No abstract

Objectives This study aimed to establish a machine learning prediction model that can be used to predict bone metastasis (BM) in patients with newly diagnosed thyroid cancer (TC). Methods Demographic and clinicopathologic variables of TC patients in the Surveillance, Epidemiology, and End Results database from 2010 to 2016 were retrospectively analyzed. On this basis, we developed a random forest (RF) algorithm model based on machine‐learning. The area under receiver operating characteristic curve (AUC), accuracy score, recall rate, and specificity are used to evaluate and compare the prediction performance of the RF model and the other model. Results A total of 17,138 patients were included in the study, with 166 (0.97%) developed bone metastases. Grade, T stage, histology, race, sex, age, and N stage were the important prediction features of BM. The RF model has better predictive performance than the other model (AUC: 0.917, accuracy: 0.904, recall rate: 0.833, and specificity: 0.905). Conclusions The RF model constructed in this study could accurately predict bone metastases in TC patients, which may provide clinicians with more personalized clinical decision‐making recommendations. Machine learning technology has the potential to improve the development of BM prediction models in TC patients.

No abstract

No abstract

No abstract

No abstract

No abstract

Background The co-culture strategy which mimics natural ecology by constructing an artificial microbial community is a useful tool to activate the biosynthetic gene clusters to generate new metabolites. However, the conventional method to study the co-culture is to isolate and purify compounds separated by HPLC, which is inefficient and time-consuming. Furthermore, the overall changes in the metabolite profile cannot be well characterized. Results A new approach which integrates computational programs, MS-DIAL, MS-FINDER and web-based tools including GNPS and MetaboAnalyst, was developed to analyze and identify the metabolites of the co-culture of Aspergillus sydowii and Bacillus subtilis. A total of 25 newly biosynthesized metabolites were detected only in co-culture. The structures of the newly synthesized metabolites were elucidated, four of which were identified as novel compounds by the new approach. The accuracy of the new approach was confirmed by purification and NMR data analysis of 7 newly biosynthesized metabolites. The bioassay of newly synthesized metabolites showed that four of the compounds exhibited different degrees of PTP1b inhibitory activity, and compound N2 had the strongest inhibition activity with an IC50 value of 7.967 μM. Conclusions Co-culture led to global changes of the metabolite profile and is an effective way to induce the biosynthesis of novel natural products. The new approach in this study is one of the effective and relatively accurate methods to characterize the changes of metabolite profiles and to identify novel compounds in co-culture systems.