Morgan Thomas (@MorganThomas263) profile picture

Morgan Thomas

@MorganThomas263

Postdoc at @UPFBarcelona in the compsciencelab working computer-aided drug design, cheminformatics and artificial intelligence

 Barcelona
Joined December 2019
  • Tweets59
  • Following159
  • Followers272
1Media
Photo by Morgan Thomas (@MorganThomas263)
Preprint release 😀 of "Speak to a Protein," an AI co-scientist that facilitates data gathering and analysis in an interactive collaborative session. It is quite amazing to use. Preprint: arxiv.org/abs/2510.17826
Image from Gianni De Fabritiis (@gdefabritiis)
1
2
8
428
Modern hit-finding with structure-guided de novo design: Identification of novel #GPCR ligands using reinforcement learning #RNN @MorganThomas263 @baoilleach @AndreasBenderUK chemrxiv.org/engage/rss/chem…
1
4
1
8
1,325
#MolScore: a scoring, evaluation and benchmarking framework for generative models in de novo drug design jcheminf.biomedcentral.com/a… with @MorganThomas263 @baoilleach @AndreasBenderUK in @jcheminf #GenAI #cheminformatics #CADD #DrugDesign
MolScore: a scoring, evaluation and benchmarking framework for generative models in de novo drug...

MolScore: a scoring, evaluation and benchmarking framework for generative models in de novo drug...

Journal of Cheminformatics - Generative models are undergoing rapid research and application to de novo drug design. To facilitate their application and evaluation, we present MolScore. MolScore...

link.springer.com
2
19
1
62
5,643
Our new library for generative de novo design using PyTorchRL. It is also compatible with MolScore for drug design objectives/benchmarking and PromptSMILES for chemically constrained generation.
Gianni De Fabritiis (@gdefabritiis) profile pictureGianni De Fabritiis@gdefabritiis9 May 2024
In #ACEGEN, we take advantage of the #TorchRL library of #PyTorch to do generative chemistry. It implements #REINFORCE, #REINVENT, #A2C, #PPO, #PPOD etc. A solid base for #RL in drug discovery. Code available under MIT. @acellera arxiv.org/abs/2405.04657
ACEGEN: Reinforcement learning of generative chemical agents for...

ACEGEN: Reinforcement learning of generative chemical agents for...

In recent years, reinforcement learning (RL) has emerged as a valuable tool in drug design, offering the potential to propose and optimize molecules with desired properties. However, striking a...

arxiv.org
1
7
929
"PromptSMILES: Prompting for scaffold decoration and fragment linking in chemical language models" doi.org/10.26434/chemrxiv-20… Thread 🧵

PromptSMILES: Prompting for scaffold decoration and fragment linking in chemical language models |...

SMILES-based generative models are amongst the most robust and successful recent methods used to augment drug design. They are typically used for complete de novo generation, however, scaffold...

chemrxiv.org
1
3
9
887
more replies
promptsmiles is installable via pip, or you can check out our github: github.com/compsciencelab/Pr…
GitHub - compsciencelab/PromptSMILES: Scaffold decoration and fragment linking with chemical...

GitHub - compsciencelab/PromptSMILES: Scaffold decoration and fragment linking with chemical...

Scaffold decoration and fragment linking with chemical language models and RL - compsciencelab/PromptSMILES

github.com
1
1
133
More exciting work to come soon ...
100
Postdoctoral positions available on machine learning, generative modelling for chemistry: compscience.org/postdoctoral…
COMPUTATIONAL SCIENCE LAB - Postdoctoral202311

COMPUTATIONAL SCIENCE LAB - Postdoctoral202311

PD202311- Postdoctoral Positions on foundation models at the Computational Science Laboratory, Barcelona

compscience.org
26
1
58
7,532
#Molscore - A Scoring and Evaluation Framework for De Novo Drug Design - @MorganThomas263 @baoilleach @AndreasBenderUK @Cambridge_Uni @soseiheptaresco #AI #drugdesign - chemrxiv.org/engage/chemrxiv…

MolScore: A scoring and evaluation framework for de novo drug design | ChemRxiv

MolScore is an open-source Python framework for scoring and evaluating molecules in the context of goal-directed generative models as used in de novo drug design. MolScore includes many relevant...

chemrxiv.org
7
40
5,604
Morgan Thomas retweeted
Chris Swain (@macinchem) profile picture
Chris Swain@macinchem22 Mar 2023
Still time to submit abstracts for the 6th AI in Chemistry Symposium rscbmcs.org/events/aichem23/. #AIChem23 #compchem The deadline for oral presentation abstract submission is Midnight (BST), Friday 14th April 2023, poster abstract submission is Midnight (BST), Friday 5th May, 2023.
6
6
1,021
How are we doing with integrating structure-based approaches into generative molecular design? sciencedirect.com/science/ar…
1
4
36
4,427
more replies
4) Ultimately, I think the current limiting factor is now fast, accurate binding mode and affinity prediction - either to act as scoring functions in goal-directed learning or to augment limited training datasets for distribution learning.
1
4
310
5) Although not discussed much in this review due to how recent they are, it'll be interesting to see how diffusion-based models fare in this field - particularly with regards to the type of ligand chemistry generated. Or, how they compare to induced fit docking softwares...
4
279
Morgan Thomas retweeted
Chris Swain (@macinchem) profile picture
Chris Swain@macinchem22 Feb 2023
RSC-BMCS/RSC-CICAG 6th AI in Chemistry Conference Churchill College, Cambridge, UK, registration is now open!! rscbmcs.org/events/aichem23/ #AIChem23
Image from Chris Swain (@macinchem)
8
12
1,907
Morgan Thomas retweeted
Chris Swain (@macinchem) profile picture
Chris Swain@macinchem29 Jan 2023
Cambridge Cheminformatics Meeting, 4pm 8 Feb at CCDC. macinchem.org/blog/files/cf2… #cheminformatics #compchem
5
1
6
2,827
Load more