Molecular optimization, which transforms a given input molecule X into another Y with desired properties, is essential in molecular drug discovery. The traditional approaches either suffer from sample-inefficient learning or ignore information that can be captured with the supervised learning of optimized molecule pairs. In this study, we present a novel molecular optimization paradigm, Graph Polish. In this paradigm, with the guidance of the source and target molecule pairs of the desired properties, a heuristic optimization solution can be derived: given an input molecule, we first predict which atom can be viewed as the optimization center, and then the nearby regions are optimized around this center. We then propose an effective and efficient learning framework, Teacher and Student polish, to capture the dependencies in the optimization steps. A teacher component automatically identifies and annotates the optimization centers and the preservation, removal, and addition of some parts of the molecules; a student component learns these knowledges and applies them to a new molecule. The proposed paradigm can offer an intuitive interpretation for the molecular optimization result. Experiments with multiple optimization tasks are conducted on several benchmark datasets. The proposed approach achieves a significant advantage over the six state-ofthe-art baseline methods. Also, extensive studies are conducted to validate the effectiveness, explainability, and time savings of the novel optimization paradigm.
Molecular optimization, which transforms a given input molecule X into another Y with desirable properties, is essential in molecular drug discovery. The traditional translating approaches, generating the molecular graphs from scratch by adding some substructures piece by piece, prone to error because of the large set of candidate substructures in a large number of steps to the final target. In this study, we present a novel molecular optimization paradigm, Graph Polish, which changes molecular optimization from the traditional "two-language translating" task into a "single-language polishing" task. The key to this optimization paradigm is to find an optimization center subject to the conditions that the preserved areas around it ought to be maximized and thereafter the removed and added regions should be minimized. We then propose an effective and efficient learning framework T&S polish to capture the longterm dependencies in the optimization steps. The T component automatically identifies and annotates the optimization centers and the preservation, removal and addition of some parts of the molecule, and the S component learns these behaviors and applies these actions to a new molecule. Furthermore, the proposed paradigm can offer an intuitive interpretation for each molecular optimization result. Experiments with multiple optimization tasks are conducted on four benchmark datasets. The proposed T&S polish approach achieves significant advantage over the five stateof-the-art baseline methods on all the tasks. In addition, extensive studies are conducted to validate the effectiveness, explainability and time saving of the novel optimization paradigm.
Background: Diffusion tensor cardiac magnetic resonance (DT-CMR) imaging has great potential to characterize myocardial microarchitecture. However, its accuracy is limited by respiratory and cardiac motion and long scan times. Here, we develop and evaluate a slice-specific tracking method to improve the efficiency and accuracy of DT-CMR acquisition during free breathing.Methods: Coronal images were obtained along with signals from a diaphragmatic navigator. Respiratory and slice displacements were obtained from the navigator signals and coronal images, respectively, and these displacements were fitted with a linear model to obtain the slice-specific tracking factors. This method was evaluated in DT-CMR examinations of 17 healthy subjects, and the results were compared with those obtained using a fixed tracking factor of 0.6. DT-CMR with breath-holding was used for reference. Quantitative and qualitative evaluation methods were used to analyze the performance of the slice-specific tracking method and the consistency between the obtained diffusion parameters.Results: In the study, the slice-specific tracking factors showed an upward trend from the basal to the apical slice. Residual in-plane movements were lower in slice-specific tracking than in fixed-factor tracking (RMSE: 2.748 ± 1.171 versus 5.983 ± 2.623, P < 0.001). The diffusion parameters obtained using slice-specific tracking were not significantly different from those obtained from breath-holding acquisition (P > 0.05). Conclusion:In free-breathing DT-CMR imaging, the slice-specific tracking method reduced misalignment of the acquired slices. The diffusion parameters obtained using this approach were consistent with those obtained with the breath-holding technique.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.