INTRODUCTION:

In the past, the discovery of drugs has been often based on the usual techniques of experimentation and studies in the laboratory. Although this method has proven its effectiveness to some extent, the downside of it is the high costs and long timelines, during which a single drug development could last over a decade and cost billions of dollars¹. The sophisticated nature of biological systems adds another layer of unpredictability; thus, drug discovery becomes a risk-taking venture. In light of these issues, the pharmaceutical industry has been facing an increase in the pressure to discover new methodologies that would reduce costs and the time for drug development ². The turning point of the era with the rise of artificial intelligence (AI) provides a potential fix to some of these drawbacks. AI-powered models, particularly those which are based on machine learning and deep learning, provide the opportunity for the rapid analysis of large datasets and reveal new insights that would be hard to figure out with traditional methods. The significant uses of AI in these aspects are the identification of new drug targets, the discovery of predictive biomarkers, and the optimization of drug design^3,4. In addition, AI can be used to speed up the clinical trial process by selecting patients that are more likely to respond to treatments which will ultimately result in shorter approval timelines⁵.

This review is about AI in drug research and it offers wide perspectives on its change making. We will look at some of the recent rises, real-life uses, and also the long-term issues that go hand in hand with such AI applications in this area. Thus, in order to show the present successful use of AI and the potential of AI in reshaping the old paradigms of drug discovery, we mainly focus on the above-mentioned points.

Methodology of Literature Review:

The literature for this review was picked as it is pertinent to AI applications in drug discovery, concentrating on studies published within the last 5–10 years. Sources were curated from reputable and most-cited journals to ensure the inclusion of high-quality and trustworthy data. Priority was given to systematic reviews, case studies, and original research articles that bring comprehensive insights into developments, practical applications, and issues in the AI-driven drug discovery.

Keywords like "artificial intelligence," "machine learning," "drug discovery," "biomarker discovery," and "clinical trials" were used to find the related studies. This study was conducted by searching major databases including PubMed and Google Scholar, which enabled the work to be broad yet focused through the selection of the best literature. This approach ensured a comprehensive set of sources and thus, further deeper analysis of the present state and future developments of AI in drug discovery was done successfully.

Innovations in AI-Driven Drug Discovery

The introduction of artificial intelligence (AI) into drug discovery has sped up the creation of innovations that are efficiency and precision-enriching and span all phases of development. Main advances include drug target identification, virtual screening, automated drug design, optimization of drug compounds, and biomarker discovery. This section will be presenting these innovations as core drivers for the transformation of drug discovery processes.

1. AI in Drug Target Identification:

AI techniques like deep learning and machine learning have turned the way of drug target identification into enabling the modelling of complex biological data and then matched the targets more accurately than conventional methods. Deep learning algorithms, more specifically, convolutional neural networks (CNNs) have been found out to be strong for the filtering of gene expression and protein interaction networks, and as a result, the essential disease-associated genes and proteins have been discovered⁶. The best example of this is AlphaFold, a project of DeepMind, which has managed to crack the protein structure prediction problem that has been there for a long by using an unthinkable degree of accuracy in 3D protein folding structure prediction. This breakthrough gives vital information on potential drug targets that will in turn fast track the initial discovery stages^7–9.

Figure 1. Innovations in AI-Driven Drug Discovery

2. AI-Enhanced Virtual Screening:

Virtual screening, by means of computational methods, is kind of screening of new drug candidates to see whether or not they would be promising for targeting biological substances ⁶. Al-based virtual screening algorithms, such as the ones that use machine learning, are the substances that act at determining ligand binding affinity with so high accuracy, it facilitates discovery of lead compounds that are accelerated. Machine learning algorithms are used to calculate the chemical elements in the ligands and receptors which have been epidermal growth factor receptor to note, thus saving screenings from months to weeks¹⁰. As Atomwise's Al model, AtomNet, which is a deep neural network that takes and processes structured data as an input for the purpose of structure-based drug discovery, leads to the rapid screening of millions of compounds further leading to the problems of diseases like Ebola and MS, respectively ^11,12.

