Machine learning framework for intelligent aeration control in wastewater treatment plants: Automatic feature engineering based on variation sliding layer.

Intelligent control of wastewater treatment plants (WWTPs) has the potential to reduce energy consumption and greenhouse gas emissions significantly. Machine learning (ML) provides a promising solution to handle the increasing amount and complexity of generated data. However, relationships between the features of wastewater datasets are generally inconspicuous, which hinders the application of artificial intelligence (AI) in WWTPs intelligent control. In this study, we develop an automatic framework of feature engineering based on variation sliding layer (VSL) to control the air demand precisely. Results demonstrated that using VSL in classic machine learning, deep learning, and ensemble learning could significantly improve the efficiency of aeration intelligent control in WWTPs. Bayesian regression and ensemble learning achieved the highest accuracy for predicting air demand. The developed models with VSL-ML models were also successfully implemented under the full-scale wastewater treatment plant, showing a 16.12 % reduction in demand compared to conventional aeration control of preset dissolved oxygen (DO) and feedback to the blower. The VSL-ML models showed great potential to be applied for the precision air demand prediction and control. The package as a tripartite library of Python is called wwtpai, which is freely accessible on GitHub and CSDN to remove technical barriers to the application of AI technology in WWTPs.

Oligomannurarate sulfate blocks tumor growth by inhibiting NF-kappaB activation.

AIM: JG3, a novel marine-derived oligosaccharide, significantly inhibits angiogenesis and tumor metastasis by blocking heparanase activity. It also arrests tumor growth, an effect that is not fully explained by its anti-heparanase activity. Here we sought to identify the mechanisms underlying JG3-mediated inhibition of tumor growth. METHODS: Heparanase expression was assessed by RT-PCR and Western blotting. NF-kappaB activation status was determined using immunofluorescence, Western blotting, DNA-binding and transcription-activity assays. The effect of JG3 on upstream components of the NF-kappaB pathway and on selected transcription factors were monitored by Western blotting. The antitumor effect of JG3 and its relation to NF-kappaB activation were evaluated using four different tumor xenograft models. RESULTS: We found that JG3 effectively inhibited NF-kappaB activation independent of heparanase expression. Our results indicate that JG3 inactivated NF-kappaB by interfering with the activation of upstream components of the NF-kappaB pathway without generally affecting the nuclear translocation of transcription factors. Further, in vivo studies demonstrated that JG3 effectively arrested the growth of tumors derived from cell lines in which NF-kappaB was constitutively active (BEL-7402 liver carcinoma and MDA-MB-435s breast carcinoma), but did not affect the growth of tumors derived from NF-kappaB-negative cell lines (SGC-7901 gastric cancer and HO-8910 ovarian carcinoma). CONCLUSION: Our data indicate that NF-kappaB mediates the JG3-induced arrest of tumor growth. These results define a new mechanism of action of JG3 and highlight the potential for JG3 as a promising lead molecule in cancer therapy.

Marine-derived oligosaccharide sulfate (JG3) suppresses heparanase-driven cell adhesion events in heparanase over-expressing CHO-K1 cells.

AIM: To elucidate the detailed mechanisms underlying the appreciable effects of JG3, a novel marine-derived oligosaccharide, on cell migration using a Chinese hamster ovary (CHO) cell line stably over-expressing heparanase. METHODS: A retrovirus infection system was used to establish a CHO-K1 cell line stably transfected with heparanase. Immunocytochemistry was used to assess cell morphology. Flow cytometry was selected to analyze the activation of beta1-integrin, and Western blotting was used to analyze the downstream effects on the cell adhesion pathway. An affinity precipitation assay was used to determine activation of the small GTPases, Rac1, and RhoA. RESULTS: JG3 abolished heparanase-driven formation of focal adhesions and cell spreading. Although JG3 failed to block the heparanase-triggered activation of beta1-integrin or the phosphorylation of Src, the oligosaccharide caused a significant dephosphorylation of FAK and subsequent inactivation of Erk. Furthermore, JG3 was found to arrest the activation of Rac1. CONCLUSION: All these findings help form an alternative view to understand the mechanisms underlying the inhibitory effects of JG3 on cell motility.Acta Pharmacologica Sinica (2009) 30: 1033-1038; doi: 10.1038/aps.2009.97; published online 22 June 2009.