Zobrazeno 1 - 10
of 5 911
pro vyhledávání: '"Maser, A."'
Autor:
Andaloussi, Meryem Abbad, Maser, Raphael, Hertel, Frank, Lamoline, François, Husch, Andreas Dominik
Publicly available data is essential for the progress of medical image analysis, in particular for crafting machine learning models. Glioma is the most common group of primary brain tumors, and magnetic resonance imaging (MRI) is a widely used modali
Externí odkaz:
http://arxiv.org/abs/2409.00109
Autor:
Nowara, Ewa M., Pinheiro, Pedro O., Mahajan, Sai Pooja, Mahmood, Omar, Watkins, Andrew Martin, Saremi, Saeed, Maser, Michael
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 scientific discovery, but it remains challenging to generate large numbers
Externí odkaz:
http://arxiv.org/abs/2407.03428
Autor:
Jonas Mueller, Doret R. van Muilekom, Jannick Ehlers, Marvin Suhr, Stéphanie C. Hornburg, Corinna Bang, Marie Wilkes, Thekla Schultheiß, Edmund Maser, Alexander Rebl, Tom Goldammer, Henrike Seibel, Carsten Schulz
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-19 (2024)
Abstract Microalgae are emerging as functional feed ingredients in aquaculture due to their immune-stimulating and stress-modulating properties. We investigated the potential of the microalgae Chlorella vulgaris as a feed supplement to improve the he
Externí odkaz:
https://doaj.org/article/31e8dd936ecc44f7b8743b9f3aaeebe1
Structure-based molecular ML (SBML) models can be highly sensitive to input geometries and give predictions with large variance. We present an approach to mitigate the challenge of selecting conformations for such models by generating conformers that
Externí odkaz:
http://arxiv.org/abs/2306.11681
Autor:
Pinheiro, Pedro O., Rackers, Joshua, Kleinhenz, Joseph, Maser, Michael, Mahmood, Omar, Watkins, Andrew Martin, Ra, Stephen, Sresht, Vishnu, Saremi, Saeed
We propose a new score-based approach to generate 3D molecules represented as atomic densities on regular grids. First, we train a denoising neural network that learns to map from a smooth distribution of noisy molecules to the distribution of real m
Externí odkaz:
http://arxiv.org/abs/2306.07473
Many scientific and industrial applications require the joint optimization of multiple, potentially competing objectives. Multi-objective Bayesian optimization (MOBO) is a sample-efficient framework for identifying Pareto-optimal solutions. At the he
Externí odkaz:
http://arxiv.org/abs/2306.00344
Autor:
Christian Rolf, Susanne Rohs, Herman G.J. Smit, Martina Krämer, Zoltán Bozóki, Stefan Hofmann, Harald Franke, Rolf Maser, Peter Hoor, Andreas Petzold
Publikováno v:
Meteorologische Zeitschrift, Vol 33, Iss 1, Pp 15-34 (2024)
Continuous water vapour measurements in the troposphere and lowermost stratosphere are crucial for the understanding of global water transport processes and climate impact. In the course of the ‘Development and Evaluation of Novel and Compact Hygro
Externí odkaz:
https://doaj.org/article/812caf3c7eff43109e6de89b73f7d207
Autor:
Maser, Michael, Park, Ji Won, Lin, Joshua Yao-Yu, Lee, Jae Hyeon, Frey, Nathan C., Watkins, Andrew
We investigate Siamese networks for learning related embeddings for augmented samples of molecular conformers. We find that a non-contrastive (positive-pair only) auxiliary task aids in supervised training of Euclidean neural networks (E3NNs) and inc
Externí odkaz:
http://arxiv.org/abs/2302.07754
Autor:
Shristi Pawnikar, Brenda S Magenheimer, Keya Joshi, Ericka Nevarez-Munoz, Allan Haldane, Robin L Maser, Yinglong Miao
Publikováno v:
eLife, Vol 13 (2024)
Polycystin-1 (PC1) is the protein product of the PKD1 gene whose mutation causes autosomal dominant Polycystic Kidney Disease (ADPKD). PC1 is an atypical G protein-coupled receptor (GPCR) with an autocatalytic GAIN domain that cleaves PC1 into extrac
Externí odkaz:
https://doaj.org/article/4f77a5a022894bf284cd5a67536e884c
Publikováno v:
STAR Protocols, Vol 5, Iss 3, Pp 103155- (2024)
Summary: Humanized mice, defined as mice with human immune systems, have become an emerging model to study human hematopoiesis, infectious disease, and cancer. Here, we describe the techniques to generate humanized NSGF6 mice using adult human CD34+
Externí odkaz:
https://doaj.org/article/cb4168375e2a454492a1e19975ce7d30