Artificial Intelligence (AI), Robotics and Computational fluid dynamics

Department of Pharmaceutics
B. K. Mody Government Pharmacy College, Rajkot
Artificial intelligence (AI), robotics and
Computational fluid dynamics
Prepared by – Chintan S Kalsariya
M.pharm (sem - II)
1

Contents
2
No Title
1 AI and its pharmaceutical automation
2 Robotics
3 Computational fluid dynamics
4 Partnerships of AI establishments with pharmaceutical firms
5 AI-Aided Computational Tools for Facilitating Drug Discovery

1. ARTIFICIAL INTELLEGENCE (AI)
3

4
 Artificial intelligence, or AI, is the field of computer science
that focuses on developing intelligent machines capable of
performing tasks that typically require human intelligence.
 These tasks include things like understanding natural
language, recognizing images, making decisions, and
learning from experience.
 AI systems use techniques like machine learning, deep
learning, and neural networks to process and analyze data,
allowing them to learn and adapt over time.
 The ultimate goal of AI research is to create machines that
can think, reason, and act in ways that are clear from human
beings.

5
 Artificial intelligence-AI- is getting increasingly sophisticated at doing what humans
do, more efficiently, more cheaply.
 According to father of AI John McCarthy…
It is a “the science and engineering of making
intelligent machines, especially intelligent
computer programs”.

7
Artificial Neural Networks (ANNs) :
 An Artificial Neural Network (ANN) is a machine
learning model inspired by the human brain's
neural structure. It comprises interconnected nodes
(neurons) organized into layers. Data flows through
these nodes, adjusting the weights of connections
to learn patterns and make predictions.
 they can create nonlinear input-output mappings,
optimize gradient conditions in chromatography,
analyze multivariate nonlinear relationships in
pharmaceutical research, design pre-formulations,
and predict the behavior of drugs.

8
Neural
Network
Static Dynamics
Types of neural networks:

9
2. Dynamic neural networks:
 It is also known as recurrent networks, utilize past
information to predict present and future system states.
They are valuable for modeling drug release from
controlled formulations due to their ability to make
predictions based on past data.
1. Static Neural Network :
 Static networks like Multilayer Perceptron (MLP) use feedforward connections to
compute outputs. They consist of multiple fully connected layers, aiding in recognizing
specific elements.
 MLPs find applications in designing controlled release formulations, predicting drug
dissolution profiles, and optimizing formulations due to their interconnected nature.

10
B. Pharma automation :
 Pharmaceutical automation, powered by robotics and AI, is
transforming drug development, manufacturing, quality
control, and distribution.
 Robotics ensure precision and speed in tasks like handling,
dispensing, and packaging, improving productivity and
reducing contamination risks.
 AI analyzes data, predicts outcomes, and learns patterns,
enhancing quality assurance and driving innovation in
pharmaceutical processes.

11
C. Advantages of AI & Pharma automation :
 Error Reduction
 Daily Application
 Digital Assistants
 Repetitive Jobs
 Medical Applications
 Save time
 Decrease in cost for the end user
 Increasing accuracy & reproducibility

12
D. Dis-advantages of AI & Pharma automation :
 Data Privacy and Security Concerns
 Job Losses Due to Automation
 Ethical Considerations
 Regulation and Compliance
 Technical Limitations
 Lack of Trust and Understanding
 Lack of Creativity
 High Cost

13
D. APPLICATIONS OF AI IN PHARMACEUTICALS
1. Drug Discovery and Development
A. Peptide synthesis
B. Identifying novel antimycobacterial drugs
C. Predicting the effectiveness of drug dosing and delivery methods
D. Rapid identification of the bioactive agents and monitoring of drug release
E. Optimizing drug release from matrix tablets
2. Manufacturing and Supply Chain
3. Patient Care and Drug Delivery
4. Regulatory Compliance and Safety
5. Clinical Research
6. Disease Identification
7. Radiology & Radiotherapy

14
1. Drug Discovery and Development
A. Peptide synthesis
 Biotechnology and peptide synthesis
advancements have enabled the exploration of
peptides' pharmacological effects.
 Artificial Neural Networks (ANNs) are used to
evaluate organ-targeting peptides, accurately
predict peptide binding, and identify immune
response targets.

15
B. Identifying novel antimycobacterial drugs
 Virtual screening techniques and an
Artificial Neural Network (ANN) model
are used to identify new antimycobacterial
drugs and reduce multidrug-resistant
tuberculosis.
 Cheminformatics tools and molecular
descriptors are employed to evaluate
antimycobacterial agents and identify
effective compounds against
Mycobacterium tuberculosis.

