Role of Artificial Intelligence in Advancing Biotechnology: A Comprehensive Review

Role of Artificial Intelligence in Advancing Biotechnology: A Comprehensive Review

Aman (1) , Virender Kumar (1), Jyoti Mundlia (1)*

College of Pharmacy, Pandit Bhagwat Dayal Sharma University of Health Sciences, Rohtak, India

Abstract – The convergence of Artificial Intelligence (AI) and biotechnology is revolutionizing scientific research, healthcare, and industrial applications. This paper examines how AI techniques, like computer vision, machine learning, deep learning, and NLP, are revolutionizing important biotechnology fields like drug discovery, genomics, personalized medicine, agricultural innovation, and industrial bioprocessing. AI enables faster data analysis, accurate prediction of biological behaviors, and automation of complex tasks, significantly accelerating the pace of innovation. We also discuss commonly used AI tools in biotechnology and highlight the growth of AI-driven biotech startups. The incorporation of AI presents a number of obstacles despite its transformative potential, such as the requirement for transparent algorithms, ethical issues, and data privacy concerns. The goal of the article is to provide a thorough review of the state of affairs, recent developments, and potential future progress in the nexus of biotechnology and artificial intelligence.

Keywords: Artificial Intelligence (AI), Biotechnology, Machine Learning

1. INTRODUCTION

   The goal of artificial intelligence (AI) is to build machines with intellect comparable to that of humans. constructing models and algorithms that simulate human intelligence to enable computers to perform complicated tasks, learn from data, and adjust to changing circumstances. NLP is one branch of Artificial intelligence that is growing in significance. This technical development provides voice assistants and machine translation applications since it allows machines to understand, interpret, and produce human language. The development of NLP has greatly improved the effectiveness of information transfer between humans and machines. Computer vision, or the capacity of computers to perceive, and analyse visual data from the outer world, is another key purpose.

   Consequently, healthcare providers can make better decisions. It enables robots to explore and interact with their surroundings without human assistance. Artificial intelligence (AI) is crucial to robotics. This phenomenon has led to the development of sophisticated robotic systems that are capable of a variety of activities, including product assembly, surgical assistance, and the exploration of hazardous regions such as the deep ocean or space. Artificial intelligence (AI) has demonstrated its versatility and potential in a number of industries, including marketing, banking, and education.

   AI is the growth of computer systems that can learn and solve problemstasks that need human intelligence. The primary objective of ML, a subdivision of AI, is to develop methodologies that let computers study and make decisions based on data. Without being specifically programmed for a given task, these systems gradually enhance their performance, which makes them incredibly adaptable for a variety of uses. The application of AI and ML in biotechnology and biochemistry is transforming traditional techniques by offering tools that can analyze large and complex datasets, identify hidden patterns, and produce accurate predictions.

   Machine learning has been a cornerstone of modern drug discovery from the early days of QSAR. Despite this long history, the use of machine learning techniques has lately increased significantly due to the success of deep learning in many application fields. Many cheminformatics and modelling applications, such as virtual screening, chemical production planning, predictive toxicology, and more, have been touched by machine learning. 5, 6 Machine learning techniques are now applicable to protein structures, imaging, text, and transcriptomics data in addition to more conventional data types like chemicals and protein sequences. We are happy to see that this range of goals, data kinds, and approaches is reflected in the works included in this special issue.

2. BIOTECHNOLOGY

   Health systems have been profoundly changed by biotechnology, including industrial applications such as enzyme development, green biotechnology (agricultural), and red biotechnology (medical applications). Through ground-breaking discoveries like CRISPR-CAS genome editing, which allows precise genetic alterations to treat diseases like cancer by correcting oncogenic mutations in preclinical research, biotechnology has transformed medicine in the healthcare industry (more specifically, biotechnology).

   In the extremely interdisciplinary field of biotechnology, advanced technologies are powered by biological systems, processes, or animals. Biotechnologists frequently manipulate DNA, proteins, and cells from live organisms (Lysunets) to address issues in a variety of domains, including human health, agriculture, and the environment. Although biotechnology has many applications, the medical field is one of the most well-known [1]. For example, industrial biotechnology. Industrial biotechnology, a third wave of biotechnology, is currently booming. Green biotechnology, which focuses on genetically modified crops, and red biotechnology, which targets the medical field, are distinct from industrial biotechnology, commonly known as white biotechnology [2][3]. Biological systems are used in industrial biotechnology to produce minerals, chemicals, and energy. Together with advances in molecular genetics, enzyme engineering, and metabolic engineering, this technology is primarily based on fermentation technology (the controlled use of microorganisms) and biocatalysis (the use of enzymes to catalyse chemical reactions) [4].

3. HISTORICAL CONTEXT OF THEIR CONVERGENCE

   A new era of creativity and discovery has been brought about by the confluence of biotechnology and artificial intelligence. Researchers can better comprehend and resolve complex biological problems by combining AI with biotechnological techniques [5]. Genomics is a good example of this convergence since it uses AI methods like ML and DL to assess enormous volumes of genomic data. By learning how genes contribute to various qualities and disorders, researchers can identify algorithms and relationships in genetic sequences [6]. Therefore, the development of targeted therapeutics and personalized treatments can be accelerated by AI-powered genomics research. One area where the two domains overlap is drug discovery [7]. The combination of AI and biotechnology has also led to advancements in synthetic biology, enabling researchers to design novel biological systems that are suited to carry out particular functions. Artificial intelligence could help with the planning procedure by predicting how modifications to DNA will impact the functionality of the creature [8]. It makes it possible to produce biomass, biopolymers, and more effective drug delivery systems. Last but not least, the combination of biotechnology with AI has the ability to revolutionize a number of sectors, including energy, agriculture, drug and environment. By using AI to analyze complicated biological data, scientists may find significant global issues and develop novel remedies.

   In the field of medical imaging, deep learning has garnered a lot of interest as a potential remedy for automated, quick, and precise medical image analysisa critical component of high-quality healthcare. In medical image analysis, convolutional neural networks and their ariations are now the most popular and extensively utilized deep learning models. The main functions of deep learning modelsclassification, segmentation, retrieval, detection, and registrationare thoroughly examined in this work, along with succinct summaries of contemporary deep learning models used in medical image analysis [9].

   Recent studies have demonstrated that deep learning models can execute some tasks better than medical specialists. It is anticipated that patients will soon be able to engage with AI-based medical systems in a safe and convenient manner, thanks to the major advancements made by deep learning techniques. These intelligent systems will genuinely enhance patient care. Deep learning- based medical image analysis has several complications and difficulties, including small datasets. However, scientists are working hard to overcome these obstacles and use AI to enhance healthcare even more.

   Table 1: AI-driven major biotech breakthroughs (2014-2025)

   Year	Biotech- Innovation	Breakthroughs
   2014	Deep learning	Drug screening and genomic pattern detection
   2016	AI in gene editing	Safe and fast genomic engineering
   2018	AI-based drug discovery	Drug discovery time reduced from years to months
   2020	Covid-19 response	Protein structure prediction
   2021	Alphafold-2	Protein engineering
   2022	Protein designing	Vaccine and enzymes development
   2023	Ai wet labs	Automated experiments robotically
   2024	Multi-omics AI system	Précised medicines
   2025	Bio-digital twins	Digital twins of human organs by AI

4. OBJECTIVES

   This review’s main goal is to inform readers about the developments, convergence, and integration of artificial intelligence. Additional goals include educating readers about artificial intelligence. To explain the function of AI in the field of health – such as diagnosis of diseases (MRI, CT), Drug discovery and personalized treatment and prediction of early disease. To talk about the effective use of AI in the healthcare sector such as personalized care of patient, and improvement in clinical trials. To talk about the limitations of integrating biotechnology with AI such as the quality of data, high cost, a lack of skilled professionals and privacy concerns [10].

5. SIGNIFICANCE

   By utilizing large data produced by contemporary high-throughput technologies and enormous databases, the combination of biotechnology and artificial intelligence (AI) has completely changed health management. By analyzing intricate datasets in proteomics, metabolomics, and genomes, AI technologies have greatly improved bioinformatics. AI has also revolutionized pharmaceutical biotechnology and vaccine production by anticipating immune responses and optimizing antigen selection, which has led to the quick development of potent vaccinations [11]. With cutting-edge approaches to diagnostics, individualized care, and therapeutic development catered to each patient’s needs, this confluence holds revolutionary possibilities for the healthcare industry [12].

