The de novo design of amino acid sequences to fold into desired structures is a way to reach a more thorough understanding of how amino acid sequences encode protein structures and to supply methods for protein engineering. Notwithstanding significant breakthroughs, there are noteworthy limitations in current computational protein design. To overcome them needs computational models to complement current ones and experimental tools to provide extensive feedbacks to theory. Here we develop a comprehensive statistical energy function for protein design with a new general strategy and verify that it can complement and rival current well-established models. We establish that an experimental approach can be used to efficiently assess or improve the foldability of designed proteins. We report four de novo proteins for different targets, all experimentally verified to be well-folded, solved solution structures for two being in excellent agreement with respective design targets.
Properly handling missing data is a fundamental challenge in recommendation. Most present works perform negative sampling from unobserved data to supply the training of recommender models with negative signals. Nevertheless, existing negative sampling strategies, either static or adaptive ones, are insufficient to yield high-quality negative samples -both informative to model training and reflective of user real needs.In this work, we hypothesize that item knowledge graph (KG), which provides rich relations among items and KG entities, could be useful to infer informative and factual negative samples. Towards this end, we develop a new negative sampling model, Knowledge Graph Policy Network (KGPolicy), which works as a reinforcement learning agent to explore high-quality negatives. Specifically, by conducting our designed exploration operations, it navigates from the target positive interaction, adaptively receives knowledgeaware negative signals, and ultimately yields a potential negative item to train the recommender. We tested on a matrix factorization (MF) model equipped with KGPolicy, and it achieves significant improvements over both state-of-the-art sampling methods like DNS [39] and IRGAN [30], and KG-enhanced recommender models like KGAT [32]. Further analyses from different angles provide insights of knowledge-aware sampling. We release the codes and datasets at https://github.com/xiangwang1223/kgpolicy.
CCS CONCEPTS• Information systems → Recommender systems.
Environmentally friendly lead-free
dielectric ceramics have attracted
wide attention because of their outstanding power density, rapid charge/dischargerate,
and superior stability. Nevertheless, as a hot material in dielectric
ceramic capacitors, the energy storage performance of Na0.5Bi0.5TiO3-based ceramics has been not satisfactory
because of their higher remnant polarization value and low dielectric
breakdown strength, which is a problem that must be urgently overcome.
In this work, the (1 – x) (0.6Na0.5Bi0.5TiO3 – 0.4Sr0.7Bi0.2TiO3) – xBa(Mg1/3Ta2/3)O3 (BNST-xBMT) systems
were designed based on a dual optimization strategy of domain and
bandgap to solve the above problems. As a result, a record-breaking
ultrahigh energy density and excellent efficiency (W
rec = 8.58 J/cm3, η = 93.5%) were obtained
simultaneously under 565 kV/cm for the BNST-0.08BMT ceramic. The introduction
of Sr0.7Bi0.2TiO3 induces the formation
of nanodomains in BNT-based ceramics, leading to slim P-E curves, and the further modification of Mg/Ta
reduces the grain sizes and increases the bandgap width, resulting
in significant enhancement of the dielectric breakdown strength. Moreover,
excellent stability and superior discharge performance (W
d = 4.7 J/cm3, E = 320 kV/cm)
in the BNST-0.08BMT ceramic were also achieved. The results suggest
that the BNST-0.08BMT ceramic shows potential applicability for dielectric
energy storage ceramics. Simultaneously, the composition-design concept
in the system provides a good reference for the further development
of ceramic dielectric capacitors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.