INTRODUCTION:

Technology is taking over in every field the pharmaceutical industry has no exception. Drug discovery is a complex and time-consuming process that typically takes 10 - 15 years and costs billions of dollars. The traditional drug discovery process relies on a combination of experimental and computational methods to identify new targets, develop and test new compounds, and bring a new drug to market. Artificial intelligence (AI) has the potential to revolutionize the drug discovery process by automating and accelerating many of these tasks. AI algorithms can be used to analyze large amounts of data from multiple sources, including genomic and proteomic data, chemical databases, and scientific literature.

By combining data from multiple sources, AI can identify new targets, predict toxicity, and prioritize compounds for further study.¹

One of the major applications of AI in drug discovery is in target identification. AI algorithms can be used to analyze genomic and proteomic data to identify potential therapeutic targets for a wide range of diseases, including cancer, cardiovascular disease, and neurodegenerative disorders. For example, AI can be used to analyze gene expression data to identify targets for cancer therapies, or to analyze protein-protein interaction data to identify targets for neurodegenerative diseases. Another important application of AI in drug discovery is in toxicity prediction. AI algorithms can be used to analyze chemical databases and scientific literature to predict the toxicity of new compounds, enabling researchers to prioritize compounds for further study and avoid compounds that are likely to be toxic. For example, AI algorithms can be used to predict the potential for a compound to cause liver toxicity, or to predict the risk of a compound causing cardiovascular toxicity. AI can also be used to optimize the design of clinical trials.

AI algorithms can be used to identify patient populations that are most likely to respond to a new treatment, to predict the efficacy of a new drug, and to optimize the design of clinical trials. For example, AI algorithms can be used to analyze large amounts of patient data to identify biomarkers that can be used to predict response to a new treatment, or to predict the potential for a new drug to cause side effects.² In addition to its potential applications in drug discovery and development, AI is also being applied to other areas of the pharmaceutical industry, including personalized medicine and patient stratification. For example, AI algorithms can be used to analyze patient data to predict response to a particular treatment, or to identify patients who are most likely to respond to a particular drug.³ Besides, massive advancement is happening in the field of medical science such as surgeries using robots. Nowadays, complex surgeries can be performed using robots such as the Da Vinci; these robots can be used for cancer treatment. Operating patients becomes very easy with the help of robots; time consumption is reduced because of the use of robots in surgeries.⁴ In this review, various aspects such as benefits, applications and, impact and challenges of AI and AI tools in pharmaceutical industry is described.

Benefits of AI in Pharmaceutical Industry:

The pharmaceutical industry is facing a growing number of challenges, including increasing costs, growing complexity, and increasing regulatory requirements. AI has the potential to significantly improve the efficiency, accuracy, and speed of drug development, while also improving patient outcomes. One of the major benefits of AI in the pharmaceutical industry is improved efficiency. AI algorithms can be used to analyze vast amounts of data from multiple sources, reducing the time and costs associated with drug development. It can also be used to streamline clinical trials by identifying the right patients and predicting the response to treatment, reducing the duration and cost of trials.⁵ Another major benefit of AI in the pharmaceutical industry is improved accuracy.

AI algorithms can be used to analyze data from multiple sources to identify new drug targets, predict toxicity, and improve the accuracy of predictions. By leveraging AI to analyze data from multiple sources, researchers can make more informed decisions about the development of new treatments, reducing the risk of failure and improving the overall success rate of drug development.⁶ Finally, AI has the potential to improve patient outcomes. AI algorithms can be used to develop personalized treatment plans based on a patient's genomic and medical data, improving the effectiveness of treatments and reducing the risk of adverse events. AI can also be used to monitor real-world data to identify adverse events and improve drug safety, ensuring that patients receive safe and effective treatments. In conclusion, AI has the potential to significantly improve the efficiency, accuracy, and speed of drug development and improve patient outcomes in the pharmaceutical field. AI can be exploited to analyze data from multiple sources, streamline clinical trials, develop personalized treatments, and enhance drug safety. The utilization of AI can bring new treatments to market more quickly and efficiently, while also improving the overall quality of healthcare.⁶

Applications of AI in Pharmaceutical Industry:

The applications of AI in healthcare and pharmaceutical industry are many, with the potential to transform key aspects of the industry and drive innovation. Some of the major applications of AI are discussed below. 