6. AI TECHNIQUES USED IN BIOTECHNOLOGY

   Fig. 1: AI Techniques used in Biotechnology

   Research, development, and advanced diagnostics are being revolutionized by the use of diverse artificial intelligence approaches in biotechnology. They are as follows:

   1. Machine Learning

      ML is a branch of (AI), used to predict outcomes without relying on traditional manual methods in the lab by performing several permutations and combinations of data sets available for medicinal compounds to identify the optimal combination [13]. For biological data analysis, traditional model-based methods are still useful, but they can’t make use of the vast amounts of data that are available, or even big data, to obtain insights, predict data behaviour, and understand complex relationships between collected data. Big data usage is becoming more and more significant in biotechnology and bioinformatics as it keeps expanding and becoming accessible for analysis by researchers globally [14].

   2. Deep learning

      Deep learning (DL) approaches emerged as a field of machine learning (ML) that is thought to be more successful and efficient when working with large volumes of data due to the vast generation of data, often known as the “big” data age. It has been demonstrated that these models can reach higher prediction accuracies than previously possible. When opposed to DL, ML’s primary drawback is its inability to effectively handle natural data in its unprocessed state. Although DL models were first proposed in the 1980s, based on the perceptron model and the idea of neurons, they have only been regarded as state-of-the-art predictive models for large datasets in the last ten years [15]. For ex.- therapeutic discovery and development may be greatly aided by the precise identification of compoundprotein interactions (CPIs) in silico, which could expand our knowledge of the fundamental mechanisms of therapeutic action. Latent characteristics from currently available large-scale unlabelled chemical and protein data are rarely used by conventional similarity- or docking-based computational approaches for predicting CPIs, and their application is frequently restricted to very small-scale datasets [16]. In order to reliably forecast CPIs on a broad scale, we present DeepCPI, a unique universal and scalable computational framework that combines potent deep learning techniques with efficient feature embedding and a representation learning methodology. DeepCPI uses a vast quantity of unlabeled data to automatically learn the low- dimensional, implicit, yet expressive characteristics of proteins and chemicals [17].

   3. Natural language processing

      Thanks to digitization, researchers today have unprecedented opportunities to compile a wide range of written information for examining simultaneous incidents. NLP, a technique that itself analyses and comprehends human language, permits scholars to simply pull useful insights from a written dataset without requiring costly computing work. NLP has advanced significantly in a few years due to the appearance of AI [18].

   4. Reinforcement learning

      A learning framework known as reinforcement learning (RL) employs interaction with an environment in which an agent sees its state in order to formulate a policy for a certain aim [19]. A learning framework known as reinforcement learning (RL) employs interaction with an environment in which an agent perceives the state of that environment to formulate a policy in terms of a predetermined goal. Its goal is simple: to make decisions and take actions that will optimize future benefits [20].

   5. Computer vision

      While AI techniques like neural nets have been widely utilized since the 1940s, computer vision approaches emerged in the late 1960s and early 1970s. Over the past few decades, computer vision has worked to develop several domains, including ML, virtual reality, augmented reality, computer graphics, and 3D reconstruction [21]. In 2010, computer vision was able to do sophisticated tasks such as robotic navigation, autonomous car navigation, object recognition, face detection, and fingerprint recognition [22]. For example, phenotyping facilitated by AI-enabled microscopy; ML, a branch of AI, has become a potent ethod in microscopy imaging. It makes it possible for biologists to more quickly, accurately, and consistently extract valuable information from tissue and cells. Without the need for specific instructions, machine learning (ML) makes use of algorithms that learn from the data to find patterns and features and provide predictions. Tasks like cell counting, phenotypic analysis, and noise correctionincluding fluorescent microscopyall benefit greatly from machine learning [23].

   6. Robotics and automation

      Compared to the industrial robots that were initially developed fifty years ago to automate dirty, tedious, and dangerous tasks, today’s medical and health-care robots are designed for entirely different environments and tasksthose that involve direct interaction with human users in the operating room and rehabilitation facility [24]. The commercial and scientific interest in medical and healthcare robots has grown significantly during the last ten years. Telerobotic equipment is now often used for surgery, which results in faster recovery times and more reliable outcomes in specific surgeries. The robotic system is enabling more intensive care that is continuously modified to meet the needs of the patient. [25].

      AI-driven automated self-driving laboratory systems.

      With the use of complex instruments and coordinated lines that integrate cutting-edge robotics and software with artificial intelligence capabilities, clinical laboratories are becoming more and more automated [26]. Robotic systems may now quickly and effectively complete tasks that were previously completed by technologists or lab assistants, thanks to automated technology. The testing volume can be significantly increased by using contemporary automated systems that handle sample storage all the way to assay analysis. However, automated laboratory testing system installation is extremely difficult, and optimal efficacy may not be attained unless the best implementation methodologies for these intricate systems are used [27].

7. Applications of AI in biotechnology

   Fig. 2: Applications of AI in Biotechnology

   1. Drug discovery and development

      AI and biotechnology together have the potential to completely transform healthcare, especially in the area of drug creation. It is feasible to uncover new compounds, anticipate drug-target interactions, improve clinical trial candidates, and use machine learning methods [28]. This can reduce the time and cost needed to bring new medications to market and hasten the introduction of innovative treatments for a variety of illnesses. This is how artificial intelligence is transforming the labour-intensive and high-risk drug discovery process into one that is quick, simple, precise, data-driven, and likely to be successful.

      Fig. 3: Drug Discovery and Development (AI vs Traditional Techniques)

   2. Target identification

      Artificial intelligence using machine learning to find new anticancer targets. Applications of ML-based biological network analysis are used to examine vast amounts of complicated data in order to find trustworthy new targets that could be used to cure human

      illnesses [29]. Classification, clustering, and neural networks are some of these ML-based biology analysis methods for finding new anticancer targets. [30].

      Fig. 4: AI-powered Therapeutic Target Discovery

   3. Molecular screening

      This technique has been used to identify TP53 changes in pathological tissue samples from primary head and neck cancer. A small percentage of cancer cells are discovered in histologically negative clinical specimens, including saliva, surgical margins, and chyle [31]. Accurately identifying these rare cancer cells in a range of clinical samples will have a major influence on otolaryngology, or head and neck surgery. This approach has the potential to screen for head and neck cancer and may require a revision of existing histopathologic staging utilizing cutting-edge molecular genetic techniques. [32].

      Fig. 5: Molecular Docking and Virtual Screening Workflow

   4. Predicting Drug Response

      Artificial intelligence (AI) systems are using an increasing quantity of preclinical data to develop and evaluate predictive models. Precision oncology and drug development are two scientific and therapeutic uses for these in silico models [33]. Here, we concentrate on predictive modelling of drug phenotypic activity in non-molecular targets, such as bacterial cultures or cancer cell lines, that serve as preclinical disease models. The AI subfield most commonly used to solve this significant healthcare issue is machine learning (ML), which includes DL [34].

   5. CRISPR Design Optimization and Gene Editing Prediction:

      Current evolution in gene editing, especially continuous development of CRISPR-Cas systems, has fundamentally changed experimental and applied procedures in medicine, and remedial design [35]. The specificity, rate, and explanatory power of genome- editing procedures have been enhanced more recently by the methodical application of AI and machine learning techniques. This has improved the prediction of aim effectiveness, assessment of non-target risks, and customization of chemical treatment designs. [36].

      Applications of CRISPR/Cas9 for Genome Editing:

      Fig. 6: Applications of CRISPR/Cas9 for Genome Editing

   6. Genomic pattern recognition

      An enormous amount of data has been produced by recent developments in molecular biology and genomic research, such as high- throughput sequencing techniques and cDNA microarray technology [37]. The Human Genome Project’s completion, which sequenced the entire human genome, has also greatly increased researchers’ desire to use this wealth of information in other scientific and medical domains. Effective computational processing of this enormous volume of data is quickly emerging as a significant challenge [38].

