Figure 2 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
The workflow of structure-based drug design (SBDD) and ligand-based drug design (LBDD). For SBDD, it starts with target identification. Then, binding site of the target requires identifying and compound library needs to be prepared. Next, dock each compound from the library into the identified binding site evaluate the score. In molecular docking, MD simulations can be utilized to obtain more flexible target and rescore for the docking process. Additionally, MD simulations can be applied to lead optimization through ligand-target interactions. Through these steps, leads are obtained primarily. For LBDD, it starts with known ligands with bioactivity. Then, extracting the chemical features of these ligands and build pharmacophore or QSAR model. Next, according to the information of known ligands (e.g., ligand similarity), ligand-based virtual screening is performed in the compound library and leads are screened. These leads are further optimized in wet and dry lab.
Source publication
Traditional drug design requires a great amount of research time and developmental expense. Booming computational approaches, including computational biology, computer-aided drug design, and artificial intelligence, have the potential to expedite the efficiency of drug discovery by minimizing the time and financial cost. In recent years, computatio...
Contexts in source publication
Context 1
... important categories of CADD, structure-based drug design (SBDD) and ligand-based drug design (LBDD), are highlighted in this review. These two categories have been widely used in lead discovery during drug discovery ( Figure 2). SBDD depends on the three-dimensional structure of the target and active sites to determine ligand-target interactions [153]. ...
Context 2
... important categories of CADD, structure-based drug design (SBDD) and ligand-based drug design (LBDD), are highlighted in this review. These two categories have been widely used in lead discovery during drug discovery ( Figure 2). SBDD depends on the three-dimensional structure of the target and active sites to determine ligand-target interactions [153]. ...
Context 3
... SBDD, some approved drugs, such as Imatinib (an abltyrosine kinase inhibitor) [154], Indinavir (Crixivan, the inhibitor of HIV-1 protease) [155], Nilotinib (Tasigna, a selective tyrosine kinase receptor inhibitor used in the treatment of chronic myelogenous leukemia) [156], and Lifitegrast (the LFA-1 antagonist that blocks binding of ICAM-1 to LFA-1) [157], were discovered. SBDD mainly includes target preparation, binding site identification, compound library preparation, molecular docking and scoring, and MD simulations (Figure 2). ...
Citations
... AMR poses a global health crisis, stemming from the rapid increase in multidrugresistant bacteria and the prolonged development of new antimicrobials [36][37][38]. In response, AI, specifically machine learning, is considered a potential solution to impede the spread of AMR [39][40][41]. AI offers effective strategies for predicting and identifying AMR in bacteria. Furthermore, the synergy between machine learning algorithms and laboratory testing can accelerate the discovery of novel antimicrobials [42,43]. ...
It is crucial to discover novel antimicrobial drugs to combat resistance. This study investigated the antibacterial properties of halicin (SU3327), an AI-identified anti-diabetic drug, against 13 kinds of common clinical pathogens of animal origin, including multidrug-resistant strains. Employing minimum inhibitory concentration (MIC) and minimum bactericidal concentration (MBC) assessments, halicin demonstrated a broad-spectrum antibacterial effect. Time-killing assays revealed its concentration-dependent bactericidal activity against Escherichia coli ATCC 25922 (E. coli ATCC 25922), Staphylococcus aureus ATCC 29213 (S. aureus ATCC 29213), and Actinobacillus pleuropneumoniae S6 (APP S6) after 4 h of treatment at concentrations above the MIC. Halicin exhibited longer post-antibiotic effects (PAEs) and sub-MIC effects (PA-SMEs) for E. coli 25922, S. aureus 29213, and APP S6 compared to ceftiofur and ciprofloxacin, the commonly used veterinary antimicrobial agents, indicating sustained antibacterial action. Additionally, the results of consecutive passaging experiments over 40 d at sub-inhibitory concentrations showed that bacteria exhibited difficulty in developing resistance to halicin. Toxicology studies confirmed that halicin exhibited low acute toxicity, being non-mutagenic, non-reproductive-toxic, and non-genotoxic. Blood biochemical results suggested that halicin has no significant impact on hematological parameters, liver function, and kidney function. Furthermore, halicin effectively treated respiratory A. pleuropneumoniae infections in murine models. These results underscore the potential of halicin as a new antibacterial agent with applications against clinically relevant pathogens in veterinary medicine.
