Information technology (IT) has significantly transformed the field of biology, enhancing data collection, analysis, and communication in scientific research. The integration of IT has led to the emergence of subfields like bioinformatics and computational biology, which leverage computational methods to manage and analyze biological data. Additionally, artificial intelligence (AI) is increasingly applied in medical science for disease diagnosis, drug development, and personalized medicine, promising to improve patient care and treatment outcomes.
Information technology (IT) has significantly transformed the field of biology, enhancing data collection, analysis, and communication in scientific research. The integration of IT has led to the emergence of subfields like bioinformatics and computational biology, which leverage computational methods to manage and analyze biological data. Additionally, artificial intelligence (AI) is increasingly applied in medical science for disease diagnosis, drug development, and personalized medicine, promising to improve patient care and treatment outcomes.
Itrpduction
Computer and internet play the most conspicuous roles in all aspects of human life. Computer
| -Jelated technologies have a strong impact on the world. These have attracted many students and
Sr{siessionals to the field of information technology. ‘There are thousands of web sites and web
‘adsmig opportunities available which are ever growing. Many information technologies, from
the qurliest computers to email and the Internet, have been developed for scientific applications.
Ag~-heney (2003) stafes: “Understanding the role of IT for science is important because of the
ceiwuil role of, —
“science in today’s information s
‘the achievement of societal From health to national security. As a result, it is important for
policy makers to understand hoff IT affects the quality and productivity of science. It can be
understood from the observation and the literature that there are several complementary
approaches to examining the implications of IT for science. One approach is to examine the role
of specific information technologies, such as email or the World Wide Web. Another approactris~
to examine the role of IT in specific aspects of the scientific process, such as scholarly
communication or scientific collaboration.
Biology is at its core an informational science based on the information embedded in the genetic
code. At the molecular level, a key challenge in biology is to understand how instructions
encoded in genomes lead to the structure and function of the proteins. and the regulation and
expression of genes. IT is essential to store, manage, and decipher the mass of information
produced in work in these areas. At levels of organization above the molecular level, computer
models are critical tools to handle the complexity of relationships in biology.
Ifis shown that IT plays the following roles in biology:
+ IT-aided instruments, such as gene sequencers, DNA microarrays, and microscopes, are used
for data collection. —
+ Large shared, Internet-connected databases, such as gene and protein data banks, allow many
researchers to obtain and contribute data to large problems.
+ Imaging and visualization, such as Magnetic Resonance Imaging (MRI) and tomography are
important in several areas of bioscience.
+ Modeling and simulation are used To mddel protein folding and to help understand complex
biological systems such as cells, tissues, organisms, and populations.
+ Electronic communication technologies are used to share scientific information and aid
ety. Advances in science affect economic performance and
scientific collaboration. ——___
oe ee
Although information technology has been used in the biosciences for a long time, the
biosciences, were initially relatively modest users of IT. A 1966-1967 survey that covered use of
computing in the life sciences, found that a lower percentage of life scientists than physical used
computers (National Academy of Sciences, 1970). In recent years, however, the use of IT in the
biosciences has expanded greatly. Lander et al. (1991) observed that biology had been going.
through major changes driven by computing for the previous ten years. Since the discovery in the1950s of how genetic information is coded in DNA, the biosciences have increasingly become
trach-more dependent on-TT- Much ‘bioscience “research “now involves: deciphering the
information stored in genetic sequences; understanding how these sequences codes for genes and
proteins; and understanding the function and structure of these proteins. In 4
a $ense, biology has become driven by the infprmation contained in the genetic code, and
information technology is ¢ irr generating and managing this information, The growth if
importance of information technology is exemplified by the growth of several new
interdisciplinary subfields of biology. One is “bioinformatics,” defined as the application of
computers, databases, and computational methods to the management and analysis of biological
mation. The human genome project and genome sequencing projes is in other organisms,—
fogether with new technologies that analyze gene expression patterns, have created vast amount
of data, Bioinformatics has become essential for_almost_cvery aspect of data management in”
modern biology (Kaminski 2000). Another subfield is “computational biology,” which uses
jathematical and computational approaches, such as mathematical modeling and computational
Simulation techniques, to address theoretical and experimental questions in biology. Other new
“subfields are the ones with the suffix “omics”— which include genomics (the study of the full
DNA sequence of organisms, including sequencing, mapping-and determining the function of —
genes); transcriptomics (RNA and gene expression); proteomics (protein expression),
jnetabolomics (metabolites and_metabolic networks); pharmacogenomics (how genetics affects
individuals responses to drugs); and physiomics (physiological dynamics and functions of whole
organisms). Each of these involves the combination of quantitative, experimental, and
computational approaches to improve understanding of complex biological systems and
processes.