   7. Protein structure prediction

      Efficient computational methods must be developed to process these sequences as they are generated in order to analyze the information they carry. Finding the genes in freshly sequenced DNA is the initial step [39]. The GRAIL system, an integrated artificial intelligence system that combines parallel processing tools and multi-sensor neural networks to identify and understand genes in DNA sequences, serves as an example [40].

      Computational biology workflow for the study of protein-protein complexes

      In all docking approaches, the native complex is thought to be around the overall least of energy landform composed of the collection of all complicated protein conformations that are conceivable in theory [41]. Any docking algorithm’s primary difficulties can be broken down into three distinct categories: The first step is to list all of the potential docking orientations at a high enough resolution. Second, it is necessary to take into account the small or large structural alterations that take place throughout complex creation. Third, the near-native solutions must be chosen from among all potential alternatives. A scoring system that differentiates between native (-like) and non-native (-like) docking solutions is necessary for a trustworthy choice [42].

      Fig. 7: Computational Biology Workflow for the Study of Protein-Protein Complexes

   8. Personalized medicine

      A novel approach to healthcare called “personalized medicine” entails simulating and modelling illnesses according to their underlying processes [43]. The paradigm of the 20th century, which defined disease by pathology or related signs and symptoms and conducted outcomes research based on the existence or absence of the disease syndrome, must be replaced by this approach. Massive volums of precise data are made possible by new technologies like next-generation sequencing, the “omics,” and powerful computers. Nevertheless, attempts to use these new technologies to comprehend complicated illnesses within the framework of the 20th century have not yielded the anticipated advancements in medicine [44].

      It is necessary to illustrate the main benefits of the new framework and the shortcomings of the old framework in order to encourage doctors to adopt a paradigm shift. Given the simplicity of the pancreas as an organ for disease modelling and the substantial benefits of personalized treatment, chronic pancreatitis is a perfect complex ailment to examine in order to weigh the advantages and disadvantages of the two frameworks [45].

      Fig. 8: Personalization of Medicine

      This image explains the process of personalized medicine.

      Its a ONE SIZE FITS ALL model of individual unique characteristics of decision making and treatment. The main aim is to produce targeted response in patient and also reduce risk of side and harmful effects [46].

   9. Biomarker identification

      By finding biomarker signals in large and varied datasets that are crucial for early disease identification and therapy, artificial intelligence (AI) in biomarker discovery enhances precision medicine By spotting trends in enormous collection of and developing novel innovations that makes it viable to administer perfect and efficient therapies, AI technologies such as DL and ML diagnostics are transforming development of biomarkers [47]. Among the gaps that currently exist are those related to algorithmic openness, data quality, and privacy ethics. AI-powered biomarker discovery techniques aim to revolutionize cancer by increasing patient survival rates via more accurate early diagnosis and focused treatment [48].

      The picture emphasizes how the AI/ML bioinformatics workflow is more efficient and uses fewer resources than the conventional approach. Although next-generation sequencing and the acquisition of genetic material are the first steps in both approaches, the analysis that follows differs greatly.

      The conventional bioinformatics workflow is based on the laborious, time-consuming, and resource-intensive manual processing and analysis of data. It frequently finds it difficult to handle the enormous volume and complexity of contemporary genetic data.

   10. Treatment prediction

       Artificial intelligence has the capacity to enhance patient results and healthcare accuracy with the help of predicting and automating a number of cancers [49]. Risk assessment, early diagnosis, patient prognosis computation, and deep knowledge-based therapy selection are some of the uses of AI in oncology. A subfield of artificial intelligence called machine learning (ML) has shown great promise in predicting several types of cancer, including those of the breast, brain, lung, liver, and prostate [50]. ML allows computers to learn from training data. In fact, AI and ML have surpassed doctors in cancer prognosis. People with diseases other than cancer may also benefit from these technologies in terms of diagnosis, prognosis, and quality of life. Hence, it’s essential for developing new projects that will benefit patients and progress current AI and ML technology. [51].

   11. Agricultural biotechnology

       Numerous significant uses of molecular biology and biotechnology exist to enhance crops, including as marker-assisted selection, plant in vitro propagation, micropropagation for embryo rescue, and specialist mutant breeding techniques such as focusing on locally caused lesions in genomes [52]. We concentrate on the subset of agricultural biotechnologies that use plant genetic engineering (GE), also known as the nonsexual transfer of foreign genes to enhance crops. This technology carries on the long- standing practice of combining agronomic techniques with genetic advancements to boost agricultural productivity [53].

       Fig. 9: Precision Farming

       The picture is an infographic describing precision farming, a cutting-edge, technologically advanced approach to agricultural management such as site-specific management, Data driven decision, and resource efficiency. This strategy maximizes output, profitability, and environmental sustainability by observing, measuring, and responding to variability within fields using data and technology.

   12. Industrial biotechnology

       Industrial biotechnology, a third wave of biotechnology, is currently booming. Green biotechnology, which focuses on genetically modified crops, and red biotechnology, which targets the medical field, are distinct from industrial biotechnology, commonly known as white biotechnology [54]. Biological systems are used in industrial biotechnology to produce minerals, chemicals, and energy. Together with advances in molecular genetics, enzyme engineering, and metabolic engineering, this technology is primarily based on fermentation technology (the controlled use of microorganisms) and biocatalysis (the use of enzymes to catalyze chemical reactions). Recently, the phrase “white biotechnology,” which refers to the beneficial environmental elements associated with the application of industrial biotechnology, was advocated by EU decision-making authorities and is currently gaining traction [55].

   13. Waste treatment

       Biotechnology applications in waste management strategies Reuse and toxicity descriptions

       The goal of analytical and biological approaches for toxicity characterisation is to specify what constitutes “toxic intoxicating amounts.” Methodologies have advanced, yet there are still issues with how to interpret the data [56]. Toxicity has an impact on biological treatment plants and is a major factor in determining water quality-based criteria. In terms of sustainability, efficient analytical and biological techniques are essential for water reuse applications. Analytical assessments, research, and application particularly with regard to process and system monitoringremain largely unfinished. More advancements in this field are required [57].

       Table 2: Various Roles of AI in Biotechnology

       S. No.	AI Subfield / Technique	Biotechnology Applications	Precise Roles	Modern Tools / Examples
       A	Machine Learning (ML)	Drug discovery, target identification, disease classification	Facilitates prediction of drug target interactions Processes and interprets large- scale omics datasets Enables classification and clustering of disease- associated markers for improved diagnosis [58]	Random Forest, XGBoost, Graph Neural Networks (GNNs), DeepChem
       1.	Supervised learning	Diagnosis of disease and drug discovery	training for neutral networks and decision trees [59]	Programming libraries, pytorch
       2.	Unsupervised learning	Anomaly detection	It can be used to investigate unknown or unprocessed data [60]	Clustering tools, t-SNE, UMAP
       3.	Reinforcement learning	Robotics, adaptive prosthetics	The objective is only to make choices that will maximize future rewards to the greatest extent feasible. [61]	Q learning, SARSA
       4.	Deep learning	MRI, X-rays and tumor detection	Facilitates new drug discovery and prediction of patient outcomes [62]	Artificial neural network, RNN, CNN LSTM
       5.	Transfer learning	Tumor detection, medical imaging	particularlyin the domains of multiple language text classification, sentiment classification, text classification, and spam email detection.[63]	MobileNet and Fast AI
       6.	Semi supervised learning	PET scans, classification of diabetic retinopathy	classification problem, the class is provided as a categorical label, and the data element to be classified is represented as a feature vector.[64]	Generative models, graph-based SSL models
       7.	Active learning	Drug development and drug discovery	Annotation of genome and protein function [65]	Pytorch and keras
       8.	Ensemble learning	Virtual screening and drug discovery	Combine random forest, svm and neural networks [66]	Pytorch and tensorflow
       9.	Federated learning	AI model training across multiple institutions.	arises as a paradigm that solves this problem by allowing institutions located in different	TFF PySyft

