Predicting Pharmacokinetics of Drugs Using Artificial Intelligence Tools: A Systematic Review

BACKGROUND AND OBJECTIVE

Pharmacokinetic studies encompass the examination of the absorption, distribution, metabolism, and excretion of bioactive compounds. The pharmacokinetics of drugs exert a substantial influence on their efficacy and safety. Consequently, the investigation of pharmacokinetics holds great importance. However, laboratory-based assessment necessitates the use of numerous animals, various materials, and significant time. To mitigate these challenges, alternative methods such as artificial intelligence have emerged as a promising approach. This systematic review aims to review existing studies, focusing on the application of artificial intelligence tools in predicting the pharmacokinetics of drugs.

METHODS

A pre-prepared search strategy based on related keywords was used to search different databases (PubMed, Scopus, Web of Science). The process involved combining articles, eliminating duplicates, and screening articles based on their titles, abstracts, and full text. Articles were selected based on inclusion and exclusion criteria. Then, the quality of the included articles was assessed using an appraisal tool.

RESULTS

Ultimately, 23 relevant articles were included in this study. The clearance parameter received the highest level of investigation, followed by the  area under the concentration-time curve (AUC) parameter, in pharmacokinetic studies. Among the various models employed in the articles, Random Forest and eXtreme Gradient Boosting (XGBoost) emerged as the most commonly utilized ones. Generalized Linear Models and Elastic Nets (GLMnet) and Random Forest models showed the most performance in predicting clearance.

CONCLUSION

Overall, artificial intelligence tools offer a robust, rapid, and precise means of predicting various pharmacokinetic parameters based on a dataset containing information of patients or drugs.

Designing user-centered decision support systems for climate disasters: What information do communities and rescue responders need during floods?

Flooding events are the most common natural hazard globally, resulting in vast destruction and loss of life. An effective flood emergency response is necessary to lessen the negative impacts of flood disasters. However, disaster management and response efforts face a complex scenario. Simultaneously, regular citizens attempt to navigate the various sources of information being distributed and determine their best course of action. One thing is evident across all disaster scenarios: having accurate information and clear communication between citizens and rescue personnel is critical. This research aims to identify the diverse needs of two groups, rescue operators and citizens, during flood disaster events by investigating the sources and types of information they rely on and information that would improve their responses in the future. This information can improve the design and implementation of existing and future spatial decision support systems (SDSSs) during flooding events. This research identifies information characteristics crucial for rescue operators and everyday citizens' response and possible evacuation to flooding events by qualitatively coding survey responses from rescue responders and the public. The results show that including local input in SDSS development is crucial for improving higher-resolution flood risk quantification models. Doing so democratizes data collection and analysis, creates transparency and trust between people and governments, and leads to transformative solutions for the broader scientific community.

Scalable flood inundation mapping using deep convolutional networks and traffic signage

Floods are one of the most prevalent and costliest natural hazards globally. The safe transit of people and goods during a flood event requires fast and reliable access to flood depth information with spatial granularity comparable to the road network. In this research, we propose to use crowdsourced photos of submerged traffic signs for street-level flood depth estimation and mapping. To this end, a deep convolutional neural network (CNN) is utilized to detect traffic signs in user-contributed photos, followed by comparing the lengths of the visible part of detected sign poles before and after the flood event. A tilt correction approach is also designed and implemented to rectify potential inaccuracy in pole length estimation caused by tilted stop signs in floodwaters. The mean absolute error (MAE) achieved for pole length estimation in pre- and post-flood photos is 1.723 and 2.846 in., respectively, leading to an MAE of 4.710 in. for flood depth estimation. The presented approach provides people and first responders with a reliable and geographically scalable solution for estimating and communicating real-time flood depth data at their locations.

Application of SPRA Technology for Delivery of Erythropoietin: Stability Evaluation of Conjugated Erythropoietin with Adamantane and in SPRA Inclusion Complex

Background

As a widely used therapeutic protein, recombinant human erythropoietin (rhEPO) is currently one of the most effective biopharmaceuticals on the market for the treatment of anemia in patients with chronic renal disease. Increasing in vivo rhEPO half-life and its bioactivity is a significant challenge. It was hypothesized that the application of self-assembly PEGylation retaining activity, named supramolecular (SPRA) technology, could prolong the protein half-life without a significant loss of bioactivity.

Objectives

This study aimed to assess the stability of rhEPO during synthetic reactions, including the conjugation with adamantane and the formation of the SPRA complex. To do this, the secondary structure of the protein was also evaluated.

Methods

FTIR, ATR-FTIR, Far-UV-CD, and SDS-PAGE methods were employed. Thermal stability studies of SPRA-rhEPO complex and rhEPO were investigated at 37°C for ten days using a nanodrop spectrophotometer.

Results

The secondary structure of lyophilized rhEPO, AD-rhEPO, and rhEPO (pH 8) was compared to rhEPO. Results showed that the secondary structure of the protein was unaffected by lyophilization, pH change, and the formation of covalent bonds in conjugation reaction. SPRA-rhEPO complex was also stable for seven days in phosphate buffer (pH 7.4) at 37°C.

Conclusions

It was concluded that the stability of rhEPO could increase by complexation using SPRA technology.

