MaltSci 麦伴科研

Appearance

Popular Reports / Drug Discovery

This report is written by MaltSci based on the latest literature and research findings

How is AI used in drug discovery? ​

Abstract ​

The integration of artificial intelligence (AI) into drug discovery represents a transformative shift in the pharmaceutical landscape, aiming to enhance the efficiency and efficacy of developing new therapeutic agents. Traditional drug discovery processes are characterized by lengthy timelines, high costs, and substantial failure rates in clinical trials. AI, particularly through machine learning (ML), natural language processing (NLP), and predictive modeling, offers innovative solutions to streamline various stages of drug development, from target identification to lead optimization and preclinical testing. This report comprehensively reviews the current applications of AI in drug discovery, highlighting its role in target identification, hit discovery, and lead optimization. Notable advancements include AI-driven approaches that enhance predictive accuracy in drug-target interactions and optimize lead compounds. Successful case studies illustrate AI's ability to accelerate drug development timelines and facilitate drug repurposing. However, challenges such as data quality, model interpretability, and regulatory considerations persist. Future directions for AI in drug discovery emphasize the need for robust data management practices, interdisciplinary collaboration, and the establishment of standardized regulatory frameworks. Overall, AI is poised to revolutionize drug discovery by improving the speed, accuracy, and cost-effectiveness of developing new therapeutic agents, ultimately benefiting patients and society.

Outline ​

This report will discuss the following questions.

  • 1 Introduction
  • 2 The Role of AI in Drug Discovery
    • 2.1 Target Identification
    • 2.2 Hit Discovery
    • 2.3 Lead Optimization
  • 3 AI Methodologies in Drug Discovery
    • 3.1 Machine Learning Techniques
    • 3.2 Natural Language Processing Applications
    • 3.3 Predictive Modeling and Simulations
  • 4 Case Studies of AI in Drug Discovery
    • 4.1 Successful AI-Driven Drug Development Projects
    • 4.2 Lessons Learned from AI Implementations
  • 5 Challenges and Limitations
    • 5.1 Data Quality and Availability
    • 5.2 Interpretability of AI Models
    • 5.3 Regulatory Considerations
  • 6 Future Directions of AI in Drug Discovery
    • 6.1 Emerging Trends and Technologies
    • 6.2 Integration of AI with Other Technologies
  • 7 Conclusion

1 Introduction ​

The integration of artificial intelligence (AI) into drug discovery signifies a pivotal shift in the pharmaceutical landscape, promising to enhance the efficiency and efficacy of developing new therapeutic agents. Traditionally, drug discovery has been characterized by its lengthy timelines, exorbitant costs, and high failure rates in clinical trials, with estimates suggesting that it can take over a decade and cost billions of dollars to bring a new drug to market [1]. This has necessitated innovative solutions that can streamline various stages of the drug development process, from target identification to lead optimization and preclinical testing. AI, particularly through its applications in machine learning (ML), natural language processing (NLP), and predictive modeling, offers transformative capabilities that could significantly reduce the time and resources required to develop new medications [2][3].

The significance of AI in drug discovery cannot be overstated. By leveraging vast datasets and advanced computational algorithms, AI technologies can enhance the predictive accuracy of drug-target interactions, optimize lead compounds, and even assist in the design of clinical trials [4][5]. Moreover, AI has the potential to facilitate the identification of novel drug candidates and repurpose existing drugs, thereby accelerating the discovery process [6][7]. As the pharmaceutical industry continues to grapple with the complexities of drug development, AI stands out as a powerful tool that not only promises to improve outcomes but also to democratize access to innovative therapies [8].

Currently, the application of AI in drug discovery is at a nascent stage, yet it is rapidly evolving. Recent advancements in AI methodologies have led to significant breakthroughs in various phases of drug development. For instance, AI-driven approaches have shown promise in target identification, where algorithms analyze biological data to pinpoint potential therapeutic targets [1]. Additionally, AI methodologies are being utilized in hit discovery and lead optimization, where machine learning models can predict the efficacy and safety of drug candidates [2]. Furthermore, the incorporation of AI into the drug development pipeline has demonstrated the ability to process millions of compounds within hours, a feat that would have taken years using traditional methods [1].

This report is structured to provide a comprehensive overview of the current applications of AI in drug discovery, covering several key areas. Section 2 delves into the specific roles AI plays in drug discovery, including target identification, hit discovery, and lead optimization. Section 3 examines the various AI methodologies employed in drug discovery, such as machine learning techniques, natural language processing applications, and predictive modeling. In Section 4, we present case studies that highlight successful AI-driven drug development projects and the lessons learned from these implementations. Section 5 discusses the challenges and limitations faced in the integration of AI within drug discovery, focusing on data quality, interpretability of AI models, and regulatory considerations. Section 6 looks ahead to the future directions of AI in drug discovery, exploring emerging trends and the potential integration of AI with other technologies. Finally, Section 7 concludes with a summary of the findings and their implications for stakeholders in the biomedical field.

In summary, AI is poised to revolutionize the drug discovery process by enhancing the speed, accuracy, and cost-effectiveness of developing new therapeutic agents. As we explore the current landscape and future prospects of AI in this domain, it is crucial to remain cognizant of the challenges that accompany these advancements, ensuring that the potential of AI is harnessed responsibly and effectively for the benefit of patients and society at large.

2 The Role of AI in Drug Discovery ​

2.1 Target Identification ​

Artificial intelligence (AI) plays a transformative role in drug discovery, particularly in the critical phase of target identification. This process involves determining the biological targets for new therapeutics, which is essential for the success of drug development. Traditional methods of target identification are often time-consuming and resource-intensive, taking years to decades to yield results. In contrast, AI offers innovative solutions that significantly enhance the efficiency and accuracy of this phase.

AI methodologies, including machine learning (ML) and deep learning (DL), are increasingly utilized to analyze large datasets and complex biological networks, thereby facilitating the identification of potential drug targets. These advanced techniques can effectively process and interpret vast amounts of biological data, leading to quicker and more reliable target identification compared to conventional methods. For instance, AI can streamline the analysis of genetic, proteomic, and metabolomic data, allowing researchers to pinpoint targets that may have been overlooked in traditional studies (Pun et al. 2023; Visan & Negut 2024).

Recent advancements in AI-driven therapeutic target exploration have shown promising results. AI systems can not only identify novel targets but also evaluate their potential therapeutic efficacy. This dual capability allows for a more systematic approach to drug discovery, where the probability of success can be enhanced at each step of the development process. AI-derived targets are increasingly validated through experimental methods, leading to a growing number of AI-identified drugs entering clinical trials (Pun et al. 2023).