       			places to work together on a model training procedure. [67]		flwr
       10.	Few shoot learning	Drug discovery and plant pathology		a remedy for the lack of data	JAX PyTorch
       			that has prevented deep learning from being used [68]
       B	Neural network architectures	Bioinformatics, Gene prediction, cancer identification	powerful as nonlinear signal processors, but obtained results are often far from satisfactory [69]		TensorFlow, Keras
       11	Convolutional neural networks	Drug discovery, genomics	most important networks in domain of deep learning. attained extraordinary progress in a variety of fields, such as natural language processing and computer vision.[70]		Deep learning, caffe, keras
       12	Recurrent neural networks	GENE expression, EHR data	extensively used in fields of study that deal with sequential data, including text, audio, and video [71]		LSTM, GRU
       13	Long term short memory networks	ANALYZE, degradation	biomaterial	transformed deep learning, especially for applications requiring sequential data modelling.[72]	MATLAB PyTORCH TENSORFLOW
       14	transformers	Protein engineering, Mutation effects	influencing the Natural Language Processing (NLP) sector. There are pertinent similarities between natural languages and biological sequences. [73]		Multihead attention, Positional encoding
       15	autoencoders	Drug discovery	an unsupervised learning model. act as a dimensionality reduction method [74]		Adam, Dense, Conv2D
       16	Variational autoencoders	Multi-omics integration	data	They are constructed using neural networks, which are typical function approximators. [75]	PyTORCH TENSORFLOW
       17	Graph neural network	Virtual screening, Protein-protein interaction prediction	capture a graph’s reliance by sending messages between its nodes. [76]		pyG DGL
       18	Generative adversarial networks	Drug discovery	presenting outcomes on segmentation [77]		remarkable image	PyTORCH TENSORFLOW

       19	Multilayer perceptrons	Predictive modelling, classification	Within the network, signals are only sent in one direction: from input to output.[78]	Keras Scikit learn
       20	Neural ordinary differential equations	Simulate and predict behavior of complex	attracting increasing attention in various research domains recently. [79]	ODE solvers JAX JULIA
       C	Stastical and predictive modelling	Accelerate drug discovery	allow for the prediction of specific facets of human behaviour, including objectives, behaviours, and preferences [80]	Python SAS IBM SPSS
       21	Bayesian network	Disease diagnosis and drug discovery	integrate various problems and system elements; make use of data from various sources; and deal with uncertainty and missing data [81]	OpenBUGS python
       22	Hidden markov models	Gene prediction, MSA	The development of hidden Markov model (HMM) techniques has given profile analysis a stronger mathematical foundation. [82]	SAM HMMER
       23	Markov chain monte carlo	DRUG development, Protein structure function	MCMC method is a statistical tool that requires a lot of computing power. [83]	Stan BUGS
       24	Logistic regression models	Biomarker detection, Clinical diagnosis	elucidate the connection between an independent variable and a qualitative dependent variable. [84]	Python SPSS
       25	Survival analysis models	Clinical trials Bio-manufacturing	capacity to deal with censored observations that are disregarded by techniques like linear regression and a t-test (or analysis of variance) for comparing the survival periods of two or more groups [85]	KAPLAN-Meirer Log-rank test
       26	Sequence alignment algorithms	To identify similarity between DNA, RNA	Numerous other tasks, such as phylogenetic analysis is guided by it. [86]	BLAST FASTA
       27	Protein structure prediction models	RATIONAL DRUG DESIGN, DIAGNOSIS	Protein structure prediction, which is mostly based on sequence and structure homology, has grown in significance. [87]	Alphafold RoseTTAFold

       28	Genome annotation models	Accelerated genomic discovery	The annotation is what connects the sequence to the organism’s biology. [88]		MAKER AUGUSTUS
       29	Metagenomic classification models	Novel enzyme screening, Targeted enzyme discovery	allowed for the direct extraction, sequencing, and study of particular phylogenetic marker genes or the complete genomic content of microbial communities, allowing researchers to get over this restriction. [89]		MEGAHIT
       30	Phylogenetic machine learning	Construction of phylogenetic tree	Tree topologies and branch lengths have been inferred, substitution models have been chosen, and introgression and diversification have been inferred downstream using methods based on simulated training data. [90]		EBG PHYDDLE
       E	Computational biology models	Synthetic biotic models	Through theoretical investigation and practical modelling, computational biology provides a strong foundation for tackling important scientific problesm. [91]		PYTHON GROMACS
       31	Systems biology modelling	Metabolic engineering, Drug discovery	seeks to forecast biological systems’ behaviour based on the collection of molecules involved. [92]		COPASI V-CELL
       32	Gene regulatory network prediction	Methodology	includes signal transduction, metabolism, cell cycle, and cell differentiation [93]		SCODE SCENIC
       33	Protein protein interaction prediction	Drug discovery Target therapeutics	have attracted interest in computer-aided drug development and bioinformatics. [94]		GNN ALPHA-FOLD HADDOCK
       34	Molecular docking AI models	Accelerated virtual screening De novo drug design	The underlying mechanism and the detailed process of molecular docking are both clear and comprehensible. [95]		ATOMNET AUTODOCK- VINA
       35	Drug target interaction prediction	Drug discovery Drug repurposing		to make large-scale	DEEPSCREEN, DRUGBANK
       			predictions about possible drug-target interactions. [96]

       F	Data driven optimization techniques	Bioprocess development, Strain engineering	However, such objective functions might not exist in many real-world optimization issues. [97]	PYTHON SQL EXCEL
       36	Evolutionary algorithms	Metabolic engineering, Protein and molecular design	This article compares three probabilistic optimization techniques based on the notion of natural evolution: GA, EP, and (ESs).[98]	GA GP DE
       37	Genetic algorithms	Bioinformatics Protein structure prediction	methods that can be used for a variety of optimization issues. They are appealing for numerous optimization issues in practice because of their adaptability.[99]	DEAP MATLAB LEAP
       38	Particle swarn optimization	Drug design Protein structure prediction	An algorithm for population- based stochastic optimization inspired by the clever collective behavior of certain animals, such schools of fish or flocks of birds [100]	MATLAB
       39	Stimulated annealing	Protein folding Bioprocess optimization	for determining a cost function’s global minimum when it may have multiple local minima [101]	MATLAB AUTODOCK
       40	Bayesian optimization	Bioprocess engineering Protein engineering and design	A method for optimizing objective functions that need a lot of time (minutes or hours) to assess [102]	BOTORCH GPyOPT
       G	Image & Signal Analysis in Biotech	Microscopy, Imaging spectroscopy	Research and development use a variety of imaging devices. Automated image analysis enables quick, precise, and trustworthy quantitative analysis when compared to human-performed manual approaches.[103]	MATLAB DEEP LEARNING
       41	Medical Image Analysis	Drug discovery Tissue engineering	is crucial to make use of this growing volume of data and to examine and display the information it contains in a manner appropriate for the particular medical purpose.[104]	3D SLICER ITK-SNAP
       42	Biomedical Signal Processing	Cross data learning, Robust handling	entails recognizing patterns, compressing or expanding into higher or lower dimensions, extracting linear and non-	MATLAB LABVIEW BIOSIG

       			linear features, and identifying signal behaviour.[105]
       43	Cell counting &Imaging Automation	Bioprocess and biopharmaceuticals	has a significant impact on drug development, toxicity, and standard cell culture. [106]	BIORAD DENOVIX
       44	Microscopy Image segmentation	Disease diagnosis, Biofilm study	has a significant impact on computer-aided diagnosis and prognosis. Numerous facets of clinical practice and medical research have benefited from machine learning approaches. [107]	CELL POSE MIB
       45	Digital Pathology AI	Drug discovery and development	plays a vital part in the scientific laboratory setting and is becoming more and more technologically necessary. [108]	IMS HALO QUPATH
       H	Natural Language Processing	Genomics and bioinformatics	The goal of NLP is to perform this task as accurately and successfully as a human would (for a limited amount of text). [109]	NLTK CLOUD NLP GENSIM
       46	Biomedical Text Mining	Target identification and validation, Genotype and phenotype mapping	High-throughput and computationally automated. However, because natural language processing is so complicated, it is prone to errors.[110]	BIOBERT PUBTATOR
       47	Named Entity Recognition for Biological Terms	Gene/protein identification, Disease mapping	a sub-task of IE which finds and classifies the names/entities. [111]	ML BERT CRF
       48	Literature Based Discovery Systems	Target identification And natural product research	The reader is introduced to important system components, evaluation techniques, contemporary trends, and both historical and contemporary LBD models. [112]	METAMAP UMLS MEDLINE
       49	Knowledge Graphs in Biology	Target identification and validation, Precision medicine	Knowledge graphs have become popular techniques for generating hypotheses and storing data. [113]	KG-HUB BIOCYPHER PETAGRAPH
       50	AI-powered Laboratory Automation	High throughput screening, Bioprocess and fermentation optimization.	have brought about the digital revolution of numerous diagnostic methods and enhanced the promptness and precision of diagnosis. [114]	AI- ASSISTATNT, AUTOMATED ROBOTICPLATFORM