16
C. Predicting the effectiveness of drug dosing and delivery methods:
 A data-driven predictive system has been developed
using a machine learning framework capable of
modeling the dynamics between pathogens and drugs.
 The system predicts the effectiveness of dosing
patterns and drug delivery methods.
 The system achieved an accuracy of 85% in
performance evaluation.

17
D. Rapid identification of the bioactive agents & monitoring of drug release
 ANNs are used in various pharmaceutical applications, including
drug modeling, drug release prediction, and controlled drug
delivery optimization.
 They aid in identifying drug structures, predicting pharmacokinetic
parameters, and enhancing drug delivery systems.
E. Optimizing drug release from matrix tablets
 ANNs are used in optimizing drug release from matrix tablets, predicting dissolution
profiles, developing sustained-release formulations, and controlling release in various
tablet types.
 They outperform traditional methods and enable accurate predictions of formulations and
release profiles.

18
2. Manufacturing and supply chain
 AI-powered systems can optimize pharmaceutical
manufacturing processes, improve quality control, and predict
supply chain disruptions, leading to cost savings and increased
productivity.
3. Patient Care and Drug Delivery
 AI can be used to personalize treatment plans, predict patient
responses to drugs, and improve drug delivery systems for
better patient outcomes.

19
4. Regulatory Compliance and Safety
 AI can assist in the analysis of adverse event reports to
identify potential safety issues with drugs and help in the
development of safer drugs.
 Automation and AI are reshaping clinical labs, boosting
efficiency and accuracy.
 Robotics handle tasks like sample management, while
AI analyzes data for diagnoses and treatment plans.
5. Clinical Research

20
 Machine learning aids in rare disease identification and treatment optimization.
 This integration improves testing speed, accuracy, and patient outcomes while lowering
costs.
 Expect further advancements as technology evolves, enhancing healthcare delivery.

21
6. Disease Identification
 Machine Learning – particularly Deep Learning algorithms – have recently made
huge advances in automatically diagnosing diseases, making diagnostics cheaper
and more accessible.
 How machines learn to diagnose
 ML algorithms can learn to see patterns similarly to the way doctors see them. A
key difference is that algorithms need a lot of concrete
 So Machine Learning is particularly helpful in areas where the diagnostic
information, a doctor examines is already digitized

22
 Cedars-Sinai investigators can identify comprehensive cardiovascular risk from CT scans
obtained without contrast dye, which some patients cannot tolerate, through the use of AI
algorithms.
[Image by Cedars-Sinai]
Exa software - AlphaMissense

23
7. Radiology & Radiotherapy
 Various kinds of data are collected during radiotherapy, including clinical
information, biological samples, images, planning parameters, and machine data.
 These data can be combined and related to events like accurate contouring, plan
passing rate, treatment response and injury through AI approaches.
Ex- Qure.AI

25
 Robots, as defined by ISO 8373, are versatile
manipulators used in industrial automation.
 In labs and pharmaceutical settings, they
handle tasks surpassing human capacity,
often in hazardous environments.
 They assemble medical devices, prepare
prescriptions, and automate assay analysis,
significantly reducing costs and time in
research and healthcare.

27
 Advantages:
 Accuracy
 Tirelessness
 Reliability
 Return on investment
 Affordability
 Production
 Quality
 Speed
 Flexibility
 Safety
 Savings
 Reduced chances of contamination

28
 Disadvantages
Expensive to set up and startup
Many techniques have not been developed for
automation yet.
There are difficultly automating instances where visual
analysis, recognition or comparison is required such as
color changes.
Systems require the use of programming languages such
as C++ or visual Basic to run more complicated tasks.
Increases job shortage as automation may replace staff
members who do tasks easily replicated by a robot

29
 Application of Robotics
i. Research & development (R&D)
ii. Laboratory robotics - Thermo Fisher Scientific Spinnaker
Microplate Mover
iii. Clean rooms (SO 14644-1)
iv. Packaging operation
v. Vial holding robot
vi. Robotic Prescription Dispensing Systems-
ex- ScriptPro’s (SP)

30
i. Research & development (R&D)
Robots now also play an essential role in the
development of new drugs.
In high throughput screening (H.T.S.) for instance,
millions of compounds are tested to determine which
could become new drugs.
There is a need for the use of robotics to test these
millions of compounds.
The use of robotics can speed this process up
significantly, just as they can any other process where
a robot replaces a person completing any repetitive
task.