Moreover, AI aids in the repositioning of existing drugs, enabling the identification of new therapeutic uses for already approved compounds. This is particularly beneficial as it can shorten development timelines and reduce costs associated with bringing new drugs to market (Wang et al. 2025). The ability to predict drug-target interactions (DTIs) using AI further complements the target identification process, as it allows for the exploration of how different compounds may interact with the identified targets (Yang & Cheng 2025).

AI's integration into drug discovery not only enhances the efficiency of target identification but also opens new avenues for polypharmacology, where drugs are designed to target multiple pathways or disease mechanisms simultaneously. This approach is particularly relevant for complex diseases, where targeting a single pathway may not be sufficient for effective treatment (Cichońska et al. 2024; Mukaidaisi et al. 2024).

In summary, AI's application in target identification within drug discovery represents a paradigm shift. By leveraging advanced computational techniques, AI significantly reduces the time and cost associated with traditional target identification methods, while also increasing the likelihood of success in drug development. The ongoing evolution of AI technologies promises to further enhance the precision and efficacy of drug discovery efforts, ultimately leading to the development of more effective therapies for various diseases.

2.2 Hit Discovery ​

Artificial intelligence (AI) is increasingly recognized as a transformative force in the field of drug discovery, particularly in the context of hit discovery, which involves identifying potential drug candidates that exhibit desirable biological activity. The integration of AI into this process addresses several traditional challenges associated with drug development, including high costs, lengthy timelines, and low success rates.

AI technologies, particularly machine learning and deep learning, are employed to enhance various stages of drug discovery. These technologies can analyze vast datasets and identify patterns that may not be readily apparent to human researchers. For instance, AI algorithms can screen millions of compounds in a matter of hours, drastically reducing the time required to identify potential drug candidates compared to conventional methods[1]. This capability is crucial in hit discovery, where the goal is to rapidly identify molecules that can interact effectively with specific biological targets.

One of the primary applications of AI in hit discovery is in the area of virtual screening. AI can assist in structure-based and ligand-based virtual screening, allowing researchers to evaluate the binding affinity of numerous compounds to a target protein without the need for extensive laboratory testing. This approach can facilitate the identification of novel hits that might have been overlooked using traditional methods[5]. Additionally, AI-driven platforms can optimize the chemical properties of these hits, predicting their pharmacokinetic and toxicological profiles early in the development process[9].

Furthermore, AI's ability to process and learn from complex biological data enhances the understanding of drug-target interactions (DTIs). By leveraging large datasets, AI can predict the efficacy and safety of drug candidates, which is essential for prioritizing compounds for further development. For example, AI has been shown to improve the accuracy of DTI predictions, thereby streamlining the drug discovery process and potentially increasing the success rates of clinical trials[10].

The integration of AI with computational chemistry methods also plays a significant role in hit identification. Novel workflows that combine AI with high-accuracy computational chemistry have been developed, leading to the discovery of potent hit compounds against specific targets, such as cancer-related proteins[11]. These workflows not only facilitate hit identification but also enable the optimization of lead compounds, enhancing their biological activity and therapeutic potential.

Moreover, AI's capabilities extend to the de novo design of drug candidates, where it can generate novel molecules based on desired biological activity and physicochemical properties. This process can lead to the discovery of entirely new classes of drugs that may not have been possible through traditional drug design approaches[12].

In summary, AI plays a pivotal role in hit discovery within drug development by enhancing virtual screening processes, improving predictions of drug-target interactions, optimizing chemical properties, and facilitating the de novo design of new compounds. These advancements not only accelerate the identification of promising drug candidates but also significantly reduce the costs and risks associated with traditional drug discovery methodologies[13][14]. As AI technologies continue to evolve, their integration into drug discovery is expected to expand, potentially revolutionizing the pharmaceutical landscape.

2.3 Lead Optimization ​

Artificial intelligence (AI) plays a transformative role in drug discovery, particularly in the phase of lead optimization. This phase is crucial as it involves refining lead compounds to improve their efficacy, safety, and pharmacokinetic properties. AI methodologies enhance the lead optimization process through various innovative approaches.

One of the significant advancements is the use of AI-driven molecular optimization techniques. These methods leverage machine learning (ML) and deep learning (DL) algorithms to analyze large datasets and identify patterns that inform the optimization of drug candidates. For instance, AI can predict the properties of lead molecules and suggest modifications that could enhance their biological activity while maintaining structural integrity. This optimization is vital for navigating the complex chemical space, which is characterized by high-dimensional data and the need for maintaining the desired molecular profiles [15].

Furthermore, AI aids in the iterative search for lead compounds within discrete and continuous chemical spaces. Techniques such as generative models allow researchers to design novel compounds by exploring vast chemical libraries, thereby increasing the chances of identifying effective drug candidates [15]. Additionally, AI can streamline the evaluation of lead candidates by predicting their ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) properties, which are critical for determining the viability of compounds for further development [2].

The integration of AI into lead optimization processes also addresses challenges such as data sparsity and the high costs associated with traditional drug development methods. By utilizing AI, researchers can reduce the time and resources needed to screen potential drug candidates, leading to more efficient development pipelines [16]. For example, AI algorithms can analyze biological data and predict the interactions between drugs and their targets, thus facilitating the identification of optimal lead candidates [3].

Moreover, AI-driven approaches enhance the precision of lead optimization by enabling the design of compounds that are not only potent but also possess favorable pharmacokinetic profiles. This capability is particularly important in the context of personalized medicine, where tailored therapies can be developed based on individual patient profiles [17].

In summary, AI significantly enhances lead optimization in drug discovery by improving the efficiency of compound design, enabling rapid exploration of chemical space, and providing predictive insights into the properties of drug candidates. This integration not only accelerates the drug development process but also increases the likelihood of successful therapeutic outcomes, marking a substantial shift in pharmaceutical innovation [18][19].

3 AI Methodologies in Drug Discovery ​

3.1 Machine Learning Techniques ​

Artificial intelligence (AI), particularly machine learning (ML), has become a transformative force in drug discovery, addressing traditional challenges such as high costs, lengthy timelines, and low success rates. The integration of AI methodologies into various phases of drug development enhances efficiency and effectiveness, enabling researchers to streamline processes that were previously time-consuming and resource-intensive.

One of the primary applications of AI in drug discovery is in the identification of drug targets. Machine learning algorithms can analyze vast datasets to identify potential therapeutic targets by recognizing patterns and relationships within biological data. For instance, AI techniques can assist in phenotypic prediction, where sets of genes associated with specific phenotypes are determined, thus aiding in the identification of novel drug targets [20].

