DDI Domination Directory International Issue 66 Brittany Andrews Like New

Product Information

Fig. 3 A brief introduction to graph neural networks. (a) The typical workflow of graph neural networks. (b) Message passing phase. (c) Readout phase. S. Kwon and S. Yoon, Proceedings of the 8th ACM international conference on bioinformatics, computational biology, and health informatics, 2017, pp. 203–212 Search PubMed . ROCHA, José Manuel (30 de outubro de 1999). «O número que marco foi alterado». Público . Consultado em 25 de junho de 2015 TWOSIDES is constructed by Zitnik et al. 39 after filtering and preprocessing the original TWOSIDES dataset. 40 It includes 645 drugs with 963 interaction types and 4 576 287 DDI tuples. As against the DrugBank dataset, these interactions are at the phenotypic level ( i.e., headache, pain in the throat, and others) rather than metabolic. The negative samples are generated by a procedure the same as the DrugBank dataset. 3.2 Experimental setup We compared the proposed SA-DDI with state-of-the-art methods, namely, DeepCCI, 26 MR-GNN, 29 SSI-DDI, 28 GAT-DDI, 30 and GMPNN-CS. 30 These baselines only consider chemical structure information as input and can work in both warm and cold start scenarios. The parameter settings for MR-GNN, SSI-DDI, and GMPNN-CS are consistent with their published source codes. As the source codes for DeepCCI and GAT-DDI are not provided, we implemented them with parameters recommended by the papers. 26,30 To investigate how the D-MPNN, substructure attention and substructure–substructure interaction module improve the model performance, we also consider the following variants of SA-DDI:

Nyborg G, Straand J, Brekke M. Inappropriate prescribing for the elderly—a modern epidemic? Eur J Clin Pharmacol. 2012;68:1085–94. https://doi.org/10.1007/s00228-012-1223-8.Menec VH, Sirski M, Attawar D, Katz A. Does continuity of care with a family physician reduce hospitalizations among older adults? J Health Serv Res Policy. 2006;11:196–201. https://doi.org/10.1258/135581906778476562. DrugBank is a unique bioinformatics and cheminformatics resource that combines detailed drug data with comprehensive drug target information. 37 It contains 1706 drugs with 191 808 DDI tuples. Eighty-six interaction types describe how one drug affects the metabolism of another one. Each drug is represented as the simplified molecular-input line-entry system (SMILES) and we converted it into a molecular graph using RDKit. Each DDI tuple from DrugBank is a positive sample from which a negative sample is generated using the strategy described by Wang et al. 38 In the DrugBank dataset, each drug pair is only associated with a single type of interaction. Overall, seven categories of MARO were investigated: Potentially inappropriate medication (PIM) [ 44, 46, 47, 49, 52, 56, 59, 64, 69], drug–drug interaction (DDI) [ 45, 50, 57, 64, 66, 68], adverse drug events (ADE) [ 58, 63], duplicated medication [ 43, 44], unnecessary drug use [ 60], overdose [ 51], and potential inappropriate drug combination (PIDC) [ 61] (Table 2). Holmes HM, Luo R, Kuo Y-F, Baillargeon J, Goodwin JS. Association of potentially inappropriate medication use with patient and prescriber characteristics in Medicare Part D. Pharmacoepidemiol Drug Saf. 2013;22:728–34. https://doi.org/10.1002/pds.3431. Johansson T, Abuzahra ME, Keller S, Mann E, Faller B, Sommerauer C, et al. Impact of strategies to reduce polypharmacy on clinically relevant endpoints: a systematic review and meta-analysis. Br J Clin Pharmacol. 2016;82:532–48. https://doi.org/10.1111/bcp.12959.

Existing computational methods can be divided into two categories, namely, text mining-based and machine learning-based methods. 2 Text mining-based methods extract drug–drug relations between various entities from scientific literature, 3–7 insurance claim databases, electronic medical records, 8 and the FDA Adverse Event Reporting System; 9 these methods are efficient in building DDI-related datasets. However, they cannot detect unannotated DDIs or potential DDIs before a combinational treatment is made. 10 Conversely, machine learning-based methods have the potential to identify unseen DDIs for downstream experimental validations by generalizing the learned knowledge to unannotated DDIs. J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals and G. E. Dahl, International conference on machine learning, 2017, pp. 1263–1272 Search PubMed . Drug–drug interaction prediction Given a DDI tuple ( d x, d y, r), the DDI prediction can be expressed as the joint probability as follows: K. Huang, C. Xiao, T. Hoang, L. Glass and J. Sun, Proceedings of the AAAI Conference on Artificial Intelligence, 2020, pp. 702–709 Search PubMed . Tamblyn RM, McLeod PJ, Abrahamowicz M, Laprise R. Do too many cooks spoil the broth? Multiple physician involvement in medical management of elderly patients and potentially inappropriate drug combinations. CMAJ. 1996;154:1177–84.

Conflict of Interest

Chu H-Y, Chen C-C, Cheng S-H. Continuity of care, potentially inappropriate medication, and health care outcomes among the elderly: evidence from a longitudinal analysis in Taiwan. Med Care. 2012;50:1002–9. https://doi.org/10.1097/MLR.0b013e31826c870f. cThe value is significantly different from the value for the corresponding control at a P of <0.05. Chen C-C, Tseng C-H, Cheng S-H. Continuity of care, medication adherence, and health care outcomes among patients with newly diagnosed type 2 diabetes: a longitudinal analysis. Med Care. 2013;51:231–7. https://doi.org/10.1097/MLR.0b013e31827da5b9. N. P. Tatonetti, P. P. Ye, R. Daneshjou and R. B. Altman, Sci. Transl. Med., 2012, 4 CrossRef PubMed , 125ra31.