31
ii. Laboratory robotics
 Robots in laboratories revolutionize scientific processes with automation, precision,
and efficiency.
 They aid in drug discovery, assembly, and packaging, ensuring safety in hazardous
environments.
 In pharmaceutical R&D, they accelerate trials and innovation. In environmental
monitoring and space exploration, robots collect data and perform tests, expanding
scientific understanding.
 Additionally, they automate DNA sequencing and high-throughput assays, reducing
errors and enhancing experiment efficiency.
Ex- Cartesian, SCARA, Anthropomorphic

32
iii. Clean rooms robots
 Cleanroom robots, built for controlled environments like
pharmaceutical manufacturing, prioritize cleanliness and particle
control.
 They're made from materials that prevent contamination deposition
and are sealed to prevent liquid ingress.
 Certified to meet ISO 14644-1 standards, they're vital in industries
like healthcare and electronics, ensuring safety and quality while
minimizing contamination risk.
 Reliable and efficient, they handle tasks with precision, reducing
human intervention and error.
 Ex - Stäubli TX2-60 Cleanroom Robot.

33
iv. Vial holding robot
 Vial holding robots are crucial in the pharmaceutical industry, handling vials with precision
for tasks like filling, labeling, capping, and packaging.
 They improve efficiency, reduce contamination and human error, and can work continuously

35
v. Robotic Prescription Dispensing Systems
 Robotic Prescription Dispensing Systems improve
efficiency, safety, and precision in the pharmaceutical
industry by automating tasks such as medication
dispensing and inventory management.
 They can process a high volume of prescriptions,
reducing workload and human error.
 Companies like ScriptPro offer systems with high
accuracy and reliability, while robots are also used in
drug discovery and cleanroom environments.

36
iv. Packaging operation
 Packaging processes, like other pharmaceutical operations, benefit from the speed and
repeatability that automation brings.
 Pharmaceutical packaging machines are often custom designed to handle specific
product configurations such as vials.

38
3. Computational fluid dynamics

39
 CFD is science that uses digital computer make quantitative prediction about fluid
flow phenomena.
 CFD based on the conversation law of fluid motion, such as conversation of mass,
momentum, energy.
 CFD can be viable tool to analyse and troubleshoot in various process & equipment
used in pharmaceutical industry.
 The integration of CFD methods leads to shortened product-process development
cycle, optimization of existing processes, reduce energy requirements, efficient
design of new product and processes and reduce to market.
 Unit operation in pharma typically handle Large amount of fluid.

40
As, a result small increment in efficiency may generate large increment in product
cost savings.
CFD is a powerful tool in the pharmaceutical industry, enabling various applications
such as optimizing drug delivery systems, enhancing equipment and process
characterization, and supporting upstream biopharmaceutical manufacturing
processes.

41
 CFD analysis involves three main steps:
I. Pre-processing:
 Identifying the flow region
 Geometrical representation of the flow region
 Defining an appropriate mesh for the region
 Application of fluid dynamics principles.
II. Solution:
 Uses a trial-and-error strategy to compute the
solution
 All steps have been computerized.
.
III. Post-processing:
 Analyzes the results
 The solution provides data of the problem,
represented on the flow field
 Plots flow variables on the 3D region of
interest
 Analyst plots.

42
 Advantage
 Enhanced understanding of fluid dynamics
 Cost and time savings
 Safety and risk management
 Design optimization
 Ability to simulation of real condition - CFD provides the ability to
theoretical simulation of any physical condition.

43
Disadvantages
 Complex setup and high computational requirements
 Modeling limitations
 Potential inaccuracies
 Very expensive.
 Possibility of error from unknown sources

44
Application of CFD:
i. CFD in Mixing Process:
 Static mixers: used for high viscous fluids, with
CFD analyzing their efficiency and mixing capacity
 Stirred mixers: large mixing tanks with various
sizes and impeller types, analyzing flow
characteristics, impeller influence, and shear stress
distribution
 Shear stress distribution is crucial for dissolution,
dispersion, and emulsification properties

45
II. CFD in Separation Process
 Centrifugation techniques for thickening,
solid-liquid separation, and post-treatment,
with CFD studying centrifuge design and
performance.
 Separation devices like cyclones and
scrubbers analyzed for efficiency,
Ex - 90% of 10-μm particles separated in
cyclones.