... Recent years have seen a rise in the development of domain-specific XAI techniques tailored to healthcare and computational biology applications [5,10]. These techniques aim to address the need for accurate and interpretable models, the integration of data from multiple sources, and the management and analysis of large datasets [5]. ...
... The future of healthcare and research is poised to be significantly influenced by advancements in AI, computational biology, and their integration into various clinical practice and research arenas. These advancements are expected to revolutionize drug discovery, disease diagnosis, treatment recommendations, and patient engagement [10,[103][104][105][106][107]. ...
... One of the most promising areas of exploration is the application of AI and computational biology in drug discovery. AI can transform large amounts of aggregated data into usable knowledge by fielding the complex relationship between input and output variables for high-dimensional data, i.e., potential chemical compounds and the range of properties or biological activities for consideration, an ability which can expedite the process of drug discovery and optimization [10,104,107,108]. For instance, the reinforcement learning for structural evolution (ReLeaSE) system, implemented at the University of North Carolina, demonstrates the ability to design new, patentable chemical entities with specific biological activities and optimal safety profiles, potentially shortening the time required to bring a new drug candidate to clinical trials [108]. ...
As artificial intelligence (AI) integrates within the intersecting domains of healthcare and computational biology, developing interpretable models tailored to medical contexts is met with significant challenges. Explainable AI (XAI) is vital for fostering trust and enabling effective use of AI in healthcare, particularly in image-based specialties such as pathology and radiology where adjunctive AI solutions for diagnostic image analysis are increasingly utilized. Overcoming these challenges necessitates interdisciplinary collaboration, essential for advancing XAI to enhance patient care. This commentary underscores the critical role of interdisciplinary conferences in promoting the necessary cross-disciplinary exchange for XAI innovation. A literature review was conducted to identify key challenges, best practices, and case studies related to interdisciplinary collaboration for XAI in healthcare. The distinctive contributions of specialized conferences in fostering dialogue, driving innovation, and influencing research directions were scrutinized. Best practices and recommendations for fostering collaboration, organizing conferences, and achieving targeted XAI solutions were adapted from the literature. By enabling crucial collaborative junctures that drive XAI progress, interdisciplinary conferences integrate diverse insights to produce new ideas, identify knowledge gaps, crystallize solutions, and spur long-term partnerships that generate high-impact research. Thoughtful structuring of these events, such as including sessions focused on theoretical foundations, real-world applications, and standardized evaluation, along with ample networking opportunities, is key to directing varied expertise toward overcoming core challenges. Successful collaborations depend on building mutual understanding and respect, clear communication, defined roles, and a shared commitment to the ethical development of robust, interpretable models. Specialized conferences are essential to shape the future of explainable AI and computational biology, contributing to improved patient outcomes and healthcare innovations. Recognizing the catalytic power of this collaborative model is key to accelerating the innovation and implementation of interpretable AI in medicine.
... Thus, physics-based refinement, like molecular dynamics (MD) simulations can help to fix the problems of structures generated by deep learning or other knowledge-based methods [57][58][59]. There have been several attempts to improve the quality of AF2 and AFM2 models using MD simulations [57,58] or applying their own recycling process when the models are used as custom template inputs [60]. ...
Histones are keys to many epigenetic events and their complexes have therapeutic and diagnostic importance. The determination of the structures of histone complexes is fundamental in the design of new drugs. Computational molecular docking is widely used for the prediction of target-ligand complexes. Large, linear peptides like the tail regions of histones are challenging ligands for docking due to their large conformational flexibility, extensive hydration, and weak interactions with the shallow binding pockets of their reader proteins. Thus, fast docking methods often fail to produce complex structures of such peptide ligands at a level appropriate for drug design. To answer this challenge, and improve the structural quality of the docked complexes, post-docking refinement has been applied using various molecular dynamics (MD) approaches. However, a final consensus has not been reached on the desired MD refinement protocol. In the present study, MD refinement strategies were systematically explored on a set of problematic complexes of histone peptide ligands with relatively large errors in their docked geometries. Six protocols were compared that differ in their MD simulation parameters. In all cases, pre-MD hydration of the complex interface regions was applied to avoid the unwanted presence of empty cavities. The best-performing protocol achieved a median of 32 % improvement over the docked structures in terms of the change of root mean squared deviations from the experimental references. The influence of structural factors and explicit hydration on the performance of post-docking MD refinements was also discussed to help their implementation in future methods and applications.
