Artificial Intelligence in Drug Identification and Validation: A Scoping Review.

The end-to-end process in the discovery of drugs involves therapeutic candidate identification, validation of identified targets, identification of hit compound series, lead identification and optimization, characterization, and formulation and development. The process is lengthy, expensive, tedious, and inefficient, with a large attrition rate for novel drug discovery. Today, the pharmaceutical industry is focused on improving the drug discovery process. Finding and selecting acceptable drug candidates effectively can significantly impact the price and profitability of new medications. Aside from the cost, there is a need to reduce the end-to-end process time, limiting the number of experiments at various stages. To achieve this, artificial intelligence (AI) has been utilized at various stages of drug discovery. The present study aims to identify the recent work that has developed AI-based models at various stages of drug discovery, identify the stages that need more concern, present the taxonomy of AI methods in drug discovery, and provide research opportunities. From January 2016 to September 1, 2023, the study identified all publications that were cited in the electronic databases including Scopus, NCBI PubMed, MEDLINE, Anthropology Plus, Embase, APA PsycInfo, SOCIndex, and CINAHL. Utilising a standardized form, data were extracted, and presented possible research prospects based on the analysis of the extracted data.

Esofagitis disecante supeEsofagitis disecante superficial: dos casos de una misma entidad poco frecuente / Esophagitis dissecans superficialis: two cases of the same rare entity

La esofagitis disecante superficial (EDS) es una entidad infrecuente que se caracteriza endoscópicamente por el desprendimiento de las capas superficiales del epitelio esofágico e, histológicamente, por el aspecto bitonal del epitelio escamoso esofágico secundario a la necrosis de los estratos más superficiales. La etiología es desconocida, aunque se ha asociado con la ingesta de determinados fármacos, enfermedades autoinmunes, estasis esofágica y procedimientos endoscópicos. Presentamos dos casos: uno de ellos acontece en una mujer tras un episodio de disfagia abrupta y el segundo en un varón con comorbilidades y clínica de dolor epigástrico. La EDS es una patología que hay que considerar en su adecuado contexto clínico y endoscópico, ya que su curso es autolimitado en comparación con otras entidades de evolución tórpida o que precisan un tratamiento específico. (AU)

Esophagitis dissecans superficialis (EDS) is a rare disease characterized by sloughing of the superficial esophageal mucosa and, histologically, by the bitonal appearance of the squamous epithelium secondary to necrosis of the most superficial layers. Etiology is uncertain, however, it has been associated with some medications, autoimmune diseases, esophageal stasis and endoscopic procedures. Here, two cases are presented, one of them which appeared in a woman after an episode of dysphagia and another one which occurred to a man with comorbidities and epigastric pain. This entity should be considered due to its self-limiting clinical course, compared to other entities with a more torpid evolution or that require more specific treatment. (AU)

Impact of Obesity on Hepatic Drug Clearance: What are the Influential Variables?

Drug clearance in obese subjects varies widely among different drugs and across subjects with different severity of obesity. This study investigates correlations between plasma clearance (CLp) and drug- and patient-related characteristics in obese subjects, and evaluates the systematic accuracy of common weight-based dosing methods. A physiologically-based pharmacokinetic (PBPK) modeling approach that uses recent information on obesity-related changes in physiology was used to simulate CLp for a normal-weight subject (body mass index [BMI] = 20) and subjects with various severities of obesity (BMI 25-60) for hypothetical hepatically cleared drugs with a wide range of properties. Influential variables for CLp change were investigated. For each drug and obese subject, the exponent that yields perfect allometric scaling of CLp from normal-weight subjects was assessed. Among all variables, BMI and relative changes in enzyme activity resulting from obesity proved highly correlated with obesity-related CLp changes. Drugs bound to α1-acid glycoprotein (AAG) had lower CLp changes compared to drugs bound to human serum albumin (HSA). Lower extraction ratios (ER) corresponded to higher CLp changes compared to higher ER. The allometric exponent for perfect scaling ranged from -3.84 to 3.34 illustrating that none of the scaling methods performed well in all situations. While all three dosing methods are generally systematically accurate for drugs with unchanged or up to 50% increased enzyme activity in subjects with a BMI below 30 kg/m2, in any of the other cases, information on the different drug properties and severity of obesity is required to select an appropriate dosing method for individuals with obesity.

