Current in silico modelling techniques, such as molecular dynamics, typically focus on compounds with the highest concentration from chromatographic analyses for bioactivity screening. Consequently, they reduce the need for labour-intensive in vitro studies but limit the utilization of extensive chromatographic data and molecular diversity for compound classification. Compound permeability across the blood-brain barrier (BBB) is a key concern in central nervous system (CNS) drug development, and this limitation can be addressed by applying cheminformatics with codeless machine learning (ML). Among the four models developed in this study, the Random Forest (RF) algorithm with the most robust performance in both internal and external validation was selected for model construction, with an accuracy (ACC) of 87.5% and 86.9% and area under the curve (AUC) of 0.907 and 0.726, respectively. The RF model was deployed to classify 285 compounds detected using liquid chromatography quadrupole time-of-flight mass spectrometry (LCQTOF-MS) in Kelulut honey; of which, 140 compounds were screened with 94 descriptors. Seventeen compounds were predicted to permeate the BBB, revealing their potential as drugs for treating neurodegenerative diseases. Our results highlight the importance of employing ML pattern recognition to identify compounds with neuroprotective potential from the entire pool of chromatographic data.
Inducing tumor-specific T cell responses and regulating suppressive tumor microenvironments have been a challenge for effective tumor therapy. CpG (ODN), the Toll-like receptor 9 agonist, has been widely used as adjuvants of cancer vaccines to induce T cell responses. We developed a novel adjuvant to improve the targeting of lymph nodes. CpG were modified with lipid and glycopolymers by the combination of photo-induced RAFT polymerization and click chemistry, and the novel adjuvant was termed as lipid-glycoadjuvant@AuNPs (LCpG). OVA protein was used as model antigen and melanoma model was established to test the immunotherapy effect of the adjuvant. In tumor model, the antitumor effect and mechanism of LCpG on the response of CTLs were examined by flow cytometry and cell cytotoxicity assay. The effects of LCpG on macrophage polarization and Tregs differentiation in tumor microenvironment were also studied by cell depletion assay and cytokine neutralization assay. We also tested the therapeutic effect of the combination of the adjuvant and anti-PD-1 treatment. LCpG could be rapidly transported to and retained longer in the lymphoid nodes than unmodified CpG. In melanoma model, LCpG controlled both primary tumor and its metastasis, and established long-term memory. In spleen and tumor draining lymphoid nodes, LCpG activated tumor-specific Tc1 responses, with increased CD8+ T-cell proliferation, antigen-specific Tc1 cytokine production and specific-tumor killing capacity. In tumor microenvironments, antigen-specific Tc1 induced by the LCpG promoted CTL infiltration, skewed tumor associated macrophages to M1 phenotype, regulated Treg and induced proinflammatory cytokines production in a CTL-derived IFN-γ-dependent manner. In vivo cell depletion and adoptive transfer experiments confirmed that antitumor activity of LCpG included vaccine was mainly dependent on CTL-derived IFN-γ. The anti-tumor efficacy of LCpG was dramatically enhanced when combined with anti-PD1 immunotherapy. LCpG was a promising adjuvant for vaccine formulation which could augment tumor-specific Tc1 activity, and regulate tumor microenvironments.