Moreover, AI facilitates high-throughput screening and virtual screening of compounds. Advanced algorithms can quickly evaluate millions of chemical compounds, identifying potential drug candidates in a fraction of the time it would take using traditional methods. This capability is particularly beneficial for de novo drug design, where machine learning models generate novel drug-like compounds with desired properties [21]. The use of deep learning models, such as convolutional neural networks (CNNs) and generative adversarial networks (GANs), has shown promise in optimizing lead compounds and predicting their efficacy and safety [16][21].

AI also plays a critical role in predicting drug-target interactions (DTIs). By employing deep learning and network-based methods, AI can streamline the prediction of DTIs, thus reducing the reliance on costly experimental assays and enhancing the success rates of drug discovery [10]. Furthermore, AI-driven models are capable of evaluating drug properties such as absorption, distribution, metabolism, excretion, and toxicity (ADMET), which are crucial for determining the viability of drug candidates [22].

In addition to identifying new drug candidates, AI methodologies support drug repurposing efforts. By analyzing existing drugs and their mechanisms, AI can uncover new therapeutic applications, potentially accelerating the availability of treatments for various diseases [5].

Despite the significant advantages offered by AI in drug discovery, challenges remain. Issues such as data quality, model interpretability, and ethical considerations are critical hurdles that need to be addressed to fully realize the potential of AI in this field [16][23]. The development of standardized datasets, transparent algorithms, and collaborative efforts among interdisciplinary teams will be essential for overcoming these challenges and advancing AI applications in drug discovery.

Overall, the application of machine learning techniques within AI has the potential to revolutionize drug discovery, making it more efficient and effective while paving the way for innovative therapies that meet unmet medical needs. As AI technology continues to evolve, its role in drug discovery is expected to expand, offering new opportunities for enhancing patient care and advancing pharmaceutical research [24][25].

3.2 Natural Language Processing Applications ​

Artificial Intelligence (AI) has significantly transformed drug discovery by integrating various methodologies, including Natural Language Processing (NLP), which plays a pivotal role in enhancing the efficiency and effectiveness of this complex process. AI technologies, particularly machine learning (ML) and deep learning (DL), are utilized to address the traditional challenges faced in drug discovery, such as high costs, lengthy timelines, and low success rates.

NLP applications in drug discovery primarily focus on extracting and analyzing vast amounts of textual data from scientific literature, clinical trial reports, and other relevant sources. This capability allows researchers to identify new drug targets, comprehend existing knowledge, and facilitate data-driven decision-making. For instance, NLP can be employed to mine information about drug interactions, side effects, and patient outcomes from unstructured data, thus accelerating the identification of potential therapeutic candidates.

Moreover, NLP techniques can enhance the drug repurposing process by analyzing existing drug data to uncover new indications for already approved medications. By leveraging large datasets, NLP can facilitate the identification of relationships between drugs and diseases, enabling researchers to explore novel applications of existing compounds more efficiently.

AI methodologies, including NLP, contribute to various stages of drug discovery. For example, during target identification, NLP can sift through scientific publications to highlight potential biological targets for drug action. In lead optimization, AI algorithms can analyze chemical databases to suggest modifications to molecular structures that enhance efficacy and reduce toxicity.

Furthermore, NLP can assist in the optimization of clinical trials by analyzing historical trial data to predict outcomes and improve trial design. This predictive capability can lead to more informed decisions regarding patient recruitment and study parameters, ultimately increasing the success rates of clinical trials.

Despite the promising applications of NLP in drug discovery, challenges remain. Issues related to data quality, model interpretability, and ethical considerations need to be addressed to fully harness the potential of AI in this field. Enhanced algorithms, standardized databases, and interdisciplinary collaboration are essential to overcome these hurdles and facilitate the integration of AI technologies into drug discovery processes [13][16][24].

In conclusion, AI, particularly through NLP applications, is reshaping the landscape of drug discovery by improving data analysis, enhancing decision-making, and streamlining various phases of the drug development process. As AI technologies continue to evolve, their role in drug discovery is expected to expand, offering innovative solutions to meet the challenges of modern pharmaceutical research [1][2][5].

3.3 Predictive Modeling and Simulations ​

Artificial Intelligence (AI) has significantly transformed the landscape of drug discovery by introducing advanced methodologies that enhance predictive modeling and simulations. These AI-driven approaches address the inherent challenges of traditional drug discovery, which often involves lengthy and costly experimental procedures.

One of the primary applications of AI in drug discovery is the prediction of drug-target interactions (DTIs). AI techniques, particularly machine learning (ML) and deep learning (DL), are employed to analyze complex biological data and identify potential interactions between drugs and their targets. These methods streamline the DTI prediction process, reducing the time and costs associated with experimental assays. By utilizing large datasets, AI models can effectively extract molecular features and perform in-depth analyses, improving the accuracy of predictions and enhancing the success rates of drug development [10].

Moreover, AI methodologies are crucial in predicting various pharmacological properties of drug candidates, such as toxicity, bioactivity, and physicochemical characteristics. For instance, AI algorithms can forecast drug toxicity by analyzing extensive toxicity databases and employing multimodal data fusion strategies. This capability allows researchers to evaluate different toxicity endpoints, including acute toxicity and organ-specific toxicity, thereby ensuring the safety of potential therapeutics before they proceed to clinical trials [26].

In addition to toxicity prediction, AI facilitates de novo drug design and lead optimization. AI models can generate novel drug candidates by simulating chemical interactions and predicting the properties of new molecules. Techniques such as generative adversarial networks (GANs) and reinforcement learning are increasingly utilized to explore vast chemical spaces, optimizing the discovery of compounds with desired therapeutic effects [16]. This capability not only accelerates the identification of viable drug candidates but also reduces the reliance on traditional trial-and-error methods.

Furthermore, AI-enhanced virtual screening processes allow researchers to evaluate millions of compounds in a fraction of the time required by conventional methods. By leveraging AI for virtual screening, researchers can prioritize compounds based on predicted binding affinities and pharmacokinetic profiles, significantly shortening the drug discovery timeline [27].

The integration of AI in drug discovery also extends to clinical trial optimization. AI algorithms can analyze historical clinical data to predict trial outcomes, design more efficient trial protocols, and enhance patient recruitment strategies. This application of AI contributes to reducing the overall costs and duration of clinical trials, ultimately facilitating faster access to new therapies [7].

