Search for: All records

Natural products are small molecules synthesized by fungi, bacteria and plants, which historically have had a profound effect on human health and quality of life. These natural products have evolved over millions of years resulting in specific biological functions that may be of interest for pharmaceutical, agricultural, or nutraceutical use. Often natural products need to be structurally modified to make them suitable for specific applications. Combinatorial biosynthesis is a method to alter the composition of enzymes needed to synthesize a specific natural product resulting in structurally diversified molecules. In this review we discuss different approaches for combinatorial biosynthesis of natural products via engineering fungal enzymes and biosynthetic pathways. We highlight the biosynthetic knowledge gained from these studies and provide examples of new-to-nature bioactive molecules, including molecules synthesized using combinations of fungal and non-fungal enzymes.

 

Providing user-understandable explanations to justify recommendations could help users better understand the recommended items, increase the system’s ease of use, and gain users’ trust. A typical approach to realize it is natural language generation. However, previous works mostly adopt recurrent neural networks to meet the ends, leaving the potentially more effective pre-trained Transformer models under-explored. In fact, user and item IDs, as important identifiers in recommender systems, are inherently in different semantic space as words that pre-trained models were already trained on. Thus, how to effectively fuse IDs into such models becomes a critical issue. Inspired by recent advancement in prompt learning, we come up with two solutions: find alternative words to represent IDs (called discrete prompt learning) and directly input ID vectors to a pre-trained model (termed continuous prompt learning). In the latter case, ID vectors are randomly initialized but the model is trained in advance on large corpora, so they are actually in different learning stages. To bridge the gap, we further propose two training strategies: sequential tuning and recommendation as regularization. Extensive experiments show that our continuous prompt learning approach equipped with the training strategies consistently outperforms strong baselines on three datasets of explainable recommendation. 

For millimeter-wave power applications, GaN high-electron mobility transistors (HEMTs) are often grown epitaxially on a high-purity semi-insulating c-axis 4H-SiC substrate. For these anisotropic hexagonal materials, the design and modeling of microstrip and coplanar interconnects require detailed knowledge of both the ordinary permittivity ε⊥ and the extraordinary permittivity εǁ perpendicular and parallel, respectively, to the c-axis. However, conventional dielectric characterization techniques make it difficult to measure εǁ alone or to separate εǁ from ε⊥. As a result, there is little data for εǁ, especially at millimeter-wave frequencies. This work demonstrates techniques for characterizing εǁ of 4H SiC using substrate-integrated waveguides (SIWs) or SIW resonators. The measured εǁ on seven SIWs and eleven resonators from 110 to 170 GHz is within ±1% of 10.2. Because the SIWs and resonators can be fabricated on the same SiC substrate together with HEMTs and other devices, they can be conveniently measured on-wafer for precise material-device correlation. Such permittivity characterization techniques can be extended to other frequencies, materials, and orientations. 

Explaining to users why some items are recommended is critical, as it can help users to make better decisions, increase their satisfaction, and gain their trust in recommender systems (RS). However, existing explainable RS usually consider explanation as a side output of the recommendation model, which has two problems: (1) It is difficult to evaluate the produced explanations, because they are usually model-dependent, and (2) as a result, how the explanations impact the recommendation performance is less investigated. In this article, explaining recommendations is formulated as a ranking task and learned from data, similarly to item ranking for recommendation. This makes it possible for standard evaluation of explanations via ranking metrics (e.g., Normalized Discounted Cumulative Gain). Furthermore, this article extends traditional item ranking to an item–explanation joint-ranking formalization to study if purposely selecting explanations could reach certain learning goals, e.g., improving recommendation performance. A great challenge, however, is that the sparsity issue in the user-item-explanation data would be inevitably severer than that in traditional user–item interaction data, since not every user–item pair can be associated with all explanations. To mitigate this issue, this article proposes to perform two sets of matrix factorization by considering the ternary relationship as two groups of binary relationships. Experiments on three large datasets verify the solution’s effectiveness on both explanation ranking and item recommendation.