Focused Library Generator: case of Mdmx inhibitors

Xia, Zhonghua; Karpov, Pavel; Popowicz, Grzegorz M.; Tetko, Igor V.

doi:10.1007/s10822-019-00242-8

Cited by 7 publications

(8 citation statements)

References 63 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To validate the model, we sampled 500,000 ChEMBLlike SMILES (only 8,617 (1.7%) of them were canonical) from a generator [56] and checked how accurately the model can restore canonical SMILES for these molecules. We intentionally selected the generated SMILES keeping in mind possible applications of the proposed method in artificial intelligence-driven pipelines of de-novo drug development.…”

Section: Smiles Canonicalization Modelmentioning

confidence: 99%

“…To have a fast, robust, and explainable tool for its prediction and interpretation is highly desirable by both academia and industry. The Transformer-CNN model built on 1311 compounds had the following statistics: q 2 = 0.92 and RMSE p = 0.57 [64]. For demonstration of its interpretability we choose haloperidol-a well-known antipsychotic drug with 14 mg/l water solubility [65].…”

Section: Aqueous Solubilitymentioning

confidence: 99%

See 1 more Smart Citation

Transformer-CNN: Swiss knife for QSAR modeling and interpretation

2020

Self Cite

View full text Add to dashboard Cite

We present SMILES-embeddings derived from the internal encoder state of a Transformer [1] model trained to canonize SMILES as a Seq2Seq problem. Using a CharNN [2] architecture upon the embeddings results in higher quality interpretable QSAR/QSPR models on diverse benchmark datasets including regression and classification tasks. The proposed Transformer-CNN method uses SMILES augmentation for training and inference, and thus the prognosis is based on an internal consensus. That both the augmentation and transfer learning are based on embeddings allows the method to provide good results for small datasets. We discuss the reasons for such effectiveness and draft future directions for the development of the method. The source code and the embeddings needed to train a QSAR model are available on https ://githu b.com/bigch em/trans forme r-cnn. The repository also has a standalone program for QSAR prognosis which calculates individual atoms contributions, thus interpreting the model's result. OCHEM [3] environment (https ://ochem .eu) hosts the on-line implementation of the method proposed.

show abstract

Section: Smiles Canonicalization Modelmentioning

confidence: 99%

Section: Aqueous Solubilitymentioning

confidence: 99%

Transformer-CNN: Swiss knife for QSAR modeling and interpretation

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since 2016, SMILES-based machinelearned methods are used to produce de novo molecules. These methods include Variational AutoEncoders (VAEs) [12], Recurrent Neural Network (RNN) [6,[13][14][15], Generative Adversarial Networks (GANs) [16] and reinforcement learning (RL) [17] or generate molecules based on molecular graph representation [18] as well as other many approaches as reviewed by [19]. Contrary to these earlier reports, we demonstrate herein that text learning on SMILES is highly efficient to explore the training space with a high degree of novelty.…”

Section: Introductionmentioning

confidence: 78%

“…The proposed approach can be also used via transfer learning to generate compounds for specific scaffolds (see e.g. [14][15][16][17]).…”

Section: Resultsmentioning

confidence: 99%

GEN: highly efficient SMILES explorer using autodidactic generative examination networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

Recurrent neural networks have been widely used to generate millions of de novo molecules in defined chemical spaces. Reported deep generative models are exclusively based on LSTM and/or GRU units and frequently trained using canonical SMILES. In this study, we introduce Generative Examination Networks (GEN) as a new approach to train deep generative networks for SMILES generation. In our GENs, we have used an architecture based on multiple concatenated bidirectional RNN units to enhance the validity of generated SMILES. GENs autonomously learn the target space in a few epochs and are stopped early using an independent online examination mechanism, measuring the quality of the generated set. Herein we have used online statistical quality control (SQC) on the percentage of valid molecular SMILES as examination measure to select the earliest available stable model weights. Very high levels of valid SMILES (95-98%) can be generated using multiple parallel encoding layers in combination with SMILES augmentation using unrestricted SMILES randomization. Our trained models combine an excellent novelty rate (85-90%) while generating SMILES with strong conservation of the property space (95-99%). In GENs, both the generative network and the examination mechanism are open to other architectures and quality criteria.

show abstract

“…More recently, applications involving Deep Learning models have gained attention due to their ability to extract important features from raw data and handle complex tasks [17], such as drug design. For instance, the Focused Library Generator designed by Xia et al [18] was able to design new inhibitor molecules with desired properties from scratch. Stokes et al [19] implemented Deep Learning for antibiotic prediction, which led to the discovery of a structurally distant antibacterial molecule.…”

Section: Introductionmentioning

confidence: 99%

Evaluating Deep Learning models for predicting ALK-5 inhibition

et al. 2021

View full text Add to dashboard Cite

Computational methods have been widely used in drug design. The recent developments in machine learning techniques and the ever-growing chemical and biological databases are fertile ground for discoveries in this area. In this study, we evaluated the performance of Deep Learning models in comparison to Random Forest, and Support Vector Regression for predicting the biological activity (pIC50) of ALK-5 inhibitors as candidates to treat cancer. The generalization power of the models was assessed by internal and external validation procedures. A deep neural network model obtained the best performance in this comparative study, achieving a coefficient of determination of 0.658 on the external validation set with mean square error and mean absolute error of 0.373 and 0.450, respectively. Additionally, the relevance of the chemical descriptors for the prediction of biological activity was estimated using Permutation Importance. We can conclude that the forecast model obtained by the deep neural network is suitable for the problem and can be employed to predict the biological activity of new ALK-5 inhibitors.

show abstract

Focused Library Generator: case of Mdmx inhibitors

Cited by 7 publications

References 63 publications

Transformer-CNN: Swiss knife for QSAR modeling and interpretation

Transformer-CNN: Swiss knife for QSAR modeling and interpretation

GEN: highly efficient SMILES explorer using autodidactic generative examination networks

Evaluating Deep Learning models for predicting ALK-5 inhibition

Contact Info

Product

Resources

About