In summary, AI methodologies in drug discovery leverage predictive modeling and simulations to enhance various stages of the drug development process. By improving the accuracy of drug-target interaction predictions, optimizing lead compounds, and streamlining clinical trial designs, AI plays a pivotal role in addressing the complexities of drug discovery and development, thereby paving the way for innovative therapeutic solutions.

4 Case Studies of AI in Drug Discovery ​

4.1 Successful AI-Driven Drug Development Projects ​

Artificial Intelligence (AI) has emerged as a transformative force in drug discovery, fundamentally altering traditional methodologies and enhancing various stages of the drug development process. Several case studies illustrate the successful application of AI in this domain, showcasing its potential to identify novel therapeutic agents and optimize development timelines.

One notable example is the work of Insilico Medicine, which utilized AI to design a molecule specifically for idiopathic pulmonary fibrosis. This project highlights how AI can facilitate de novo drug design by predicting the properties and activities of new compounds, ultimately leading to the identification of viable drug candidates. The AI-designed molecule progressed rapidly through the development pipeline, underscoring the efficiency of AI in accelerating drug discovery processes[16].

Another significant case involves BenevolentAI, which employed AI to identify baricitinib as a treatment for COVID-19. This instance illustrates the capability of AI in drug repurposing, where existing drugs are analyzed for new therapeutic applications. The ability of AI to sift through vast datasets and identify patterns has proven invaluable in rapidly addressing urgent public health challenges, such as the COVID-19 pandemic[16].

Additionally, the integration of AI technologies has been demonstrated in the identification of a novel class of antibiotics. This case study exemplifies how AI can enhance the discovery of new drug classes by modeling complex interactions and predicting the efficacy of various compounds against specific bacterial targets. Such advancements not only contribute to the arsenal of available antibiotics but also address the growing concern of antibiotic resistance[28].

AI's role in optimizing clinical trials is also noteworthy. By predicting outcomes and designing more efficient trial protocols, AI has the potential to improve success rates in clinical testing. For instance, a study analyzing AI-discovered drugs found that molecules designed with AI achieved an 80-90% success rate in Phase I clinical trials, significantly higher than historical averages. Although the success rate in Phase II trials was approximately 40%, this still aligns with industry standards, suggesting that AI can effectively identify drug candidates with favorable properties[29].

Furthermore, AI has facilitated advancements in drug-target interaction prediction and lead optimization, enhancing the accuracy of these processes and reducing the costs associated with trial-and-error methodologies. This systematic approach to modeling relationships among drugs, targets, and diseases has improved the likelihood of successful drug development outcomes[2].

In summary, the application of AI in drug discovery is exemplified by successful projects such as those from Insilico Medicine and BenevolentAI, demonstrating AI's ability to accelerate drug design, repurpose existing medications, and optimize clinical trial processes. As AI technologies continue to evolve, they hold promise for further enhancing the efficiency and success rates of drug development, paving the way for innovative therapeutic solutions to meet unmet medical needs[16][28][29].

4.2 Lessons Learned from AI Implementations ​

Artificial Intelligence (AI) is increasingly integrated into various stages of drug discovery, offering transformative solutions that enhance efficiency, reduce costs, and improve success rates. Several case studies highlight the practical applications of AI in this field, demonstrating its significant impact on drug development processes.

One notable example is Insilico Medicine, which utilized AI to design a novel molecule for idiopathic pulmonary fibrosis. The company employed deep learning algorithms to generate and optimize drug candidates, significantly expediting the drug discovery timeline. This approach allowed for the identification of viable compounds that would have traditionally taken years to develop through conventional methods. Similarly, BenevolentAI successfully identified baricitinib for COVID-19 treatment by leveraging AI-driven insights to repurpose existing drugs, showcasing the potential of AI in drug repositioning and accelerating the response to urgent health crises [16].

In the realm of clinical trials, AI has been pivotal in optimizing trial design and execution. AI algorithms can analyze vast datasets to predict outcomes, streamline patient recruitment, and enhance trial efficiency. For instance, machine learning models are used to identify suitable candidates for clinical trials based on complex criteria, thus improving enrollment rates and ensuring that trials are conducted more effectively [7].

Furthermore, AI technologies such as AlphaFold have revolutionized protein structure prediction, aiding in the identification of new drug targets and improving the understanding of disease mechanisms. This has allowed researchers to design targeted therapies more efficiently [16].

Lessons learned from these implementations emphasize the importance of data quality and accessibility. High-quality datasets are crucial for training AI models, and the success of AI applications often hinges on the availability of comprehensive and well-structured data. Moreover, ethical considerations regarding data privacy and the interpretability of AI models remain critical challenges that must be addressed to fully realize the potential of AI in drug discovery [23].

The integration of AI in drug discovery is not without its challenges. Issues such as the need for robust data-sharing mechanisms, the establishment of comprehensive intellectual property protections for AI algorithms, and the integration of biological sciences with computational methods are vital for the future success of AI-driven drug development [7]. Despite these hurdles, the trajectory of AI in pharmaceuticals suggests a promising future, where AI technologies will increasingly facilitate the development of innovative and effective therapies for unmet medical needs [3].

In conclusion, AI's role in drug discovery is multifaceted, ranging from target identification and drug design to clinical trial optimization and drug repurposing. The ongoing advancements in AI technologies are poised to further revolutionize the pharmaceutical industry, making drug development faster, more efficient, and ultimately more successful in delivering new treatments to patients.

5 Challenges and Limitations ​

5.1 Data Quality and Availability ​

Artificial intelligence (AI) is increasingly being integrated into drug discovery processes, revolutionizing how potential therapeutic candidates are identified, optimized, and brought to market. However, despite its transformative potential, the application of AI in this field faces significant challenges, particularly concerning data quality and availability.

AI's effectiveness in drug discovery is heavily reliant on the quality and quantity of data utilized to train and test its algorithms. High-quality data is crucial because AI models learn from existing datasets to make predictions about new compounds. Insufficient, unlabeled, and non-uniform data present notable limitations, which can severely impact the accuracy and reliability of AI-driven outcomes (Gangwal et al. 2024). Moreover, the resemblance of some AI-generated molecules to existing compounds raises concerns about novelty and patentability, which can hinder innovation (Gangwal et al. 2024).

Data quality issues can manifest in several ways, including bias, inconsistency, skewness, and irrelevance. These factors can compromise the performance of AI models, leading to misleading predictions and ineffective drug candidates (Ghislat et al. 2024). For instance, the reliance on retrospective benchmarks that do not accurately predict prospective performance can limit the applicability of AI models in real-world scenarios, resulting in a failure to discover novel and effective drug leads (Ghislat et al. 2024).

