A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Filters
Deep Evolutionary Learning for Molecular Design
[article]
2020
arXiv
pre-print
In this paper, we propose a deep evolutionary learning (DEL) process that integrates fragment-based deep generative model and multi-objective evolutionary computation for molecular design. ...
Thus, DEL implements a data-model co-evolution concept which improves both sample population and generative model learning. ...
Zhavoronkov. druGAN: An advanced generative adversarial autoencoder model for de novo generation of new molecules with desired molecular properties in silico. ...
arXiv:2102.01011v1
fatcat:5f3mwjmwwzbbvgf3uj5ks6335y
Letter from the President of WFITN
2015
Interventional Neuroradiology
in the neural network model. ...
This is a first report of a de novo AVM in a patient with HHT. In patients with family histories of HHT, de novo AVMs are possible, even though no lesions have been detected at the first screening. ...
The robust design minimised the effect of uncertainties by sacrificing some degree of multiobjective optimisation. ...
doi:10.1177/1591019915618059
pmid:26547766
pmcid:PMC4757183
fatcat:fvlfbc5e3zac5l7gpae3qxtgzy
Chamonix, France BIOTECHNO 2014 Editors BIOTECHNO 2014 Committee BIOTECHNO Advisory Chairs BIOTECHNO 2014 Technical Program Committee
2014
Daisuke Kihara
unpublished
While progress is achieved with a high speed, challenges must be overcome for large-scale bio-subsystems, special genomics cases, bio-nanotechnologies, drugs, or microbial propagation and immunity. ...
Using bio-ontologies, biosemantics and special processing concepts, progress was achieved in dealing with genomics, biopharmaceutical and molecular intelligence, in the biology and microbiology domains ...
Research supported in part by NSF grants CCF-0926190 and CCF-1018459, and by AFOSR grant FA0550-09-1-0481. ...
fatcat:mrib6ha45ra7vlyxc57i5shr2y