SynCluster: Reaction Type Clustering and Recommendation Framework for Synthesis Planning.

AI-assisted synthesis planning has emerged as a valuable tool in accelerating synthetic chemistry for the discovery of new drugs and materials. The template-free approach, which showcases superior generalization capabilities, is seen as the mainstream direction in this field. However, it remains unclear whether such an end-to-end approach can achieve problem-solving performance on par with experienced chemists without fully revealing insights into the chemical mechanisms involved. Moreover, there is a lack of unified and chemically inspired frameworks for improving multitask reaction predictions in this area. In this study, we have addressed these challenges by investigating the impact of fine-grained reaction-type labels on multiple downstream tasks and propose a novel framework named SynCluster. This framework incorporates unsupervised clustering cues into the baseline models and identifies plausible chemical subspaces which is compatible with multitask extensions and can serve as model-independent indicators to effectively enhance the performance of multiple downstream tasks. In retrosynthesis prediction, SynCluster achieves significant improvements of 4.1 and 11.0% in top-1 and top-10 prediction accuracy, respectively, compared to the baseline Molecular Transformer, and achieves a notable enhancement of 13.9% in top-10 accuracy when combined with Retroformer. By incorporating simplified molecular-input line-entry system augmentation, our framework achieves higher top-10 accuracy compared to state-of-the-art sequence-based retrosynthesis models and improves over the baseline on the diversity and validity of reactants. SynCluster also achieves 94.9% top-10 accuracy in forward synthesis prediction and 51.5% top-10 Maxfrag accuracy in reagent prediction. Overall, SynCluster provides a fresh perspective with chemical interpretability and reinforcement of domain knowledge in the synthesis design. It offers a promising solution for improving the accuracy and efficiency of AI-assisted synthesis planning and bridges the gap between template-free approaches and the problem-solving abilities of experienced chemists.

Root-aligned SMILES: a tight representation for chemical reaction prediction.

Chemical reaction prediction, involving forward synthesis and retrosynthesis prediction, is a fundamental problem in organic synthesis. A popular computational paradigm formulates synthesis prediction as a sequence-to-sequence translation problem, where the typical SMILES is adopted for molecule representations. However, the general-purpose SMILES neglects the characteristics of chemical reactions, where the molecular graph topology is largely unaltered from reactants to products, resulting in the suboptimal performance of SMILES if straightforwardly applied. In this article, we propose the root-aligned SMILES (R-SMILES), which specifies a tightly aligned one-to-one mapping between the product and the reactant SMILES for more efficient synthesis prediction. Due to the strict one-to-one mapping and reduced edit distance, the computational model is largely relieved from learning the complex syntax and dedicated to learning the chemical knowledge for reactions. We compare the proposed R-SMILES with various state-of-the-art baselines and show that it significantly outperforms them all, demonstrating the superiority of the proposed method.

Drug-loading three-dimensional scaffolds based on hydroxyapatite-sodium alginate for bone regeneration.

Bone tissue engineering is a promising approach for tackling clinical challenges. Osteoprogenitor cells, osteogenic factors, and osteoinductive/osteoconductive scaffolds are employed in bone tissue engineering. However, scaffold materials remain limited due to their source, low biocompatibility, and so on. In this study, a composite hydrogel scaffold composed of hydroxyapatite (HA) and sodium alginate (SA) was manufactured using three-dimensional printing. Naringin (NG) and calcitonin-gene-related peptide (CGRP) were used as osteogenic factors in the fabrication of drug-loaded scaffolds. Investigation using animal experiments, as well as scanning electron microscopy, cell counting kit-8 testing, alkaline phosphatase staining, and alizarin red-D staining of bone marrow mesenchymal stem cell culture showed that the three scaffolds displayed similar physicochemical properties and that the HA/SA/NG and HA/SA/CGRP scaffolds displayed better osteogenesis than that of the HA/SA scaffold. Thus, the HA/SA scaffold could be a biocompatible material with potential applications in bone regeneration. Meanwhile, NG and CGRP doping could result in better and more positive proliferation and differentiation.

MicroRNA expression profile of human periodontal ligament cells under the influence of Porphyromonas gingivalis LPS.

Periodontitis is a chronic inflammatory disease which is caused by bacterial infection and leads to the destruction of periodontal tissues and resorption of alveolar bone. Thus, special attention should be paid to the mechanism under lipopolysaccharide (LPS)-induced periodontitis because LPS is the major cause of periodontitis. However, to date, miRNA expression in the LPS-induced periodontitis has not been well characterized. In this study, we investigated miRNA expression patterns in LPS-treated periodontal ligament cells (PDLCs). Through miRNA array and differential analysis, 22 up-regulated miRNAs and 28 down-regulated miRNAs in LPS-treated PDLCs were identified. Seven randomly selected up-regulated (miR-21-5p, 498, 548a-5p) and down-regulated (miR-495-3p, 539-5p, 34c-3p and 7a-2-3p) miRNAs were examined by qRT-PCR, and the results proved the accuracy of the miRNA array. Moreover, targets of these deregulated miRNAs were analysed using the miRWalk database. Database for Annotation, Visualization and Integration Discovery software were performed to analyse the Gene Ontology and Kyoto Encyclopaedia of Genes and Genomes pathway of differential expression miRNAs, and the results shown that Toll-like receptor signalling pathway, cAMP signalling pathway, transforming growth factor-beta signalling pathway, mitogen-activated protein kinase (MAPK) signalling pathway and other pathways were involved in the molecular mechanisms underlying LPS-induced periodontitis. In conclusion, this study provides clues for enhancing our understanding of the mechanisms and roles of miRNAs as key regulators of LPS-induced periodontitis.

[Clinical research of immediate restoration implant with mini-implants in edentulous space].

OBJECTIVE: The purpose of this study was to investigate the clinical effective of immediate restoration with Osstem MS mini-implant in the edentulous space of 5-6 mm. METHODS: The sample consisted of 36 consecutively treated partially edentulous patients who had a total of 36 Osstem MS mini-implants, which were 2.5 mm or 3.0 mm in diameter and placed in 5-6 mm gap. The chair-side-made or laboratory-made provisional crowns for implants were fabricated at the time of fixtures placed. The final restorations were fabricated with gold alloy-fused-porcelain crown 3 to 5 months later. During the mean 21.3 months (12-37 months) follow-up time since fixtures placement, all implants were examined clinically and radiologically. RESULTS: No implant failed before restoration. One implant led an adjacent tooth pulp necrosis after the implantation, but the natural tooth and implant were successfully retained by root canal therapy. 36 implants in 36 patients who were followed-up were successful and their aesthetic results were satisfactory. CONCLUSION: Immediate loaded implant with Osstem MS mini-implant has good clinical prosthetic effects in the edentulous space of 5-6 mm.