Stanisław JastrzęBski

Stanisław JastrzęBski

Auto-generated profile, based on publicly available information

Stanisław JastrzęBski

Doctoral School of Exact and Life Sciences Jagiellonian University

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
12 July 2021 in Journal of Chemical Information and Modeling
Verified
Journal Article
Closed access
MSMikołaj Sacha
Mikołaj Sacha
MBMikołaj Błaż
Mikołaj Błaż
PBPiotr Byrski
Piotr Byrski
Pawel Dabrowski-TumanskiPawel Dabrowski-Tumanski
Pawel Dabrowski-Tumanski
MCMikołaj Chromiński
Mikołaj Chromiński
SJStanisław Jastrzębski
Stanisław Jastrzębski

24 May 2023 in Journal of Chemical Information and Modeling
Verified
Journal Article
Open access
TCTobiasz Ciepliński
Tobiasz Ciepliński
TDTomasz Danel
Tomasz Danel
Sabina PodlewskaSabina Podlewska
Sabina Podlewska
SJStanisław Jastrzȩbski
Stanisław Jastrzȩbski
Designing compounds with desired properties is a key element of the drug discovery process. However, measuring progress in the field has been challenging due to the lack of realistic retrospective benchmarks, and the large cost of prospective validation. To close this gap, we propose a benchmark based on docking, a widely used computational method for assessing molecule binding to a protein. Concretely, the goal is to generate drug-like molecules that are scored highly by SMINA, a popular docking software. We observe that various graph-based generative models fail to propose molecules with a high docking score when trained using a realistically sized training set. This suggests a limitation of the current incarnation of models for de novo drug design. Finally, we also include simpler tasks in the benchmark based on a simpler scoring function. We release the benchmark as an easy to use package available at https://github.com/cieplinski-tobiasz/smina-docking-benchmark. We hope that our benchmark will serve as a stepping stone toward the goal of automatically generating promising drug candidates.

19 November 2020
Verified
Book Chapter
Closed access
PDF file
PSPrzemysław Spurek
Przemysław Spurek
ANAleksandra Nowak
Aleksandra Nowak
JTJacek Tabor
Jacek Tabor
ŁMŁukasz Maziarka
Łukasz Maziarka
SJStanisław Jastrzębski
Stanisław Jastrzębski

25 November 2020 in arXiv
Verified
Preprint
Open access
PDF file
CLCheng-Hao Liu
Cheng-Hao Liu
MKMaksym Korablyov
Maksym Korablyov
SJStanisław JastrzęBski
Stanisław JastrzęBski
PWPaweł Włodarczyk-Pruszyński
Paweł Włodarczyk-Pruszyński
YBYoshua BENGIO
Yoshua BENGIO
MSMarwin H. S. Segler
Marwin H. S. Segler
De novo molecule generation often results in chemically unfeasible molecules. A natural idea to mitigate this problem is to bias the search process towards more easily synthesizable molecules using a proxy for synthetic accessibility. However, using currently available proxies still results in highly unrealistic compounds. We investigate the feasibility of training deep graph neural networks to approximate the outputs of a retrosynthesis planning software, and their use to bias the search process. We evaluate our method on a benchmark involving searching for drug-like molecules with antibiotic properties. Compared to enumerating over five million existing molecules from the ZINC database, our approach finds molecules predicted to be more likely to be antibiotics while maintaining good drug-like properties and being easily synthesizable. Importantly, our deep neural network can successfully filter out hard to synthesize molecules while achieving a $10^5$ times speed-up over using the retrosynthesis planning software.

25 May 2021 in arXiv
Verified
Preprint
Open access
PDF file
MSMikołaj Sacha
Mikołaj Sacha
MBMikołaj Błaż
Mikołaj Błaż
PBPiotr Byrski
Piotr Byrski
PDPaweł Dąbrowski-Tumański
Paweł Dąbrowski-Tumański
MCMikołaj Chromiński
Mikołaj Chromiński
SJStanisław Jastrzębski
Stanisław Jastrzębski
The central challenge in automated synthesis planning is to be able to generate and predict outcomes of a diverse set of chemical reactions. In particular, in many cases, the most likely synthesis pathway cannot be applied due to additional constraints, which requires proposing alternative chemical reactions. With this in mind, we present Molecule Edit Graph Attention Network (MEGAN), an end-to-end encoder-decoder neural model. MEGAN is inspired by models that express a chemical reaction as a sequence of graph edits, akin to the arrow pushing formalism. We extend this model to retrosynthesis prediction (predicting substrates given the product of a chemical reaction) and scale it up to large datasets. We argue that representing the reaction as a sequence of edits enables MEGAN to efficiently explore the space of plausible chemical reactions, maintaining the flexibility of modeling the reaction in an end-to-end fashion, and achieving state-of-the-art accuracy in standard benchmarks. Code and trained models are made available online at https://github.com/molecule-one/megan.

2 July 2019 in arXiv
Verified
Preprint
Open access
PDF file
SKSzymon Knop
Szymon Knop
JTJacek Tabor
Jacek Tabor
PSPrzemysław Spurek
Przemysław Spurek
IPIgor Podolak
Igor Podolak
MMMarcin Mazur
Marcin Mazur
SJStanisław JastrzęBski
Stanisław JastrzęBski
We propose a new generative model, Cramer-Wold Autoencoder (CWAE). Following WAE, we directly encourage normality of the latent space. Our paper uses also the recent idea from Sliced WAE (SWAE) model, which uses one-dimensional projections as a method of verifying closeness of two distributions. The crucial new ingredient is the introduction of a new (Cramer-Wold) metric in the space of densities, which replaces the Wasserstein metric used in SWAE. We show that the Cramer-Wold metric between Gaussian mixtures is given by a simple analytic formula, which results in the removal of sampling necessary to estimate the cost function in WAE and SWAE models. As a consequence, while drastically simplifying the optimization procedure, CWAE produces samples of a matching perceptual quality to other SOTA models.