Maciej Wójcikowski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Maciej Wójcikowski has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Pawel Siedlecki
Institute of Biochemistry and Biophysics, Polish Academy of Sciences, Warsaw, Poland
4 shared publications - Piotr Zielenkiewicz
Institute of Biochemistry and Biophysics, Polish Academy of Sciences, 02-106 Warsaw, Poland
3 shared publications - Marta M. Stepniewska-Dziubinska
Institute of Biochemistry and Biophysics, Polish Academy of Sciences, Warsaw, Poland
2 shared publications Michał Kukiełka
Faculty of Mathematics, Informatics, and Mechanics, University of Warsaw, Banacha 2, Warsaw, Poland
2 shared publicationsAnna Lukasik
Institute of Biochemistry and Biophysics, Polish Academy of Sciences, 02-106 Warsaw, Poland
1 shared publicationPawel Siedlecki
1 shared publication
Latest Publications
- Open Access
- 8 September 2018
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 35 (8) , 1334-1341
Development of a protein–ligand extended connectivity (PLEC) fingerprint and its application for binding affinity predictions
Fingerprints (FPs) are the most common small molecule representation in cheminformatics. There are a wide variety of FPs, and the Extended Connectivity Fingerprint (ECFP) is one of the best-suited for general applications. Despite the overall FP abundance, only a few FPs represent the 3D structure of the molecule, and hardly any encode protein–ligand interactions. Here, we present a Protein–Ligand Extended Connectivity (PLEC) FP that implicitly encodes protein–ligand interactions by pairing the ECFP environments from the ligand and the protein. PLEC FPs were used to construct different machine learning models tailored for predicting protein–ligand affinities (pKi∕d). Even the simplest linear model built on the PLEC FP achieved Rp = 0.817 on the Protein Databank (PDB) bind v2016 ‘core set’, demonstrating its descriptive power. The PLEC FP has been implemented in the Open Drug Discovery Toolkit (https://github.com/oddt/oddt). Supplementary data are available at Bioinformatics online.
- 8 September 2018
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 35 (8) , 1334-1341
Open AccessDevelopment of a protein–ligand extended connectivity (PLEC) fingerprint and its application for binding affinity predictions
Fingerprints (FPs) are the most common small molecule representation in cheminformatics. There are a wide variety of FPs, and the Extended Connectivity Fingerprint (ECFP) is one of the best-suited for general applications. Despite the overall FP abundance, only a few FPs represent the 3D structure of the molecule, and hardly any encode protein–ligand interactions. Here, we present a Protein–Ligand Extended Connectivity (PLEC) FP that implicitly encodes protein–ligand interactions by pairing the ECFP environments from the ligand and the protein. PLEC FPs were used to construct different machine learning models tailored for predicting protein–ligand affinities (pKi∕d). Even the simplest linear model built on the PLEC FP achieved Rp = 0.817 on the Protein Databank (PDB) bind v2016 ‘core set’, demonstrating its descriptive power. The PLEC FP has been implemented in the Open Drug Discovery Toolkit (https://github.com/oddt/oddt). Supplementary data are available at Bioinformatics online.
- Open Access
- 28 February 2018
- Published by American Chemical Society (ACS) in ChemRxiv
Development of a Protein-Ligand Extended Connectivity (PLEC) Fingerprint and Its Application for Binding Affinity Predictions.
Fingerprints (FPs) are the most common small molecule representation in cheminformatics. There are a wide variety of fingerprints, and the Extended Connectivity Fingerprint (ECFP) is one of the best-suited for general applications. Despite the overall FP abundance, only a few FPs represent the 3D structure of the molecule, and hardly any encode protein-ligand interactions. Here, we present a Protein-Ligand Extended Connectivity (PLEC) fingerprint that implicitly encodes protein-ligand interactions by pairing the ECFP environments from the ligand and the protein. PLEC fingerprints were used to construct different machine learning (ML) models tailored for predicting protein-ligand affinities (pKi/d). Even the simplest linear model built on the PLEC fingerprint achieved Rp=0.83 on the PDBbind v2016 "core set”, demonstrating its descriptive power. The PLEC fingerprint has been implemented in the Open Drug Discovery Toolkit (https://github.com/oddt/oddt).
- 28 February 2018
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessDevelopment of a Protein-Ligand Extended Connectivity (PLEC) Fingerprint and Its Application for Binding Affinity Predictions.
Fingerprints (FPs) are the most common small molecule representation in cheminformatics. There are a wide variety of fingerprints, and the Extended Connectivity Fingerprint (ECFP) is one of the best-suited for general applications. Despite the overall FP abundance, only a few FPs represent the 3D structure of the molecule, and hardly any encode protein-ligand interactions. Here, we present a Protein-Ligand Extended Connectivity (PLEC) fingerprint that implicitly encodes protein-ligand interactions by pairing the ECFP environments from the ligand and the protein. PLEC fingerprints were used to construct different machine learning (ML) models tailored for predicting protein-ligand affinities (pKi/d). Even the simplest linear model built on the PLEC fingerprint achieved Rp=0.83 on the PDBbind v2016 "core set”, demonstrating its descriptive power. The PLEC fingerprint has been implemented in the Open Drug Discovery Toolkit (https://github.com/oddt/oddt).