IT has a substantial impact on biology. Information technology plays three following impacts in
biological sciences: ULmakss 2 grest revolution in semote fusstion; IT
leads to a remarkable improvement in biological simulation; and last but not least Information
Technology makes a visible in laboratory studies.
“The review shows blatantly that IT is used in a wide variety of applications in bioscience. These
applications include automated data collection, statistical analysis of data, Internet-accessible
shared databases, modeling and simulation, imaging and visualization of data and analysis,
Internet-based communication among scie
electronic dissemination of research results, Another role played by IT is that throughout the_
scientific cycle in biology. IT is used in many ways throughout the scientific process. This
distinguishes IT from most other kinds of scientific equipment, such as microscopes or physits
accelerators, which are generally used in one stage of the scientific process, such as data
collection. IT aids in hypothesis formation, research design, data collection, data analysis, and
communications of scientific results. '
Table 5 shows the relation of TT to stages of the scientific process. IT is especially important in
bioinformatics and the "omics" -- (genomics, proteomics, transcriptomics, etc.). In the
geosciences, IT is especially important in analyzing subsurface formations, mappi
modeling complex systems. There appear to be few, if any, fields that are untouched by IT.
Shared Internet accessible databases are important in paleontology; and_
important in population biology and ecology; and genomics are influencing many fields in
ale gy {a ——
dels and databases areThere are some systems that are too intricate to study without advanced computational tools for
managing and integrating the data into mechanistic models (Department of Energy, 2001).
> Systems biology aims to model and simulate various systems and visualize the results to
s
help better understand living processes. Instead of the data driven approach of genomics,
researth in blologieal systems can be characterized es “model-driven” (Yao, 2002).
> The complexity of biological systems and the explosion of the quantity of biological
information that is rapidly becomi: ilable from experimental and clinical studies
Tequire the use of mathematical and computational modeling (Mehr, 2001).
> _Modeling requires taking knowledge in the form of qualitative biological theories and
expressing it as explicitly and quantitatively as possible. It requires that implicit
knowledge be made explicit so that disparate human knowledge can accumulate in an
integrated way (Yao, 2002).
> _Model building also helps point out areas where knowledge is lacking, such as unknown
pathways and parameters. —
> Simulation can identify missing components and suggest experiments to gather missing
information. The number of activities that apply information technology to model activity
at the cellular and sub cellular levels is on the rise and wide variety.
> Computer-aided algorithms are being used to analyze the behavior of thousands of genes
at a time and are creating a foundation of data for building integrated models of cellular
processes (Schilling et. al 1999 and Kao 1999).
> Gene expression is regulated through networks of interactions between DNA, RNA,
proeins, and small molecules.
& Because most genetic regulatory networks involve many components connected through
interlocking positive and negative feedback loops, it is difficult to obtain an intuitive
understanding of their dynamics.
> Formal methods and computer tools for the modeling and simulation of genetic
regulatory networks are needed to understand their operation.
> Although past attempts to model cellular processes have been disappointing, increases
in biological understanding combined with advances in computational methods and in
computer power make it possible to foresee construction of useful and predictive
simulations of cellular processes (Endy and Brent 2001, Covert et. al. 2001).