Furthermore, data scarcity is particularly problematic in the context of rare diseases, where the limited availability of relevant datasets can stifle the development of effective treatments. AI has the potential to integrate heterogeneous datasets and leverage expert biological knowledge to overcome these challenges, but the routine use of AI in the conservative pharmaceutical domain remains constrained by data access issues (Napolitano et al. 2024).

To address these challenges, several strategies have been proposed. Techniques such as transfer learning, active learning, single or one-shot learning, multi-task learning, data augmentation, and data synthesis can help mitigate the effects of low data availability and improve AI model outputs (Gangwal et al. 2024). Additionally, federated learning offers a promising avenue for sharing proprietary data across different entities while maintaining data privacy, thereby enriching the datasets available for training AI models (Gangwal et al. 2024).

In summary, while AI holds great promise for enhancing drug discovery, the challenges associated with data quality and availability remain significant barriers. The integration of robust data management practices, alongside innovative learning techniques, is essential for unlocking the full potential of AI in this domain and ensuring that it contributes effectively to the development of new therapeutic agents.

5.2 Interpretability of AI Models ​

Artificial intelligence (AI) has become an integral part of the drug discovery process, offering significant advantages in efficiency, accuracy, and speed. However, the application of AI in this field is not without challenges, particularly regarding the interpretability of AI models.

AI technologies, including machine learning (ML) and deep learning (DL), are employed throughout various stages of drug discovery. They enhance processes such as target identification, lead optimization, and drug repurposing by analyzing vast datasets more rapidly than traditional methods. For instance, AI can conduct swift screenings of extensive compound libraries, predict the efficacy and safety profiles of candidate compounds, and streamline the drug development pipeline, ultimately improving the success rate of clinical trials [30].

Despite these advancements, a significant challenge in the deployment of AI in drug discovery is the interpretability of AI models. The "black-box" nature of many AI algorithms complicates the understanding of how decisions are made. This lack of transparency can hinder the acceptance of AI-driven solutions within the scientific and regulatory communities, as stakeholders often require clear explanations of model predictions to trust and validate the outcomes [31].

Several studies emphasize the importance of explainable AI (XAI) techniques to address this issue. XAI methods aim to elucidate the decision-making processes of AI models, thereby enhancing their transparency. Techniques such as SHAP (SHapley Additive exPlanations) and LIME (Locally Interpretable Model-agnostic Explanations) can provide insights into the contributions of different features in the model's predictions, making it easier for researchers to understand and trust the AI's recommendations [32].

Furthermore, challenges related to data quality also impact model interpretability. High-quality, diverse datasets are essential for training robust AI models. However, issues such as bias, inconsistency, and limited data accessibility can affect the reliability of AI predictions [33]. Moreover, AI models trained on biased datasets may yield misleading results, which further complicates the interpretability of their outputs [31].

To enhance interpretability and trust in AI models, it is crucial to integrate interdisciplinary collaboration, where AI developers work closely with domain experts in biology and pharmacology. This collaboration can lead to the development of AI frameworks that are not only effective but also biologically contextualized, ensuring that AI applications align more closely with real-world biological processes [34].

In conclusion, while AI holds great promise in revolutionizing drug discovery, its effective application is contingent upon overcoming challenges related to the interpretability of models. Emphasizing explainability, improving data quality, and fostering collaboration between AI and domain experts are vital steps toward harnessing the full potential of AI in drug discovery.

5.3 Regulatory Considerations ​

Artificial Intelligence (AI) has emerged as a transformative force in drug discovery, revolutionizing traditional methodologies and enhancing the efficiency and effectiveness of the drug development process. AI applications in drug discovery encompass various stages, including target identification, lead optimization, virtual screening, and clinical trial design, among others. However, the integration of AI into drug discovery also presents several challenges and limitations, particularly in regulatory considerations.

AI technologies, particularly machine learning (ML) and deep learning (DL), are utilized to analyze vast datasets, enabling the identification of new drug targets and the design of novel molecules. These technologies can predict the efficacy and safety profiles of potential drug candidates, significantly reducing the time and cost associated with traditional drug discovery methods. For instance, AI algorithms can screen millions of compounds in a matter of hours, identifying candidates that might take years to discover using conventional approaches [1][30]. Additionally, AI can facilitate the prediction of pharmacokinetics and toxicity, allowing for a more targeted and efficient approach to drug development [17].

Despite these advancements, the deployment of AI in drug discovery is not without challenges. One of the primary hurdles is the need for high-quality, diverse datasets. AI models rely heavily on the data fed into them, and poor data quality can lead to unreliable predictions and outcomes [35]. Furthermore, the interpretability of AI models is crucial for regulatory acceptance. Regulatory bodies require transparency in AI-driven decisions to ensure that they meet safety and efficacy standards [30]. This necessitates the development of explainable AI (XAI) frameworks that can elucidate how AI models arrive at their conclusions, thereby fostering trust among regulatory agencies and stakeholders [36].

Ethical considerations also play a significant role in the regulatory landscape of AI in drug discovery. Issues such as data privacy, bias in AI algorithms, and the ethical use of AI-generated data need to be addressed comprehensively. The lack of established standards and guidelines for the use of AI in drug regulation poses an additional challenge, as it can lead to inconsistencies in how different regulatory agencies approach AI technologies [35][37].

As AI continues to evolve, it is essential for regulatory bodies to adapt their frameworks to accommodate these technologies. Interdisciplinary collaboration among AI experts, regulatory professionals, and pharmaceutical scientists is vital to navigate the complexities associated with AI integration in drug discovery. This collaboration can help establish best practices and guidelines that ensure the safe and effective use of AI in drug development [6][35].

In summary, while AI offers substantial benefits in drug discovery by improving efficiency and reducing costs, its implementation faces significant challenges related to data quality, model interpretability, ethical considerations, and regulatory standards. Addressing these challenges is critical for realizing the full potential of AI in transforming the pharmaceutical landscape.

6 Future Directions of AI in Drug Discovery ​

6.1 Emerging Trends and Technologies ​

Artificial Intelligence (AI) is increasingly integrated into drug discovery, fundamentally transforming traditional methodologies and paving the way for innovative approaches. The application of AI spans various stages of the drug development process, including target identification, lead optimization, and clinical trial design, thereby enhancing efficiency and reducing costs associated with drug discovery.