3. Automated Drug Design:

In the cybersecurity domain, the forms of AI might be generative adversarial networks (GAN) and recurrent neural networks (RNN) which respectively mark the threat modelling and activity¹³. Among the AI models that are most awesome GANs, which are able to generate data from arbitrary noise, are used as well because they enable the generation of drug-like molecules that meet the chemical constraints of particular interest 6. As an illustration, Insilico Medicine's GAN-based platform fabricates the compound suitable to connect the particular protein, which causes the speed and cost of preclinical drug production to come down¹⁴. The RNNs are utilized as well with their self-training ability being the main contributing factor. They are trained with a massive steroid library and their information generating a new design of molecules having proper structure and biorelevant characteristics¹⁵.

4. AI-Powered Optimization of Drug Compounds:

After the chemical compounds that could be used for drugs are discovered, AI can, through the optimization of these compounds, make them more effective, less toxic, and increase their solubility in the body. AI utilizes reinforcement learning (RL) models as well as multi-objective optimization algorithms in such cases due to the fact that they improve the compounds step by step depending on their desired characteristics. These models mimic pharmacokinetic and pharmacodynamic properties and give rise to compounds with the desired efficacy and safety profile. A case in point is the AI platform created by Exscientia, which aided in the production of a compound for the therapy of obsessive-compulsive disorder that underwent clinical testing in far less time than was usual^16–18.

5. AI in Biomarker Discovery:

AI's contribution to the field of biomarker discovery has been instrumental in the development of personalized medicine, thereby helping in the correct classification of patients and, as a result, increasing the clinical trial success rate. Through the examination of vast datasets containing patient genetic and clinical information, AI finds predictive biomarkers, which then can be used in order to choose individuals who are likely to respond to specific treatments¹⁹. An example of this is the machine learning models that discovered the biomarkers that predict the response of cancer patients to immunotherapy, thus, making it possible for the patients to be treated with the most effective approach and as a consequence, the efficacy of the clinical trials has also been increased^20,21.

AI-powered breakthroughs in drug discovery are bringing about an unprecedented transformation in the sector through more accurate, faster, and less expensive strategies that span several phases. Such breakthroughs in target identification, virtual screening, automated design, compound optimization, and biomarker discovery highlight the versatility of AI in aiding pharmaceutical companies to reach lightning speed from drug design to validation^22,23.

Applications of AI in Real-World Drug Discovery

AI has now graduated from being just theoretical models to a mainstay in the drug's discovery pipeline, thus it actively contributes from the basic research to clinical trials, drug reparation, and personalized medicine. This section presents reports on practical experiences in the research area which implies AI optimizing research and boosting productivity in each of these sectors²⁴.

Figure 2: Applications of AI in Real-World Drug Discovery

1. Preclinical Research:

A preclinical project is a process during which a new drug candidate is always studied to determine if it can be safely and effectively applied to humans. It is the initial process of development where AI can fasten the discovery by compound screening and toxicity testing in a short time and thereby opening up innovations that might give room for further improvement in other stages of the drug discovery pipeline. Algorithms of machine learning help in the prediction of biological activity and toxicity of compounds with the help of huge chemical databases, thus this saves time and money otherwise spent on laboratory testing²⁵. To be specific, Atomwise, a particular company employs deep learning models to screen billions of compounds against specific targets and therefore, finding promising leads faster than the conventional methods of screening. In instances like partnerships between IBM Watson Health and pharmaceutical companies, the power of artificial intelligence in enhancing preclinical research is further reflected in peach systems where computers with strongest data mining and pattern recognition capabilities are able to reformulate a patient's chart of the pharmaceutical profile that contains set of sequences that are produced in biology experiments. These collaborations are examples of the way AI has been used to improve this aspect of preclinical research, which ultimately means that the drug development process might be sped up by pointing out negative results at an earlier stage and making it possible to allocate resources only to those compounds that hold greater^26–29.

