American Journal of Applied Science and Technology
9
https://theusajournals.com/index.php/ajast
VOLUME
Vol.05 Issue01 2025
PAGE NO.
9-12
10.37547/ajast/Volume05Issue01-03
Review on the use of artificial intelligence to predict
suitable drugs (AIPD)
1
Nawras Yahya Hussein Al-Khafaji,
2
Sabreen Hassan Howaidy,
3
Zahraa Khawawm Abdulwahid
123
College of Pharmacy, University of Babylon
Received:
16 November 2024;
Accepted:
18 December 2024;
Published:
08 January 2025
Abstract:
Artificial intelligence and machine learning have revolutionized the pharmaceutical industry, offering
new approaches to drug discovery and development. These techniques have the potential to improve the
efficiency and accuracy of the drug discovery process, leading to the development of more effective
medications.In particular, AI-based algorithms can be employed to predict the efficacy and toxicity of new drug
compounds, as well as to identify new targets for drug development. This paper provides an overview of the
current landscape of AI in large-molecule drug discovery, highlighting the increasing application of these
techniques to areas such as antibodies, gene therapies, and RNA-based therapies. The paper also discusses the
challenges and opportunities associated with the use of AI in pharmaceutical research and development,
emphasizing the importance of balancing the promise of AI with a continued reliance on the scientific method.
While the promise of AI in pharmaceutical research is significant, it is crucial to recognize the limitations of these
technologies and to maintain a balanced approach that leverages the strengths of both AI-driven and traditional,
scientific methods. By doing so, researchers and developers can harness the power of AI to accelerate the drug
discovery process, while ensuring that the development of new drugs remains grounded in robust scientific
principles.
Keywords:
Artificial Intelligence, Machine Learning, Drug Discovery, Large Molecule Therapies, Pharmaceutical
Research and Development.
Introduction:
The Utilizing Artificial Intelligence for
Drug Prediction The pharmaceutical industry has long
relied on traditional methods of drug discovery, which
are often time-consuming and inefficient. However, the
rise of powerful statistical and biophysical modeling
programs, as well as the growth of the field of
bioinformatics, has led to the development of
computational tools that can predict the properties of
molecules with greater accuracy and efficiency.
(Freedman, 2019) Artificial intelligence techniques,
such as machine learning, are transforming the drug
research and development process, enabled by the
increasing availability of data and computational
power. (Nagra et al., 2023),These AI-based approaches
have the ability to improve the efficiency and accuracy
of drug discovery processes, leading to the
development of more effective medications. (Blanco-
González et al., 2022) Some AI companies are focusing
on the problem of designing a drug that can safely and
effectively work on a known target, usually a specific,
well-studied protein that is associated with a particular
disease. (Freedman, 2019) ,Predicting Binding
Interactions with AI-Bind One such AI-based tool is AI-
Bind, which offers a powerful high-throughput
approach to identify drug-target combinations. The
accurate prediction of binding interactions between
chemicals and proteins is a critical step in drug
discovery, as it helps to identify new drugs and novel
therapeutic targets, reduce the failure rate in clinical
trials, and predict the safety of drugs. (Chatterjee et al.,
2021),AI-Bind utilizes machine learning algorithms to
predict protein-ligand binding interactions, and the
predictions are validated through docking simulations
and comparison with recent experimental evidence.
The tool also helps to identify potential active binding
sites on the amino acid sequence, providing valuable
insights into the interpretation of machine learning
predictions of protein-ligand binding,. (Chatterjee et
al., 2021),Expanding the Scope of Drug Discovery with
AI While traditional methods of pharmaceutical
American Journal of Applied Science and Technology
10
https://theusajournals.com/index.php/ajast
American Journal of Applied Science and Technology (ISSN: 2771-2745)
research have been relatively successful in the past,
they are limited by their reliance on trial-and-error
experimentation and their inability to accurately
predict the behavior of new potential bioactive
compounds,. (Blanco-González et al., 2022) AI-based
approaches, on the other hand, have the ability to
expand the scope of drug discovery beyond the
limitations of more conventional approaches,
potentially leading to the development of novel and
more effective medications (Blanco-González et al.,
2022).
AI-Driven Approach to Identifying Appropriate Drugs
The rise of artificial intelligence techniques, such as
machine learning and bioinformatics, has transformed
the landscape of drug research and development.
These AI-based methods offer a powerful approach to
identify drug-target combinations, with the potential to
become a valuable tool in drug discovery. (Chatterjee
et al., 2021) ,One key advantage of AI-driven drug
discovery is its ability to accurately predict binding
interactions between chemicals and proteins, a critical
step in identifying new drugs and therapeutic targets.
