Series 4 optimization through Collective Intelligence

[gcincilla]

Series 4 optimization through Collective Intelligence

Human Collective Intelligence (HCI) is the knowledge, skills & intuition of all the members of a team empowered by their real-time collaboration. Here we propose to use HCI to optimize OSM Series 4 compounds through the predictive model that won the competition and a Molomics web-based technology working with the most popular web browsers (e.g. Firefox, Chrome).

The technology allows to collaboratively explore & exploit the chemical space by designing & evaluating molecules. For any designed molecule, the system will currently provide prediction of Pfal activity, solubility (logS) and Caco-2 cells permeability. Other molecular properties (e.g. synthetic accessibility) can be evaluated by team members. The technology is rather intuitive so, if you prefer, you can stop reading and directly access it at:

https://osm.molomics.com/w/signup/signup.html

Otherwise, please get a better understanding about the technology following the instructions below:

Step 1: learn the technology basics through the Sandbox

The first time you access the technology you'll be able to access only 1 toy project called “Sandbox”. There you will learn the technology basics in about 10 minutes. This includes how to sketch an organic molecule, how to browse all the team molecules and how to access molecule information.

Step 2: browse the team molecules

Upon completion of the Sandbox, you'll be able to access the real project called “Plasmodium falciparum OSM-S4”. Once inside, you can browse all the molecules generated by the team for this project and you can filter them by tags, molecular properties and team members. Through the molecule information you can see its structural alerts, human evaluations and also how the molecule was generated.

Step 3: design new molecules

After you get inspired by for example exploring already tested molecules, you can design new molecules by modifying any existing compound or by starting drawing from scratch. The objective is to design new Series 4 molecules with good predicted properties. Please consider that any molecule prediction has a prediction confidence (based on the model applicability domain) associated to it (i.e. traffic light colors on the right side of prediction represent high, medium and low confidence). An ideal molecule has favorable predictions and high prediction confidences. Molecules with low confidence predictions should be avoided.

Step 4: evaluate molecules

Molecules can be evaluated by the team members by accessing the evaluation tab in the molecule information.

Questions

Any question about the technology can be asked here. Questions about molecules are addressed directly in the technology.

[edwintse]

We've been having a play around with the web app, trying out modifications on the pyrrole compound M4625 and have come across this interesting furan compound below which seems to score slightly better than the original suggestion where the ring is a pyrrole.

[MedChemProf]

Anyone try this site and run into problems? I completed the Sandbox items, but I cannot get access to any of the OSM molecules. I have emailed Molomics. Not sure if a browser issue or something I am doing.

[edwintse]

@MedChemProf Yeah, you just have to wait a few minutes. You should then get an email to start exploring the OSM project molecules

[MedChemProf]

Thank you @edwintse

[gcincilla]

@edwintse, thank you for playing a bit and exploring the chemical space around molecule M4625. The score of M4922 it's a bit higher than M4625 due to its better predicted Caco2 permeability. As we don't have a 3D structure of the putative target and we cannot simulate how these molecules interact with it, in terms of our predictive model the 2 molecules are equivalent. Do you find M4922 easier in terms of synthetic accessibility? The only thing that concern me a bit about M4922 is that it has a higher flexibility degree respect M4625. Did you test activity of such flexible molecules?

P.S.: I will report such discussion on the technology inside M4922 card so that we can keep track of it also there.

[edwintse]

@gcincilla We have made and tested compounds with a benzylic primary alcohol in the past and such flexibility is generally tolerated well (examples in the second figure here). In terms of accessibility we are thinking of pursuing M4928 (with a 2-furan) as it's easier and cheaper to get a hold of the required starting material.