Registration for a live webinar on 'Precision medicine treatment for anticancer drug resistance' is now open.
See webinar detailsWe noted you are experiencing viewing problems
-
Check with your IT department that JWPlatform, JWPlayer and Amazon AWS & CloudFront are not being blocked by your network. The relevant domains are *.jwplatform.com, *.jwpsrv.com, *.jwpcdn.com, jwpltx.com, jwpsrv.a.ssl.fastly.net, *.amazonaws.com and *.cloudfront.net. The relevant ports are 80 and 443.
-
Check the following talk links to see which ones work correctly:
Auto Mode
HTTP Progressive Download Send us your results from the above test links at access@hstalks.com and we will contact you with further advice on troubleshooting your viewing problems. -
No luck yet? More tips for troubleshooting viewing issues
-
Contact HST Support access@hstalks.com
-
Please review our troubleshooting guide for tips and advice on resolving your viewing problems.
-
For additional help, please don't hesitate to contact HST support access@hstalks.com
We hope you have enjoyed this limited-length demo
This is a limited length demo talk; you may
login or
review methods of
obtaining more access.
Printable Handouts
Navigable Slide Index
- Introduction
- Can you imagine a chemist?
- The growing impact of molecular modeling and informatics
- Zoo of AI methods
- Classes of machine-learning techniques and some chemical questions
- The long & winding road to drug discovery
- Choosing a disease
- Identifying a drug target
- The mapping of the human genome helps
- NIH biomedical data translator
- Knowledge graph mining
- AlphaFold 2: Protein structure prediction
- Choosing the bioassay
- Finding the lead
- Computational drug discovery (virtual screening) (1)
- Computer-assisted drug design
- NIH IDG-DREAM drug-kinase binding prediction challenge
- Computational drug discovery (virtual screening) (2)
- Why do we need generative models?
- Predictive vs. generative models
- Style transfer
- Generative adversarial networks (GANs)
- Molecular generators
- Generative models in chemistry
- De novo molecular design with deep reinforcement learning
- Reinforcement learning for chemical design
- Evolution of activity with reinforcement
- Melting temperature optimization
- Structure-bases drug discovery: Protein-ligand interactions
- Quantum mechanics 101
- Where does ML/AI fit?
- Accurate IR spectra simulation with time-domain ML
- Fast but accurate property predictions with ML
- Tyk2 is a protein-ligand system
- MM free energy cycle extension and ML/MM potential
- Accuracy of absolute binding free energy calculations
- Torsion profiles and couplings differ between MM and ANI & QM
- Thank you for listening
Topics Covered
- Machine-learning techniques
- Artificial intelligence methods
- Drug discovery
- Molecular modeling
- Choosing a disease
- Identifying a drug target
- Choosing the bioassay
- AlphaFold 2: Protein structure prediction
- Computer-assisted drug design
- NIH IDG-DREAM
- Predictive vs. generative models
- Molecular design with deep reinforcement learning
Links
Series:
Categories:
External Links
- Slide 3 - Next RSC president predicts that in 15 years no chemist will do bench experiments without computer-modeling them first
- Slide 10 - Toward A Universal Biomedical Data Translator
- Slide 17 - NIH IDG-DREAM drug-kinase binding prediction challenge
- Slide 24 - Generative models in chemistry review
Talk Citation
Isayev, O. (2024, May 19). Accelerating drug discovery with machine learning and AI [Video file]. In The Biomedical & Life Sciences Collection, Henry Stewart Talks. Retrieved December 21, 2024, from https://doi.org/10.69645/DGYT9242.Export Citation (RIS)
Publication History
Financial Disclosures
- Dr. Olexandr Isayev has not informed HSTalks of any commercial/financial relationship that it is appropriate to disclose.
Other Talks in the Series: Periodic Reports: Advances in Clinical Interventions and Research Platforms
Transcript
Please wait while the transcript is being prepared...
0:00
Hello, everyone. My name is Olexandr Isayev.
I'm an assistant professor at the Department of Chemistry at Carnegie Mellon University.
Today's topic of my talk is accelerating drug discovery with machine learning and AI.
0:16
So, when you ask a layperson,
can you imagine a chemist?
What most people will typically mention as scientists doing some experiments,
explosions, mixing colorful liquids,
and making fumes out there.
However, modern labs are actually quite advanced.
You see a lot of digital equipment and things like that,
but these traditional kinds of chemistry have also been advanced
and supported via an array of computational and theoretical methods.
In particular, in my lab, we don't have any lab equipment.
Our offices who looks like a normal office
and therefore, in fact, the science what we do
runs on the world's largest supercomputers
because we do a simulation of chemical processes and materials.
The key advantage for all of this
is this little chip called GPU: graphical processing unit.
Those chips are widely used to play games,
but also those chips are what's behind
the current machine learning and AI revolution that is happening in the industry,
and many sciences, and it's transforming the way many sciences are done, currently.
1:38
So, here's a little example from the news.
When the president of the Royal Society of Chemistry took his job,
he predicted that in 15-years-time,
no chemists will be doing an experiment at the bench without modeling first.
Therefore, appreciation of this computational modeling aspect of chemistry is growing.
Now, there is more in news from, again,
The Royal Society of Chemistry or American Chemical Society Chemistry Engineering News.
They show you the importance of these technologies,
for example, "wanted synthetic chemists (humans need not apply)",
or "the rise of the smartish machines."
But I'd like to motivate this talk with
this actually thought-provoking quote by Derek Lowe.
Derek Lowe is a pharmaceutical industry veteran who
writes a blog in the Pipeline for the Science Translational Medicine.
What Derek said is interesting.
"It is not that machines are going to replace chemists.
It is that the chemists who use machines will replace those that do not."
I think this is a very interesting quote and it certainly motivates our work,
and I think that would be a good motivation for this talk.