Файл:Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks 1701.01329.pdf

Материал из Материалы по машинному обучению
Перейти к: навигация, поиск
Generating_Focussed_Molecule_Libraries_for_Drug_Discovery_with_Recurrent_Neural_Networks_1701.01329.pdf(0 × 0 пикселей, размер файла: 1,7 МБ, MIME-тип: application/pdf)

Marwin HS Segler, Thierry Kogej, Christian Tyrchan and Mark P Waller


Abstract

In de novo drug design, computational strategies are used to generate novel molecules with good affinity to the desired biological target. In this work, we show that recurrent neural networks can be trained as generative models for molecular structures, similar to statistical language models in natural language processing. We demonstrate that the properties of the generated molecules correlate very well with the properties of the molecules used to train the model. In order to enrich libraries with molecules active towards a given biological target, we propose to fine-tune the model with small sets of molecules, which are known to be active against that target.

Against Staphylococcus aureus, the model reproduced 14% of 6051 hold-out test molecules that medicinal chemists designed, whereas against Plasmodium falciparum (Malaria) it reproduced 28% of 1240 test molecules. When coupled with a scoring function, our model can perform the complete de novo drug design cycle to generate large sets of novel molecules for drug discovery.

Keywords: computer-assisted drug design; recurrent neural networks

История файла

Нажмите на дату/время, чтобы просмотреть, как тогда выглядел файл.

Дата/времяРазмерыУчастникПримечание
текущий19:46, 14 июня 20170 × 0 (1,7 МБ)Slikos (обсуждение | вклад)
  • Вы не можете перезаписать этот файл.

Нет страниц, ссылающихся на данный файл.