8. ETHICAL CONSIDERATION

   Although there are numerous useful applications of AI and biotechnology in healthcare, there are also significant ethical issues and challenges. There are significant ethical questions raised by the unequal distribution of AI-driven healthcare solutions, which may worsen health disparities. Preventing the expansion of health disparities and ensuring that the benefits of contemporary technologies are distributed equitably among all populations is imperative. [115].

9. TRENDS IN ARTIFICIAL INTELLIGENCE

Trends in AI-biotech start-ups and industry investment: Biotechnology could undergo a radical transformation thanks to blockchain, the Internet, and artificial intelligence. AI-based algorithms help biotech companies in increasing quality control, optimizing operations, and streamlining manufacturing. Through predictive analytics and real-time data collection from sensors and equipment, AI can facilitate proactive maintenance of IoT devices, minimizing downtime and increasing productivity. Blockchain technology may help improve supply chain transparency in terms of security and traceability, safeguarding biotech products or resources. Consequently, the biotech production industry will benefit from these three factors in terms of innovation, efficiency, and reliability. AI is essential for customized medications [116].

1. AI IN DIAGNOSIS

   Healthcare practitioners can identify and diagnose a range of conditions by using AI algorithms to examine medical images from DXA, CT scan, MRI, and ultrasound. AI methods including fuzzy logic, recurrent neural networks (RNNs), logistic regression (LR), and artificial neural networks (ANNs) have been used to detect difficult medical issues with high precision levels. TB, high blood pressure, stroke, brain disease, dermatosis, and harmful illnesses are notable examples of these. Additionally, AI algorithms have shown remarkable efficacy in improving patient outcomes, lowering the financial burden of malignant diseases on the healthcare system, and detecting various malignancies in their initial development, like liver carcinoma. A 2020 study by Chen et al.7 that looked into the use of ANNs in the diagnosis of liver illness demonstrated exceptional accuracy of diagnosis.

   The introduction of AI in the 1950s revolutionized the healthcare sector by fusing machine learning and precision medicine to alter treatment planning, medical imaging, and diagnostic processes. From its early information-based system that depended on therapeutic data and guidelines to more recent Artificial intelligence platforms that employ artificial neural networks (ANNs) and statistical methods for disease identification and treatment, artificial intelligence in healthcare has changed throughout time [117].

   Fig. 10: Biomedical Image Analysis (AI vs Traditional Techniques)

   The above image is a flowchart that describes the steps involved in Biomedical Image Analysis, emphasising the benefits and distinctions between applying artificial intelligence (AI) and more conventional methods. Predictive AI imaging techniques can be far quicker and more accurate than conventional, human-reliant techniques, as the graphic highlights. It also shows how patient data is collected, processed, and examined for diagnosis. Various technologies such as Deep learning (DL), Machine learning (ML), and data analyses are used to study different diseases. AI have transformed the way of diagnosis of critical conditions such as heart disease, brain disease, cancers, nervous system disorders and immune system disorders. Although AI cannot replace medical professionals, it acts as a powerful tool that supports medical professionals. Here are some specific diseases that can be diagnosed by AI faster as compared to conventional methods.

   1. Cancer: It is one of the most dangerous and widely spread disease around the world with the greatest number of deaths. In this disease, cancerous cells replicate in our body, leading to the death of normal cells. Early detection is mandatory in case of cancer. For instance, AI helps in fast and precise diagnosis of breast, lung, skin (melanoma), colon, and prostate cancer. Medical imaging (MRI, CT, PET, and histopathology slides) is analysed by AI models (such as Deep Learning CNNs). AI uses genetic data to discover mutations, categorize tumor stages, and detect tumor borders. By predicting which medications will be effective based on a patient’s genetic profile, AI aids in precision oncology. Tools such as Google DeepMind’s use advanced AI for breast cancer screening, which outperforms radiologists in accuracy.

   2. Heart conditions (CVDs): All over the world, millions of people are affected by CVDs. In this condition, blood vessels and the heart are affected, which leads to heart attacks. It reduces the heart’s ability to pump and blood flow is affected. In this case, it is necessary to detect and diagnose minor and critical symptoms. Diseases such as Heart Attack, Coronary Artery Disease, Arrhythmia are diagnosed by AI and tools. AI-based ECG analysis identifies blockage patterns, heart failure concerns, and abnormal heart rhythms. It uses lifestyle information, blood test results, and patient vitals to predict the likelihood of a heart attack. Tools such as IBM Watson Health, which predict cardiac risk using AI.

   3. Hereditary Conditions: It is a disorder that is transferred from parents to children and affects their genes too. It can occur due to gene mutation, abnormality or chromosomal disorder. Symptoms can be weakness, fatigue, abnormal growth, organ dysfunction etc. It includes Huntington’s disease, Cystic Fibrosis, and Down syndrome. To find gene mutations connected to hereditary disorders, AI systems examine genomic sequences. Deep learning algorithms expedite the interpretation of next-generation sequencing (NGS) data and identify uncommon genomic variations. Tools used such as Googles Deep Variant accurately identify genomic variations.

   4. Nervous System Disorder: The condition in which spinal cord and brain is affected. Nervous system controls various functions like thinking, sensation, coordination etc. if it is damaged, there will be disturbance between brain and body. This disorder includes stroke, epilepsy, Parkinson’s disease, and Alzheimer’s disease. Here, AI examines MRI and PET scans of the brain to find early structural or metabolic alterations. To predict Alzheimer’s disease early, machine learning models monitor speech patterns, locomotion, and cognitive deterioration. Tools used: MRI-based AI is used by IBM Watson and Neuro Predict to detect Alzheimer’s disease.

   5. Immune System Disorders: Immunity is the ability of our body to fight against various foreign diseases. The immune system helps in preventing our body from those diseases and helps us attain a healthy lifestyle. If there is a lack of immunity, it can lead to any immune disorder or may be an autoimmune disease. This disorder slowly affects our own immune system and shows major symptoms. It is essential to diagnose and detect those symptoms as soon as possible. AI helps in the detection of any kind of autoimmune disorder.

   It includes multiple sclerosis, lupus, and rheumatoid arthritis. AI uses omics data (transcriptomics, proteomics) to identify biomarkers. Microsoft’s AI for MS progression analysis is an example tool.

   S.NO.	DISEASE	TRADITIONAL METHODS	AI/BIOTECH BASED TREATMENT	LIMITATIONS
   1.	Cancer	Chemotherapy, surgery	MRI, CT, DeepMind	High cost, data privacy
   2.	CVD	Medication, surgery	AI-Based ECG analysis	Limited availability and a highly affected population

   4.

   3.	Hereditary conditions	Physical or occupational therapies, surgery	Genomic sequence examination through AI	Data security, black box problem
   Nervous system disorders	Medication therapies, surgeries	Machine learning models for the prediction of early Alzheimers disease	Lack of transparency, data privacy
   5.	Immune system disorders	Stem cell transplantation, surgery	AI use omics data to identify biomarkers	Data availability, clinical and ethical challenges
   6.	Liver failure	Medication, supportive care	Additionally, MLAs are starting to be used as instruments for LT recipient screening and selection as well as for posttransplant outcome prediction.	Biased and incomplete datasets, data standardization.
   7.	COVID-19 diagnosis and tracing	Viral test, PCR test, antigen test	ANN (Artificial Neural Networks) helps trace and diagnosing symptoms of COVID-19 in 5 layers	Data privacy and interpretability.