(1) Drug Discovery:

Drug discovery is a complex and time-consuming process that involves identifying potential therapeutic targets, developing and testing new chemical entities, and bringing a new drug to the market. AI has the potential to revolutionize the drug discovery process by analyzing vast amounts of data from various sources to identify new drug targets and predict toxicity and side effect potential. The traditional drug discovery process is data-intensive that relies at large on a range of experimental and computational methods to identify new targets and predict toxicity. AI algorithms can be used to reduce these tedious tasks by analyzing large amounts of data from multiple sources, including genomic and proteomic data, chemical databases, and scientific literature. By combining data from multiple sources, AI can identify new targets, predict toxicity, and prioritize compounds for further study and avoid compounds that are likely to be toxic. AI algorithms can be used to analyze genomic and proteomic data to identify potential therapeutic targets for a wide range of diseases, including cancer, cardiovascular disease, and neurodegenerative disorders. For example, AI can be used to analyze gene expression data to identify targets for cancer therapies, or to analyze protein-protein interaction data to identify targets for neurodegenerative diseases. Another important application of AI in drug discovery is in toxicity prediction. For example, AI algorithms can be used to predict the potential for a compound to cause liver toxicity, or to predict the risk of a compound causing cardiovascular toxicity.^{7, 8}

(2) Clinical Trial and Designs:

Clinical trials are a critical component of the drug development process, as they provide the data needed to determine the safety and efficacy of a new treatment. However, clinical trials are often time-consuming and expensive, with the average clinical trial taking several years to complete and costing hundreds of millions of dollars. AI has the potential to significantly reduce the duration and costs of clinical trials by improving the efficiency of the clinical trial process. One of the major applications of AI in clinical trial design is patient selection. AI algorithms can be used to analyze patient data, such as demographic information, medical history, and genetic data, and to identify the patients who are most likely to respond to a new treatment. By selecting the right patients for a clinical trial, researchers can reduce the number of patients needed to demonstrate efficacy, thereby reducing the duration and costs of the clinical trial.⁹

Another important application of AI in clinical trial design is response prediction. AI algorithms can be used to analyze patient data to predict the response of patients to a new treatment. This information can be used to optimize the design of clinical trials, such as determining the optimal dose and treatment regimen, and reducing the number of patients needed to demonstrate efficacy. AI can also be used to monitor adverse events in clinical trials. AI algorithms can be used to analyze patient data to identify potential adverse events and monitor the safety of a new treatment. This information can be used to quickly identify and address potential safety concerns, improving the overall safety of clinical trials and reducing the risk of harm to patients.¹⁰

(3) Personalized Medicine:

Personalized medicine is an emerging field in healthcare that aims to tailor treatment plans to the unique needs of each patient, based on their genomic and medical data. Personalized medicine has the potential to revolutionize the way that diseases are treated, by enabling healthcare providers to develop individualized treatment plans that are optimized for each patient. AI is playing an increasingly important role in personalized medicine, as it has the ability to analyze vast amounts of genomic and medical data to identify new treatment targets and predict treatment response. Using AI algorithms, researchers can identify patterns in patient data that are associated with particular diseases or conditions, and develop new treatments that are specifically designed for individual patients. One of the major applications of AI in personalized medicine is the development of predictive models. AI algorithms can be used to analyze patient data to predict the response of patients to a particular treatment. This information can be used to develop personalized medicines that are optimized for each patient, based on their unique genetic and medical profile.¹¹ Another important application of AI in personalized medicine is the identification of new drug targets. AI algorithms can be used to analyze genomic and medical data to identify new targets for drug development. Employing AI to identify new drug targets, researchers can develop new medicines that are specifically designed for individual patients, improving its overall effectiveness.¹²