NMR Longitudinal Rotating Frame Relaxation Time (T1ρ) with a Weak Spin Locking Field as an Approach to Characterize Solid-State Active Pharmaceutical Ingredients: Proof of Concept.

Nuclear magnetic resonance (NMR) longitudinal rotating frame relaxation time (T1ρ), rarely used in low-field NMR, can be more effective than conventional T1 and T2 relaxation times to differentiate polymorphic forms of solid pharmaceuticals. This could be attributed to T1ρ sensibility to structural and molecular dynamics that can be enhanced by changing the strength of the oscillating magnetic field (B1) of spinlock pulses. Here, we compared the capacity of T1, T2, and T1ρ to differentiate inactive (A) and active (C) crystalline forms of the World Health Organization essential drug Mebendazole. The results showed that T1 and T2 values of both forms were statistically identical at 0.47 T. Conversely, T1ρ of both forms measured with weak spinlock B1 fields, ranging from 0.08 to 0.80 mT were statistically different in the same spectrometer. The T1ρ also has the limit of detection to detect the presence of at least 10% of inactive A form in the active C form. Therefore, T1ρ, measured with weak spinlock B1 fields can be an effective, streamlined, and complementary approach for characterizing not only solid active pharmaceutical ingredients but other solid-state materials as well.

Advances in Nanotechnology for Enhancing the Solubility and Bioavailability of Poorly Soluble Drugs.

This manuscript offers a comprehensive overview of nanotechnology's impact on the solubility and bioavailability of poorly soluble drugs, with a focus on BCS Class II and IV drugs. We explore various nanoscale drug delivery systems (NDDSs), including lipid-based, polymer-based, nanoemulsions, nanogels, and inorganic carriers. These systems offer improved drug efficacy, targeting, and reduced side effects. Emphasizing the crucial role of nanoparticle size and surface modifications, the review discusses the advancements in NDDSs for enhanced therapeutic outcomes. Challenges such as production cost and safety are acknowledged, yet the potential of NDDSs in transforming drug delivery methods is highlighted. This contribution underscores the importance of nanotechnology in pharmaceutical engineering, suggesting it as a significant advancement for medical applications and patient care.

In-depth Mechanism, Challenges, and Opportunities of Delivering Therapeutics in Brain Using Intranasal Route.

Central nervous system-related disorders have become a continuing threat to human life and the current statistic indicates an increasing trend of such disorders worldwide. The primary therapeutic challenge, despite the availability of therapies for these disorders, is to sustain the drug's effective concentration in the brain while limiting its accumulation in non-targeted areas. This is attributed to the presence of the blood-brain barrier and first-pass metabolism which limits the transportation of drugs to the brain irrespective of popular and conventional routes of drug administration. Therefore, there is a demand to practice alternative routes for predictable drug delivery using advanced drug delivery carriers to overcome the said obstacles. Recent research attracted attention to intranasal-to-brain drug delivery for promising targeting therapeutics in the brain. This review emphasizes the mechanisms to deliver therapeutics via different pathways for nose-to-brain drug delivery with recent advancements in delivery and formulation aspects. Concurrently, for the benefit of future studies, the difficulties in administering medications by intranasal pathway have also been highlighted.

A culture-independent nucleic acid diagnostics method for use in the detection and quantification of Burkholderia cepacia complex contamination in aqueous finished pharmaceutical products.

