Presentacion individual ingles

AI in drug discovery

Productos Farmacéuticos, Biotecnológicos y afines.

Candela García Vioque

START!

INDEX

Areas of aplication

What is AI?

Introduction

Conclusion

Companies

Pros and cons

References

Introduction

The traditional drug discovery process is time-consuming (taking between 10 and 15 years), has a high failure rate, and is costly. However, AI offers tools to accelerate and optimize this process, enabling the identification of promising compounds, designing molecules, and predicting how they will interact with biological targets. This makes AI one of the most interesting advances for the pharmaceutical industry.

WHAT IS AI?

Artificial intelligence better known as AI, is a set of technologies that enable computers to perform a variety of advanced functions, including the ability to see, understand and translate spoken and written language, analyze data, make recommendations, and more. AI is the backbone of innovation in modern computing, unlocking value for individuals and buisnesses.

How AI works?

Main areas of aplication

3. Optimization of clinical trials

2. Toxicity and side effect prediction

1. dESIGN OF NEW DRUGS.

In this case, AI uses generative algorithms to design novel molecules that could become new medications. This uses tools such as machine learning models like Generative Adversarial Networks and molecular design alagorithms.

Here, AI can predict potential adverse effects of compounds before they reach clinical trials, using computational models.

In this case, AI identifies patient populations, predicts outomes, and optimizes study designs to reduce costs and time.

+ info

+ info

+ info

Main areas of aplication

4. Identification of therapeutic Targets

5. Drug reprosing

Here, AI analyze existing data to find new uses for already approved drugs.

In this case, AI analyzes large genomic and protein datasets to identify proteins or genes associated with a specific disease.

+ info

+ info

Pros and cons

• Adaptability
• Cost
• Precision
• Speed

PROS

• Ethical and regulatory concerns
• Lack of transparency
• Over-reliance on data

CONS

COMPANIES THAT USE ai

CONCLUSION

As I have shown, AI is a tool that is here to stay, and we will increasingly see it in our daily lives. In the pharmatheutical industry, it is already playing a significant role, simplifying the process of discovering new drugs, among other aplications I have explained. When used correctly, AI will be an extremly valuable tool.

REFERENCES

• Google Cloud. (n.d.). What is artificial intelligence? Google Cloud. Retrieved November 27, 2024, from https://cloud.google.com/learn/what-is-artificial-intelligence?hl=en

• Shah-Neville, W. (2024, January 5). Five AI drug discovery companies you should know about. Labiotech.eu. https://www.labiotech.eu/best-biotech/ai-drug-discovery-companies/

• Wang, F., & Preiss, J. (2021). Artificial intelligence in drug discovery: Applications, opportunities, and challenges. National Center for Biotechnology Information. Retrieved November 27, 2024, from https://pmc.ncbi.nlm.nih.gov/articles/PMC10302890/#:~:text=By%20using%20AI%20algorithms%20to,the%20needs%20of%20individual%20patients.

• DataCamp. (2024, November 27). AI in pharmaceuticals: How AI is transforming the pharmaceutical industry. DataCamp. https://www.datacamp.com/blog/ai-in-pharmaceuticals
• Vial. (n.d.). AI-designed drugs vs. traditional drug discovery: Pros and cons. Vial. Retrieved November 27, 2024, from https://vial.com/blog/articles/ai-designed-drugs-vs-traditional-drug-discovery-pros-and-cons/

Thanks for listening!

For example

In BenevolentAI is used to identify baricitinib (drug for the rheumatoid arthritis) as a potential treatment for COVID-19.

For example

In 2020 artificial intelligence designed a compound for fibrosis treatment that entered clinical trials in just 12 months.

For example

In tbe company Insilico Medicine AI is use to identify new therapeutic targets for pulmonary fibrosis.

For example

Atomwise uses AI to analyze millions of compounds and filter out those with high toxicity potential.

For example

Companies like Deep 6 AI use machine learning to quickly identify eligible patientes for clinical trials.