Determining the Balance Between Drug Efficacy and Safety by the Network and Biological System Profile of Its Therapeutic Target

Abstract

One of the most challenging puzzles in drug discovery is the identification and characterization of candidate drug of well-balanced profile between efficacy and safety. So far, extensive efforts have been made to evaluate this balance by estimating the quantitative structure–therapeutic relationship and exploring target profile of adverse drug reaction. Particularly, the therapeutic index (TI) has emerged as a key indicator illustrating this delicate balance, and a clinically successful agent requires a sufficient TI suitable for it corresponding indication. However, the TI information are largely unknown for most drugs, and the mechanism underlying the drugs with narrow TI (NTI drugs) is still elusive. In this study, the collective effects of human protein–protein interaction (PPI) network and biological system profile on the drugs' efficacy–safety balance were systematically evaluated. First, a comprehensive literature review of the FDA approved drugs confirmed their NTI status. Second, a popular feature selection algorithm based on artificial intelligence (AI) was adopted to identify key factors differencing the target mechanism between NTI and non-NTI drugs. Finally, this work revealed that the targets of NTI drugs were highly centralized and connected in human PPI network, and the number of similarity proteins and affiliated signaling pathways of the corresponding targets was much higher than those of non-NTI drugs. These findings together with the newly discovered features or feature groups clarified the key factors indicating drug's narrow TI, and could thus provide a novel direction for determining the delicate drug efficacy-safety balance.

Protein functional annotation of simultaneously improved stability, accuracy and false discovery rate achieved by a sequence-based deep learning

“…Moreover, the statistical differences of these measurements between any two methods were shown in Figure 2 . As one of the most comprehensive parameters in any category of predictors [ 57 ], the MCC reflected the stability of protein function predictor, which described the correlation between a predictive value and the actual value [ 62 , 105 , 106 ]. As illustrated on the left panel of Figure 2A , the variations of MCC values among methods were provided (the actual MCC value of each method was subtracted by the minimum MCC value among four different methods).…”

Identification of the gene signature reflecting schizophrenia’s etiology by constructing artificial intelligence‐based method of enhanced reproducibility

“…As one of the most popular machine learning algorithms, the support vector machine (SVM) showed good performance in classifying microarray datasets, and the corresponding wrapper or embedded recursive feature elimination algorithm (SVM‐RFE) was widely used in current study . During SVM‐RFE‐based feature selection, a gene ranking function was initially generated based on the artificial intelligence (AI) classifier (SVM), and the signature was then identified by discarding the genes that were not differentially expressed .…”

Precision Dosing Priority Criteria: Drug, Disease, and Patient Population Variables

“…These are also called "critical-dose drugs" and often require therapeutic drug monitoring (TDM) and dose individualization based on patientspecific characteristics (Pater, 2004). Values of ≤2 (Bialer et al, 1998;Greenberg et al, 2016;Ericson et al, 2017) or ≤3 (Li et al, 2018) have been considered therapeutic index cut off points for NTI drugs. Examples of drugs that have been specified as NTI by regulatory agencies include anticoagulants (e.g., warfarin), antiarrhythmics (e.g., digoxin, flecainide), antiepileptics (e.g., phenytoin, carbamazepine), hormones (e.g., levothyroxine, ethinyl estradiol), and immunosuppressants (e.g., tacrolimus, sirolimus, cyclosporine) (Yu, 2011).…”

“…Examples of drugs that have been specified as NTI by regulatory agencies include anticoagulants (e.g., warfarin), antiarrhythmics (e.g., digoxin, flecainide), antiepileptics (e.g., phenytoin, carbamazepine), hormones (e.g., levothyroxine, ethinyl estradiol), and immunosuppressants (e.g., tacrolimus, sirolimus, cyclosporine) (Yu, 2011). A review performed by Li et al contains a more comprehensive list of drugs that could be considered NTI that also includes antimicrobials, oncology drugs, and opioids (Li et al, 2018). The majority of these potential NTI drugs are not classified as such by the FDA, which is partially due to the difficulty of characterizing the therapeutic index.…”