The Burkholderia cepacia complex (Bcc) is the number one bacterial complex associated with contaminated Finished Pharmaceutical Products (FPPs). This has resulted in multiple healthcare related infection morbidity and mortality events in conjunction with significant FPP recalls globally. Current microbiological quality control of FPPs before release for distribution depends on lengthy, laborious, non-specific, traditional culture-dependent methods which lack sensitivity. Here, we present the development of a culture-independent Bcc Nucleic Acid Diagnostic (NAD) method for detecting Bcc contaminants associated with Over-The-Counter aqueous FPPs. The culture-independent Bcc NAD method was validated to be specific for detecting Bcc at different contamination levels from spiked aqueous FPPs. The accuracy in Bcc quantitative measurements was achieved by the high degree of Bcc recovery from aqueous FPPs. The low variation observed between several repeated Bcc quantitative measurements further demonstrated the precision of Bcc quantification in FPPs. The robustness of the culture-independent Bcc NAD method was determined when its accuracy and precision were not significantly affected during testing of numerous aqueous FPP types with different ingredient matrices, antimicrobial preservative components and routes of administration. The culture-independent Bcc NAD method showed an ability to detect Bcc in spiked aqueous FPPs at a concentration of 20 Bcc CFU/mL. The rapid (≤ 4 hours from sample in to result out), robust, culture-independent Bcc NAD method presented provides rigorous test specificity, accuracy, precision, and sensitivity. This method, validated with equivalence to ISO standard ISO/TS 12869:2019, can be a valuable diagnostic tool in supporting microbiological quality control procedures to aid the pharmaceutical industry in preventing Bcc contamination of aqueous FPPs for consumer safety.

Premix technologies for drug delivery: manufacturing, applications, and opportunities in regulatory filing.

Active pharmaceutical ingredients (APIs) and excipients can be carefully combined in premix-based materials before being added to dosage forms, providing a flexible platform for the improvement of drug bioavailability, stability, and patient compliance. This is a promising and transformative approach in novel and generic product development, offering both the potential to overcome challenges in the delivery of complex APIs and viable solutions for bypassing patent hurdles in generic product filing. We discuss the different types of premixes; manufacturing technologies such as spray drying, hot melt extrusion, wet granulation, co-crystal, co-milling, co-precipitation; regulatory filing opportunities; and major bottlenecks in the use of premix materials in different aspects of pharmaceutical product development.

Vaginal drug delivery system: A promising route of drug administration for local and systemic diseases.

Scientists around the globe have done cutting-edge research to facilitate the delivery of poorly absorbed drugs via various routes of administration and different delivery systems. The vaginal route of administration has emerged as a promising mode of drug delivery, attributed to its anatomy and physiology. Novel drug delivery systems overcome the demerits of conventional systems via nanobiotechnology. This review will focus on the disorders associated with women that are currently targeted by vaginal drug delivery systems. In addition, it will provide insights into innovations in drug formulations for the general benefit of women.

MolLoG: A Molecular Level Interpretability Model Bridging Local to Global for Predicting Drug Target Interactions.

Developing new pharmaceuticals is a costly and time-consuming endeavor fraught with significant safety risks. A critical aspect of drug research and disease therapy is discerning the existence of interactions between drugs and proteins. The evolution of deep learning (DL) in computer science has been remarkably aided in this regard in recent years. Yet, two challenges remain: (i) balancing the extraction of profound, local cohesive characteristics while warding off gradient disappearance and (ii) globally representing and understanding the interactions between the drug and target local attributes, which is vital for delivering molecular level insights indispensable to drug development. In response to these challenges, we propose a DL network structure, MolLoG, primarily comprising two modules: local feature encoders (LFE) and global interactive learning (GIL). Within the LFE module, graph convolution networks and leap blocks capture the local features of drug and protein molecules, respectively. The GIL module enables the efficient amalgamation of feature information, facilitating the global learning of feature structural semantics and procuring multihead attention weights for abstract features stemming from two modalities, providing biologically pertinent explanations for black-box results. Finally, predictive outcomes are achieved by decoding the unified representation via a multilayer perceptron. Our experimental analysis reveals that MolLoG outperforms several cutting-edge baselines across four data sets, delivering superior overall performance and providing satisfactory results when elucidating various facets of drug-target interaction predictions.