(Chatterjee et al., 2021) Tools like AI-Bind utilize
machine learning algorithms to predict protein-ligand
binding, and validate these predictions through docking
simulations and experimental evidence. (Chatterjee et
al., 2021),Beyond binding prediction, AI-based
approaches also have the potential to expand the scope
of drug discovery. Traditional pharmaceutical research
methods are often limited by their reliance on trial-
and-error experimentation and their inability to
accurately predict the behavior of new bioactive
compounds. (Blanco-González et al., 2022) ,In contrast,
AI-driven techniques can identify new drug targets,
such as specific proteins or genetic pathways involved
in diseases, and can lead to the development of novel
and more effective medications. (Blanco-González et
al., 2022),"The pharmaceutical industry is increasingly
adopting AI-based tools to improve the efficiency and
accuracy of drug discovery processes. As the availability
of data and computational power continues to grow,
the role of artificial intelligence in drug research and
development is expected to become even more
prominent. (Nagra et al., 2023).
Artificial Intelligence: A Tool for Drug Suitability
Prediction
The pharmaceutical industry has long faced challenges
in the drug discovery process, often relying on time-
consuming and inefficient traditional methods.
However, the rise of artificial intelligence techniques,
such as machine learning and bioinformatics, has the
potential to transform this landscape. (Freedman,
2019)(Hasselgren & Oprea, 2023) , One key advantage
of AI-driven drug discovery is its ability to accurately
predict binding interactions between chemicals and
proteins, a critical step in identifying new drugs and
therapeutic targets. (Chatterjee et al., 2021) Tools like
AI-Bind utilize machine learning algorithms to predict
protein-ligand binding, and validate these predictions
through docking simulations and experimental
evidence. (Chatterjee et al., 2021) ,Beyond binding
prediction, AI-based approaches also have the
potential to expand the scope of drug discovery.
Traditional pharmaceutical research methods are often
limited
by
their
reliance
on
trial-and-error
experimentation and their inability to accurately
predict the behavior of new bioactive compounds.
(Blanco-González et al., 2022) ,In contrast, AI-driven
techniques can identify new drug targets, such as
specific proteins or genetic pathways involved in
diseases, and can lead to the development of novel and
more effective medications. (Blanco-González et al.,
2022),The pharmaceutical industry is increasingly
adopting AI-based tools to improve the efficiency and
accuracy of drug discovery processes. As the availability
of data and computational power continues to grow,
the role of artificial intelligence in drug research and
development is expected to become even more
prominent. ,Overall, the integration of AI into the drug
discovery pipeline holds significant promise.
AI-Enabled Drug Suitability Forecasting
The pharmaceutical industry has long faced challenges
in the drug discovery process, often relying on time-
consuming and inefficient traditional methods.
However, the rise of artificial intelligence techniques,
such as machine learning and bioinformatics, has the
potential to transform this landscape. (Freedman,
2019) (Hasselgren & Oprea, 2023) ,One key advantage
of AI-driven drug discovery is its ability to accurately
predict binding interactions between chemicals and
proteins, a critical step in identifying new drugs and
therapeutic targets. (Chatterjee et al., 2021) ,Tools like
AI-Bind utilize machine learning algorithms to predict
protein-ligand binding, and validate these predictions
through docking simulations and experimental
evidence. (Chatterjee et al., 2021) ,Beyond binding
prediction, AI-based approaches also have the
potential to expand the scope of drug discovery.
Traditional pharmaceutical research methods are often
limited
by
their
reliance
on
trial-and-error
experimentation and their inability to accurately
predict the behavior of new bioactive compounds.
(Blanco-González et al., 2022) ,In contrast, AI-driven
techniques can identify new drug targets, such as
specific proteins or genetic pathways involved in
diseases, and can lead to the development of novel and
more effective medications. (Blanco-González et al.,
American Journal of Applied Science and Technology
11
https://theusajournals.com/index.php/ajast
American Journal of Applied Science and Technology (ISSN: 2771-2745)
2022),The pharmaceutical industry is increasingly
adopting AI-based tools to improve the efficiency and
accuracy of drug discovery processes. As the availability
of data and computational power continues to grow,
the role of artificial intelligence in drug research and
development is expected to become even more
prominent. (Nagra et al., 2023),Overall, the integration
of AI into the drug discovery pipeline holds significant
promise and could lead to the development of more
effective and safer medications.