2. Clinical Trials:

AI has revolutionized clinical trials by streamlining patient recruitment, enhancing risk assessment, and enabling real-time monitoring of participants. In traditional trials, recruiting suitable candidates is a major bottleneck, often prolonging study timelines. AI addresses this by analysing electronic health records and genomic data to match patients with specific study criteria, improving recruitment speed and accuracy. An example is Deep 6 AI, a company that uses AI algorithms to scan millions of medical records for eligible trial participants, significantly reducing the time needed to fill trials. Furthermore, AI tools enable continuous monitoring of patient health during trials, using wearable devices and predictive analytics to detect adverse events early, which helps lower the risk of trial failures. By reducing inefficiencies, AI-driven clinical trials can achieve substantial cost savings while accelerating the path to regulatory approval^30–34.

3. Repurposing of Existing Drugs:

AI too is a crucial player in drug repurposing that is the strategy to discover old but newly invented drugs for new indications. This is a smart way to address a problem because it can cut the cost and time of discovering a drug. The COVID-19 pandemic is leveraged with AI by such tools as BenevolentAI led to the discovery of baricitinib, which was actually a treatment for arthritis, but due to the anti-inflammatory effects, it is now used as a drug for COVID-19³⁵. These examples show that AI can analyse drug information and molecular interactions stored in huge databases, and find out the candidates which might have otherwise been ignored. It can heather researchers by finding solutions for new illnesses or coming up with the same treatments used previously for different diseases^36–40.

4. Precision Medicine:

AI is a keystone of personalized medicine which refers to treatments that are personalized to individual patients based on DNA, environmental and lifestyle factors⁴¹. By analysing patient genomic data through machine learning algorithms, AI determines the biomarkers that will be crucial in the patient-specific treatment decisions. In addition to its core research area, this space has achieved important initiatives such as the project of Tempus - a company that integrates genomics and AI analytics to run oncology practices based on data-driven decisions regarding cancer treatments^42,43. Use of personalized medicines has come to be a promising strategy, especially in oncology, because it is the course of action that the biological background of each patient's cancer gives rise to the successful therapy, thus causing them to suffer fewer side effects⁴⁴.

AI applications in drug discovery, which is a real-world subject, are multifaceted. The challenges are faced at the initial development stages, during clinical trials, at the stage of drug repurposing, and in precision medicine. These examples just reinforce the argument that AI can upgrade the degree of efficiency, accuracy, and cost-effectiveness of the drug discovery pipeline, which in turn will lead to the development of new and human-centered therapies^45–48.

Challenges in AI-Driven Drug Discovery

Although AI-based drug discovery offers great potential, it still gets stuck in various difficulties that hinder the complete assimilation of it into the pharmaceutical industry. These limitations include issues related to data quality and availability (of the data), model interpretability, regulatory and compliance hurdles, ethical concerns, and skill gaps in the workforce. It is of supreme importance to overcome these challenges to allow AI to truly develop in the drug industry^49,50.

Figure 3: Challenges in AI-Driven Drug Discovery

1. Data Quality and Availability:

One of the main challenges of AI drug discovery is the quality and accessibility of the data. AI models efficiently perform if they have access to a large number of identical training and validation sets. But, data in drug discovery is, most of the time, in parts, not diverse, and not labelled consistently, which can reduce the model's precision and generalizability⁵¹. Inconsistencies in experimental procedures and differences in data labelling are the main barriers to cross-dataset unification. Thus, the pharmaceutical industry needs to address this issue by developing critical and universally standardized data sets, characterizing different disease states, demographics, and molecular properties, along with those that can be utilized without AI bias, in order to promote the model's reliability^52–55.