Pharmaceutically active compounds removal from aqueous solutions by MIL-101(Cr)-NH2: A molecular dynamics study.

Discharging pharmaceutically active drugs into water and wastewater has become a significant environmental threat. Traditional methods are unable to effectively remove these compounds from wastewater, so it is necessary to search for more effective methods. This study investigates the potential of MIL-101(Cr)-NH2 as a preferable and more effective adsorbent for the adsorption and removal of pharmaceutically active compounds from aqueous solutions. By utilizing its large porosity, high specific surface area, and high stability, the structural and transport properties of three pharmaceutically active compounds naproxen (NAP), diclofenac (DIC) and sulfamethoxazole (SMX)) studied using molecular dynamics simulation. The results indicate that the MIL-101(Cr)-NH2 adsorbent is suitable for removing drug molecules from aqueous solutions, with maximum adsorption capacities of 697.75 mg/g for naproxen, 704.99 mg/g for diclofenac, and 725.51 mg/g for sulfamethoxazole.

The VERA software: Implementation of the acute fish toxicity endpoint and its application to pharmaceutical compounds.

The Virtual Extensive Read-Across software (VERA) is a new tool for read-across using a global similarity score, molecular groups, and structural alerts to find clusters of similar substances; these clusters are then used to identify suitable similar substances and make an assessment for the target substance. A beta version of VERA GUI is free and available at vegahub.eu; the source code of the VERA algorithm is available on GitHub. In the past we described its use to assess carcinogenicity, a classification endpoint. The aim here is to extend the automated read-across approach to assess continuous endpoints as well. We addressed acute fish toxicity. VERA evaluation on the acute fish toxicity endpoint was done on a dataset containing general substances (pesticides, industrial products, biocides, etc.), obtaining an overall R2 of 0.68. We employed the VERA algorithm also on active pharmaceutical ingredients (APIs). We included a portion of the APIs in the training dataset to predict APIs, successfully achieving an overall R2 of 0.63. VERA evaluates the assessment's reliability, and we reached an R2 of 0.78 and Root Mean Square Error (RMSE) of 0.44 for predictions with high reliability.

Unveiling the potential of machine learning in cost-effective degradation of pharmaceutically active compounds: A stirred photo-reactor study.

In this study, neural networks and support vector regression (SVR) were employed to predict the degradation over three pharmaceutically active compounds (PhACs): Ibuprofen (IBP), diclofenac (DCF), and caffeine (CAF) within a stirred reactor featuring a flotation cell with two non-concentric ultraviolet lamps. A total of 438 datapoints were collected from published works and distributed into 70% training and 30% test datasets while cross-validation was utilized to assess the training reliability. The models incorporated 15 input variables concerning reaction kinetics, molecular properties, hydrodynamic information, presence of radiation, and catalytic properties. It was observed that the Support Vector Regression (SVR) presented a poor performance as the ε hyperparameter ignored large error over low concentration levels. Meanwhile, the Artificial Neural Networks (ANN) model was able to provide rough estimations on the expected degradation of the pollutants without requiring information regarding reaction rate constants. The multi-objective optimization analysis suggested a leading role due to ozone kinetic for a rapid degradation of the contaminants and most of the results required intensification with hydrogen peroxide and Fenton process. Although both models were affected by accuracy limitations, this work provided a lightweight model to evaluate different Advanced Oxidation Processes (AOPs) by providing general information regarding the process operational conditions as well as know molecular and catalytic properties.

Re-discover the value of protein binding assessments in hepatic and renal impairment studies and its contributions in drug labels and dose decisions.