IL6R haplotype rs4845625*T/rs4537545*C is a risk factor for simultaneously high CRP, LDL and ApoB levels

Interleukin 6 receptor (IL-6R), mediating IL-6's biological functions, plays an important role in different diseases such as diabetes, obesity and cardio-vascular diseases. In this study, we investigated the effects of two single nucleotide polymorphisms (SNPs), within the IL-6R loci, previously associated with C-reactive protein (CRP) and coronary heart diseases risk, and with controversial effects on lipids traits: SNP rs4845625 and SNP rs4537545. The results showed that both investigated SNPs were antagonistically related with CRP levels; the minor rs4845625*T allele was associated with increased CRP levels (P-value=0.011), while the minor rs4537545*T allele was associated with decreased CRP levels (P-value=0.009). Interestingly, the minor rs4845625*T allele was significantly associated with higher low-density lipoprotein cholesterol (LDL-C) and ApoB levels (P=0.007 and P=0.009 respectively). Haplotype analysis showed that the TC haplotype, having the minor rs4845625*T allele, was related simultaneously with increased levels of CRP, LDL-C and ApoB levels, thus could be considered as a risk factor. Our investigation detects for the first time an independent effect of rs4845625 on LDL-C and ApoB traits, explaining an important range of those traits variability (3.49 and 5.57% respectively). Our findings might be of high clinical significance in pharmacogenomics studies of tocilizumab for which IL-6R is target.

Frequency Evaluation of T6235C (m1) and A4889G (m2) Polymorphisms of CYP1A1 Gene in a Healthy Population from the west of Mazandaran Province, Iran

CYP1A1 is an important phase I xenobiotic metabolizing enzyme involved in the metabolism of numbers of toxins, endogenous hormones and drugs. Polymorphisms in this phase I gene can alter enzyme activity and induction, also are known to be associated with cancer susceptibility related to environmental toxins and hormone exposure. The present study was aimed to determine the frequencies of commonly known functional polymorphismsof CYP1A1 gene including CYP1A1 m1 (MspI), and CYP1A1 m2 (Ile-Val) in a healthy population from the west of Mazandaran province, Iran. A total of 200 unrelated healthy subjects from Mazandaran province, residing in Tonekabon city, coming for blood donating at Tonekabon Blood Transfusion Center were enrolled. Genomic DNA was extracted from peripheral blood lymphocytes of each subject. All subjects were genotyped for CYP1A1 m1 (T>C) and m2 (A>G) by polymerase chain reaction-restriction fragment length polymorphism method. The frequencies of the TT(wt/wt), TC(wt/mt) and CC(mt/mt) genotypes were as 65.5%, 32.0% and 2.5% respectively for m1 and frequencies of the AA(wt/wt), AG(wt/mt) and GG(mt/mt) genotypes were as 84.5%, 15% and 0.5% respectively for the m2. The frequencies of T and C alleles in the population were 81.5% and 18.5% respectively and the frequencies of A and G alleles were 92% and 8% respectively. Results of the present study might be important in understanding the distribution of CYP1A1 (m1) and CYP1A1 (m2) polymorphisms in Mazandaran province of Iran. Moreover, these results may determine the susceptibilities of individuals towards environmental procarcinogens that result in several cancers.

Does the genetic and familial background of males undertaking ICSI affect the outcome?

Purpose

To investigate whether the success rate of ICSI is (1) related to the etiology of infertility or (2) adversely affected by a family history of potential genetic disorders.

Methods

All men with an ICSI indication in our hospital between 1994 and 2005 were included in our cohort study. Data on the ICSI process, etiology of infertility, and family history were collected. ICSI success rates of infertility subgroups and a subgroup with a positive family history were compared to a group with unknown etiology and a negative family history.

Results

There was no significant difference in clinical pregnancy or delivery rates between the subgroups. Couples achieving a pregnancy underwent significantly more ICSI cycles compared to couples not achieving a pregnancy.

Conclusion

Our results suggest that the success rate of ICSI treatment is not related to the cause of infertility or a family history positive for potential genetic disorders.

Relation of circulating concentrations of chemokine receptor CCR5 ligands to C-peptide, proinsulin and HbA1c and disease progression in type 1 diabetes

Th1 related chemokines CCL3 and CCL5 and Th2 related CCL4 as ligands of the receptor CCR5 contribute to disease development in animal models of type 1 diabetes. In humans, no data are available addressing the role of these chemokines regarding disease progression and remission. We investigated longitudinally circulating concentrations of CCR5 ligands of 256 newly diagnosed patients with type 1 diabetes. CCR5 ligands were differentially associated with beta-cell function and clinical remission. CCL5 was decreased in remitters and positively associated with HbA1c suggestive of a Th1 associated progression of the disease. Likewise, CCL3 was negatively related to C-peptide and positively associated with the beta-cell stress marker proinsulin but increased in remitters. CCL4 associated with decreased beta-cell stress shown by negative association with proinsulin. Blockage of chemokines or antagonism of CCR5 by therapeutic agents such as maraviroc may provide a new therapeutic target to ameliorate disease progression in type 1 diabetes.

Myosin degradation fragments in skeletal muscle

Myosin heavy chain degradation fragments produced in vivo have been identified in chicken pectoralis muscle. The fragments were identified by electrophoresis of unfractionated extracts of chicken pectoralis muscle on sodium dodecyl sulfate/polyacrylamide gels followed by immunoblotting on nitrocellulose sheets. Monoclonal antibodies directed against the S2 and light meromyosin subfragments as well as type II myosin-specific polyclonal antibodies directed against the entire myosin heavy chain were used to characterize the fragments, which range in molecular weight from approximately 80,000 to 180,000. All fragments contain the extreme carboxy-terminal portion of the molecule and are distinct from the classical proteolytic fragments such as heavy and light meromyosin, S1, S2 or rod. These fragments appear to be produced in vivo by proteolytic cleavage of peptides from the amino-terminal (S1) end of the heavy chain while the myosin molecule is still embedded in the thick filament. Fragment concentrations are estimated to be approximately 5 to 10% of that of the intact myosin heavy chain. These fragments are not the result of artifactual damage to myosin, e.g. proteolysis or hydrodynamic shear. The techniques described in this paper provide a probe into the early stages of myosin and thick filament degradation in vivo.