2. Model Interpretability and Explainability:

One of the main issues in AI applications used for drug discovery is the interpretability of the model, commonly known as the “black box” problem. Many AI models, especially deep learning networks, are successful in making predictions but they have no straight explanations as to how their decisions are made⁵⁶. This obfuscation is a problem in drug discovery, as the ability to know the reasoning behind a model’s prediction is important both for regulatory approval by the bodies and the clinicians, who should have trust in the model, respectively. Interpretability tools, for example, attention mechanisms and explainable AI (XAI) techniques are being invented to shed more light on AI and these have been used as teaching examples to assist students in the learning process but it is not yet fully explainable. However, it is only the icing on the cake transparency is one of the best elements as the regulatory bodies, for instance, require AI-derived results to be reproducible and scientifically valid^57,58.

3. Regulatory and Compliance Issues:

We can face the problem of meeting regulations when the drug discovery process is Al-driven, as existing accounting systems have been planned around apps. The regulatory authorities, such as the U.S. Food and Drug Administration, are coming up with specific Al guidelines for healthcare, but the overall standards are still in the process of being developed. AT present, the regulatory framework is not clear on issues of model validation, data governance, and risk assessment for Al-generated drug candidates. Therefore, developers have uncertain terrain to navigate, which in turn slows down Al adoption in the industry. These initiatives target the creation of regulatory pathways that deal with these issues, thereby guaranteeing that Al technologies are safe and efficient^59,60.

4. Ethical and Societal Concerns:

Ethical issues are also important barriers. Patient privacy and data ownership are primary concerns, as Al models often rely on huge stores of data that contain sensitive health information. Data privacy law compliance, such as trite General Data Protection Regulation in Europe, makes things even more difficult when the data is transferred between countries⁶¹.

Besides, the Al can gain biases that are already there or be the cause of those biases becoming worse, which can lead to disparate treatment outcomes. Biases can be neutralized and thus ethical frameworks and algorithmic fairness checks should be done to confidently proceed with Al applications in drug discovery that will truly be non-discriminatory^62,63.

5. Skill Gaps and Workforce Challenges:

The workforce faces a significant skills gap because life sciences along with the application of artificial intelligence in drug discovery require advanced machine learning skills. At present, the lack of personnel with such cross-disciplinary expertise is one of the major hindrances to the development and deployment of AI-based models in drug discovery^64,65. The problem is being tackled by universities, research institutions, and pharmaceutical companies who are providing specialized training programs and promoting interdisciplinary cooperation, however, more coordinated efforts are still required to build the workforce capable of dealing with complex applications. Getting over these hurdles is fundamental for the great AI to be brought to pharmacology. Tackling data quality, enhancing the accuracy and reliability of the models, laying down regulatory frameworks, maintaining ethical standards, and investing in workforce development will be the most important aspects of the development of AI-guided drug discovery^66,67.

Future Directions and Emerging Trends

The future of AI in drug discovery promises great breakthroughs as new technologies and teamwork drive progress in the area. AI methods like reinforcement learning, federated learning, and natural language processing (NLP) are making the traditional models capable of doing more things. E.g., Reinforcement learning is being used to optimize molecular structures for desirable properties by means of iterative improvement. Likewise, federated learning, which allows the production of models on distributed data without any data exchange, provides a compromise between privacy concerns and efficiency. Notably, NLP tools are key by drawing out useful information from biomedical literature and clinical records, thus, speeding up the process of target identification and hypothesis generation⁶⁸.

Joint data-sharing projects are really dealing with the data scarcity and standardization problems that have been the biggest obstacles for AI model development. Organizations and open-access platforms, like the Open Targets, facilitate data accessibility and interoperability, which in turn, help researchers draw more diverse datasets for AI-driven drug discovery⁶⁹.

Figure 4: Future Directions and Emerging Trends in AI Driven Drug Discovery

Merging AI with state-of-the-art technologies such as CRISPR gene-editing and quantum computing results in a substantial strengthening of the drug discovery horizon. Trying quantum computing, for example, by calculating very complicated molecular interactions quantum computing can massively extend a molecular interaction process to a magnitude that was never before possible-it will make that AI simulating molecular interactions to a never before possible extent allow AI to predict if the drug is that effective or not. Furthermore, AI together with CRISPR can also development DNA-specific medicines, thus introducing precision medicine ^70–72.