(4) Analyzing Data for New Drug Development:

AI has the potential to streamline the drug development process by improving the efficiency of the process and reducing costs. Therefore, one of the major applications of AI in drug development is the analysis of data from multiple sources. AI algorithms can be used to analyze data from a variety of sources, such as clinical trials, preclinical studies, and electronic health records, to identify new drug targets and predict the response of patients to treatments. In such situations, AI can be used to analyze data from multiple sources. Besides, researchers can make more informed decisions about the development of new treatments and reduce the duration and costs of the drug development process. Another important application of AI in drug development is the optimization of preclinical studies.¹³ AI algorithms can be used to analyze preclinical data to identify the most promising candidates for further development. AI is much more useful and efficient to optimize compounds during preclinical studies. Using AI researchers can reduce the number of potential NCEs that are selected forward for further development, thereby reducing the duration and costs of the drug development process.¹⁴

(5) Enhancing Drug Safety:

Ensuring the safety of drugs is a critical aspect in the drug development. AI has the potential to enhance drug safety by monitoring and analyzing real-world data to identify adverse events and improve drug safety. Since one of the major applications of AI in drug safety is the analysis of real-world data, it can be used to analyze data from a variety of sources, such as electronic health records, claims data, and patient-generated data, to identify adverse events that may not have been detected during clinical trials. Utilizing AI to analyze real-world data, researchers can identify new safety concerns and improve the overall safety of already approved drugs. Another important application of AI in drug safety is the monitoring of adverse events. AI algorithms can be used to monitor real-world data to identify adverse events and track the progression of the event over time. This information can be used to develop new strategies for reducing the risk of adverse events and improving drug safety.¹⁵ Therefore, AI is a very much potential technique to play a critical role in enhancing drug safety by monitoring and analyzing real-world data to identify adverse events and develop drug safety thereby improve the overall quality of healthcare.

Impact of AI and Tools on Pharmaceutical Industry:

There are several AI techniques and AI tools that impact various aspects of pharmaceutical industry especially drug discovery and drug development. These are described below.

(1) Machine learning (ML) algorithms: ML algorithms, such as decision trees, random forests, and support vector machines, are commonly used in the pharmaceutical industry to analyze large amounts of data to identify new drug targets, predict toxicity, and improve the accuracy of predictions.

(2) Natural language processing: Natural language processing (NLP) algorithms are used to analyze unstructured data, such as electronic health records and scientific literature, to extract insights and improve decision-making in the pharmaceutical field.

(3) Deep learning algorithms: Deep learning algorithms (DLA), such as convolution neural networks and recurrent neural networks, are used to analyze complex data sets, such as genomic data and imaging data, to develop personalized treatment plans and improve the accuracy of predictions.

(4) Predictive analytics algorithms: Predictive analytics algorithms (PLA) are used to analyze data from multiple sources, such as electronic health records and clinical trials, and predict patient outcomes, improve the efficiency of clinical trials, and identify new drug targets.

(5) Robotics process automation: Robotics process automation (RPA) is used to automate repetitive tasks and improve the efficiency of the drug development process.

These are some of the most commonly used AI techniques and tools in the pharmaceutical industry, and they have the potential to significantly impact all aspects of drug discovery and development.

AI Technology Start-Ups in Pharmaceutical Industry:

Pharmaceutical industries have started utilizing the power of AI to assist the relatively expensive and competitive drug discovery and development process. AI solutions can successfully identify disease patterns in large datasets and help understand which drug compositions would be best suited for treating different diseases. Some of the leading organizations and start-ups worldwide using AI algorithms in pharmaceuticals providing products and services related to AI are presented in Table 1.