... 35 In our sample, 45.87% of participants reported that some specialties would be replaced by artificial intelligence. These findings corroborate the study conducted by Sit et al (2020), which found that nearly half of the medical students believed that certain specialties would be replaced by AI. 23 According to Zhang et al, healthcare professionals believed that AI would eventually replace humans in some tasks and these professionals were worried about losing their job due to AI. 36 Another study found that implementing artificial intelligence in healthcare could reduce the workforce in medical specialties. 37 This study also sheds light on the understanding of artificial intelligence among Saudi undergraduate medical students, which is an important aspect in considering the impact of artificial intelligence on the healthcare sector. ...
Purpose
Artificial Intelligence is drastically used nowadays in healthcare, but little is known about the attitude and perception of medical students towards AI in Saudi Arabia. This study aimed to explore undergraduate medical student’s views on AI, assessed their understanding of AI, and the level of confidence of using basic AI tools in the future.
Methods
This cross-sectional study invited 303 medical undergraduate students to complete an anonymous electronic survey, which consists of questions related to attitude, understanding and confidence of using basic AI tools. We examined the statistical association between the categorical variables by using Chi-square test.
Results
The results of the study indicate that eighty-seven percent of participants believed that AI will play significant role in healthcare. Thirty-eight percent respondents reported that they have an understanding of the basic computational principle of AI. 71.29% respondents agreed that teaching in AI would be favorable for their career. More than half of the participants were confident in using basic AI tools in the future, Male students (p = 0.00), 26–30 years old participants (p = 0.03), intern students (p = 0.00), and Imam Abdulrahman Bin Faisal University medical students (p = 0.04) had positive attitude of artificial intelligence. Male participants (p = 0.02), and intern students (p = 0.00) had the highest proportion of confidence in using basic healthcare AI tool. Nearly 14% students received training on AI. Participants who received training on AI reported better understanding of AI (p = 0.03), develops positive attitude towards teaching in AI (p = 0.05), more confidence in using basic healthcare AI tools (p = 0.05).
Conclusion
Saudi medical undergraduate students understand the significance of AI and demonstrated a positive attitude towards AI. Medical students training on AI should be expanded and improved to avoid threats for seeking jobs by adapting artificial intelligence.
... A variety of data sources, including scientific publications, clinical trials, and chemical databases, can be analysed using AI algorithms to identify prospective drug targets and predict the effectiveness and safety of novel compounds. Using AI-based algorithms to conduct computational chemistry enables the process of finding new drugs to be greatly accelerated, through anticipating the characteristics of micro molecules, such as their solubility, stability, and bioactivity [43]. Virtual screening is a different area where AI is being used in the drug discovery process. ...
This review provides a comprehensive examination of the integration of Artificial Intelligence (AI) into healthcare, focusing on its transformative implications and challenges. Utilising a systematic search strategy across electronic databases such as PubMed, Scopus, Embase, and ScienceDirect, relevant peer-reviewed articles published in English between January 2010 till date were identified. Findings reveal AI's significant impact on healthcare delivery, including its role in enhancing diagnostic precision, enabling treatment personalisation, facilitating predictive analytics, automating tasks, and driving robotics. AI algorithms demonstrate high accuracy in analysing medical images for disease diagnosis and enable the creation of tailored treatment plans based on patient data analysis. Predictive analytics identify high-risk patients for proactive interventions, while AI-powered tools streamline workflows, improving efficiency and patient experience. Additionally, AI-driven robotics automate tasks and enhance care delivery, particularly in rehabilitation and surgery. However, challenges such as data quality, interpretability, bias, and regulatory frameworks must be addressed for responsible AI implementation. Recommendations emphasise the need for robust ethical and legal frameworks, human-AI collaboration, safety validation, education, and comprehensive regulation to ensure the ethical and effective integration of AI in healthcare. This review provides valuable insights into AI's transformative potential in healthcare while advocating for responsible implementation to ensure patient safety and efficacy.
... Overall, this process from initial research to market release reflects the rigorous nature and substantial financial commitment of drug development in the pharmaceutical sector. [2] Generative AI significantly impacts each stage of the drug discovery process-from initial research to post-market surveillance, enhancing efficiency and effectiveness. ...