These trends are anticipated to shrink the time of drug development, R&D expenses, and improvement of treatment outcomes. Due to the maturation of these advancements, AI-based drug discovery is expected to replace intervention and diagnosis in modern medicine as a foundation of faster and more effective medical treatments.

CONCLUSION:

Undoubtedly, AI will mostly improve the drug discovery field thereby allowing more methodology and precision to be applied throughout the whole process from target identification to clinical trials. Implementing AI tools, which include discovering a target through deep learning, virtual screening, and generative models for drug design, is revolutionizing the methods of drug development, meaning speeding up is possible with fewer resources in contrast with conventional procedures. The real-world AI–enabled use cases besides fast preclinical research, smart clinical trials, and drug repurposing include personalized medicine as well that prove the nearly limitless capabilities of AI to transform medicine. Although, as a matter of fact, these challenges refer to deficiencies and ambiguous data, an unclear model explanation, compliance standards, and even ethical matters.

Eliminating this road will be imperative for AI to be in its full capacity through drug discovery. Yet, obstacles do exist the industry moves along collaborative data-sharing initiatives, formulates sufficient regulatory frameworks and human resources training thus AI-driven drug development will seem increasingly feasible. On the other hand, in the coming years, AI will unveil a future when discovery has a lot quicker, more inexpensive, and most importantly, guaranteeing highly personalized treatment that improves patients' health and even worldwide levels of health.

CONFLICT OF INTEREST:

The authors declare no conflict of interest.

REFERENCES:

1. Paul SM, Mytelka DS, Dunwiddie CT, Persinger CC, Munos BH, Lindborg SR, et al. How to improve R&D productivity: the pharmaceutical industry’s grand challenge. Nat Rev Drug Discov. 2010 Mar; 9(3): 203–14.

2. DiMasi JA, Grabowski HG, Hansen RW. Innovation in the pharmaceutical industry: new estimates of R&D costs. Journal of Health Economics. 2016 May; 47:20–33.

3. Schneider G. Automating drug discovery. Nat Rev Drug Discov. 2018 Feb;17(2): 97–113.

4. Mak KK, Pichika MR. Artificial intelligence in drug development: present status and future prospects. Drug Discovery Today. 2019 Mar;24(3):773–80.

5. Wong CH, Siah KW, Lo AW. Estimation of clinical trial success rates and related parameters. Biostatistics. 2019 Apr 1; 20(2): 273–86.

6. Chen H, Engkvist O, Wang Y, Olivecrona M, Blaschke T. The rise of deep learning in drug discovery. Drug Discovery Today. 2018 Jun; 23(6): 1241–50.

7. Jumper J, Evans R, Pritzel A, Green T, Figurnov M, Ronneberger O, et al. Highly accurate protein structure prediction with Alpha Fold. Nature. 2021 Aug 26; 596(7873): 583–9.

8. Wang X, Liu J, Zhang C, Wang S. SSGraphCPI: A novel model for predicting compound-protein interactions based on deep learning. International Journal of Molecular Sciences. 2022; 23(7): 3780.

9. Gomes J, Ramsundar B, Feinberg EN, Pande VS. Atomic convolutional networks for predicting protein-ligand binding affinity. arXiv preprint arXiv:1703.10603. 2017 Mar 30.

10. Mamoshina P, Vieira A, Putin E, Zhavoronkov A. Applications of Deep Learning in Biomedicine. Mol Pharmaceutics. 2016 May 2; 13(5): 1445–54.

11. Gawehn E, Hiss JA, Schneider G. Deep Learning in Drug Discovery. Molecular Informatics. 2016 Jan; 35(1): 3–14.

12. Yang X, Wang Y, Byrne R, Schneider G, Yang S. Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery. Chem Rev. 2019 Sep 25; 119(18): 10520–94.

13. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial networks. Commun ACM. 2020 Oct 22; 63(11): 139–44.