> There are other uses of IT in biology too. For instance, another cross-cutting area at the
intersection of IT and bioscience is the application of artificial intelligence to biology.
Molecular biologists and computer scientists have experimented with various
computational methods developed in artificial intelligence, including knowledge-based.
and expert systems, qualitative simulation, and artificial neural networks and other
automated learning techniques (Rawlings and Fox 1994).
> These methods have been applied to problems in data analysis, construction of databases
Ss
with advanced retrieval capabilities, and modeling of biological systems. Practical
\sqnte
hy :>
results have been obtained in identifying active genes in genomic sequences, assembling
physical and genetic maps, and predicting protein structure.
To sum up, IT has proved to be of conspicuously great impacts on different areas of
bioscience and the uses will be on the rise both in new areas and new perspectives.
Application of AI in Biology
>
AI has now made its way into the biological field, demonstrating its worth through
innovative and cutting-edge procedures .
» Additionally, the world has seen a true revolution in the field of information technology
vv
(IT), leading to the production and storage of an enormous amount of data, not just in the
field of technology but in other areas as well in recent years.
Computational resources are inextricably linked to big data, which encompasses
annotated and raw information due to the ever-increasing volume and complexity of data
from multiple sources .
Because of developments in sequencing and other high-throughput techniques, the
biosciences and biotech industries have made remarkable strides in recent years .
Al-based algorithms have the capacity to effectively store and process large amounts of
Taw, unstructured data and make them available for quick extraction, which is necessary
to build an intelligent computing system with complex decision-making capability. Such
advancement in data generation, storage and analysis allows the development of a wide
range of products and services in different sectors including biosciences.
While advances in computing and the Internet ushered in the third industrial revolution
and laid the groundwork for AI’s meteoric rise, Big Data and the analytics it spawned
have allowed us to take our intelligence to new heights .
Al is now considered a major invention of the fourth industrial revolution.
Experiments that would have taken years to execute are now feasible and often
inexpensive due to recent advances in data and methodology.
Raw data in a variety of formats are generated as a result of these experimental analyses.
The ability to store and analyze data with the help of AI has created new possibilities for
the academic community, scientific researchers and the biotech industry.
Various applications of AI are used in biology, including the precise identification of the
3D geometry of biological molecules such as proteins which is one of the most critical
tasks and useful in biological research.
Moreover, in biological science, AI plays a critical role in promoting innovation not only
in laboratories, but also throughout the lifecycle of a medication or chemical product
Furthermore, Al-based tools and applications help automate complicated production
procedures, thereby meeting the fast-rising demand for medications, chemicals for use in
industry and food and other bio-based raw materials.
ML, a subset of Al, aids in the prediction of outcomes by executing massive
permutations and combinations of datasets available for the drug molecules to determine
the best combination without relying on traditional manual methods in the lab.
Although traditional model-driven methods are still useful for analyzing biological data,
they lack the ability to use vast amounts of available data, or even big data, to uncover
information, forecast data behavior and comprehend complex data linkages.The extensive use of big data is becoming increasingly important in biotechnology and
bioinformatics as it continues to grow and becomes available to academicians and
scientists for analysis throughout the world.
‘Al and deep neural network designs might efficiently analyze genomic data to determine
the genetic basis of a trait and to uncover genetic markers linked with certain traits .
The use of AI may aid in deciphering complex links across diverse information hidden in
data to obtain meaningful insights from them.
‘As a result, the incorporation of Al approaches is now widely observed in the field of
biological science and is expected to increase further in the near future as this technology
matures.
Furthermore, medical images and drug responses contribute complex but significant data
and need efficient algorithmic programs to analyze them.
Therefore, ML- and DL-based Al is garnering much attention due to their capabilities for
faster processing of huge data and extraction of meaningful information. Al-based digital
image processing, drug designing and virtual drug tests might transform medical science
in the near future.
Al in Medical Science
>
>
Medical science and biotechnology advancements have opened new avenues for
developing medications and antibiotics.