(1) Standigm:

The pharmaceutical industry has always been at the forefront of innovation, constantly searching for new and innovative ways to develop drugs that can improve patient outcomes. The drug development process, however, is a long and complex journey that can take years to complete and billions of dollars to fund. This is why Standigm, a South Korean start-up, has created a novel drug design solution that harnesses the power of AI to speed up the drug discovery process. Standigm BEST, Standigm's AI-based platform, uses ML algorithms to explore the latent chemical space and generate novel compounds. This process eliminates the uncertainty in drug discovery and saves time and costs during the development process. Once the candidate drugs are identified, Standigm BEST provides biological interpretations to help researchers discover pathways and therapeutic patterns, prioritize potential targets, and advance their drug design. The platform’s ability to analyse biomedical literature also helps to speed up drug design and development by providing researchers with a comprehensive view of the existing knowledge in a particular field. This allows them to make informed decisions and design drugs that display the desired properties more efficiently. Standigm's AI-based platform offers a revolutionary approach to drug design, helping to reduce the time and costs associated with drug discovery. This innovative solution has the potential to significantly impact the pharmaceutical industry and improve patient outcomes.¹⁶

(2) CytoReason:

CytoReason is a start-up based in Israel that offers innovative solutions in the field of drug discovery. The company uses AI and ML algorithms to analyse large amounts of biological data, including genomics, proteomics, and other omics data. By exploring this vast amount of information, CytoReason is able to facilitate data-driven target discovery, helping to identify potential targets for drug development. One of the early steps in the drug discovery process is the identification of target molecules in the human body that drugs can interact with. However, due to a lack of understanding about many human genes and proteins, this can be a difficult and time-consuming process. CytoReason solves these problems by using its platform to analyse multi-omic human clinical data. This allows the company to uncover disease-related cell and gene maps, providing researchers with valuable insights into potential targets for drug discovery and development. The platform also supports research and development efforts throughout the entire drug development cycle, making the process faster and more efficient. Using AI and ML to analyse large amounts of biological data, CytoReason is helping to transform the drug discovery process and making it easier to develop new treatments for a wide range of diseases.¹⁷

(3) Genome Biologics:

Genome Biologics is a German start-up that is making a significant impact in the field of preclinical drug discovery. By automating sample analysis for the effects of drugs, Genome Biologics is reducing the uncertainty in preclinical experiments and helping to speed up the drug development process. The start-up's product, GENIMPAS, uses pattern recognition and ML to match compound databases and drug discovery pipelines with profiles of disease-relevant genes. This enables the identification of novel compounds and repurposing of existing compounds to treat a range of diseases, including cardio-metabolic and cardiovascular diseases, and cancers. GENISYST, another patented solution offered by Genome Biologics, is a multiplexed disease modelling solution that uses single cell transgenics for preclinical testing. This innovative approach allows for the simultaneous testing of multiple targets, saving time and resources. Overall, Genome Biologics is providing valuable tools and solutions that are helping to make preclinical drug discovery more efficient and effective. Their contributions to the field will likely lead to the development of more effective treatments for a range of diseases.¹⁸

(4) Bullfrog AI:

Bullfrog AI is a US-based start-up that is aimed to revolutionize the drug development process with its proprietary AI platform bfLEAP. The platform utilizes advanced data analysis technique such as NLP to analyse clinical trial data sets and, looking for relationships and correlations between therapies and patients. The ultimate goal of bfLEAP is to provide novel insights for late-stage drug candidates; identify novel drug targets; screen synergistic drug combinations; and patient populations that may benefit greatly from a particular drug. This innovative approach is significant importance because the success rate of clinical trials is low, and any tools that can help to improve the efficiency and accuracy of the process will be greatly welcomed. The use of NLP to parse complex data sets and identify useful information is an exciting development in the field of AI and pharmaceuticals, and the potential benefits of this approach are numerous. Overall, BullFrog AI's bfLEAP platform is an example of the innovative solutions that AI can offer to the pharmaceutical industry. By utilizing advanced data analysis techniques, it is possible to streamline the drug development process and improve patient outcomes, making the journey from discovery to market faster, more efficient, and more cost-effective.¹⁹