One of the key pharmacokinetic properties of most small molecule drugs is their ability to bind to serum proteins. Unbound or free drug is responsible for pharmacological activity while the balance between free and bound drug can impact drug distribution, elimination, and other safety parameters. In the hepatic impairment (HI) and renal impairment (RI) clinical studies, unbound drug concentration is often assessed; however, the relevance and impact of the protein binding (PB) results is largely limited. We analyzed published clinical safety and pharmacokinetic studies in subjects with HI or RI with PB assessment up to October 2022 and summarized the contribution of PB results on their label dose recommendations. Among drugs with HI publication, 32% (17/53) associated product labels include PB results in HI section. Of these, the majority (9/17, 53%) recommend dose adjustments consistent with observed PB change. Among drugs with RI publication, 27% (12/44) of associated product labels include PB results in RI section with the majority (7/12, 58%) recommending no dose adjustment, consistent with the reported absence of PB change. PB results were found to be consistent with a tailored dose recommendation in 53% and 58% of the approved labels for HI and RI section, respectively. We further discussed the interpretation challenges of PB results, explored treatment decision factors including total drug concentration, exposure-response relationships, and safety considerations in these case examples. Collectively, comprehending the alterations in free drug levels in HI and RI informs treatment decision through a risk-based approach.

Solid-phase microextraction - a future technique in pharmacology and coating trends.

Traditional sample preparation techniques based on liquid-liquid extraction (LLE) or solid-phase extraction (SPE) often suffer from a major error due to the matrix effects caused by significant co-extraction of matrix components. The implementation of a modern extraction technique such as solid-phase microextraction (SPME) was aimed at reducing analysis time and the use of organic solvents, as well as eliminating pre-analytical and analytical errors. Solid-phase microextraction (SPME) is an innovative technique for extracting low molecular weight compounds (less than 1500 Da) from highly complex matrices, including biological matrices. It has a wide range of applications in various types of analysis including pharmaceutical, clinical, metabolomics and proteomics. SPME has a number of advantages over other extraction techniques. Among the most important are low environmental impact, the ability to sample and preconcentrate analytes in one step, simple automation, and the ability to extract multiple analytes simultaneously. It is expected to become, in the future, another method for cell cycle research. Numerous available literature sources prove that solid-phase microextraction can be a future technique in many scientific fields, including pharmaceutical sciences. This paper provides a literature review of trends in SPME coatings and pharmacological applications.

Understanding the impact of binding free energy and kinetics calculations in modern drug discovery.

INTRODUCTION: For rational drug design, it is crucial to understand the receptor-drug binding processes and mechanisms. A new era for the use of computer simulations in predicting drug-receptor interactions at an atomic level has begun with remarkable advances in supercomputing and methodological breakthroughs. AREAS COVERED: End-point free energy calculation methods such as Molecular Mechanics/Poisson Boltzmann Surface Area (MM/PBSA) or Molecular-Mechanics/Generalized Born Surface Area (MM/GBSA), free energy perturbation (FEP), and thermodynamic integration (TI) are commonly used for binding free energy calculations in drug discovery. In addition, kinetic dissociation and association rate constants (koff and kon) play critical roles in the function of drugs. Nowadays, Molecular Dynamics (MD) and enhanced sampling simulations are increasingly being used in drug discovery. Here, the authors provide a review of the computational techniques used in drug binding free energy and kinetics calculations. EXPERT OPINION: The applications of computational methods in drug discovery and design are expanding, thanks to improved predictions of the binding free energy and kinetic rates of drug molecules. Recent microsecond-timescale enhanced sampling simulations have made it possible to accurately capture repetitive ligand binding and dissociation, facilitating more efficient and accurate calculations of ligand binding free energy and kinetics.

Another string to your bow: machine learning prediction of the pharmacokinetic properties of small molecules.