The landscape of drug discovery is experiencing a substantial transformation driven by the integration of Generative Artificial Intelligence (AI). This shift promises a future where the design, optimization, and evaluation of novel pharmaceutical compounds are significantly accelerated, diverging from the time-intensive and financially taxing traditional methods reliant on empirical molecular screening. Generative AI leverages advanced computational models to predict the biological effects and pharmacokinetic properties of novel entities, enhancing the precision of the drug discovery process. This paper discusses the impact of Generative AI across the various stages of drug discovery, from target identification to post-market surveillance, highlighting the profound economic implications within the pharmaceutical sector. We provide a blueprint for how this technology can reshape the identification and development of new pharmaceutical compounds, including molecule generation, lead optimization, and biomarker discovery, and how these capabilities can lead to more personalized medicine. The paper also addresses the challenges faced by Generative AI, such as the representation of multi-modal biological data, the risk of clinical bias and stereotyping, and the difficulties navigating proprietary and fragmented data landscapes. These issues, alongside the shift in regulatory and data collection practices, underscore the nuanced complexities of fully harnessing Generative AI's power in the realm of biomedicine.
... Standard or quantum mechanics molecular simulations can provide data and insights into the understudied conformational changes of binding site due to acquired mutations, 9 stability and conformational changes of drug-protein complexes, and aid the AI-enabled design of next-generation optimized inhibitors. 21 To understand resistance arising from the changes in the protein, AI can integrate structural modelling, docking, and molecular dynamics simulation with pharmacophore modelling; 13,22,23 strategies that can lead to novel targeted therapies against resistance-causing mutations and improved treatment outcomes. This powerful combination enables the evaluation of drugprotein interactions and provides crucial insights into the binding modes upon treatment-acquired mutations. ...
... In summary, AI can serve as a bridge, facilitating interdisciplinary research by integrating expertise from medicinal chemistry, molecular and computational biology, bioinformatics, and pharmacology. 22,23 The synergy of these fields, combined with AI-driven analyses, allows for a comprehensive understanding of resistance mechanisms and the development of effective therapeutic strategies and translation to the clinic. 16 The collaborative efforts between AI, other computational, and experimental research are crucial for translating these discoveries into clinical applications and advancing personalized medicine approaches for patients in need. ...
In this Opinion article, we confront the role of artificial intelligence (AI) in targeting and understanding resistance to targeted therapy using the most frequently mutated oncoprotein family in human cancer, rat sarcoma virus guanosine triphosphate hydrolases (RAS GTPases), here Kirsten RAS (KRAS), as an example. Aberrant regulation of the active GTP-bound state of KRAS is associated with tumourigenesis, aggressive disease, and poor prognosis. KRAS mutations (eg, G12C, G12D, G12V, G13D, inter al.) are drivers of numerous cancer types, including non-small cell lung, colorectal, and pancreatic cancers. These mutations have shown to play a significant role in cell behaviour and response to treatment. Since its discovery in the 1980s, it has been recognized that over-expression of KRAS and other RAS family members induces resistance to radiotherapy. Moreover, over the years preclinical and clinical studies showed that tumours with KRAS mutations exhibit different treatment sensitivities compared to tumours with wild-type KRAS.
... Continuous testing and comparison with data ensure that these algorithms are constantly improving and being validated. In addition to speeding up drug development, this approach also offers insights into drug mechanisms and toxicity, aiding in the discovery of more effective treatments [3]. In response to the increased demand for novel pharmacological drugs, researchers have turned their focus to the vast reservoir of natural chemicals residing in medicinal plants [4]. ...
Pharmacognosy and its application in healthcare have witnessed significant advancements, especially with the resurgence of interest in natural pharmaceuticals and herbal remedies. Morocco’s unique geographic location, diverse climate, and rich cultural heritage have fostered a tradition of herbal medicine, with numerous endemic plants possessing valuable therapeutic properties. To promote drug discovery from these national assets, the development of a comprehensive database containing chemical compounds from Moroccan medicinal plants is crucial. This paper introduces MoroChem, a user-friendly database offering extensive information on Moroccan medicinal plants and their chemical composition. Additionally, the database incorporates a docking feature, enabling the prediction of binding affinities between chemical compounds and user-provided target proteins, aiding in research into their efficacy and safety through bioinformatics. Currently encompassing 700 compounds from 30 plant species, MoroChem serves as a valuable resource for researchers and practitioners in medicinal plant research, drug discovery, and pharmacology. The database facilitates the identification of active compounds in traditional remedies, their potential therapeutic properties, and their mechanisms of action, thereby expediting the development of new drugs. The MoroChem portal can be accessed at https://moro-chem-jabran.vercel.app/.