One significant trend is the utilization of machine learning (ML) and deep learning (DL) algorithms to analyze vast datasets. These algorithms are capable of discerning patterns that may not be immediately evident to human researchers, which is crucial in the early stages of drug discovery. For instance, AI can expedite the identification of new drug targets and optimize lead compounds by predicting their pharmacokinetic and pharmacodynamic properties [7].

AI methodologies are also employed in virtual screening, where algorithms can evaluate millions of compounds rapidly, identifying potential drug candidates that would have taken years to discover using conventional methods [1]. This capability not only accelerates the drug discovery timeline but also improves the predictive accuracy of drug interactions and efficacy, leading to higher success rates in clinical trials [16].

Furthermore, AI plays a critical role in drug repositioning, where existing drugs are identified for new therapeutic uses. This process benefits from AI's ability to analyze existing clinical data and predict new applications for already approved drugs, significantly shortening the development timeline for new treatments [5].

Despite these advancements, challenges remain, including issues related to data quality, model interpretability, and ethical considerations surrounding AI applications in healthcare [23]. Addressing these challenges is essential for the broader adoption of AI technologies in drug discovery. Future directions may involve the establishment of standardized regulatory frameworks to govern AI applications in pharmaceuticals, ensuring safe and equitable implementation [38].

The ongoing evolution of AI technology suggests a promising future where its integration into drug discovery not only enhances efficiency but also fosters innovations that can lead to novel therapeutic agents [16]. Collaborative efforts between computational scientists and domain experts will be vital to harness AI's full potential in revolutionizing drug discovery and development processes [6].

6.2 Integration of AI with Other Technologies ​

Artificial Intelligence (AI) is significantly transforming the landscape of drug discovery by enhancing various stages of the drug development process. The integration of AI technologies, such as machine learning (ML) and deep learning (DL), is not only improving the efficiency and accuracy of drug discovery but also facilitating the development of novel therapeutics. The application of AI in drug discovery encompasses several key areas, including target identification, compound screening, biomarker discovery, and clinical trial optimization.

One of the primary roles of AI in drug discovery is in the identification of drug targets. By analyzing vast datasets, AI algorithms can rapidly identify and validate new drug targets, which is critical for developing effective therapies. For instance, machine learning techniques are utilized to analyze complex biological data, allowing researchers to discern patterns that may indicate potential therapeutic targets [39][40]. Furthermore, AI-driven approaches in molecular modeling and virtual screening enable the efficient design of new drug candidates by predicting their interactions with biological targets [6][7].

In addition to target identification, AI enhances the drug design process through computer-aided drug design (CADD) and generative artificial intelligence (GAI). These technologies allow for the rapid generation and optimization of molecular structures, predicting their pharmacokinetic and pharmacodynamic properties [16][23]. The use of AI in this context not only accelerates the discovery of novel compounds but also minimizes the associated costs and time traditionally required for drug development [7][40].

AI also plays a crucial role in optimizing clinical trial designs. By leveraging data analytics, AI can improve patient recruitment and stratification, thus enhancing the efficiency of clinical trials and reducing their duration and costs [39][40]. This is particularly important as traditional clinical trials often face challenges related to patient variability and recruitment timelines.

Looking towards the future, the integration of AI with other technologies, such as big data analytics and digital health tools, is expected to further revolutionize drug discovery. The combination of AI with high-throughput screening (HTS) techniques can facilitate the rapid evaluation of thousands of compounds, significantly expediting the drug discovery process [4][40]. Additionally, the use of AI in conjunction with bioinformatics and systems biology will likely enhance the understanding of complex biological systems, leading to more precise and personalized medicine [3][23].

Despite the promising advancements, several challenges remain. Issues related to data quality, integration, model interpretability, and ethical considerations must be addressed to fully realize the potential of AI in drug discovery [16][38]. The establishment of standardized regulations and collaborative frameworks will be essential to ensure the responsible and equitable implementation of AI technologies in the pharmaceutical industry [7][38].

In summary, AI is poised to play a transformative role in drug discovery by enhancing the efficiency of the drug development pipeline, improving the accuracy of target identification, and optimizing clinical trial processes. The future directions of AI in this field will likely focus on its integration with other technological advancements, further accelerating the discovery and development of innovative therapies.

7 Conclusion ​

The integration of artificial intelligence (AI) in drug discovery has ushered in a new era of pharmaceutical development, fundamentally altering traditional methodologies and enhancing the efficiency and effectiveness of the drug development process. Key findings indicate that AI significantly improves target identification, hit discovery, and lead optimization by leveraging vast datasets and advanced computational algorithms. The successful application of AI technologies, such as machine learning and natural language processing, demonstrates their potential to streamline various stages of drug development, reduce costs, and accelerate timelines. However, challenges remain, particularly regarding data quality, model interpretability, and regulatory considerations. Moving forward, addressing these challenges will be crucial for realizing the full potential of AI in drug discovery. Future research should focus on developing standardized regulatory frameworks, enhancing data sharing practices, and fostering interdisciplinary collaboration between AI developers and domain experts. As AI technologies continue to evolve, they hold the promise of not only revolutionizing drug discovery but also delivering innovative therapeutic solutions that meet unmet medical needs.