46
III. CFD in Drying Process:
Analyzes spray dryer performance and congregation changes during drying to
avoid unnecessary costs and risks

47
IV. CFD in Packing Process
Used for liquid formulations like syrups, suspensions, and emulsions to optimize
filing lines and avoid issues like delayed filling, spilling, splashing, and frothing.
V. CFD in Designing of Inhalers
 MDI and DPI are common, with Computational
Fluid Dynamics (CFD) improving efficiency and
reproducibility of drug products.
 CFD technology traces drug particle trajectories
inside the lung.

48
VI. Dissolution apparatus hydrodynamics
 Dissolution testing is crucial in pharma for
optimization, stability, and more.
 CFD simulates and analyzes dissolution apparatus
hydrodynamics.
 The USP paddle apparatus, the most common,
shows small tablet position changes significantly
impact dissolution rates due to varying
hydrodynamics.

49
VII. CFD for energy generation and energy transfer device
 CFD techniques analyze thermal and flow fields in devices, including flame
characteristics.
 Flame stability and burner efficiency are crucial for process heaters, power plants, and
furnaces.
 Flame length, shape, and size affect the process; long flames may cause damage, while
short flames can wear out the burner tip.

50
 Partnerships of AI establishments with pharmaceutical firms.

51
 AI-Aided Computational Tools for Facilitating Drug Discovery.

52
 References:
 Automation and artificial intelligence in the clinicalLaboratory by Christopher Naugler & Deirdre L.
Church https://doi.org/10.1080/10408363.2018.1561640
 The journal of “ Advanced Drug Delivery Reviews “ The significance of artificial intelligence in
drug delivery system design by Parichehr Hassanzadeh ⁎, Fatemeh Atyabi, Rassoul Dinarvand
 The Journal of Young Pharmacists Artificial Intelligence the Futuristic Technology in the Drug
Discovery Process: A Review Annammadevi Govardhini Sayam*, Maharnab Pradhan, Aman Kumar
Choudhury
 International Journal of Molecular Sciences Review Artificial Intelligence and Machine Learning
Technology Driven Modern Drug Discovery and Development by Chayna Sarkar 1, Biswadeep Das
2,* , Vikram Singh Rawat 3 , Julie Birdie Wahlang 1, Arvind Nongpiur 4, Iadarilang Tiewsoh 5,
Nari M. Lyngdoh 6, Debasmita Das 7, Manjunath Bidarolli 2 and Hannah Theresa Sony 2.

53
 Tamanna Sharma, Abhinav Mankoo, Vivek Sood. Artificial intelligence in advanced pharmacy.
International Journal of Science and Research Archive. 2021;2(1):047-054.
doi:10.30574/ijsra.2021.2.1.0301
 Panwar V, Vandrangi SK, Emani S. Artificial intelligence-based computational fluid dynamics
approaches. In: Hybrid Computational Intelligence. Elsevier; 2020:173-190. doi:10.1016/b978-0-12-
818699-2.00009-3.
 Wang B, Wang J. Application of Artificial Intelligence in Computational Fluid Dynamics. Ind Eng
Chem Res. 2021;60(7):2772-2790. doi:10.1021/acs.iecr.0c05045.
1. https://www.pharmatutor.org/articles/pharmaceutical-industrial-applications-robots-current-scenario-
recent-review.
1. Ivana Masic, Jelena Parojcic, and Zorica Djuric, University of Belgrade “Computer- aided
applications in pharmaceutical technology”Published by Woodhead Publishing Limited, 2013,
(page no.233)

54
 G.T.U QUESTINS
1. Give merits and demerits of pharmaceutical automation.
2. Write a note on artificial intelligence.
3. Give general overview of robotics and computational fluid
dynamics
4. Discuss the application of AI in drug delivery.
5. Discuss the application of computational fluid dynamics in drug
delivery.
6. Discuss the role of robotic system in pharmaceutical industry.
7. What are the advantages and disadvantages of automation in
pharmaceutical industry.

Artificial Intelligence (AI), Robotics and Computational fluid dynamics

Related slideshows

Recommended for you

Recommended for you

Recommended for you

Recommended for you

Recommended for you

Recommended for you

Recommended for you

Recommended for you

Recommended for you

Recommended for you

Recommended for you

Recommended for you

Recommended for you

More Related Content

Similar to Artificial Intelligence (AI), Robotics and Computational fluid dynamics

Similar to Artificial Intelligence (AI), Robotics and Computational fluid dynamics (20)

Recently uploaded

Recently uploaded (20)

Artificial Intelligence (AI), Robotics and Computational fluid dynamics