Simon Viet Johansson

Simon Viet Johansson

Auto-generated profile, based on publicly available information

Simon Viet Johansson

AstraZeneca AB

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 December 2020 in Frontiers in Pharmacology
Verified
Journal Article
Open access
PDF file
DPDaniil Polykovskiy
Daniil Polykovskiy
AZAlexander Zhebrak
Alexander Zhebrak
BSBenjamin Sanchez-Lengeling
Benjamin Sanchez-Lengeling
SGSergey Golovanov
Sergey Golovanov
OTOktai Tatanov
Oktai Tatanov
AZAlex Zhavoronkov
Alex Zhavoronkov
Generative models are becoming a tool of choice for exploring the molecular space. These models learn on a large training dataset and produce novel molecular structures with similar properties. Generated structures can be utilized for virtual screening or training semi-supervized predictive models in the downstream tasks. While there are plenty of generative models, it is unclear how to compare and rank them. In this work, we introduce a benchmarking platform called Molecular Sets (MOSES) to standardize training and comparison of molecular generative models. MOSES provides training and testing datasets, and a set of metrics to evaluate the quality and diversity of generated structures. We have implemented and compared several molecular generation models and suggest to use our results as reference points for further advancements in generative chemistry research. The platform and source code are available athttps://github.com/molecularsets/moses.

3 December 2019 in Journal of Cheminformatics
Verified
Journal Article
Open access
PDF file
OPOleksii Prykhodko
Oleksii Prykhodko
SJSimon Viet Johansson
Simon Viet Johansson
PKPanagiotis-Christos Kotsias
Panagiotis-Christos Kotsias
JAJosep Arús-Pous
Josep Arús-Pous
EBEsben Jannik Bjerrum
Esben Jannik Bjerrum
HCHongming Chen
Hongming Chen
Deep learning methods applied to drug discovery have been used to generate novel structures. In this study, we propose a new deep learning architecture, LatentGAN, which combines an autoencoder and a generative adversarial neural network for de novo molecular design. We applied the method in two scenarios: one to generate random drug-like compounds and another to generate target-biased compounds. Our results show that the method works well in both cases. Sampled compounds from the trained model can largely occupy the same chemical space as the training set and also generate a substantial fraction of novel compounds. Moreover, the drug-likeness score of compounds sampled from LatentGAN is also similar to that of the training set. Lastly, generated compounds differ from those obtained with a Recurrent Neural Network-based generative model approach, indicating that both methods can be used complementarily.

21 November 2019 in Journal of Cheminformatics
Verified
Journal Article
Open access
PDF file
JAJosep Arús-Pous
Josep Arús-Pous
SJSimon Viet Johansson
Simon Viet Johansson
OPOleksii Prykhodko
Oleksii Prykhodko
EBEsben Jannik Bjerrum
Esben Jannik Bjerrum
CTChristian Tyrchan
Christian Tyrchan
OEOla Engkvist
Ola Engkvist
Recurrent Neural Networks (RNNs) trained with a set of molecules represented as unique (canonical) SMILES strings, have shown the capacity to create large chemical spaces of valid and meaningful structures. Herein we perform an extensive benchmark on models trained with subsets of GDB-13 of different sizes (1 million, 10,000 and 1000), with different SMILES variants (canonical, randomized and DeepSMILES), with two different recurrent cell types (LSTM and GRU) and with different hyperparameter combinations. To guide the benchmarks new metrics were developed that define how well a model has generalized the training set. The generated chemical space is evaluated with respect to its uniformity, closedness and completeness. Results show that models that use LSTM cells trained with 1 million randomized SMILES, a non-unique molecular string representation, are able to generalize to larger chemical spaces than the other approaches and they represent more accurately the target chemical space. Specifically, a model was trained with randomized SMILES that was able to generate almost all molecules from GDB-13 with a quasi-uniform probability. Models trained with smaller samples show an even bigger improvement when trained with randomized SMILES models. Additionally, models were trained on molecules obtained from ChEMBL and illustrate again that training with randomized SMILES lead to models having a better representation of the drug-like chemical space. Namely, the model trained with randomized SMILES was able to generate at least double the amount of unique molecules with the same distribution of properties comparing to one trained with canonical SMILES.

1 February 2021 in Drug Discovery Today
Verified
Journal Article
Closed access
LMLewis H. Mervin
Lewis H. Mervin
SJSimon Johansson
Simon Johansson
ESElizaveta Semenova
Elizaveta Semenova
KGKathryn A. Giblin
Kathryn A. Giblin
OEOla Engkvist
Ola Engkvist

5 November 2020 in Reaction Chemistry & Engineering
Verified
Journal Article
Closed access
PDF file
ATAmol Thakkar
Amol Thakkar
SJSimon Johansson
Simon Johansson
KJKjell Jorner
Kjell Jorner
DBDavid Buttar
David Buttar
JRJean-Louis Reymond
Jean-Louis Reymond
OEOla Engkvist
Ola Engkvist
In this perspective we deal with questions pertaining to the development of synthesis planning technologies over the course of recent years.

1 December 2019 in Drug Discovery Today: Technologies
Verified
Journal Article
Closed access
SJSimon Johansson
Simon Johansson
ATAmol Thakkar
Amol Thakkar
TKThierry Kogej
Thierry Kogej
EBEsben Bjerrum
Esben Bjerrum
SGSamuel Genheden
Samuel Genheden
OEOla Engkvist
Ola Engkvist