Harnessing the Power of AI for Optimal Drug Selection
The pharmaceutical industry has long faced challenges
in the drug discovery process, often relying on time-
consuming and inefficient traditional methods.
However, the rise of artificial intelligence techniques,
such as machine learning and bioinformatics, has the
potential to transform this landscape. (Freedman,
2019) (Hasselgren & Oprea, 2023) ,One key advantage
of AI-driven drug discovery is its ability to accurately
predict binding interactions between chemicals and
proteins, a critical step in identifying new drugs and
therapeutic targets. (Chatterjee et al., 2021) ,Tools like
AI-Bind utilize machine learning algorithms to predict
protein-ligand binding, and validate these predictions
through docking simulations and experimental
evidence. (Chatterjee et al., 2021) ,Beyond binding
prediction, AI-based approaches also have the
potential to expand the scope of drug discovery.
Traditional pharmaceutical research methods are often
limited
by
their
reliance
on
trial-and-error
experimentation and their inability to accurately
predict the behavior of new bioactive compounds.
(Blanco-González et al., 2022) ,In contrast, AI-driven
techniques can identify new drug targets, such as
specific proteins or genetic pathways involved in
diseases, and can lead to the development of novel and
more effective medications. (Blanco-González et al.,
2022),The pharmaceutical industry is increasingly
adopting AI-based tools to improve the efficiency and
accuracy of drug discovery processes. As the availability
of data and computational power continues to grow,
the role of artificial intelligence in drug research and
development is expected to become even more
prominent. (Nagra et al., 2023),Overall, the integration
of AI into the drug discovery pipeline holds significant
promise and could lead to the development of more
effective and safer medications.While the potential of
AI in drug discovery is evident, there are also challenges
that must be addressed. The scientific community must
carefully vet known information to address the
reproducibility crisis, and ensure that AI-derived
insights are backed by robust experimental validation.
(Hasselgren & Oprea, 2023) Additionally, human
intervention and expertise remain crucial at later
stages of the drug discovery pipeline, as AI tools cannot
fully replace the complexity of the systematic scientific
process. (Hasselgren & Oprea, 2023) (Maria et al.,
2023) ,By judiciously applying AI techniques and
maintaining appropriate human oversight, the
pharmaceutical industry can leverage the power of
artificial intelligence to predict suitable drug candidates
more accurately and efficiently, ultimately leading to
the development of more effective and safer
medications.
Balancing AI and Human Expertise in Drug Discovery
The integration of artificial intelligence into the drug
discovery process holds significant promise, as AI-
driven techniques have the potential to improve the
efficiency and accuracy of identifying suitable drug
candidates. One key advantage of AI-powered drug
discovery is its ability to predict binding interactions
between chemicals and proteins, a crucial step in the
identification of new drugs and therapeutic targets.
(Chatterjee et al., 2021) Tools like AI-Bind utilize
machine learning algorithms to predict protein-ligand
binding and validate these predictions through docking
simulations and experimental evidence. (Chatterjee et
al., 2021) , Beyond binding prediction, AI-based
approaches can also expand the scope of drug
discovery, as they have the potential to identify new
drug targets, such as specific proteins or genetic
pathways involved in diseases, which may lead to the
development of novel and more effective medications.
(Blanco-González et al., 2022) ,The pharmaceutical
industry is increasingly adopting AI-based tools to
leverage the growing availability of data and
computational power, and the role of artificial
intelligence in drug research and development is
expected to become even more prominent. (Nagra et
al., 2023) ,However, it is important to note that the
integration of AI into the drug discovery pipeline is not
without its challenges. The scientific community must
carefully vet known information to address the
reproducibility crisis, and ensure that AI-derived
insights are backed by robust experimental validation.
(Hasselgren & Oprea, 2023) ,Additionally, human
intervention and expertise remain crucial at later
stages of the drug discovery pipeline, as AI tools cannot
fully replace the complexity of the systematic scientific
process. (Hasselgren & Oprea, 2023) (Maria et al.,
2023) ,By judiciously applying AI techniques and
maintaining appropriate human oversight, the
pharmaceutical industry can leverage the power of
artificial intelligence to predict suitable drug candidates
more accurately and efficiently, ultimately leading to
the development of more effective and safer
medications. As the availability of data and
computational power continues to grow, the
American Journal of Applied Science and Technology
12
https://theusajournals.com/index.php/ajast
American Journal of Applied Science and Technology (ISSN: 2771-2745)
pharmaceutical industry is increasingly adopting AI-
based tools to streamline the drug discovery process.
