Generating 3D compound structure using machine learning: testing Auto3D

 

Generating 3D structure of the compounds from prior knowledge is a challenge. Machine learning models can be used to accurately predict 3D conformers of small molecules and larger compounds (e.g. AlphaFold). GeoMol, TorsionNet and alike methods are basically taking well-known knowledge-based methods for 3D generation on the next level.  But none of the published models can be reproduced without any pretraining and/or easy to install, except for Auto3D. Auto3D was developed in the group of Professor Olexandr Isayev and published in 2022 including code.

Auto3D automatically generates conformational space further optimized by atomistic neural network potentials (NNPs) such as ANI or AIMNet (also by the Isayev Lab). Tautomers and isomer enumeration are in my opinion is not necessary as part of the package, but they are nice addition.  I tested for 10 random drug-like compounds from ChEMBL. For whatever reason running algorithm on CPU gave me abysmal running time of 450 seconds per compound on average, compared to 10 seconds on GPU. Not sure why… Anyway, Google Colaboratory notebook can be found here. All generated 3D conformers look perfect and zero clashes between the atoms.

Algorithms like this will have a huge impact on bringing 3D into the compound generation and general CADD approaches. There is still need to speed up the process and add water phase for conformer generation (gas phase only at the moment), but water phase is already in progress and speeding it up will be achieved very soon I am pretty sure.

Comments

Post a Comment

Popular posts from this blog

Paper comment: "MELLODDY: cross pharma federated learning at unprecedented scale unlocks benefits in QSAR without compromising proprietary information"

Image
 Intro I finally got my hand on carefully reading papers by the MELLODDY consortium led by my ex-supervisor (and fantastic visionary) - Hugo Ceulemans. I participated in some very-very early discussions and saw the painful process of the project's initiation. What Hugo did is colossal, and he helped to build a PRECEDENT! Honestly, the amount of PR the project got is too little! (Compared to PR of some other ML-for-chemistry companies). The project united ten big pharma companies to build a federated multi-task model for activity assays (activity on proteins, PK/PD, toxicity):  40000+ assays on 21+ million compounds with 2.6+ billion end-points . MELLODDY used federated learning to improve individual models of the consortium partners by confidential sharing of the "model"  without sharing private data itself. An exciting approach that has a lot of tiny, small, and big challenges related to fairness, data security, MLOps, ML engineering, ML algorithms, and legal questions. ...
Read more

How many actual bits in unfolded Morgan fingerprint?

Image
The easiest  possible descriptors used in ML for chemistry are fragments, and they are usually used in a folded form. The default folded size is 1024, with some recommendations to use higher dimensionality (>=4096) for computational chemogenomics tasks.  Folding of descriptors is done for several reasons: to save space, get a uniform length, with a price of  bit collision , and sometimes insensitivity to small changes.  Let's check how many actual bits are in drugs as an example of FDA-approved chemical space vs random selection of 300K compounds from Enamine REAL virtual space of 3B compounds commonly used in virtual screening. Number of unique bits So, as we can see, on average, for radius 3, there are 16 bits per compound on average for drug space that's going down 4 and 2 bits for increased chemical space of 100K and 300K diverse compounds from the Enamine REAL library.  Enamine virtual space is, of course, repetitive, but it still indicates that with a l...
Read more

ChatGPT: Practical AI revolution is here... (1)

The text below is a private opinion not linked in any form to my current employee.   So, all hands on deck… the AI revolution everyone was talking about for a long time arrived. I played a bit with ChatGPT for some of the general R&D and chemoinformatics tasks… and saying that impressed is nothing, I am shocked by the quality of the generated text and code, and the future possibilities of those products. Some people claim that ChatGPT will not replace search engines. With a bit of time, it will likely be a merge between personal assistance and worldwide web search engines. ChatGPT and its successors will revolutionize how software is built, increasing productivity while reducing costs. That, in turn, gives programmers more flexibility and time for more complex tasks. Furthermore, these tools can help bridge gaps between different programming languages, making it easier for coders to operate in heterogeneous environments. ChatGPT-like models will overtake enterprise text mining ...
Read more