(5) Causaly:

Causaly is a UK-based AI start-up that specializes in causal relationship extraction from biomedical literature. The company was founded in 2017 by CEO Alexander Jarasch, CTO Julius Juettner, and COO Rodolfo Bellesi. Causaly's platform uses NLP and ML algorithms to identify causal relationships between biomedical concepts, such as drugs, genes, diseases, and biological pathways. The platform can also identify new drug targets and repurpose existing drugs for new indications. The company's technology has applications in drug discovery and development, precision medicine, and pharmacovigilance. It has collaborated with several pharmaceutical companies, academic institutions, and government agencies to accelerate drug discovery and identify potential adverse drug reactions.²⁰

(6) DeepCure:

DeepCure is a promising start-up in the pharmaceutical industry that leverages AI technology to streamline the discovery of small molecule therapeutics. It is a combination of deep learning, cloud computing, and its proprietary database, MolDBTM that allows it to quickly identify promising small molecules with desired properties. The optimization of small molecules for important pharmacokinetic properties, such as ADMET, helps to minimize the risks and costs associated with later stages of drug development. Small molecules play a crucial role in the pharmaceutical industry and account for a large portion of drugs in the market. They are relatively easy to develop from derivatives of known therapeutic compounds, but their interactions with other substances can sometimes minimize their safety or efficacy. This is where DeepCure's innovative approach is explored, using ML algorithms, to analyse structural and chemical data from public sources to ensure that the identified therapeutics are of high quality. Overall, DeepCure's focus on small molecule therapeutics is a valuable contribution to the pharmaceutical industry and has the potential to reduce the time and cost involved in drug discovery and development. The company's innovative approach and use of innovative technology is a promising sign for the future of the industry and its ability to improve patient outcomes.²¹

(7) Polaris Quantum Biotech:

Polaris Quantum Biotech is a UK-based start-up that focuses on AI-based drug discovery solutions. The start-up was founded in 2018 and is headquartered in London, UK. Polaris Quantum Biotech's platform uses quantum mechanics to simulate the behavior of molecules, allowing for the rapid screening of potential drug candidates. The platform also incorporates ML algorithms to identify the most promising compounds and predict their effectiveness. The start-up claims that their approach can reduce the time and cost of drug discovery by up to 90%. The Company has partnerships with several pharmaceutical companies and academic institutions, including AstraZeneca, GlaxoSmithKline, and the University of Oxford.²² There are some of the leading organisations which are using AI for drug discovery and development and other related aspects.

The coming years will be more about practical uses of AI because it addresses specific use cases in the pharmaceutical industry. Though it is a highly regulated industry and has historically been slow to adopt new technologies and modernise, these industries using AI will lead despite various hurdles and challenges. With many benefits, the use of AI in the pharma industry, as well as in the healthcare, is expected to continue to increase in the coming years. 

Challenges in Adopting AI in Pharmaceutical Industry:

One of the challenges to the adoption of AI in the pharmaceutical industry is the lack of clear regulatory guidance. While some regulatory agencies have provided general guidelines, there is a lack of specific regulations for the use of AI in drug discovery and development, and clinical trials. This can create uncertainty for companies that are developing AI-based solutions and may result in slower adoption of these technologies.

(1) Lack of Regulatory Framework:

The US Food and Drug Administration (FDA) have issued guidance on the use of AI and ML in medical devices, but the guidance is not specific to drug development or clinical trials.²³ In a 2019 report, the FDA acknowledged the need for specific guidance on the use of AI in drug development and stated that it was working on developing such guidance.²⁴ Similarly, the European Medicines Agency (EMA) has published a reflection paper on the use of AI in medicine, but the paper does not provide specific guidance for the pharmaceutical industry. The paper highlights the need for regulatory oversight of AI-based solutions, but it is not clear how this oversight will be implemented.²⁵ Without clear regulatory guidance, companies may be hesitant to invest in AI-based solutions for drug development and clinical trials, as they may not be sure what types of data and algorithms will be acceptable to regulatory agencies. These issues of non-specific and insufficient regulatory framework can slow down the adoption of these technologies and delay the discovery and development of new drugs.

