Coati: Multimodal contrastive pretraining for representing and traversing chemical space
B Kaufman, EC Williams, C Underkoffler… - Journal of Chemical …, 2024 - ACS Publications
Creating a successful small molecule drug is a challenging multiparameter optimization
problem in an effectively infinite space of possible molecules. Generative models have …
problem in an effectively infinite space of possible molecules. Generative models have …
RGFN: Synthesizable Molecular Generation Using GFlowNets
M Koziarski, A Rekesh, D Shevchuk… - arXiv preprint arXiv …, 2024 - arxiv.org
Generative models hold great promise for small molecule discovery, significantly increasing
the size of search space compared to traditional in silico screening libraries. However, most …
the size of search space compared to traditional in silico screening libraries. However, most …
NEBULA: Neural Empirical Bayes Under Latent Representations for Efficient and Controllable Design of Molecular Libraries
We present NEBULA, the first latent 3D generative model for scalable generation of large
molecular libraries around a seed compound of interest. Such libraries are crucial for …
molecular libraries around a seed compound of interest. Such libraries are crucial for …
Structure-based drug design by denoising voxel grids
We present VoxBind, a new score-based generative model for 3D molecules conditioned on
protein structures. Our approach represents molecules as 3D atomic density grids and …
protein structures. Our approach represents molecules as 3D atomic density grids and …
3D Vessel Graph Generation Using Denoising Diffusion
C Prabhakar, S Shit, F Musio, K Yang… - arXiv preprint arXiv …, 2024 - arxiv.org
Blood vessel networks, represented as 3D graphs, help predict disease biomarkers,
simulate blood flow, and aid in synthetic image generation, relevant in both clinical and pre …
simulate blood flow, and aid in synthetic image generation, relevant in both clinical and pre …
Field-based Molecule Generation
A Dumitrescu, D Korpela, M Heinonen, Y Verma… - arXiv preprint arXiv …, 2024 - arxiv.org
This work introduces FMG, a field-based model for drug-like molecule generation. We show
how the flexibility of this method provides crucial advantages over the prevalent, point-cloud …
how the flexibility of this method provides crucial advantages over the prevalent, point-cloud …
Molreactgen: Generating molecules and reaction templates with a transformer decoder model/author mag. stephan holzgruber
S Holzgruber - 2024 - epub.jku.at
Artificial intelligence models have become indispensable in the fields of chemical research
and life sciences. Generative models play a pivotal role in the innovation and development …
and life sciences. Generative models play a pivotal role in the innovation and development …
ECloudGen: Access to Broader Chemical Space for Structure-based Molecule Generation
AI-aided drug design has facilitated structure-based molecule generation strategies.
However, despite significant success, the restriction of the scarcity of protein-ligand data …
However, despite significant success, the restriction of the scarcity of protein-ligand data …