AT has enormous potential for widespread applications in the pharmaceutical industry
(Figure 4). With Al, novel therapeutic molecules based on known target structures can be
discovered.
A branch of AI known as ML is commonly employed in disease diagnosis since it
leverages the outcomes of diagnostic testing to improve the accuracy of results.
Al allows researchers to manage challenging issues, including quantitative and
predictive epidemiology, precision-based medicines and host-pathogen interactions .
Al can help in disease detection and diagnosis and make computer code more accessible
to non-technical individuals.
Predictive epidemiology, individual-based precision medicine and the analysis of host-
pathogen interactions are examples of research areas that could benefit from machine and
deep learning breakthroughs.
These approaches aid with disease diagnosis and individual case identification, more
accurate forecasts and fewer mistakes, faster decision making and better risk analysis
(Figure 4).
The growing number of tissue biomarkers and the complexity of their evaluations
significantly promote the use of Al-based techniques.
These Al-based biomarkers help physicians in the prediction and analysis of the
diagnosis, patient responses to the treatment and patient survival.
More realistic models of complex socio-biological systems are achievable because of
knowledge representation and reasoning modelling .
ML-based methods can also be used to improve the efficiency and reliability of
epidemiological models.
ML advances helped develop ten cellular parameters algorithmic program-based models
that can accurately distinguish benign from malignant tumors.Ee anit
_s
(Samm rretare mE
> Researchers could use AI in DNA, RNA and protein studies to better visualize the effects
of drug doses on living tissue over time and reorganize signaling networks during therapy.
> Based on AI, IBM Watson assists in the creation of the appropriate treatment
plan for a patient depending on the patient’s medical history and personal data, including
genetic makeup.
(Oe
(Ol
(a
> An Al-based system of personalized medicine will not only reduce treatment cost but
also minimize the side effects of drugs in the patient .
> In addition to saving time and improving patient care, Al can also simplify gene editing,
radiography and drug management planning procedure.
> Furthermore, electronic health records (EHRs) can be improved with evidence-based.
clinical decision support systems.
> Al involves massive processing capacity (supercomputers), algorithms that can learn at a
phenomenal rate (deep learning) and a new strategy that utilizes physicians’ cognitive
talents.
> Inarecent study, an Al-based approach was found to be very beneficial for the early
identification, diagnosis, prognosis and treatment of myopia.
> In cardiology, dermatology and oncology, deep learning algorithms outperform
physicians at least in the diagnosis of disease.
> Evidently, computer algorithms can detect metastatic breast cancer in sentinel lymph
node biopsies in full slide images with an accuracy rate of more than 91 percent, and this
was raised to 99.5 percent when physician inputs were added.
> One of the proven applications of AI in risk analysis is for diagnosing heart
malfunctioning through cardiovascular imaging. It includes automated monitoring of any
K< {a0
‘
z
eSdeviations from normal conditions based on image processing, myocardial function and
the detection and analysis of coronary atherosclerotic plaques.
Diseases Studied
AMD
Alzheimer's disease
COVID-9
Ovarian cancer
Pulmonary cancer
Algorithm
ML-based predictive
model
PA
ANN
LCP-CNN, Brock
model
IAT-BPNN
Modality
ch
I data
Clinical and Imaging,
data
Clinical data
Clinical data
Clinical data
CDC data and Twitter
dataset
Findings
‘At-based predictive model was able to
‘predict the progression of AMD with
high accuracy
‘Ab-model was able to accurately
detect and predict the progression of
Alzheimer’s disease with accuracy of
98.95% in first layer and 87.08% in
second layer
‘An accuracy of 70-80% was achieved
inn predicting severe COVID-19 cases
‘An accuracy of 93% was achieved in
predicting the survival of ovarian
cancer patients, and 77% accuracy was
achieved in predicting the
surgical outcome
LCP-CNN was able to predict the
malignancy of pulmonary nodules
with higher accuracy and lower false
negative results than Brock model
TAT-BPNN was able to predict
influenza-like illness ina large
population size with an high accuracy