(2) Data Quality and Availability:

Data quality and availability are significant challenges in drug design using AI. The success of any AI-based drug design approach depends heavily on the quality and quantity of data available for analysis. Here are some ways in which data quality and availability can pose challenges:

(a) Lack of standardization: Drug discovery data comes from a variety of sources, and the lack of standardization in data collection can pose significant challenges. As an example, different experiments might measure the same parameter differently, leading to inconsistencies in the data.

(b) Limited data availability: Drug discovery datasets are often small and limited, especially for rare diseases. This can make it challenging to train AI models that are both accurate and generalizeable.²⁵

(c) Data bias: Data bias can lead to inaccurate predictions and perpetuate disparities in healthcare. As an example, if clinical trial data only includes a certain demographic group, an AI model trained on that data may not be accurate for other demographic groups.

(d) Data noise: Noise in the data can also pose challenges for AI-based drug design approaches. Noise can come from a variety of sources, including experimental error, measurement errors, and outliers.

(3) Acceptance among the people:

As per the recent survey from the American Academy of Family Physicians (AAFP) shows that most people from the healthcare industry are not comfortable with the AI. The survey was taken online in Nov 2018, asked 2000 nationally representatives about their thoughts on AI in the healthcare. Amongst those interviewed 56% respondents said that they are not comfortable and only 44% said they are comfortable with it.²⁷

(4) Ethical concerns:

Data privacy and security are crucial considerations when using AI in the pharmaceutical industry, especially given the sensitive nature of patient health data. There are several ways that AI applications can pose risks to data privacy and security, such as:

(a) Data breaches: If the data used in AI applications are not properly secured, it can be vulnerable to cyber-attacks and data breaches. This can result in patient data being compromised, which can have serious consequences for both patients and healthcare providers.

(b) Misuse of data: There is a risk that AI applications may be used to extract data for purposes other than the intended use, which can lead to the misuse of patient data.

(c) Lack of transparency: AI algorithms can be opaque, making it difficult for patients and healthcare providers to understand how decisions are made and what data is being used.

In order to address these risks, it is important to implement following strong data privacy and security protocols.

(1) Encryption and secure storage: Patient data should be encrypted and stored securely to minimize the risk of data breaches.

(2) Access controls: Access to patient data should be restricted to authorized personnel only, and data should only be shared on a need-to-know basis.

(3) Transparency:

AI algorithms should be transparent and explainable so that patients and healthcare providers can understand how decisions are being made.

(4) Consent:

Patients should be informed of how their data will be used in AI applications and provide consent.

(e) Compliance: Compliance with regulatory frameworks such as HIPAA and GDPR is essential to ensure that patient data is handled in accordance with the relevant laws and regulations.

Addressing all above described challenges requires a concerted effort from researchers, data providers, and regulatory bodies. Researchers must work to develop standards for data collection and analysis to ensure that data is of high quality and can be easily integrated into AI models. Data providers must ensure that data is made available in a standardized format and is sufficiently large and diverse. Finally, regulatory bodies must develop guidelines for the collection, use, and sharing of healthcare data to ensure that data is used ethically and equitably.²⁶ Implementing these measures, pharmaceutical companies can help to ensure that patient data is kept private and secure while still benefiting from the insights and efficiencies that AI can provide.