14. Zhavoronkov A, Ivanenkov YA, Aliper A, Veselov MS, Aladinskiy VA, Aladinskaya AV, et al. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nat Biotechnol. 2019 Sep; 37(9): 1038–40.

15. Popova M, Isayev O, Tropsha A. Deep reinforcement learning for de novo drug design. Sci Adv. 2018 Jul 6; 4(7): EAAP7885.

16. Stokes JM, Yang K, Swanson K, Jin W, Cubillos-Ruiz A, Donghia NM, et al. A Deep Learning Approach to Antibiotic Discovery. Cell. 2020 Feb; 180(4): 688-702.e13.

17. Segler MHS, Kogej T, Tyrchan C, Waller MP. Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks. ACS Cent Sci. 2018 Jan 24; 4(1): 120–31.

18. Sanchez-Lengeling B, Aspuru-Guzik A. Inverse molecular design using machine learning: Generative models for matter engineering. Science. 2018 Jul 27; 361(6400): 360–5.

19. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019 Jan;25(1):44–56.

20. Ghaffari Laleh N, Ligero M, Perez-Lopez R, Kather JN. Facts and hopes on the use of artificial intelligence for predictive immunotherapy biomarkers in cancer. Clinical Cancer Research. 2023; 29(2): 316–23.

21. Trebeschi S, Drago SG, Birkbak NJ, Kurilova I, Cǎlin AM, Pizzi AD, et al. Predicting response to cancer immunotherapy using noninvasive radiomic biomarkers. Annals of Oncology. 2019; 30(6): 998–1004.

22. Park S, Ahn CH, Jung G, Lee S, Paeng K, Shin J, et al. Deep learning-based predictive biomarker for immune checkpoint inhibitor response in metastatic non-small cell lung cancer. JCO. 2019 May 20; 37(15_suppl): 9094–9094.

23. Xie J, Luo X, Deng X, Tang Y, Tian W, Cheng H, et al. Advances in artificial intelligence to predict cancer immunotherapy efficacy. Frontiers in Immunology. 2023; 13: 1076883.

24. Vamathevan J, Clark D, Czodrowski P, Dunham I, Ferran E, Lee G, et al. Applications of machine learning in drug discovery and development. Nat Rev Drug Discov. 2019 Jun; 18(6): 463–77.

25. Lo YC, Rensi SE, Torng W, Altman RB. Machine learning in chemoinformatics and drug discovery. Drug Discovery Today. 2018 Aug; 23(8): 1538–46.

26. Korotcov A, Tkachenko V, Russo DP, Ekins S. Comparison of Deep Learning with Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets. Mol Pharmaceutics. 2017 Dec 4; 14(12): 4462–75.

27. Rajkomar A, Dean J, Kohane I. Machine Learning in Medicine. N Engl J Med. 2019 Apr 4; 380(14): 1347–58.

28. Smalley E. AI-powered drug discovery captures pharma interest. Nature Biotechnology. 2017; 35(7):604–6.

29. Gao B, Qiang B, Tan H, Jia Y, Ren M, Lu M, Liu J, Ma WY, Lan Y. Drugclip: Contrasive protein-molecule representation learning for virtual screening. Advances in Neural Information Processing Systems. 2024 Feb 13; 36.

30. Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, et al. A guide to deep learning in healthcare. Nat Med. 2019 Jan; 25(1):24–9.

31. Harrer S, Shah P, Antony B, Hu J. Artificial intelligence for clinical trial design. Trends in Pharmacological Sciences. 2019; 40(8): 577–91.

32. Miyasato G, Kasivajjala VC, Misra M, Kumar K, Kadam AS, Friedman HS. AI-driven real-time patient identification for randomized controlled trials. JCO. 2023 Jun 1;41(16_suppl):e13565–e13565.

33. Bhande P. Adoption of AI-Enabled Solutions for Patient Recruitment Process in Clinical Trials.

34. Chopra H, Shin DK, Munjal K, Dhama K, Emran TB. Revolutionizing clinical trials: the role of AI in accelerating medical breakthroughs. International Journal of Surgery. 2023; 109(12): 4211–20.

