ABSTRACT
Molecular optimization, which aims to improve molecular properties by modifying complex molecular structures, is a crucial and challenging task in drug discovery. In recent years, translation models provide a promising way to transform low-property molecules to high-property molecules, which enables molecular optimization to achieve remarkable progress. However, most existing models require matched molecular pairs, which are prone to be limited by the datasets. Although some models do not require matched molecular pairs, their performance is usually sacrificed due to the lack of useful supervising information. To address this issue, a domain-label-guided translation model is proposed in this paper, namely DLTM. In the model, the domain label information of molecules is exploited as a control condition to obtain different embedding representations, enabling the model to generate diverse molecules. Besides, the model adopts a classifier network to identify the property categories of transformed molecules, guiding the model to generate molecules with desired properties. The performance of DLTM is verified on two optimization tasks, namely the quantitative estimation of drug-likeness and penalized logP. Experimental results show that the proposed DLTM is superior to the compared baseline models.
Subject(s)
Drug DiscoveryABSTRACT
Optimization techniques play a pivotal role in advancing drug development, serving as the foundation of numerous generative methods tailored to efficiently design optimized molecules derived from existing lead compounds. However, existing methods often encounter difficulties in generating diverse, novel, and high-property molecules that simultaneously optimize multiple drug properties. To overcome this bottleneck, we propose a multiobjective molecule optimization framework (MOMO). MOMO employs a specially designed Pareto-based multiproperty evaluation strategy at the molecular sequence level to guide the evolutionary search in an implicit chemical space. A comparative analysis of MOMO with five state-of-the-art methods across two benchmark multiproperty molecule optimization tasks reveals that MOMO markedly outperforms them in terms of diversity, novelty, and optimized properties. The practical applicability of MOMO in drug discovery has also been validated on four challenging tasks in the real-world discovery problem. These results suggest that MOMO can provide a useful tool to facilitate molecule optimization problems with multiple properties.
Subject(s)
Drug Discovery , Drug Discovery/methods , Drug Design , AlgorithmsABSTRACT
Space manipulators are expected to perform more challenging missions in on-orbit service (OOS) systems, but there are some unique characteristics that are not found on ground-based robots, such as dynamic coupling between space bases and manipulators, limited fuel supply, and working with unfixed bases. This paper focuses on trajectory-tracking control and internal force control for free-floating close-chain manipulators. First, the kinematics and dynamics of free-floating close-chain manipulators are given using the momentum conservation and spatial operator algebra (SOA) methodologies, respectively. Furthermore, an adaptive fuzzy integral sliding mode controller (AFISMC) based on time delay estimation (TDE) was designed for trajectory-tracking control, and a proportional-integral (PI) control strategy was adopted for internal force control. The global asymptotic stability of the proposed controller was proven by using the Lyapunov methodology. Three cases were conducted to verify the efficiency of the controller by using numerical simulations on two six-link manipulators with a free-floating base. The controller presents the desired tracking capability.
ABSTRACT
Exploration of the intricate connections between long noncoding RNA (lncRNA) and diseases, referred to as lncRNA-disease associations (LDAs), plays a pivotal and indispensable role in unraveling the underlying molecular mechanisms of diseases and devising practical treatment approaches. It is imperative to employ computational methods for predicting lncRNA-disease associations to circumvent the need for superfluous experimental endeavors. Graph-based learning models have gained substantial popularity in predicting these associations, primarily because of their capacity to leverage node attributes and relationships within the network. Nevertheless, there remains much room for enhancing the performance of these techniques by incorporating and harmonizing the node attributes more effectively. In this context, we introduce a novel model, i.e., Adaptive Message Passing and Feature Fusion (AMPFLDAP), for forecasting lncRNA-disease associations within a heterogeneous network. Firstly, we constructed a heterogeneous network involving lncRNA, microRNA (miRNA), and diseases based on established associations and employing Gaussian interaction profile kernel similarity as a measure. Then, an adaptive topological message passing mechanism is suggested to address the information aggregation for heterogeneous networks. The topological features of nodes in the heterogeneous network were extracted based on the adaptive topological message passing mechanism. Moreover, an attention mechanism is applied to integrate both topological and semantic information to achieve the multimodal features of biomolecules, which are further used to predict potential LDAs. The experimental results demonstrated that the performance of the proposed AMPFLDAP is superior to seven state-of-the-art methods. Furthermore, to validate its efficacy in practical scenarios, we conducted detailed case studies involving three distinct diseases, which conclusively demonstrated AMPFLDAP's effectiveness in the prediction of LDAs.
ABSTRACT
Flavonoids are a class of secondary metabolites widely distributed in plants. Regiospecific modification by methylation and glycosylation determines flavonoid diversity. A rare flavone glycoside, diosmin (luteolin-4'-methoxyl-7-O-glucosyl-rhamnoside), occurs in Chrysanthemum indicum. How Chrysanthemum plants evolve new biosynthetic capacities remains elusive. Here, we assemble a 3.11-Gb high-quality C. indicum genome with a contig N50 value of 4.39 Mb and annotate 50,606 protein-coding genes. One (CiCOMT10) of the tandemly repeated O-methyltransferase genes undergoes neofunctionalization, preferentially transferring the methyl group to the 4'-hydroxyl group of luteolin with ortho-substituents to form diosmetin. In addition, CiUGT11 (UGT88B3) specifically glucosylates 7-OH group of diosmetin. Next, we construct a one-pot cascade biocatalyst system by combining CiCOMT10, CiUGT11, and our previously identified rhamnosyltransferase, effectively producing diosmin with over 80% conversion from luteolin. This study clarifies the role of transferases in flavonoid diversity and provides important gene elements essential for producing rare flavone.