... [8] Recent years have seen rise in development of domain-specific XAI techniques tailored to healthcare and computational biology applications. [5,10] These techniques aim to address the unique challenges in these fields, such as the need for accurate and interpretable models, the integration of data from multiple sources, and the management and analysis of large datasets. [5] Despite the progress made in XAI research, there is still much work to be done in developing effective and transparent AI systems that are specifically tailored to healthcare and computational biology applications. ...
... These advancements are expected to revolutionize drug discovery, disease diagnosis, treatment recommendations, and patient engagement. [10,46,[91][92][93][94] One of the most promising areas of exploration is the application of AI and computational biology in drug discovery. AI can transform large amounts of aggregated data into usable knowledge, which can expedite the process of drug discovery and optimization. ...
... AI can transform large amounts of aggregated data into usable knowledge, which can expedite the process of drug discovery and optimization. [10,91,94,95] For instance, the system 12 known as Reinforcement Learning for Structural Evolution (ReLeaSE), implemented at the University of North Carolina, has shown potential in this area. [95] Furthermore, AI can handle the complex relationship between input and output variables for high-dimensional data, which is crucial in drug discovery. ...
Interdisciplinary conferences play a vital role in advancing explainable Artificial Intelligence (AI) within increasingly intersecting healthcare and computational biology arenas. Challenges result-ing from algorithmic bias and the necessity for domain-specific Explainable AI (XAI) techniques underscore the increasing significance of transparent and interpretable AI systems used in patient care. Collaborative efforts between clinicians, data scientists, and various stakeholders are nec-essary to innovate solutions tailored to healthcare needs. Specialized conferences may foster these interdisciplinary interactions, providing platforms for knowledge exchange, networking, and collaborative partnerships. The legal, ethical, and societal dimensions of medical AI advocate for an integrative approach that aligns technological advancements with patient-centered care val-ues. The role of specialized conferences is therefore essential for shaping future directions in ex-plainable AI and computational biology that contribute to improved patient outcomes and healthcare innovations.
... AI-assisted technologies and associated apps can now send reminders and lifestyle interventions throughout the day via digital devices based on a person's vital indicators. In order to increase the overall efficacy of patient outcomes, AI-based technologies are anticipated to fundamentally transform how healthcare organisations' healthcare systems operate, communicate with patients, and provide care services (Zhang et al., 2022). ...
... While this "AI model may not always outperform experienced clinicians," it "may potentially assist junior physicians in diagnoses". The study also discovered that the AI system could diagnose ailments with an accuracy of 90 to 95% (Zhang et al., 2022). ...
... According to James Scheulen, Johns Hopkins' chief administrative officer for emergency services and capacity management, "emergency room patients are assigned a bed 30% faster; transfer delays from operating rooms have Ambulances are dispatched 63 minutes sooner to pick up patients from other hospitals, and the hospital's capacity to accept patients with difficult medical conditions from other regional and national hospitals has increased (Zhang et al., 2022). ...
The use of computers and other technologies to replicate human-like intelligent behaviour and critical thinking is known as artificial intelligence (AI).The development of AI-assisted applications and big data research has accelerated as a result of the rapid advancements in computing power, sensor technology, and platform accessibility that have accompanied advances in artificial intelligence. AI models and algorithms for planning and diagnosing endodontic procedures. The search engine evaluated information on artificial intelligence (AI) and its function in the field of endodontics, and it also incorporated databases like Google Scholar, PubMed, and Science Direct with the search criterion of original research articles published in English. Online appointment scheduling, online check-in at medical facilities, digitization of medical records, reminder calls for follow-up appointments and immunisation dates for children and pregnant women, as well as drug dosage algorithms and adverse effect warnings when prescribing multidrug combinations, are just a few of the tasks that already use artificial intelligence. Data from the review supported the conclusion that AI can play a significant role in endodontics, including the identification of apical lesions, classification and numbering of teeth, detection of dental caries, periodontitis, and periapical disease, diagnosis of various dental problems, aiding dentists in making referrals, and helping them develop more precise treatment plans for dental disorders. Although artificial intelligence (AI) has the potential to drastically alter how medicine is practised in ways that were previously unthinkable, many of its practical applications are still in their infancy and need additional research and development. Over the past ten years, artificial intelligence in ophthalmology has grown significantly and will continue to do so as imaging techniques and data processing algorithms improve.