35. Richardson P, Griffin I, Tucker C, Smith D, Oechsle O, Phelan A, et al. Baricitinib as potential treatment for 2019-nCoV acute respiratory disease. The Lancet. 2020 Feb; 395(10223): e30–1.

36. Krittanawong C, Zhang H, Wang Z, Aydar M, Kitai T. Artificial Intelligence in Precision Cardiovascular Medicine. Journal of the American College of Cardiology. 2017 May; 69(21):2657–64.

37. Richardson PJ, Robinson BW, Smith DP, Stebbing J. The AI-assisted identification and clinical efficacy of baricitinib in the treatment of COVID-19. Vaccines. 2022; 10(6):951.

38. Smith DP, Oechsle O, Rawling MJ, Savory E, Lacoste AM, Richardson PJ. Expert-augmented computational drug repurposing identified baricitinib as a treatment for COVID-19. Frontiers in Pharmacology. 2021; 12:709856.

39. Stebbing J, Krishnan V, De Bono S, Ottaviani S, Casalini G, Richardson PJ, et al. Mechanism of baricitinib supports artificial intelligence‐predicted testing in COVID ‐19 patients. EMBO Mol Med. 2020 Aug 7; 12(8): e12697.

40. Zhou Y, Wang F, Tang J, Nussinov R, Cheng F. Artificial intelligence in COVID-19 drug repurposing. The Lancet Digital Health. 2020; 2(12): e667–76.

41. Dilsizian SE, Siegel EL. Artificial Intelligence in Medicine and Cardiac Imaging: Harnessing Big Data and Advanced Computing to Provide Personalized Medical Diagnosis and Treatment. Curr Cardiol Rep. 2014 Jan; 16(1): 441.

42. Bejnordi BE, Veta M, Van Diest PJ, Van Ginneken B, Karssemeijer N, Litjens G, Van Der Laak JA, Hermsen M, Manson QF, Balkenhol M, Geessink O. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017 Dec 12; 318(22): 2199-210.

43. Gandomi A, Haider M. Beyond the hype: big data concepts, methods, and analytics. International Journal of Information Management. 2015;35(2):137–44.

44. Patel NM, Michelini VV, Snell JM, Balu S, Hoyle AP, Parker JS, et al. Enhancing next-generation sequencing-guided cancer care through cognitive computing. The oncologist. 2018;23(2):179–85.

45. Esteva A, Chou K, Yeung S, Naik N, Madani A, Mottaghi A, et al. Deep learning-enabled medical computer vision. NPJ Digital Medicine. 2021;4(1):5.

46. Beaubier N, Bontrager M, Huether R, Igartua C, Lau D, Tell R, et al. Integrated genomic profiling expands clinical options for patients with cancer. Nature biotechnology. 2019;37(11):1351–60.

47. André F, Ciccolini J, Spano JP, Penault-Llorca F, Mounier N, Freyer G, et al. Personalized Medicine in Oncology: Where Have we Come from and where are we Going? Pharmacogenomics. 2013 Jun;14(8):931–9.

48. Kalia M. Personalized oncology: Recent advances and future challenges. Metabolism. 2013;62: S11–4.

49. Lee SI, Celik S, Logsdon BA, Lundberg SM, Martins TJ, Oehler VG, et al. A machine learning approach to integrate big data for precision medicine in acute myeloid leukemia. Nature Communications. 2018; 9(1): 42.

50. He J, Baxter SL, Xu J, Xu J, Zhou X, Zhang K. The practical implementation of artificial intelligence technologies in medicine. Nature Medicine. 2019; 25(1): 30–6.

51. Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: review, opportunities and challenges. Briefings in Bioinformatics. 2018; 19(6): 1236–46.

52. Blanco-Gonzalez A, Cabezon A, Seco-Gonzalez A, Conde-Torres D, Antelo-Riveiro P, Pineiro A, et al. The role of AI in drug discovery: challenges, opportunities, and strategies. Pharmaceuticals. 2023; 16(6): 891.

