MCD-LightGBM System for Intelligent Analyzing Heterogeneous Clinical Drug Therapeutic Effects.

Causal effect estimation of individual heterogeneity is a core issue in the field of causal inference, and its application in medicine poses an active and challenging problem. In high-risk decision-making domain such as healthcare, inappropriate treatments can have serious negative impacts on patients. Recently, machine learning-based methods have been proposed to improve the accuracy of causal effect estimation results. However, many of these methods concentrate on estimating causal effects of continuous outcome variables under binary intervention conditions, and give less consideration to multivariate intervention conditions or discrete outcome variables, thus limiting their scope of application. To tackle this issue, we combine the double machine learning framework with Light Gradient Boosting Machine (LightGBM) and propose a double LightGBM model. This model can estimate binary causal effects more accurately and in less time. Two cyclic structures were added to the model. Data correction method was introduced and improved to transform discrete outcome variables into continuous outcome variables. Multivariate Cyclic Double LightGBM model (MCD-LightGBM) was proposed to intelligently estimate multivariate treatment effects. A visual human-computer interaction system for heterogeneous causal effect estimation was designed, which can be applied to different types of data. This paper reports that the system improved the Logarithm of the Minimum Angle of Resolution (LogMAR) of visual acuity change after Vascular Endothelial Growth Factor (anti-VEGF) treatment in patients with diabetic macular degeneration. The improvement was observed in two clinical problems, from 0.05 to 0.33, and the readmission rate of diabetic patients after cure was reduced from 48.4% to 10.5%. The results above demonstrate the potential of the proposed system in predicting heterogeneous clinical drug treatment effects.

Ganoderma triterpenes slow cyst growth in polycystic kidney disease / 中国药理学与毒理学杂志

OBJECTIVE Autosomal dominant polycystic kidney disease (ADPKD) is a common inherited disease with a high morbidity around 1/1000-1/400, characterized by progressive enlargement of fluid-filled cysts derived from renal tubular epithelial cells. Massive cysts gradually compress renal parenchyma destroying normal renal structures and compromising renal functions. Unfortunately, it will cause end-stage renal disease in most of the patients but without effective therapy now, who have to live on hemodialysis or kidney transplantation. Based on this present situation, it is of great significance to find early intervention to inhibit renal cyst development. The projective of this study was to investigate whether Ganoderma triterpenes (GT) can inhibit renal cyst development and study the related mechanism. METHODS and RESULTS First, we used MDCK cyst model, cultivated MDCK cells in vitro to form fluid-filled cysts surrounded by monolayer cells. GT inhibited MDCK cyst formation significantly, and inhibited cyst enlargement dose-dependently proving GT cyst inhibition in vitro. Then we used an embryonic kidney cyst model, wile-type mice kidneys were taken out on embryonic day 13.5 to form renal cysts stimulated with 8-Br-cAMP. GT inhibited embryonic kidney cyst development significantly in a dose-dependent and reversible manner proving GT cyst inhibition at organ level. Furthermore, we used two ADPKD mouse models with severe cystic kidney disease phenotypes. GT dramatically inhibited renal cyst development, decreased ADPKD mouse kidney volume and the cyst index inside proving GT cyst inhibition in vivo. By Western blot, we proved GT down-regulated Ras/MAPK signal pathway without detectable effect on mTOR signal pathway both in MDCK cells and two ADPKD mouse kidneys. CONCLUSION GT retard renal cyst development both in vitro and in vivo significantly. The related mechanisms were involved in GT promoting renal tubular epithelial cell differentiation, down-regulating intracellular cAMP level and Ras/MAPK signal pathway.

Synthesis and pharmacological evaluation of novel bisindolylalkanes analogues.

In an effort to develop potent anti-cancer chemopreventive agents that act on topoisomerase II, a novel series of bisindolylalkanes analogues such as 3,3'-(thiochroman-4,4-diyl)bis(1H-indole) are synthesized. Structures of all compounds are elucidated by (1)H NMR, (13)C NMR and HRMS. Anti-proliferative activities for all of these compounds are investigated by the method of MTT assay on 7 human cancer lines. Most of them showed antitumor activities in vitro, the half maximal inhibitory concentration (IC50) value is 7.798 µg/mL of 3a against MCF7. Compound 3a showed comparable topoisomerase II inhibitory activity to etoposide (VP-16) at 100 µM concentration. The rest of the compounds also showed varying degree topoisomerase II inhibitory activity.

Correlation study of toxicity of substituted phenols to river bacteria and their biodegradability in river water.

OBJECTIVE: To study the correlation of toxicity with biodegradability (BODT) in order to promote QSBR development and understand the degradation mechanism. METHODS: Toxicity of substituted phenols to river bacteria was determined by the turbidities that were measured using a spectrophotometer (UV-190) at 530 nm against a blank control. The biodegradability of substituted phenols was expressed as BODT and the DO concentrations were determined by the iodometric titration method. RESULTS: The BODT and toxicity(log 1/IC50) of 12 substituted phenols to bacteria from the Songhua River were determined respectively. The correlation of biodegradability with toxicity was developed: BODT=8.21 (+/-2.22) pKa -32.44 (+/-8.28) log 1/IC50 +89.04 (+/-38.20), n=12, R2=0.791, R2(adj)=0.745, SE=9.134, F=17.066, P=0.001. CONCLUSION: The BODT of substituted phenols was influenced by their toxicity and the ionization constant pKa. The stronger the toxicity, the less readily the compound was degraded by river bacteria.