References ​

  • [1] Periyasamy Natarajan Shiammala;Navaneetha Krishna Bose Duraimutharasan;Baskaralingam Vaseeharan;Abdulaziz S Alothaim;Esam S Al-Malki;Babu Snekaa;Sher Zaman Safi;Sanjeev Kumar Singh;Devadasan Velmurugan;Chandrabose Selvaraj. Exploring the artificial intelligence and machine learning models in the context of drug design difficulties and future potential for the pharmaceutical sectors.. Methods (San Diego, Calif.)(IF=4.3). 2023. PMID:37778659. DOI: 10.1016/j.ymeth.2023.09.010.
  • [2] Qiqi Wang;Boyan Sun;Yunpeng Yi;Tony Velkov;Jianzhong Shen;Chongshan Dai;Haiyang Jiang. Progress of AI-Driven Drug-Target Interaction Prediction and Lead Optimization.. International journal of molecular sciences(IF=4.9). 2025. PMID:41155330. DOI: 10.3390/ijms262010037.
  • [3] Ashfaq Ur Rehman;Mingyu Li;Binjian Wu;Yasir Ali;Salman Rasheed;Sana Shaheen;Xinyi Liu;Ray Luo;Jian Zhang. Role of artificial intelligence in revolutionizing drug discovery.. Fundamental research(IF=6.3). 2025. PMID:40528990. DOI: 10.1016/j.fmre.2024.04.021.
  • [4] Mahroza Kanwal Khan;Mohsin Raza;Muhammad Shahbaz;Iftikhar Hussain;Muhammad Farooq Khan;Zhongjian Xie;Syed Shoaib Ahmad Shah;Ayesha Khan Tareen;Zoobia Bashir;Karim Khan. The recent advances in the approach of artificial intelligence (AI) towards drug discovery.. Frontiers in chemistry(IF=4.2). 2024. PMID:38882215. DOI: 10.3389/fchem.2024.1408740.
  • [5] Anita Ioana Visan;Irina Negut. Integrating Artificial Intelligence for Drug Discovery in the Context of Revolutionizing Drug Delivery.. Life (Basel, Switzerland)(IF=3.4). 2024. PMID:38398742. DOI: 10.3390/life14020233.
  • [6] Ri Han;Hongryul Yoon;Gahee Kim;Hyundo Lee;Yoonji Lee. Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery.. Pharmaceuticals (Basel, Switzerland)(IF=4.8). 2023. PMID:37765069. DOI: 10.3390/ph16091259.
  • [7] Chen Fu;Qiuchen Chen. The future of pharmaceuticals: Artificial intelligence in drug discovery and development.. Journal of pharmaceutical analysis(IF=8.9). 2025. PMID:40893437. DOI: 10.1016/j.jpha.2025.101248.
  • [8] Sean Ekins;Thomas R Lane. Applications of artificial intelligence in drug discovery for neurological diseases.. Neurotherapeutics : the journal of the American Society for Experimental NeuroTherapeutics(IF=6.9). 2025. PMID:40533306. DOI: 10.1016/j.neurot.2025.e00624.
  • [9] Jordi Carreras-Puigvert;Ola Spjuth. Artificial intelligence for high content imaging in drug discovery.. Current opinion in structural biology(IF=7.0). 2024. PMID:38797109. DOI: 10.1016/j.sbi.2024.102842.
  • [10] Yuxin Yang;Feixiong Cheng. Artificial intelligence streamlines scientific discovery of drug-target interactions.. British journal of pharmacology(IF=7.7). 2025. PMID:39843168. DOI: 10.1111/bph.17427.
  • [11] Lin Wei;Min Xu;Zhiqiang Liu;Chongguo Jiang;Xiaohua Lin;Yaogang Hu;Xiaoming Wen;Rongfeng Zou;Chunwang Peng;Hongrui Lin;Guo Wang;Lijun Yang;Lei Fang;Mingjun Yang;Peiyu Zhang. Hit Identification Driven by Combining Artificial Intelligence and Computational Chemistry Methods: A PI5P4K-β Case Study.. Journal of chemical information and modeling(IF=5.3). 2023. PMID:37549337. DOI: 10.1021/acs.jcim.3c00543.
  • [12] Gerhard Hessler;Karl-Heinz Baringhaus. Artificial Intelligence in Drug Design.. Molecules (Basel, Switzerland)(IF=4.6). 2018. PMID:30279331. DOI: 10.3390/molecules23102520.
  • [13] Hyunho Kim;Eunyoung Kim;Ingoo Lee;Bongsung Bae;Minsu Park;Hojung Nam. Artificial Intelligence in Drug Discovery: A Comprehensive Review of Data-driven and Machine Learning Approaches.. Biotechnology and bioprocess engineering : BBE(IF=3.0). 2020. PMID:33437151. DOI: 10.1007/s12257-020-0049-y.
  • [14] Frank W Pun;Ivan V Ozerov;Alex Zhavoronkov. AI-powered therapeutic target discovery.. Trends in pharmacological sciences(IF=19.9). 2023. PMID:37479540. DOI: 10.1016/j.tips.2023.06.010.
  • [15] Xin Xia;Yajie Zhang;Xiangxiang Zeng;Xingyi Zhang;Chunhou Zheng;Yansen Su. Artificial Intelligence in Molecular Optimization: Current Paradigms and Future Frontiers.. International journal of molecular sciences(IF=4.9). 2025. PMID:40430017. DOI: 10.3390/ijms26104878.
  • [16] Somayah J Jarallah;Fahad A Almughem;Nada K Alhumaid;Nojoud Al Fayez;Ibrahim Alradwan;Khulud A Alsulami;Essam A Tawfik;Abdullah A Alshehri. Artificial intelligence revolution in drug discovery: A paradigm shift in pharmaceutical innovation.. International journal of pharmaceutics(IF=5.2). 2025. PMID:40451590. DOI: 10.1016/j.ijpharm.2025.125789.
  • [17] Lalitkumar K Vora;Amol D Gholap;Keshava Jetha;Raghu Raj Singh Thakur;Hetvi K Solanki;Vivek P Chavda. Artificial Intelligence in Pharmaceutical Technology and Drug Delivery Design.. Pharmaceutics(IF=5.5). 2023. PMID:37514102. DOI: 10.3390/pharmaceutics15071916.
  • [18] Jane Dagher;Moussa Nassar;Wissam H Faour. Harnessing AI for precision medicine and its applications in genomics, systems pharmacology, and drug discovery.. European journal of pharmacology(IF=4.7). 2025. PMID:40983121. DOI: 10.1016/j.ejphar.2025.178183.
  • [19] Victor O K Li;Yang Han;Tushar Kaistha;Qi Zhang;Jocelyn Downey;Illana Gozes;Jacqueline C K Lam. DeepDrug as an expert guided and AI driven drug repurposing methodology for selecting the lead combination of drugs for Alzheimer's disease.. Scientific reports(IF=3.9). 2025. PMID:39814937. DOI: 10.1038/s41598-025-85947-7.
  • [20] Óscar Álvarez-Machancoses;Juan Luis Fernández-Martínez. Using artificial intelligence methods to speed up drug discovery.. Expert opinion on drug discovery(IF=4.9). 2019. PMID:31140873. DOI: 10.1080/17460441.2019.1621284.