2. AI-POWERED PERSONALIZED MEDICINE

Precision medicine, often known as personalized medicine, is an alternative method of managing diseases that is adapted to the unique needs of each patient. Conventional medicine usually employs a one-size-fits-all treatment strategy, which could overlook individual differences in lifestyle, environment, and genetics that are crucial in determining treatment response and disease susceptibility. Deep neural networks, big data analytics, ML, and AI in medical care are exciting medical topics that may result in patient-specific therapy regimens and predictive diagnostic techniques. Another remarkable accomplishment is the incorporation of artificial intelligence in the medical field, with the main benefactors being cardiology, cancer, and dermatology. For instance, 5.4 million Americans with skin cancer each year were able to classify many forms of the condition at a level comparable to a clinician using deep neural networks. Similarly, 30 million US adults with cardiac conditions may benefit from the application of AI-powered techniques in cardiology for risk assessment and diagnosis [118].

CONCLUSION

The integration of AI and biotechnology represents a pivotal advancement in life sciences, enabling researchers and practitioners to uncover insights from complex biological data with unprecedented speed and accuracy. AI-driven tools and techniques have enhanced various biotechnological domains, including genomics, drug development, diagnostics, and agricultural biotechnology. These technologies not only streamline research processes but also contribute to more precise, personalized, and predictive approaches in healthcare and industrial biotechnology. Despite its enormous promise, issues like data privacy, algorithm transparency, and the requirement for interdisciplinary cooperation must be resolved in order to fully reap the rewards of AI. The future of biotechnology will be redefined, innovation will be accelerated, and results will be improved as both sectors continue to develop.

REFERENCE:

1. Faraji SN, Masjoodi S, Azmand S. Biotechnology, Nanotechnology, and AI: Transformative Convergence in Healthcare (A Mini-Review). Advances in Applied NanoBio-Technologies. 2024; 5:23-8.

2. Barcelos, M.C.S., et al., The colors of biotechnology: general overview and developments of white, green and blue areas. FEMS Microbiol Lett, 2018. 365(21).

3. Khoshandam, M., et al., Clinical applications of the CRISPR/Cas9 genome-editing system: Delivery options and challenges in precision medicine. Genes Dis, 2024. 11(1): p. 268-282

4. Soetaert W, Vandamme E. The impact of industrial biotechnology. Biotechnology Journal: Healthcare Nutrition Technology. 2006 Aug;1(78):756-69.

5. Abonamah AA, Tariq MU, Shilbayeh S. On the commoditization of artificial intelligence. Frontiers in psychology. 2021 Sep 30;12:696346.

6. Aguilera S, Quintana L, Khan T, Garcia R, Shoman H, Caddell L, Latifi R, Park KB, Garcia P, Dempsey R, Rosenfeld JV. Global health, global surgery and mass casualties: II. Mass casualty centre resources, equipment and implementation. BMJ global health. 2020 Jan 13;5(1).

7. Muzamal Hussain N, Afzal M, Ullah O, Raheem MA. Biotechnology-Artificial Intelligence Nexus: A Mini Review of Advanced Applications, Benefits, and Challenges in the Healthcare Domain. Biotechnology. 2024 Jan;7(1):185-200.

8. Ahmed MN, Toor AS, O’Neil K, Friedland D. Cognitive computing and the future of health care: the cognitive power of IBM Watson has the potential to transform global personalized medicine. IEEE pulse. 2017;8(3):4-9.

9. Al-Alusi MA, Ding E, McManus DD, Lubitz SA. Wearing your heart on your sleeve: the future of cardiac rhythm monitoring. Current cardiology reports. 2019 Dec;21(12):158.

10. MuzamalHussain N, Afzal M, Ullah O, Raheem MA. Biotechnology-Artificial Intelligence Nexus: A Mini Review of Advanced Applications, Benefits, and Challenges in the Healthcare Domain. Biotechnology. 2024 Jan;7(1):185-200.

11. P. Chakravarthi G, R. Babu V, R. DSVNM, G. Rahul, and P. SVGVA, AI and Machine Learning in Biotechnology: A Paradigm Shift in Biochemical Innovation, Int J Plant Anim Environ Sci 14, no. 4 (2024),

12. H. Decheng, Y. Mingxuan, W. Xin, X. Siwei, and Y. Bo, AI-Driven Drug Discovery: Accelerating the Development of Novel Therapeutics in Biopharmaceuticals, Int Med Sci Res J 4, no. 8 (2024): 882-899.

13. Oliveira AL. Biotechnology, big data and artificial intelligence. Biotechnology journal. 2019 Aug;14(8):1800613.

14. Notin P, Rollins N, Gal Y, Sander C, Marks D. Machine learning for functional protein design. Nature biotechnology. 2024 Feb;42(2):216-28.

15. Koumakis L. Deep learning models in genomics; are we there yet? Computational and Structural Biotechnology Journal. 2020 Jan 1; 18:1466-73.

16. Potamias G, Koumakis L, Moustakis V. Gene selection via discretized gene-expression profiles and greedy feature-elimination. InHellenic Conference on Artificial Intelligence 2004 May 5 (pp. 256-266). Berlin, Heidelberg: Springer Berlin Heidelberg.

17. Koumakis L, Kanterakis A, Kartsaki E, Chatzimina M, Zervakis M, Tsiknakis M, Vassou D, Kafetzopoulos D, Marias K, Moustakis V, Potamias G. MinePath: mining for phenotype differential sub-paths in molecular pathways. PLoS computational biology. 2016 Nov 10;12(11):e1005187.

18. Kang Y, Cai Z, Tan CW, Huang Q, Liu H. Natural language processing (NLP) in management research: A literature review. Journal of Management Analytics. 2020 Apr 2;7(2):139-72.

19. Abdolmaleki A, Springenberg JT, Tassa Y, Munos R, Heess N, Riedmiller M. Maximum a posteriori policy optimisation. arXiv preprint arXiv:1806.06920. 2018 Jun 14.

20. Matsuo Y, LeCun Y, Sahani M, Precup D, Silver D, Sugiyama M, Uchibe E, Morimoto J. Deep learning, reinforcement learning, and world models. Neural Networks. 2022 Aug 1; 152:267-75.

21. Abbasi AZ, Islam N, Shaikh ZA. A review of wireless sensors and networks’ applications in agriculture. Computer Standards & Interfaces. 2014 Feb 1;36(2):263-70.

22. Kakani V, Nguyen VH, Kumar BP, Kim H, Pasupuleti VR. A critical review on computer vision and artificial intelligence in food industry. Journal of Agriculture and Food Research. 2020 Dec 1; 2:100033.

23. Alexandratos N, editor. World agriculture: towards 2010: an FAO study.

24. Kazanzides P, Fichtinger G, Hager GD, Okamura AM, Whitcomb LL, Taylor RH. Surgical and interventional robotics-core concepts, technology, and design [tutorial]. IEEE robotics & automation magazine. 2008 Jun 30;15(2):122-30.

25. Okamura AM, Matari MJ, Christensen HI. Medical and health-care robotics. IEEE Robotics & Automation Magazine. 2010 Sep 9;17(3):26-37.

26. Hood L, Friend SH. Predictive, personalized, preventive, participatory (P4) cancer medicine. Nature reviews Clinical oncology. 2011 Mar;8(3):184-7.

27. Naugler C, Church DL. Automation and artificial intelligence in the clinical laboratory. Critical reviews in clinical laboratory sciences. 2019 Feb 17;56(2):98- 110.

28. Ahn S, Lee SE, Kim MA-O (2022) Random-forest model for drug-target interaction prediction via Kullbeck-Leibler divergence. J Chem 14:67.

29. Shabani, M. & Hojjat-Farsangi, M. Targeting receptor tyrosine kinases using monoclonal antibodies: the most specific tools for targeted-based cancer therapy. Curr. Drug Targets 17, 16871703 (2016).