53. Tiwari PC, Pal R, Chaudhary MJ, Nath R. Artificial intelligence revolutionizing drug development: Exploring opportunities and challenges. Drug Development Research. 2023 Dec; 84(8): 1652–63.

54. Walters WP, Barzilay R. Critical assessment of AI in drug discovery. Expert Opinion on Drug Discovery. 2021 Sep 2; 16(9): 937–47.

55. Kumar SA, Ananda Kumar TD, Beeraka NM, Pujar GV, Singh M, Narayana Akshatha HS, et al. Machine Learning and Deep Learning in Data-Driven Decision Making of Drug Discovery and Challenges in High-Quality Data Acquisition in the Pharmaceutical Industry. Future Med Chem. 2022 Feb; 14(4): 245–70.

56. Doshi-Velez F, Kim B. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608. 2017 Feb 28.

57. Holzinger A, Langs G, Denk H, Zatloukal K, Müller H. Causability and explainability of artificial intelligence in medicine. WIREs Data Min and Knowl. 2019 Jul; 9(4): e1312.

58. Samek W. Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. arXiv preprint arXiv:170808296. 2017;

59. Luxton DD. Recommendations for the ethical use and design of artificial intelligent care providers. Artificial Intelligence in Medicine. 2014; 62(1):1–10.

60. Gerke S, Minssen T, Cohen G. Ethical and legal challenges of artificial intelligence-driven healthcare. In Artificial Intelligence in Healthcare. 2020 Jan 1 (pp. 295-336). Academic Press.

61. Amann J, Blasimme A, Vayena E, Frey D, Madai VI, Precise4Q Consortium. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Medical Informatics and Decision Making. 2020 Dec; 20:1-9.

62. Wiens J, Saria S, Sendak M, Ghassemi M, Liu VX, Doshi-Velez F, et al. Do no harm: a roadmap for responsible machine learning for health care. Nat Med. 2019 Sep;25(9):1337–40.

63. Mehrabi N, Morstatter F, Saxena N, Lerman K, Galstyan A. A Survey on Bias and Fairness in Machine Learning. ACM Comput Surv. 2022 Jul 31;54(6):1–35.

64. Patel VL, Shortliffe EH, Stefanelli M, Szolovits P, Berthold MR, Bellazzi R, et al. The coming of age of artificial intelligence in medicine. Artificial Intelligence in Medicine. 2009;46(1):5–17.

65. Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nature Biomedical Engineering. 2018; 2(10):719–31.

66. Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future healthcare journal. 2019; 6(2): 94–8.

67. Ribeiro MT, Singh S, Guestrin C. " Why should i trust you?” Explaining the predictions of any classifier. InProceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining 2016 Aug 13 (pp. 1135-1144).

68. Sheller MJ, Edwards B, Reina GA, Martin J, Pati S, Kotrotsou A, et al. Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Scientific Reports. 2020; 10(1): 12598.

69. Munoz-Price LS, Poirel L, Bonomo RA, Schwaber MJ, Daikos GL, Cormican M, et al. Clinical epidemiology of the global expansion of Klebsiella pneumoniae carbapenemases. The Lancet Infectious Diseases. 2013 Sep; 13(9): 785–96.

70. Srivastava R. Quantum computing in drug discovery. Information System and Smart City. 2023 Dec 11; 3(1).

71. Ravichandran M, Maddalo D. Applications of CRISPR-Cas9 for advancing precision medicine in oncology: from target discovery to disease modeling. Frontiers in Genetics. 2023; 14: 1273994.

72. Flöther FF. The state of quantum computing applications in health and medicine. Research Directions: Quantum Technologies. 2023; 1: e10.

Received on 10.11.2024 Revised on 05.12.2024

Accepted on 31.12.2024 Published on 03.03.2025

Available online from March 07, 2025

Asian J. Res. Pharm. Sci. 2025; 15(1):61-67.

DOI: 10.52711/2231-5659.2025.00009

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Creative Commons License.