  • [21] Subiya Ambreen;Mohammad Umar;Aaisha Noor;Himangini Jain;Ruhi Ali. Advanced AI and ML frameworks for transforming drug discovery and optimization: With innovative insights in polypharmacology, drug repurposing, combination therapy and nanomedicine.. European journal of medicinal chemistry(IF=5.9). 2025. PMID:39721292. DOI: 10.1016/j.ejmech.2024.117164.
  • [22] Yuyuan Wu;Lijing Ma;Xinyi Li;Jingpeng Yang;Xinyu Rao;Yiru Hu;Jingyi Xi;Lin Tao;Jianjun Wang;Lailing Du;Gongxing Chen;Shuiping Liu. The role of artificial intelligence in drug screening, drug design, and clinical trials.. Frontiers in pharmacology(IF=4.8). 2024. PMID:39679365. DOI: 10.3389/fphar.2024.1459954.
  • [23] Grace Edet Bassey;Ernest Aniefiok Daniel;Kazeem Bidemi Okesina;Adeyemi Fatai Odetayo. Transformative Role of Artificial Intelligence in Drug Discovery and Translational Medicine: Innovations, Challenges, and Future Prospects.. Drug design, development and therapy(IF=5.1). 2025. PMID:40909917. DOI: 10.2147/DDDT.S538269.
  • [24] Xin Qi;Yuanchun Zhao;Zhuang Qi;Siyu Hou;Jiajia Chen. Machine Learning Empowering Drug Discovery: Applications, Opportunities and Challenges.. Molecules (Basel, Switzerland)(IF=4.6). 2024. PMID:38398653. DOI: 10.3390/molecules29040903.
  • [25] Peter Chinedu Agu;Chidiebere Nwiboko Obulose. Piquing artificial intelligence towards drug discovery: Tools, techniques, and applications.. Drug development research(IF=4.2). 2024. PMID:38375772. DOI: 10.1002/ddr.22159.
  • [26] Ruiqiu Zhang;Hairuo Wen;Zhi Lin;Bo Li;Xiaobing Zhou. Artificial Intelligence-Driven Drug Toxicity Prediction: Advances, Challenges, and Future Directions.. Toxics(IF=4.1). 2025. PMID:40710970. DOI: 10.3390/toxics13070525.
  • [27] Yash Mathur;Arunabh Choudhury;Sneh Prabha;Mohammad Umar Saeed;Md Nayab Sulaimani;Taj Mohammad;Md Imtaiyaz Hassan. Current advancement in AI-integrated drug discovery: Methods and applications.. Biotechnology advances(IF=12.5). 2025. PMID:40639749. DOI: 10.1016/j.biotechadv.2025.108642.
  • [28] Aurore Crouzet;Nicolas Lopez;Benjamin Riss Yaw;Yves Lepelletier;Luc Demange. The Millennia-Long Development of Drugs Associated with the 80-Year-Old Artificial Intelligence Story: The Therapeutic Big Bang?. Molecules (Basel, Switzerland)(IF=4.6). 2024. PMID:38930784. DOI: 10.3390/molecules29122716.
  • [29] Madura Kp Jayatunga;Margaret Ayers;Lotte Bruens;Dhruv Jayanth;Christoph Meier. How successful are AI-discovered drugs in clinical trials? A first analysis and emerging lessons.. Drug discovery today(IF=7.5). 2024. PMID:38692505. DOI: 10.1016/j.drudis.2024.104009.
  • [30] Prafulla C Tiwari;Rishi Pal;Manju J Chaudhary;Rajendra Nath. Artificial intelligence revolutionizing drug development: Exploring opportunities and challenges.. Drug development research(IF=4.2). 2023. PMID:37712494. DOI: 10.1002/ddr.22115.
  • [31] Qingyao Ding;Rufan Yao;Yue Bai;Limu Da;Yujiang Wang;Rongwu Xiang;Xiwei Jiang;Fei Zhai. Explainable Artificial Intelligence in the Field of Drug Research.. Drug design, development and therapy(IF=5.1). 2025. PMID:40458811. DOI: 10.2147/DDDT.S525171.
  • [32] Kevser Kübra Kırboğa;Sumra Abbasi;Ecir Uğur Küçüksille. Explainability and white box in drug discovery.. Chemical biology & drug design(IF=3.3). 2023. PMID:37105727. DOI: 10.1111/cbdd.14262.
  • [33] Ghita Ghislat;Saiveth Hernandez-Hernandez;Chayanit Piyawajanusorn;Pedro J Ballester. Data-centric challenges with the application and adoption of artificial intelligence for drug discovery.. Expert opinion on drug discovery(IF=4.9). 2024. PMID:39316009. DOI: 10.1080/17460441.2024.2403639.
  • [34] Yueming Yin;Afu Fu;Lipo Wang. Gaps between medical biology and AI drug discovery.. Drug discovery today(IF=7.5). 2025. PMID:41201649. DOI: 10.1016/j.drudis.2025.104512.
  • [35] Lixia Fu;Guoshu Jia;Zhenming Liu;Xiaocong Pang;Yimin Cui. The applications and advances of artificial intelligence in drug regulation: A global perspective.. Acta pharmaceutica Sinica. B(IF=14.6). 2025. PMID:40041903. DOI: 10.1016/j.apsb.2024.11.006.
  • [36] Alexandre Blanco-González;Alfonso Cabezón;Alejandro Seco-González;Daniel Conde-Torres;Paula Antelo-Riveiro;Ángel Piñeiro;Rebeca Garcia-Fandino. The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies.. Pharmaceuticals (Basel, Switzerland)(IF=4.8). 2023. PMID:37375838. DOI: 10.3390/ph16060891.
  • [37] Rominder Singh;Mark Paxton;Jared Auclair. Regulating the AI-enabled ecosystem for human therapeutics.. Communications medicine(IF=6.3). 2025. PMID:40382515. DOI: 10.1038/s43856-025-00910-x.
  • [38] Haoran Cheng;Joy Le Yi Wong;Chrystie Wan Ning Quek;Jeffrey L Goldberg;Vinit B Mahajan;Tien Yin Wong;Jodhbir S Mehta;Daniel S W Ting;Darren S J Ting. Ophthalmic drug discovery and development using artificial intelligence and digital health technologies.. NPJ digital medicine(IF=15.1). 2025. PMID:40998989. DOI: 10.1038/s41746-025-01954-y.
  • [39] Vinay Kumar;Kunal Roy. Embracing the changes and challenges with modern early drug discovery.. Expert opinion on drug discovery(IF=4.9). 2025. PMID:40098331. DOI: 10.1080/17460441.2025.2481259.
  • [40] Fatimah G Albani;Sahar S Alghamdi;Mohammed M Almutairi;Tariq Alqahtani. Artificial Intelligence-Driven Innovations in Oncology Drug Discovery: Transforming Traditional Pipelines and Enhancing Drug Design.. Drug design, development and therapy(IF=5.1). 2025. PMID:40626099. DOI: 10.2147/DDDT.S509769.

MaltSci Intelligent Research Services ​

Search for more papers on MaltSci.com ​

Artificial Intelligence · Drug Discovery · Machine Learning · Natural Language Processing · Predictive Modeling

© 2025 MaltSci