INTRODUCTION: Prediction of pharmacokinetic (PK) properties is crucial for drug discovery and development. Machine-learning (ML) models, which use statistical pattern recognition to learn correlations between input features (such as chemical structures) and target variables (such as PK parameters), are being increasingly used for this purpose. To embed ML models for PK prediction into workflows and to guide future development, a solid understanding of their applicability, advantages, limitations, and synergies with other approaches is necessary. AREAS COVERED: This narrative review discusses the design and application of ML models to predict PK parameters of small molecules, especially in light of established approaches including in vitro-in vivo extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) models. The authors illustrate scenarios in which the three approaches are used and emphasize how they enhance and complement each other. In particular, they highlight achievements, the state of the art and potentials of applying machine learning for PK prediction through a comphrehensive literature review. EXPERT OPINION: ML models, when carefully crafted, regularly updated, and appropriately used, empower users to prioritize molecules with favorable PK properties. Informed practitioners can leverage these models to improve the efficiency of drug discovery and development process.

Emerging opportunities of using large language models for translation between drug molecules and indications.

A drug molecule is a substance that changes an organism's mental or physical state. Every approved drug has an indication, which refers to the therapeutic use of that drug for treating a particular medical condition. While the Large Language Model (LLM), a generative Artificial Intelligence (AI) technique, has recently demonstrated effectiveness in translating between molecules and their textual descriptions, there remains a gap in research regarding their application in facilitating the translation between drug molecules and indications (which describes the disease, condition or symptoms for which the drug is used), or vice versa. Addressing this challenge could greatly benefit the drug discovery process. The capability of generating a drug from a given indication would allow for the discovery of drugs targeting specific diseases or targets and ultimately provide patients with better treatments. In this paper, we first propose a new task, the translation between drug molecules and corresponding indications, and then test existing LLMs on this new task. Specifically, we consider nine variations of the T5 LLM and evaluate them on two public datasets obtained from ChEMBL and DrugBank. Our experiments show the early results of using LLMs for this task and provide a perspective on the state-of-the-art. We also emphasize the current limitations and discuss future work that has the potential to improve the performance on this task. The creation of molecules from indications, or vice versa, will allow for more efficient targeting of diseases and significantly reduce the cost of drug discovery, with the potential to revolutionize the field of drug discovery in the era of generative AI.

Unused, expired pharmaceuticals and their disposal practices among the general public in Burdur-Türkiye: a cross-sectional study.

BACKGROUND: Unused pharmaceuticals are currently a public health problem. This study aimed to identify unused pharmaceuticals, research practices about the disposal methods, classify the medicines according to Anatomical Therapeutic Chemical codes (ATC) and, to determine the number of unused medicines. METHODS: The study was designed as a cross-sectional study. Data were collected between April and August 2023 in Burdur-Türkiye by non-probability sampling technique (convenience method). Pharmaceuticals were classified according to ATC. Statistical Package for Social Science SPSS (V.24) package program was used for data analysis. RESULTS: A total of 1120 people, 1005 in the first sample group and 115 in the second sample group, participated in the study. Findings of first sample group: A total of 4097 boxes of unused pharmaceuticals (4.7 ± 4.3 boxes/per capita) were detected. It was found that pharmaceuticals were stored in areas such as kitchens (59.1%) and refrigerators (38.6%), the reason for keeping them was reuse (41%), and the disposal practice was household garbage (81%). Paracetamol (648 boxes), Other cold preparation (303 boxes), Dexketoprofen (239 boxes), Diclofenac (218 boxes), Amoxicillin and beta-lactamase inhibitor (190 boxes) were found to be the most frequently unused pharmaceuticals. Using the unused medicines at home without consulting a physician was 94.1% (self-medication). Findings of second sample group: Of the 6189 dosage forms in 265 boxes pharmaceutical, 3132(50.6%) dosage forms were used and 3057(49.4%) were found to be unused. CONCLUSION: There is a significant amount and number of unused medicines in households, and self-medication is common. Medicines are not properly disposed of and some of them expire. Public information is needed. A "drug take-back system" for unused medicines can be useful in solving this problem.