shape optimization by capturing multi-scalar, freeform geometries in an overparameterized representation scheme, enabling effective optimization in a smoothened, high dimensional geometric design space. We show that Neuroshaper can enforce constraints and topology manipulation in a manner where local constraints lead to global changes in device morphology. We further show numerically and experimentally that Neuroshaper can apply to a diversity of nanophotonic devices. The versatility and capabilities of Neuroshaper reflect the ability of neural representation to augment concepts in topological design. 

ABSTRACT Venturia canescensis a parasitoid wasp that harbors a domesticated endogenous virus (DEV) and parasitizes host insects likeEphestia kuehniella. TheV. canescensDEV evolved from an alphanudivirus and produces virus-like particles (VLPs) in females that protect wasp eggs from a host immune defense called encapsulation. In contrast, very few DEV genes required for VLP formation and function have been identified. In this study, we characterized fiveV. canescensDEV genes of unknown function that all nudiviruses encode. Three of these genes are single copy (OrNVorf18-like,OrNVorf61-like, andOrNVorf76-like), whileOrNVorf41-likehas expanded into a six-member family andOrNVorf47-likehas expanded into a three-member family. Sequence analysis indicated all of these genes retain essential motifs present in nudivirus homologs, while transmission electron microscopy (TEM) studies characterized the timing of VLP formation during the wasp pupal stage. RNA interference (RNAi) assays identifiedOrNVorf18-like,OrNVorf61-like,OrNVorf41-like-1,andOrNVorf41-like-2as genes that are required for normal VLP formation. Knockdown ofOrNVorf47-likefamily members did not affect VLP formation but did disable binding of VLPs toV. canescenseggs and protection against encapsulation. Disabled formation of VLPs in response to RNAi knockdown ofOrNVorf18-like,OrNVorf61-like,OrNVorf41-like-1,andOrNVorf41-like-2also resulted in wasp eggs being encapsulated. In contrast, knockdown ofOrNVorf76-likehad no effect on VLP assembly, egg binding, or encapsulation. Altogether, reported results significantly advance our understanding ofV. canescensVLP (VcVLP) formation and function. IMPORTANCEUnderstanding howV. canescenscoopted an alphanudivirus to produce VcVLPs is of interest to the study of virus evolution. Our results show that three nudivirus core genes have essential functions in VcVLP formation, while one is essential for the novel function of binding to wasp eggs and protection from encapsulation, which is the most important immune defense of insects against parasitoids. 

Over the past decade, deep reinforcement learning (RL) techniques have significantly advanced robotic systems. However, due to the complex architectures of neural network models, ensuring their trustworthiness is a considerable challenge. Programmatic reinforcement learning has surfaced as a promising approach. Nonetheless, synthesizing robot-control programs remains challenging. Existing methods rely on domain-specific languages (DSLs) populated with user-defined state abstraction predicates and a library of low-level controllers as abstract actions to boot synthesis, which is impractical in unknown environments that lack such predefined components. To address this limitation, we introduce RoboScribe, a novel abstraction refinement-guided program synthesis framework that automatically derives robot state and action abstractions from raw, unsegmented task demonstrations in high-dimensional, continuous spaces. It iteratively enriches and refines an initially coarse abstraction until it generates a task-solving program over the abstracted robot environment. RoboScribe is effective in synthesizing iterative programs by inferring recurring subroutines directly from the robot’s raw, continuous state and action spaces, without needing predefined abstractions. Experimental results show that RoboScribe programs inductively generalize to long-horizon robot tasks involving arbitrary numbers of objects, outperforming baseline methods in terms of both interpretability and efficiency. 

Abstract Quantitative structure–activity relationship (QSAR) modeling has become a critical tool in drug design. Recently proposed Topological Regression (TR), a computationally efficient and highly interpretable QSAR model that maps distances in the chemical domain to distances in the activity domain, has shown predictive performance comparable to state-of-the-art deep learning-based models. However, TR’s dependence on simple random sampling-based anchor selection and utilization of radial basis function for response reconstruction constrain its interpretability and predictive capacity. To address these limitations, we propose Adaptive Topological Regression (AdapToR) with adaptive anchor selection and optimization-based reconstruction. We evaluated AdapToR on the NCI60 GI50 dataset, which consists of over 50,000 drug responses across 60 human cancer cell lines, and compared its performance to Transformer CNN, Graph Transformer, TR, and other baseline models. The results demonstrate that AdapToR outperforms competing QSAR models for drug response prediction with significantly lower computational cost and greater interpretability as compared to deep learning-based models.