XAI-enabled neural network analysis of metabolite spatial distributions.

We used deep neural networks to process the mass spectrometry imaging (MSI) data of mouse muscle (young vs aged) and human cancer (tumor vs normal adjacent) tissues, with the aim of using explainable artificial intelligence (XAI) methods to rapidly identify biomarkers that can distinguish different classes of tissues, from several thousands of metabolite features. We also modified classic neural network architectures to construct a deep convolutional neural network that is more suitable for processing high-dimensional MSI data directly, instead of using dimension reduction techniques, and compared it to seven other machine learning analysis methods' performance in classification accuracy. After ascertaining the superiority of Channel-ResNet10, we used a novel channel selection-based XAI method to identify the key metabolite features that were responsible for its learning accuracy. These key metabolite biomarkers were then processed using MetaboAnalyst for pathway enrichment mapping. We found that Channel-ResNet10 was superior to seven other machine learning methods for MSI analysis, reaching > 98% accuracy in muscle aging and colorectal cancer datasets. We also used a novel channel selection-based XAI method to find that in young and aged muscle tissues, the differentially distributed metabolite biomarkers were especially enriched in the propanoate metabolism pathway, suggesting it as a novel target pathway for anti-aging therapy.

Immunogenicity and safety of the quadrivalent human papillomavirus vaccine in Chinese females aged 9 to 26 years: A phase 3, open-label, immunobridging study.

BACKGROUND: The quadrivalent human papillomavirus (qHPV; HPV6/11/16/18) vaccine was approved for use in Chinese women aged 20-45 years in 2017. This Phase 3, open-label study (NCT03493542) aimed to assess immunogenicity and safety of the qHPV vaccine in Chinese girls aged 9-19 years versus Chinese young women aged 20-26 years; we report results from Day 1 through Month 7. The study will continue through Month 60 to assess antibody persistence in Chinese girls aged 9-19 years. METHODS: Participants aged 9-26 years received three doses of the qHPV vaccine (Day 1, Month 2, Month 6). Geometric mean titers (GMTs) and seroconversion percentages for anti-HPV6/11/16/18 antibodies were determined by competitive Luminex immunoassay (cLIA) in serum samples obtained on Day 1 and at Month 7. Injection-site adverse events (AEs) and systemic AEs within 30 days post-vaccination, and serious AEs (SAEs) occurring at any time during the study, were recorded. RESULTS: In total, 766 participants (383 aged 9-19 years; 383 aged 20-26 years) were enrolled and received ≥1 vaccine dose. All participants in the per-protocol immunogenicity population of both age groups seroconverted to each of the vaccine HPV types at Month 7. Anti-HPV6/11/16/18 antibody GMTs at Month 7 in participants aged 9-19 years were non-inferior to those in participants aged 20-26 years. Injection-site AEs and systemic AEs were reported by 36.6% and 49.3% of 9-19-year-olds, and 40.7% and 54.8% of 20-26-year-olds, respectively. There were no vaccine-related SAEs. No participants discontinued the vaccine due to an AE and no deaths were reported. CONCLUSION: Antibody responses induced by the 3-dose qHPV vaccination regimen in Chinese girls aged 9-19 years were non-inferior to those in Chinese young women aged 20-26 years. The vaccine was generally well tolerated in the study population. ClinicalTrials.gov Identifier: NCT03493542.

XRCC1 genetic polymorphism acts a potential biomarker for lung cancer.

Lung cancer is one of the most common but serious cancers in the world. Both the X-ray repair cross-complementing group 1 (XRCC1) gene and the human multidrug resistance 1 (MDR1) gene are important candidate genes influencing the susceptibility to various diseases, including lung cancer. This study aimed to assess the correlation of genetic polymorphisms in XRCC1 and MDR1 with the susceptibility to lung cancer. In this study, a total of 320 lung cancer patients and 346 cancer-free controls in Chinese population were enrolled in this study. Data about the clinical characteristics and related risk factors of lung cancer were collected by questionnaires. The single-nucleotide polymorphisms (SNPs) of XRCC1 and MDR1 genes were genotyped by created restriction site-polymerase chain reaction method. Our data showed that the risk for lung cancer increased significantly among the variant Arg194Trp (C > T, rs1799782) and Arg399Gln (G > A, rs25487) of XRCC1, but there are no significant differences in the allelic and genotypic frequencies of c.1564A > T and c.3073A > C of MDR1 between lung cancer patients and cancer-free controls. In conclusion, these preliminary results suggest that the C > T, rs1799782 and C > T, rs25487 of XRCC1 genetic variants might be used as molecular markers for detecting lung cancer susceptibility.

Rapid catalytic microwave method to damage Microcystis aeruginosa with FeCl3-loaded active carbon.

In recent years, effective methods for cyanobacterial blooms treatment have been an important issue. In this study, we demonstrated a rapid catalytic microwave method to deal with Microcystis aeruginosa with FeCl(3)-loaded active carbon. Microcystis aeruginosa damage process was monitored by measuring optical density, chlorophyll-a content, superoxide dismutase activity, l-glutathione content, and turbidity of the treated Microcystis aeruginosa suspension. It was found that this method could quickly and efficiently induce the degradation of Microcystis aeruginosa. On the basis of control experiments and characterization results, we attributed the excellent catalytic performance to the synergy effect between hole-doping of the catalyst and hot spot of microwave irradiation. This work provides a fast and green treatment method for cyanobacterial blooms.