Few-Shot Learning for Low-Data Drug Discovery
Sign Up to like & getrecommendations! Published in 2022 at "Journal of chemical information and modeling"
DOI: 10.1021/acs.jcim.2c00779
Abstract: The discovery of new hits through ligand-based virtual screening in drug discovery is essentially a low-data problem, as data acquisition is both difficult and expensive. The requirement for large amounts of training data hinders the… read more here.
Keywords: drug discovery; low data; shot; shot learning ... See more keywords
Correlated RNN Framework to Quickly Generate Molecules with Desired Properties for Energetic Materials in the Low Data Regime
Sign Up to like & getrecommendations! Published in 2022 at "Journal of chemical information and modeling"
DOI: 10.1021/acs.jcim.2c00997
Abstract: Motivated by the challenging of deep learning on the low data regime and the urgent demand for intelligent design on highly energetic materials, we explore a correlated deep learning framework, which consists of three recurrent… read more here.
Keywords: detonation velocity; low data; framework; data regime ... See more keywords
De Novo Design of Nurr1 Agonists via Fragment-Augmented Generative Deep Learning in Low-Data Regime.
Sign Up to like & getrecommendations! Published in 2023 at "Journal of medicinal chemistry"
DOI: 10.1021/acs.jmedchem.3c00485
Abstract: Generative neural networks trained on SMILES can design innovative bioactive molecules de novo. These so-called chemical language models (CLMs) have typically been trained on tens of template molecules for fine-tuning. However, it is challenging to… read more here.
Keywords: nurr1 agonists; low data; novo design; fragment augmented ... See more keywords
Generative AI enables medical image segmentation in ultra low-data regimes
Sign Up to like & getrecommendations! Published in 2024 at "Nature Communications"
DOI: 10.1038/s41467-025-61754-6
Abstract: Semantic segmentation of medical images is pivotal in applications like disease diagnosis and treatment planning. While deep learning automates this task effectively, it struggles in ultra low-data regimes for the scarcity of annotated segmentation masks.… read more here.
Keywords: deep learning; segmentation; image; ultra low ... See more keywords
Molecular property prediction in the ultra‐low data regime
Sign Up to like & getrecommendations! Published in 2025 at "Communications Chemistry"
DOI: 10.1038/s42004-025-01592-1
Abstract: Data scarcity remains a major obstacle to effective machine learning in molecular property prediction and design, affecting diverse domains such as pharmaceuticals, solvents, polymers, and energy carriers. Although multi-task learning (MTL) can leverage correlations among… read more here.
Keywords: property; property prediction; prediction ultra; low data ... See more keywords
Cascaded Self-Supervision to Advance Cardiac MRI Segmentation in Low-Data Regimes
Sign Up to like & getrecommendations! Published in 2025 at "Bioengineering"
DOI: 10.3390/bioengineering12080872
Abstract: Deep learning has shown remarkable success in medical image analysis over the last decade; however, many contributions focused on supervised methods which learn exclusively from labeled training samples. Acquiring expert-level annotations in large quantities is… read more here.
Keywords: mri segmentation; segmentation; cardiac mri; cascaded self ... See more keywords