(Nagra et al., 2023),While the potential of AI in drug
discovery is evident, there are also challenges that
must be addressed. The scientific community must
carefully vet known information to address the
reproducibility crisis, and ensure that AI-derived
insights are backed by robust experimental validation.
(Hasselgren & Oprea, 2023) Additionally, human
intervention and expertise remain crucial at later
stages of the drug discovery pipeline, as AI tools cannot
fully replace the complexity of the systematic scientific
process. (Hasselgren & Oprea, 2023) (Maria et al.,
2023) By judiciously applying AI techniques and
maintaining appropriate human oversight, the
pharmaceutical industry can leverage the power of
artificial intelligence to predict suitable drug candidates
more accurately and efficiently, ultimately leading to
the development of more effective and safer
medications.
Conclusion
Artificial intelligence has revolutionized the field of
drug discovery, offering a more efficient and accurate
approach to identifying potential drug candidates AI-
based algorithms can predict the efficacy and toxicity
of new drug compounds with greater accuracy than
traditional methods , and can also be used to identify
new drug targets, such as specific proteins or genetic
pathways involved in diseases AI tools tackle different
aspects of drug discovery, from modeling small-
molecule-target interactions to lead candidate
optimization and safety prediction, While traditional
drug discovery methods have been successful in the
past, they are limited by their reliance on trial-and-
error experimentation and their inability to accurately
predict the behavior of new potential bioactive
compounds . AI-based approaches, on the other hand,
have the ability to improve the efficiency and accuracy
of drug discovery processes, ultimately leading to the
development of more effective medications However,
it is important to recognize that the scientific method is
not obsolete when making inferences about data, and
that separating hope from hype is crucial in ensuring
the optimal use of AI/ML in drug development , the use
of artificial intelligence in drug discovery has immense
potential, but it must be balanced with a careful
consideration of the limitations and challenges
associated with this technology.
References
1.
Blanco-González, A., Cabezon, A., Seco-
González, A., Conde-Torres, D., Antelo-Riveiro, P.,
Piñeiro, Á., & García‐Fandiño, R. (2022). The Role of AI
in Drug Discovery: Challenges, Opportunities, and
Strategies. In A. Blanco-González, A. Cabezon, A. Seco-
González, D. Conde-Torres, P. Antelo-Riveiro, Á.
Piñeiro, & R. García‐Fandiño, arXiv (Cornell University).
Cornell
University.
https://doi.org/10.48550/arxiv.2212.08104
2.
Chatterjee, A., Walters, R., Shafi, Z., Ahmed, O.
S., Šebek, M., Gysi, D. M., Yu,
R., Eliassi‐Rad, T.,
Barabási, A., & Menichetti, G. (2021). AI-Bind:
Improving Binding Predictions for Novel Protein Targets
and Ligands. In A. Chatterjee, R. Walters, Z. Shafi, O. S.
Ahmed, M. Šebek, D. M. Gysi, R. Yu, T. Eliassi‐Rad, A.
Barabási, & G. Menichetti, arXiv (Cornell University).
Cornell
University.
https://doi.org/10.48550/arxiv.2112.13168
3.
Freedman, D. H. (2019). Hunting for New Drugs
with AI. In D. H. Freedman, Nature (Vol. 576, Issue
7787).
Nature
Portfolio.
https://doi.org/10.1038/d41586-019-03846-0
4.
Hasselgren, C., & Oprea, T. I. (2023). Artificial
Intelligence for Drug Discovery: Are We There Yet?
[Review of Artificial Intelligence for Drug Discovery: Are
We There Yet?]. The Annual Review of Pharmacology
and Toxicology, 64(1), 527. Annual Reviews.
https://doi.org/10.1146/annurev-pharmtox-040323-
040828
5.
Maria, J. P. S., Wang, Y., & Camargo, L. M.
(2023).
Perspective
on
the
challenges
and
opportunities of accelerating drug discovery with
artificial intelligence. In J. P. S. Maria, Y. Wang, & L. M.
Camargo, Frontiers in Bioinformatics (Vol. 3). Frontiers
Media. https://doi.org/10.3389/fbinf.2023.1121591
6.
Nagra, N. S., Veken, L. van der, Stanzl, E. G.,
Champagne, D. W., Devereson, A., & Macak, M. (2023).
The company landscape for artificial intelligence in
large-molecule drug discovery [Review of The company
landscape for artificial intelligence in large-molecule
drug discovery]. Nature Reviews Drug Discovery,
22(12),
949.
Nature
Portfolio.
https://doi.org/10.1038/d41573-023-00139-
0/doi.org/10.1016/j.jchas.2006.11.001
