@@LAinLA86 As a ML scientist working in the same area of research I found Prof Kellis' questions really insightful. Many of the questions he asked were what I wanted to ask at those moments.
Great lecture! Thank you very much for uploading this. I just got two questions: 1. We know that drugs are 3D when they bind to their targes. But the grape in GNN is a 2D representation of drug structures. For some drugs which are only active in one enantiomer form not the other one, the 2D graph will be the same for the two enantiomers. How can GNN capture this stereochemical difference? 2. Remdesivir used in the ComboNet on slide 36 is a prodrug, its active form is a metabolite which is a triphosphate. I suppose most of the drugs used in the training are not prodrug, so I'm curious about whether remdesivir or it's active form is used in the work? Did the author consider this?
Adding 3D hasn't seen much progress so far. One reason is 2D structure is informative enough, the other is 3D structures is deeply corresponding to its 3D conformer, which is very hard to determine or predict.
Great lecture. For the compound on the right at 47.36min with better MIC, did you observe the different moieties by cleaving the azo bond? It is my guess that the aminosulphonamide or the hydrazine analog may be the actual active drug and not the whole compound shown.
2.6B only when considering the failures, so for a startup looking to raise money, its not as important. Rather the average cost to get one drug into FIH trials is more relevant, and then how much to get the $ to run the phase 1 trial. The 2.6B is more a big pharma number.
Hi Wengong, I’m thinking about starting up a Biotech company for a widespread unmet medical need and am currently seeking capital. If and when that happens, I will be seeking scientists who can assist with advancing a therapeutic solution for this critical global disease.. I think GNN would be a worthwhile starting point in my endeavor, might you be interested in assisting? Kind regards, Jennifer
![The moment we stopped understanding AI [AlexNet]](http://i.ytimg.com/vi/UZDiGooFs54/mqdefault.jpg)
It's great that lectures like these are publicly available.
The guy interrupts waay too much, he's so annoying..my goodness
@@LAinLA86 As a ML scientist working in the same area of research I found Prof Kellis' questions really insightful. Many of the questions he asked were what I wanted to ask at those moments.
This is an excellent resource for getting to know GNNs in drug de novo drug design, thank you!
thank you so much for sharing this valuable lecture about GNNs in drug discovery. The idea of junction tree VAE is awesome and making sense
Brilliant! Thanks for making this available
Good Information - Thanks for the presentation.
Thank you for sharing this!
keep it up
Amazing lecture !
great content
Great lecture! Thank you very much for uploading this. I just got two questions:
1. We know that drugs are 3D when they bind to their targes. But the grape in GNN is a 2D representation of drug structures. For some drugs which are only active in one enantiomer form not the other one, the 2D graph will be the same for the two enantiomers. How can GNN capture this stereochemical difference?
2. Remdesivir used in the ComboNet on slide 36 is a prodrug, its active form is a metabolite which is a triphosphate. I suppose most of the drugs used in the training are not prodrug, so I'm curious about whether remdesivir or it's active form is used in the work? Did the author consider this?
Add geometric data such as bond angle etc.. to the bond embedding vector is one approach perhaps
@@jessedeng3300 Thanks for the reply. I learned afterwards that chirality information of atoms (nodes) are used as descriptor.
Adding 3D hasn't seen much progress so far. One reason is 2D structure is informative enough, the other is 3D structures is deeply corresponding to its 3D conformer, which is very hard to determine or predict.
Thank you. The lecture is great.
Awesome lecture!
very helpful! great lecture!
Thanks. Super quality.
Great lecture. For the compound on the right at 47.36min with better MIC, did you observe the different moieties by cleaving the azo bond? It is my guess that the aminosulphonamide or the hydrazine analog may be the actual active drug and not the whole compound shown.
life saving lecture omg
An amazing lecture indeed. I just wanted to clarify as to how the viral/host targets are represented or vector encoded in the combonet model.
Thats unfortunate, you have to work with those types in the top left corner. Yeesh.
Who are you referring to?
How this is different from QSAR using graph theory descriptors with 1D,2D, and 3D info
2.6B only when considering the failures, so for a startup looking to raise money, its not as important. Rather the average cost to get one drug into FIH trials is more relevant, and then how much to get the $ to run the phase 1 trial. The 2.6B is more a big pharma number.
Ambitious I like...🤓
Too bad had to skip over the COVID part due to PTSD 🤣
is ComboNet publicly accessible?
"it comes from a novel called Space Odissey..."
Zoomers will zoom.
Hi Wengong, I’m thinking about starting up a Biotech company for a widespread unmet medical need and am currently seeking capital. If and when that happens, I will be seeking scientists who can assist with advancing a therapeutic solution for this critical global disease.. I think GNN would be a worthwhile starting point in my endeavor, might you be interested in assisting? Kind regards, Jennifer
I'm sorry Dave, I'm afraid I can't do that.
1000th like
😉
why look for a cv19 drug? There are so many more deadly conditions to treat that need drug discovery!
Good morning ❤❤🎉😊😊😊