30. You Y, Lai X, Pan Y, Zheng H, Vera J, Liu S, Deng S, Zhang L. Artificial intelligence in cancer target identification and drug discovery. Signal transduction and targeted therapy. 2022 May 10;7(1):156.

31. Challa AP, Beam AL, Shen M, Peryea T, Lavieri RR, Lippmann ES, Aronoff DM. Machine learning on drug-specific data to predict small molecule teratogenicity. Reproductive Toxicology. 2020 Aug 1;95:148-58.

32. Sidransky D, Boyle J, Koch W. Molecular screening: Prospects for a new approach. Archives of OtolaryngologyHead & Neck Surgery. 1993 Nov 1;119(11):1187-90.

33. Jordan MI. Artificial intelligencethe revolution hasnt happened yet. Harvard Data Science Review. 2019 Jul 1;1(1):1-9.

34. Ballester PJ, Stevens R, Haibe-Kains B, Huang RS, Aittokallio T. Artificial intelligence for drug response prediction in disease models. Briefings in bioinformatics. 2022 Jan;23(1): bbab450.

35. A. Raval and R. Oza, Advancing AI With Quantum Computing: Synergies Between Quantum Neural Networks and Quantum Reinforcement Learning (Springer Nature Switzerland, 2025), 305332.

36. Patel J, Patel D, Raval A. Artificial Intelligence for Predictive Modeling in CRISPR/Cas9 Gene Editing: a Survey of Methods and Design Strategies. The Journal of Gene Medicine. 2025 Dec;27(12): e70061.

37. Smith TF, Waterman MS. Identification of common molecular subsequences. Journal of molecular biology. 1981 Mar 25;147(1):195-7.

38. Liew AW, Yan H, Yang M. Pattern recognition techniques for the emerging field of bioinformatics: A review. Pattern Recognition. 2005 Nov 1;38(11):2055- 73.

39. E. C. Uberbacher and R. J. Mural, “Locating protein-coding regions in human DNA sequences by a multiple sensor-neural network approach”, Proc. Natl. Acad. Sci. USA, vol. 88, pp. 11261-11265.

40. Guan X, Mural RJ, Uberbacher EC. Protein structure prediction using hybrid AI methods. In Proceedings of the Tenth Conference on Artificial Intelligence for Applications 1994 Mar 1 (pp. 471-473). IEEE.

41. Berman, H. M.;Westbrook, J.;Feng, Z.;Gilliland, G.;Bhat, T. N.;Weissig, H.;Shindyalov, I. N.;Bourne, P. E. Nucleic Acids Res 2000, 28, 235.

42. Fink F, Hochrein J, Wolowski V, Merkl R, Gronwald W. PROCOS: Computational analysis of proteinprotein complexes. Journal of computational chemistry. 2011 Sep;32(12):2575-86.

43. Kuhn, T. S. The Structure of Scientific Revolutions 1st edn (University of Chicago, Chicago, 1962).

44. Committee on a Framework for Development a New Taxonomy of Disease; National Research Council. Toward Precision Medicine: Building a Knowledge Network for Biomedical Research and a New Taxonomy of Disease. (National Academies Press, Washington, DC, 2011).

45. Whitcomb DC. What is personalized medicine and what should it replace? Nature reviews Gastroenterology & hepatology. 2012 Jul;9(7):418-24.

46. Eddy DM, Adler J, Patterson B, Lucas D, Smith KA, Morris M. Individualized guidelines: the potential for increasing quality and reducing costs. Annals of Internal Medicine. 2011 May 3;154(9):627-34.

47. Alum EU. AI-driven biomarker discovery: enhancing precision in cancer diagnosis and prognosis. Discover oncology. 2025 Mar 13;16(1):313.

48. Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, Jemal A. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA A Cancer J Clin. 2024;74:22963.

49. Harbeck N, Gnant M. Breast cancer. Lancet. 2017;389(10074):11341150. doi:10.1016/S0140-6736(16)31891-8

50. Zhang B, Shi H, Wang H. Machine learning and AI in cancer prognosis, prediction, and treatment selection: a critical approach. Journal of multidisciplinary healthcare. 2023 Dec 31:1779-91.

51. Afolabi LO, Afolabi MO, Sani MM, et al. Exploiting the CRISPRCas9 geneediting system for human cancers and immunotherapy. Clinical Translat Immunol. 2021;10(6):e1286. doi:10.1002/cti2.1286

52. Bennett AB, Chi-Ham C, Barrows G, Sexton S, Zilberman D. Agricultural biotechnology: economics, environment, ethics, and the future. Annual Review of Environment and Resources. 2013 Oct 17; 38:249-79.

53. Díaz S, Malhi Y. Biodiversity: Concepts, patterns, trends, and perspectives. Annual Review of Environment and Resources. 2022 Oct 17;47(1):31-63.

54. Soetaert W, Vandamme E. The impact of industrial biotechnology. Biotechnology Journal: Healthcare Nutrition Technology. 2006 Aug;1(78):756-69.

55. Dale, B. E., Greening the chemical industry: research and development priorities for biobased industrial products. J. Chem. Technol. Biotechnol. 2003, 78, 10931103.

56. Englande AJ, Jin G. Application of biotechnology in waste management for sustainable development: An overview. Management of Environmental Quality: An International Journal. 2006 Jul 1;17(4):467-77.

57. Sivakumar D, Srikanth P, Ramteke PW, Nouri J. Agricultural waste management generated by agro-based industries using biotechnology tools.

58. Nasteski V. An overview of the supervised machine learning methods. Horizons. b. 2017 Dec 15;4(51-62):56

59. Naeem S, Ali A, Anam S, Ahmed MM. An unsupervised machine learning algorithm: Comprehensive review. International Journal of Computing and Digital Systems. 2023 Mar 2

60. Matsuo Y, LeCun Y, Sahani M, Precup D, Silver D, Sugiyama M, Uchibe E, Morimoto J. Deep learning, reinforcement learning, and world models. Neural Networks. 2022 Aug 1; 152:267-75.

61. Matsuo Y, LeCun Y, Sahani M, Precup D, Silver D, Sugiyama M, Uchibe E, Morimoto J. Deep learning, reinforcement learning, and world models. Neural Networks. 2022 Aug 1; 152:267-75

62. Weiss K, Khoshgoftaar TM, Wang D. A survey of transfer learning. Journal of Big data. 2016 May 28;3(1):9

63. Reddy YC, ViswanathP, Reddy BE. Semi-supervised learning: A brief review. Int. J. Eng. Technol. 2018 Feb 9;7(1.8):81

64. Mueller AL, Knoblock NA, Orvis KS. The effects of an active-learning biotechnology and genomics unit on high school students knowledge, motivation, and learning experiences. In Proceedings from American Association for Agricultural Education Research Conference. Louisville, KY 2009

65. Che D, Liu Q, Rasheed K, Tao X. Decision tree and ensemble learning algorithms with their applications in bioinformatics. Software tools and algorithms for biological systems. 2011 Mar 15:191-9

66. Schoenpflug LA, Nie Y, Sheikhzadeh F, Koelzer VH. A review on federated learning in computational pathology. Computational and Structural Biotechnology Journal. 2024 Dec 1; 23:3938-45

67. Lin H, Qiang Z, Tse R, Tang SK, Pau G. A few-shot learning method for tobacco abnormality identification. Frontiers in Plant Science. 2024 Mar 28; 15:1333236

68. Wilamowski BM. Neural network architectures and learning algorithms. IEEE Industrial Electronics Magazine. 2009 Dec 11;3(4):56-63

69. Li Z, Liu F, Yang W, Peng S, Zhou J. A survey of convolutional neural networks: analysis, applications, and prospects. IEEE transactions on neural networks and learning systems. 2021

70. Yu Y, Si X, Hu C, Zhang J. A review of recurrent neural networks: LSTM cells and network architectures. Neural computation. 2019 Jul 1;31(7):1235-70.

71. Krichen M, Mihoub A. Long short-term memory networks: A comprehensive survey. AI. 2025 Sep 5;6(9):215

72. Ghosh N, Santoni D, Saha I, Felici G. A review on the applications of Transformer-based language models for nucleotide sequence analysis. Computational and Structural Biotechnology Journal. 2025 Mar 18.

