scispace - formally typeset
Open AccessJournal ArticleDOI

PaccMannRL: De novo generation of hit-like anticancer molecules from transcriptomic data via reinforcement learning.

Reads0
Chats0
TLDR
In this article, a hybrid VAE was used to generate drugs with high predicted efficacy against cell lines or cancer types, using an anticancer drug sensitivity prediction model as reward function.
About
This article is published in iScience.The article was published on 2021-03-05 and is currently open access. It has received 38 citations till now.

read more

Citations
More filters
Journal ArticleDOI

De novo molecular design and generative models

TL;DR: In this paper, the authors present de novo approaches according to the coarseness of their molecular representation: that is, whether molecular design is modeled on an atom-based, fragment-based or reaction-based paradigm.
Journal ArticleDOI

TITAN: T-cell receptor specificity prediction with bimodal attention networks

TL;DR: Mann et al. as mentioned in this paper proposed a bimodal neural network that explicitly encodes both TCR sequences and epitopes to enable the independent study of generalization capabilities to unseen TCRs and/or epitopes.
Journal ArticleDOI

De Novo Structure-Based Drug Design Using Deep Learning.

TL;DR: This work proposes a deep learning-based method, where the knowledge of the active site structure of the target protein is sufficient to design new molecules, and validated it against two well-studied proteins.
Journal ArticleDOI

OUP accepted manuscript

TL;DR: DeepTTA as discussed by the authors is a novel end-to-end deep learning model that utilizes transformer for drug representation learning and a multilayer neural network for transcriptomic data prediction of the anti-cancer drug responses.
Journal ArticleDOI

Generative machine learning for de novo drug discovery: A systematic review

TL;DR: A systematic literature review of experimental articles and reviews over the last five years, machine learning models, challenges associated with computational molecule design along with proposed solutions, and molecular encoding methods are discussed in this article .
References
More filters
Journal ArticleDOI

Generative Model for Proposing Drug Candidates Satisfying Anticancer Properties Using a Conditional Variational Autoencoder.

TL;DR: A conditional variational autoencoder (CVAE) is proposed as a generative model to propose drug candidates with the desired property outside a data set range to solve the problem of syntactically invalid molecules in molecular generative models.
Journal ArticleDOI

Structural similarity assessment for drug sensitivity prediction in cancer

TL;DR: It is shown that it is possible to extend the usefulness of existing screens to untested drugs by deriving substitute sensitivity profiles from structurally similar drugs part of the screen.
Journal Article

Nitro-oxidative Stress Is Involved in Anticancer Activity of 17β-Estradiol Derivative in Neuroblastoma Cells.

TL;DR: It is proposed that 2-methoxyestradiol may be a natural modulator of cancer cell death and survival through nitric oxide generation and reduction of mitochondrial membrane potential through nitro-oxidative stress-dependent mechanisms.
Patent

Lipid-containing compositions and methods of using them

Leonard Girsh
TL;DR: Anabolic compositions can be administered to patients with chronic diseases, or who suffer from conditions precipitated by such diseases or long term treatment regimes, such as organ or tissue transplant procedures as discussed by the authors.
Journal ArticleDOI

Author Correction: DNA damage in circulating leukocytes measured with the comet assay may predict the risk of death.

Related Papers (5)