CONCLUSION:

AI has brought significant benefits to the pharmaceutical industry. It has shown great potential in various aspects, which includes drug discovery, clinical trials, and patient care. AI-powered tools can help identify new drug targets and speed up the drug development process while reducing costs. These applications have led to improved efficiency and reduced costs in drug development Additionally, AI can aid in patient stratification and personalization of medicine, leading to more effective treatments and better health outcomes. However, the implementation of AI in the pharmaceutical industry can face several challenges, such as the need for massive amounts of data, regulatory and ethical considerations, and the integration of AI tools with existing workflows. Regulatory guidelines, lack of high-quality data, and limited transparency and interpretability of AI models remain key obstacles. The lack of transparency and interpretability of AI algorithms also poses challenges in gaining trust and acceptance from healthcare professionals and patients. There are concerns about job displacement and the ethical implications of using AI in decision-making processes. Despite the challenges, AI is expected to continue revolutionizing the pharmaceutical industry, paving the way for more efficient, precise, and personalized healthcare. Addressing the challenges and maximizing the potential benefits of AI in the pharmaceutical industry will require collaboration between industry players, regulatory bodies, and the broader healthcare ecosystem. With a concerted effort, AI can help transform the pharmaceutical industry and improve patient outcomes in the years to come and thus the potential benefits of AI in the pharmaceutical industry cannot be ignored. Continued investment and research in this area will be crucial in overcoming these challenges and realizing the full potential of AI to improve drug development and patient care.

REFERENCES:

1. Gupta R, Srivastava D, Sahu M, Tiwari S, Ambasta RK, Kumar P. AI to Deep Learning: Machine Intelligence Approach for Drug Discovery. Molecular Diversity. 2021 Aug; 25(3):1315-1360. doi: 10.1007/s11030-021-10217-3..

2. Yang X, Wang Y, Byrne R, Schneider G, Yang S. Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery. Chemical Reviews. 2019 Sep 25; 119(18): 10520-10594. doi: 10.1021/acs.chemrev.8b00728.

3. Tripathi MK, Nath A, Singh TP, Ethayathulla AS, Kaur P. Evolving Scenario of Big Data and Artificial Intelligence (AI) in Drug Discovery. Molecular Diversity. 2021 Aug; 25(3): 1439-1460. doi: 10.1007/s11030-021-10256-w.

4. Patil P, Nrip NK, Hajare AA, et al. Study of Robotic Surgeries in India: Economical Aspects and Applications in Cancer Treatment. Research Journal of Pharmacy and Technology. 2023; 16(1):429-4. doi: 10.52711/0974-360X.2023.00073

5. Sahu A, Mishra J, Kushwaha N. Artificial Intelligence (AI) in Drugs and Pharmaceuticals. Combinatorial Chemistry and High Throughput Screening. 2022; 25(11):1818-1837. doi: 10.2174/1386207325666211207153943.

6. Tripathi N, Goshisht MK, Sahu SK, Arora C. Applications of Artificial Intelligence to Drug Design and Discovery in the Big Data Era: A Comprehensive Review. Molecular Diversity. 2021 Aug; 25(3):1643-1664. doi: 10.1007/s11030-021-10237-z.

7. Paul D, Sanap G, Shenoy S, Kalyane D, Kalia K, Tekade RK. Artificial Intelligence in Drug Discovery and Development. Drug Discovery Today. 2021 Jan; 26(1):80-93. doi: 10.1016/j.drudis.2020.10.010.

8. Patil KS, Hajare AA, Manjappa AS, et al. Design, development, in silico and in vitro characterization of Docetaxel-loaded TPGS/ Pluronic F108 mixed micelles for improved cancer treatment. Journal of Drug Delivery Science and Technology, 65, 2021, 10268, https://doi.org/10.1016/j.jddst.2021.102685

9. Akhondzadeh S. The Importance of Clinical Trials in Drug Development. Avicenna Journal of Medical Biotechnology. 2016 Oct-Dec; 8(4):151. PMID: 27920881; PMCID: PMC5124250.

10. Zhong F, Xing J, Li X, Liu X, et al. Artificial intelligence in drug design. Sci China Life Sci. 2018 Oct;61(10):1191-1204. doi: 10.1007/s11427-018-9342-2.