73. Li P, Pei Y, Li J. A comprehensive survey on design and application of autoencoder in deep learning. Applied Soft Computing. 2023 May 1; 138:110176

74. Doersch C. Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908. 2016 Jun 19

75. Zhou J, Cui G, Hu S, Zhang Z, Yang C, Liu Z, Wang L, Li C, Sun M. Graph neural networks: A review of methods and applications. AI open. 2020 Jan 1; 1:57-81

76. Aggarwal A, Mittal M, Battineni G. Generative adversarial network: An overview of theory and applications. International Journal of Information Management Data Insights. 2021 Apr 1;1(1):100004

77. Popescu MC, Balas VE, Perescu-Popescu L, Mastorakis N. Multilayer perceptron and neural networks. WSEAS Transactions on Circuits and Systems. 2009 Jul 1;8(7):579-88

78. Yan H, Du J, Tan VY, Feng J. On robustness of neural ordinary differential equations. arXiv preprint arXiv:1910.05513. 2019 Oct 12

79. Zukerman I, Albrecht DW. Predictive statistical models for user modelling. User Modelling and User-Adapted Interaction. 2001 Mar;11(1):5-18.

80. Chen SH, Pollino CA. Good practice in Bayesian network modelling. Environmental Modelling & Software. 2012 Nov 1; 37:134-45

81. Eddy SR. Hidden markov models. Current opinion in structural biology. 1996 Jun 1;6(3):361-5

82. Geyer CJ. Practical markov chain monte carlo. Statistical science. 1992 Nov 1:473-83

83. Nick TG, Campbell KM. Logistic regression. Topics in biostatistics. 2007 Jan 1:273-301

84. George B, Seals S, Aban I. Survival analysis and regression models. Journal of nuclear cardiology. 2014 Aug 1;21(4):686-94.

85. Chowdhury B, Garai G. A review on multiple sequence alignment from the perspective of genetic algorithm. Genomics. 2017 Oct 1;109(5-6):419-31

86. Al-Lazikani B, Jung J, Xiang Z, Honig B. Protein structure prediction. Current opinion in chemical biology. 2001 Feb 1;5(1):51-6

87. Stein L. Genome annotation: from sequence to biology. Nature reviews genetics. 2001 Jul 1;2(7):493-503

88. Mande SS, Mohammed MH, Ghosh TS. Classification of metagenomic sequences: methods and challenges. Briefings in bioinformatics. 2012 Nov 1;13(6):669- 81.

89. Mo YK, Hahn MW, Smith ML. Applications of machine learning in phylogenetics. Molecular Phylogenetics and Evolution. 2024 Jul 1; 196:108066

90. Kitano H. Computational systems biology. Nature. 2002 Nov 14;420(6912):206-10

91. Aloy P, Russell RB. Structural systems biology: modelling protein interactions. Nature reviews Molecular cell biology. 2006 Mar 1;7(3):188-97

92. Karlebach G, Shamir R. Modelling and analysis of gene regulatory networks. Nature reviews Molecular cell biology. 2008 Oct;9(10):770-80.

93. Soleymani F, Paquet E, Viktor H, Michalowski W, Spinello D. Proteinprotein interaction prediction with deep learning: A comprehensive review.

    Computational and Structural Biotechnology Journal. 2022 Jan 1; 20:5316-41

94. docking tools: understanding drug discovery and design. Future Journal of Pharmaceutical Sciences. 2025 Aug 18;11(1):111

95. Chen X, Yan CC, Zhang X, Zhang X, Dai F, Yin J, Zhang Y. Drugtarget interaction prediction: databases, web servers and computational models. Briefings in bioinformatics. 2016 Jul 1;17(4):696-712

96. Jin Y, Wang H, Chugh T, Guo D, Miettinen K. Data-driven evolutionary optimization: An overview and case studies. IEEE Transactions on Evolutionary Computation. 2018 Sep 6;23(3):442-58

97. Kramer O. Genetic algorithms. In Genetic algorithm essentials 2017 Jan 8 (pp. 11-19). Cham: Springer International Publishing

98. Kramer O. Genetic algorithms. In Genetic algorithm essentials 2017 Jan 8 (pp. 11-19). Cham: Springer International Publishing

99. Wang D, Tan D, Liu L. Particle swarm optimization algorithm: an overview. Soft computing. 2018 Jan;22(2):387-408 [100]Bertsimas D, Tsitsiklis J. Simulated annealing. Statistical science. 1993 Feb;8(1):10-5

1. Frazier PI. A tutorial on Bayesian optimization. arXiv preprint arXiv:1807.02811. 2018 Jul 8.

2. Jung SK. Image Processing and Analysis for Biotechnology and Bioprocess Engineering. Applied Sciences. 2024 Jan 14;14(2):711 [103]Ritter F, Boskamp T, Homeyer A, Laue H, Schwier M, Link F, Peitgen HO. Medical image analysis. IEEE pulse. 2011 Dec 1;2(6):60-70

[104]Krishnan S, Athavale Y. Trends in biomedical signal feature extraction. Biomedical Signal Processing and Control. 2018 May 1; 43:41-63.

[105]Chen YW, Chiang PJ. An automated approach for haemocytometer cell counting based on image-processing method. Measurement. 2024 Jul 1; 234:114894 [106]Xing F, Xie Y, Su H, Liu F, Yang L. Deep learning in microscopy image analysis: A survey. IEEE transactions on neural networks and learning systems. 2017

Nov 22;29(10):4550-68

[107]Niazi MK, Parwani AV, Gurcan MN. Digital pathology and artificial intelligence. The lancet oncology. 2019 May 1;20(5): e253-61 [108]Chowdhary K. Natural language processing. Fundamentals of artificial intelligence. 2020 Apr 5:603-49.

1. Zhu F, Patumcharoenpol P, Zhang C, Yang Y, Chan J, Meechai A, Vongsangnak W, Shen B. Biomedical text mining and its applications in cancer research.

   Journal of biomedcal informatics. 2013 Apr 1;46(2):200-11.

2. Kundeti SR, Vijayananda J, Mujjiga S, Kalyan M. Clinical named entity recognition: Challenges and opportunities. In2016 IEEE International Conference on Big Data (Big Data) 2016 Dec 5 (pp. 1937-1945). IEEE

3. Henry S, McInnes BT. Literature based discovery: models, methods, and trends. Journal of biomedical informatics. 2017 Oct 1; 74:20-32 [112]MacLean F. Knowledge graphs and their applications in drug discovery. Expert opinion on drug discovery. 2021 Sep 2;16(9):1057-69

[113]Lara J. AI-powered laboratory diagnostics technology. In Recent Advancements in the Diagnosis of Human Disease 2024 Jun 14 (pp. 1-45). CRC Press [114]MuzamalHussain N, Afzal M, Ullah O, Raheem MA. Biotechnology-Artificial Intelligence Nexus: A Mini Review of Advanced Applications, Benefits, and

Challenges in the Healthcare Domain. Biotechnology. 2024 Jan;7(1):185-200.

1. Mehta A, Niaz M, Adetoro A, Nwagwu U. Advancements in manufacturing technology for the biotechnology industry: The role of artificial intelligence and emerging trends. International Journal of Chemistry, Mathematics and Physics. 2024;8(2):12-8.

2. Aamir A, Iqbal A, Jawed F, Ashfaque F, Hafsa H, Anas Z, Oduoye MO, Basit A, Ahmed S, Rauf SA, Khan M. Exploring the current and prospective role of artificial intelligence in disease diagnosis. Annals of Medicine and Surgery. 2024 Feb 1;86(2):943-9.

3. Kolluri VE. Revolutionizing Healthcare With AI: Personalized Medicine: Predictive. JETIR-Int. J. Emerg. Technol. Innov. Res. 2016;3(11):2349-5162. [118]D. C. Mohr, M. N. Burns, S. M. Schueller, G. Clarke, and M. Klinkman, Behavioral Intervention Technologies: Evidence review and recommendations for

future research in mental health, General Hospital Psychiatry, vol. 35, no. 4, pp. 332338, Jul. 2013, doi: https://doi.org/10.1016/j.genhosppsych.2013.03.008