Artificial intelligence in Pharmaceutical Industry

GUIDED BY :
D.MADHURI MADAM
M.PHARMACY ( PhD)
PHARMACEUTICS
SUBMITTED BY :
P.MOUNIKA
Y18MPH325
PHARMACEUTICS
ARTIFICIAL INTELLIGENCE IN
PHARMACEUTICAL INDUSTRY
ACHARYA NAGARJUNA UNIVERSITY COLLEGE OF
PHARMACEUTICAL SCIENCES

CONTENTS:
Introduction of AI
Types of AI
AI with Pharma

 Artificial Intelligence is the simulation of human
intelligence process by Machines, especially computer
systems.
 The process include Learning, Reasoning and self
correction.
 Particular Applications of AI include Expert Systems,
Speech recognition and Machine vision.
 AI is accomplished by studying human brain thinks, and
how human brain learn, decide, and work while trying to
save a problem, and then using the outcomes of this study
as a basis of developing intelligent software and systems.
 It stores a large amount of information and process it at a
very high speed.

AI can be viewed from variety of
perspectives:
 From the perspective of Intelligence AI is making
machines intelligent- acting as we would expect
people to act.
 From a business perspective AI is a set of very
powerful tools, and methodologies for using those
tools to solve business problems.
 From a programming perspective, AI includes the
study of symbolic programming, problem solving
and search.

Brief history of AI
 1941- First electronic computer
 1956- Term AI introduced
 1960- Checkers- Playing program that was able to
play with opponents
 1980- Quality Control System
 2000- First sophisticated walking robot

Goals of AI:
 While exploring the power of the computer systems, the
curiosity of human, lead him to wonder, “ Can a machine
think and behave like humans do??
 Thus the development of AI started with the intention of
creating similar intelligence in machines that we find and
regard high in humans.
 The goals of AI are
 To create expert systems
 To implement human intelligence in systems

Types of AI:
AI
Type 1
Weak AI
Strong AI
Type 2
Reactive
machines
Limited
Memory
Theory of
Mind
Self
awareness

There are many ways where AI can be Achieved:
ArtificialIntelligence
Machine Learning
Natural language
Processing
Expert systems
Vision
Speech
Planning
Robotics

AI inspired by nature - Biological neuron:

Programming without AI Programming with AI
A computer program without AI can
answer the specific questions it is meant
to solve
A computer program with AI can answer
the generic questions it is meant to solve.
Modifications in the program leads to
change in structure
AI programs can absorb new modifications
by putting highly independent pisces of
information together. We can modify the
information of a program without affecting
it's structure.
Modification is not quick and easy. It may
lead to affecting the program adversely.
Quick and easy program modification.

AI WITH PHARMA
 The current Pharma environment is expensive and lengthy
drug discovery cycles coupled with pricing pressures by
both payers and consumers.
 The average cost to research and develop each drug is
estimated to be $2.6 billion.
 This number incorporates the cost of failure‘s – of the
thousands and sometimes million of compounds.
 The overall probability of the clinical success is estimated to
be less than 12%.
 Pharmaceutical R&D suffers from declining success rates
and a stagnant pipeline.

 Big data and the analytics that go with it could be a key
element for the cure.
 Applying big data strategies will eventually lead to
optimizing innovation, improving the efficiency of research
and clinical trials, and building new tools for physicians,
consumers and regulators to meet the promise of more
individualizes approaches.
 As pharmaceutical industry is plagued with a lot of operating
expenses, regulatory requirements, stakeholder expectations.
All these are making drug companies to search for
efficiencies in their processes in an efforts to achieve
corporate financial goals more than ever before.

 Most pharma players understand the benefit of adopting new
technologies but there remains a persistent and troubling gap
between strategy and the organizations ability to adopt and
develop a data analytics working solution.
 It is not simply enough to analyze drug discovery data but to
remain competitive, pharma must learn from the analytics.
 This is accomplished a new disruptive technology, here
comes the
ARTIFICIAL INTELLIGENCE

The adoption of AI includes:
 It allows for learning from real time data.
 Identify the right candidates for clinical trials.
 Processing real time patient feedback
 Integrating data exchanges with partners
 Reducing costs
 Increasing productivity
 It perform analysis faster and more accurately
 It is capable of seeing patterns that even trained professionals
might miss.

Let us consider three specific areas within the pharmaceutical
industry that will greatly benefit from AI:
RESEARCH & DEVELOPMENT
Precision Medicine
Evidence based outcome
Clinical intelligence

 Accelerating drug discovery with artificial intelligence
 Clinical trail research with artificial intelligence
 Drug Repurposing with artificial intelligence

A connected approach to Pharma:

Risks of AI:
 High cost
 No replicating Humans
 Lesser jobs
 Lack of personal connections
 Addiction
 Efficient decision making

AI in healthcare:
 Detection
 Diagnosis
 Prediction
 Drug discovery
 Personalized medicine
 Medical imaging
 Genomics
 Cancer research
 Brain tumors
 Dermatology
 Mental health
 Speech patterns
 Diabetes
 Radiology

AI in Pharmaceutical Industry:
 Fuzzy logic - Especially useful in describing target proteins
for optimization, Process control.
 Genetic logarithms - they provide a search technique which
is particularly suited to Optimization.
 Drug repositioning
 To predict drug resistance
 Medication adherence
 Alternative indication identification
 Competitive landscape
 Correlation detection

 Failure analysis
 Clinical trail research
 Epidemic outbreak prediction
 Predicting treatment results
 Personalizing the treatment
 Insilco medicine

To predict study risks and their
drivers to enable preventive
maintenance and remediation of the
drugs .
To generate predictive models
to design novel small
molecular leads.
To improve drug discovery
process.

Current challenges:
 Executives in our survey identified several factors that can
stall or derail AI initiatives, ranging from integration issues
to scarcity of talent.
 Percentage who cite the following as obstacles.

CONCLUSION:
As can be seen, the recent developments in artificial intelligence
have resulted in several technologies that have an application in
pharmaceutical product development. In an era of escalating
competition, the ‘winners’ will be those that can seize and exploit
this technology as a strategic weapon. The challenge is to translate
opportunity into action because where applications have proved
successful there is an opportunity of increasing productivity as
well as improving consistency and quality.

REFERENCES:
 Sean Ekins, The Next Era: Deep Learning in Pharmaceutical
Research; Pharm Res (2016) 33:2594–2603.
 Svetlanaibric,Zoricadjuric,Jelenaparojcic,JelenaPetrovic;Chemic
al Industry & Chemical Engineering Quarterly 15 (4) 227−236
(2009).
 Duch, Karthikeyan Swaminathan and Jaroslaw Meller; Artificial
Intelligence Approaches for Rational Drug Design and
Discovery:Current Pharmaceutical Design, 2007, 13, 1497-1508.
 https://emerj.com/ai-sector-overviews/artificial-intelligence-for-
pharmacies-an-overview-of-innovations web based.
 TEDX talks.

Artificial intelligence in Pharmaceutical Industry

More Related Content

What's hot (20)

Similar to Artificial intelligence in Pharmaceutical Industry (20)

Recently uploaded (20)

Artificial intelligence in Pharmaceutical Industry