11. Schork NJ. Artificial Intelligence and Personalized Medicine. Cancer Treat Res. 2019;178:265-283. doi: 10.1007/978-3-030-16391-4_11.

12. Awwalu, Jamilu, et al. Artificial Intelligence In Personalized Medicine Application of AI Algorithms in Solving Personalized Medicine Problems. International Journal of Computer Theory and Engineering. 2015 Dec.; 7(6), 439-443. doi: 10.7763/ijcte.2015.v7.999

13. Lamberti, Mary Jo, et al. A Study On The Application And Use Of Artificial Intelligence To Support Drug Development. Clinical Therapeutics 41.8 (2019): 1414-1426.

14. Lee JW, Maria-Solano MA, Lan VTN and Yoon SC. Big Data And Artificial Intelligence (AI) Methodologies For Computer-Aided Drug Design (CADD). Biochemical Society Transactions. 2022 Feb.; 50 (1): 241–252. doi: https://doi.org/10.1042/BST20211240

15. Basile AO, Yahi A, Tatonetti NP. Artificial Intelligence for Drug Toxicity and Safety. Trends in Pharmacological Science. 2019 Sep; 40(9):624-635. doi: 10.1016/j.tips.2019.07.005.

16. https://www.standigm.com/about/company (accessed on 10/01/2023)

17. https://www.cytoreason.com/company/ (accessed on 15/01/2023)

18. https://genomebiologics.com/technology (accessed on 08/02/2023)

19. https://bullfrogai.com/solutions/ (accessed on 08/02/2023)

20. https://www.causaly.com/company (accessed on 16/02/2023)

21. https://deepcure.ai/about-us/ (accessed on 09/03/2023)

22. https://polarisqb.com/mission/ (accessed on 16/03/2023)

23. Institute of Medicine (US) Roundtable on Research and Development of Drugs, Biologics, and Medical Devices; Davis JR, Nolan VP, Woodcock J, et al. (editors). Assuring Data Quality and Validity in Clinical Trials for Regulatory Decision Making: Workshop Report. Washington (DC): National Academies Press (US); 1999. Introduction. Available from: https://www.ncbi.nlm.nih.gov/books/NBK224582/

24. https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-software-medical-device (accessed on 08/03/2023)

25. Vokinger KN, Gasser U. Regulating AI in Medicine in the United States and Europe. Nature Machine Intelligence. 2021 Sep; 3(9):738-739. doi: 10.1038/s42256-021-00386-z.

26. Tormay P. Big Data in Pharmaceutical R&D: Creating a Sustainable R&D Engine. Pharmaceutical Medicine. 2015; 29(2):87-92. doi: 10.1007/s40290-015-0090-x. 

27. https://veritytalks.com/the-majority-of-americans-not-comfortable-healthcare-survey-says/ (accessed on 10/03/2023)

Received on 10.02.2023 Modified on 18.03.2023

Research J. Pharm. and Tech 2023; 16(4):2075-2082.

DOI: 10.52711/0974-360X.2023.00341

Organisation	Year of Establishment	Location	Technology	Products and Services
Standigm	2015	South Korea	AI- Core	Drug design
CytoReason	2016	Israel	AI and ML	Data driven drug discovery
Gnome Biologics	2016	Germany	Pattern Recognition and ML	Preclinical drug discovery
BullFrog AI	2017	USA	NLP	Advanced data analysis techniques
Causaly	2017	UK	NLP and ML	Causaly knowledge graph consisting of a variety of data sources, including biomedical literature, and clinical trials and several side effect databases
Deep Cure	2018	USA	AI, Deep Learning	Discovery of small molecule therapeutics
Polaris Quantum Biotech	2020	USA	Quantum computing-driven search of large chemical datasets	Drug design platform that can produce a drug blueprint

Benefits of AI in Pharmaceutical Industry:

Applications of AI in Pharmaceutical Industry:

Polaris Quantum Biotech

Drug design platform that can produce a drug blueprint