Predict multi-type drug-drug interactions in cold start scenario.

BACKGROUND: Prediction of drug-drug interactions (DDIs) can reveal potential adverse pharmacological reactions between drugs in co-medication. Various methods have been proposed to address this issue. Most of them focus on the traditional link prediction between drugs, however, they ignore the cold-start scenario, which requires the prediction between known drugs having approved DDIs and new drugs having no DDI. Moreover, they're restricted to infer whether DDIs occur, but are not able to deduce diverse DDI types, which are important in clinics. RESULTS: In this paper, we propose a cold start prediction model for both single-type and multiple-type drug-drug interactions, referred to as CSMDDI. CSMDDI predict not only whether two drugs trigger pharmacological reactions but also what reaction types they induce in the cold start scenario. We implement several embedding methods in CSMDDI, including SVD, GAE, TransE, RESCAL and compare it with the state-of-the-art multi-type DDI prediction method DeepDDI and DDIMDL to verify the performance. The comparison shows that CSMDDI achieves a good performance of DDI prediction in the case of both the occurrence prediction and the multi-type reaction prediction in cold start scenario. CONCLUSIONS: Our approach is able to predict not only conventional binary DDIs but also what reaction types they induce in the cold start scenario. More importantly, it learns a mapping function who can bridge the drugs attributes to their network embeddings to predict DDIs. The main contribution of CSMDDI contains the development of a generalized framework to predict the single-type and multi-type of DDIs in the cold start scenario, as well as the implementations of several embedding models for both single-type and multi-type of DDIs. The dataset and source code can be accessed at https://github.com/itsosy/csmddi .

Effects of Cu2+ on morphological structure, functional groups, and elemental composition of aerobic granular sludge.

Aerobic granular sludge (AGS) is shaped by the self-immobilization of microorganisms. In this study, AGS was cultivated successively in a column sequencing batch reactor (SBR) with glucose and sodium acetate as the carbon sources. The shock-loading effects of varying the Cu2+ concentration (0.0, 1.0, 3.0, 5.0, or 10.0 mg/L) on the characteristics of aerobic granules were studied. The results show that Cu2+ has a toxic effect on the aerobic granules. Although the aerobic granules became increasingly loose as the Cu2+ concentration increased from 1.0 to 5.0 mg/L, their structural integrity was largely maintained. However, the aerobic granules disintegrated and their skeletons consisting of internal filamentous bacteria were exposed at the Cu2+ concentration of 10.0mg/L. The functional groups -NH2, -OH, -COOH, and C-N reacted with Cu2+. Ca, Fe, and P were the major trace elements observed in the AGS. With an increase in the Cu2+ concentration from 0.0 to 10.0 mg/L, the weight percentages of the essential elements Fe, Ca, Na, and K in the granules decreased from 23.98%, 24.64%, 3.86%, and 3.87% to 14.90%, 13.93%, 0%, and 0%, respectively, whereas the weight percentage of copper increased correspondingly from 0% to 35.43%. Cu2+ was exchanged with the essential metals and chelated by the nitrogen-containing functional groups (-NH2 or C-N) of the protein. These effects influenced the structural stability of the sludge.

Fate and removal of typical pharmaceuticals and personal care products by three different treatment processes.

The presence and distribution of typical of pharmaceuticals and personal care products (PPCPs), which comprise two types of polycyclic musks (PCMs) including Galaxolide (HHCB) and Tonalide (AHTN) as well as six types of estrogens containing estrone (E1), 17ß-estradiol (E2), estriol (E3), 17α-ethynylestradiol (EE2), diethylstilbestrol (DES), and bisphenol A (BPA), were investigated at two wastewater treatment plants (WWTPs) in Jiangsu, China. Only raw wastewater was treated in WWTP A while WWTP B was serving an urban-industrialized area. In the influent, the concentrations of EE2 (2193-4437ngL(-1)), E2 (1126-1170ngL(-1)), and DES (268-421ngL(-1)) were generally higher than the previously reported values, whereas the concentrations of HHCB (306-316ngL(-1)), E1 (29-129ngL(-1)), E3 (53ngL(-1)), and BPA (26-176ngL(-1)) were much lower than those reported in other previous studies. In addition, AHTN was not detected in either WWTP and E3 was not found in WWTP B. The detected processes including anaerobic/oxic process (A/O), combined orbal oxidation ditch process (C-orbal OD) and anaerobic/anoxic/anoxic/oxic membrane biological reactor (A/A/A/O-MBR) showed higher removal efficiencies for HHCB (67-71%) and EE2 (87%) than those in other previous studies. Besides, the total hydraulic retention time (HRT) ranged between 6.7 and 20.0h, sludge retention time (SRT) ranged between 8 and 23d, and water temperature ranged from 24.8 to 28.2°C. The removal efficiencies for estrogens in biological processes were related to the following factors: the level of hydrophobic estrogens, the type of removal process (C-orbal OD was consistently less efficient in removing estrogens than A/O and A/A/A/O-MBR), and a high SRT or HRT (A/A/A/O-MBR with higher SRT and HRT showed higher and more stable removal of hydrophobic estrogens).