- Top Cited PapersOpen Access
- 25 April 2017
- Published by Springer Nature in Scientific Reports
- Vol. 7 (1) , srep46710
Performance of machine-learning scoring functions in structure-based virtual screening
Classical scoring functions have reached a plateau in their performance in virtual screening and binding affinity prediction. Recently, machine-learning scoring functions trained on protein-ligand complexes have shown great promise in small tailored studies. They have also raised controversy, specifically concerning model overfitting and applicability to novel targets. Here we provide a new ready-to-use scoring function (RF-Score-VS) trained on 15 426 active and 893 897 inactive molecules docked to a set of 102 targets. We use the full DUD-E data sets along with three docking tools, five classical and three machine-learning scoring functions for model building and performance assessment. Our results show RF-Score-VS can substantially improve virtual screening performance: RF-Score-VS top 1% provides 55.6% hit rate, whereas that of Vina only 16.2% (for smaller percent the difference is even more encouraging: RF-Score-VS top 0.1% achieves 88.6% hit rate for 27.5% using Vina). In addition, RF-Score-VS provides much better prediction of measured binding affinity than Vina (Pearson correlation of 0.56 and −0.18, respectively). Lastly, we test RF-Score-VS on an independent test set from the DEKOIS benchmark and observed comparable results. We provide full data sets to facilitate further research in this area (http://github.com/oddt/rfscorevs) as well as ready-to-use RF-Score-VS (http://github.com/oddt/rfscorevs_binary).
- 25 April 2017
- Published by Springer Nature in Scientific Reports
- Vol. 7 (1) , srep46710
Top Cited PapersOpen AccessPerformance of machine-learning scoring functions in structure-based virtual screening
Classical scoring functions have reached a plateau in their performance in virtual screening and binding affinity prediction. Recently, machine-learning scoring functions trained on protein-ligand complexes have shown great promise in small tailored studies. They have also raised controversy, specifically concerning model overfitting and applicability to novel targets. Here we provide a new ready-to-use scoring function (RF-Score-VS) trained on 15 426 active and 893 897 inactive molecules docked to a set of 102 targets. We use the full DUD-E data sets along with three docking tools, five classical and three machine-learning scoring functions for model building and performance assessment. Our results show RF-Score-VS can substantially improve virtual screening performance: RF-Score-VS top 1% provides 55.6% hit rate, whereas that of Vina only 16.2% (for smaller percent the difference is even more encouraging: RF-Score-VS top 0.1% achieves 88.6% hit rate for 27.5% using Vina). In addition, RF-Score-VS provides much better prediction of measured binding affinity than Vina (Pearson correlation of 0.56 and −0.18, respectively). Lastly, we test RF-Score-VS on an independent test set from the DEKOIS benchmark and observed comparable results. We provide full data sets to facilitate further research in this area (http://github.com/oddt/rfscorevs) as well as ready-to-use RF-Score-VS (http://github.com/oddt/rfscorevs_binary).
- Open Access
- 8 April 2016
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 32 (17) , 2722-2724
Tools4miRs – one place to gather all the tools for miRNA analysis
Summary: MiRNAs are short, non-coding molecules that negatively regulate gene expression and thereby play several important roles in living organisms. Dozens of computational methods for miRNA-related research have been developed, which greatly differ in various aspects. The substantial availability of difficult-to-compare approaches makes it challenging for the user to select a proper tool and prompts the need for a solution that will collect and categorize all the methods. Here, we present tools4miRs, the first platform that gathers currently more than 160 methods for broadly defined miRNA analysis. The collected tools are classified into several general and more detailed categories in which the users can additionally filter the available methods according to their specific research needs, capabilities and preferences. Tools4miRs is also a web-based target prediction meta-server that incorporates user-designated target prediction methods into the analysis of user-provided data. Availability and Implementation : Tools4miRs is implemented in Python using Django and is freely available at tools4mirs.org. Contact : piotr@ibb.waw.pl Supplementary information: Supplementary data are available at Bioinformatics online.
- 8 April 2016
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 32 (17) , 2722-2724
Open AccessTools4miRs – one place to gather all the tools for miRNA analysis
Summary: MiRNAs are short, non-coding molecules that negatively regulate gene expression and thereby play several important roles in living organisms. Dozens of computational methods for miRNA-related research have been developed, which greatly differ in various aspects. The substantial availability of difficult-to-compare approaches makes it challenging for the user to select a proper tool and prompts the need for a solution that will collect and categorize all the methods. Here, we present tools4miRs, the first platform that gathers currently more than 160 methods for broadly defined miRNA analysis. The collected tools are classified into several general and more detailed categories in which the users can additionally filter the available methods according to their specific research needs, capabilities and preferences. Tools4miRs is also a web-based target prediction meta-server that incorporates user-designated target prediction methods into the analysis of user-provided data. Availability and Implementation : Tools4miRs is implemented in Python using Django and is freely available at tools4mirs.org. Contact : piotr@ibb.waw.pl Supplementary information: Supplementary data are available at Bioinformatics online.
- Open Access
- 22 June 2015
- Published by Springer Nature in Journal of Cheminformatics
- Vol. 7 (1) , 26
Open Drug Discovery Toolkit (ODDT): a new open-source player in the drug discovery field
There has been huge progress in the open cheminformatics field in both methods and software development. Unfortunately, there has been little effort to unite those methods and software into one package. We here describe the Open Drug Discovery Toolkit (ODDT), which aims to fulfill the need for comprehensive and open source drug discovery software. The Open Drug Discovery Toolkit was developed as a free and open source tool for both computer aided drug discovery (CADD) developers and researchers. ODDT reimplements many state-of-the-art methods, such as machine learning scoring functions (RF-Score and NNScore) and wraps other external software to ease the process of developing CADD pipelines. ODDT is an out-of-the-box solution designed to be easily customizable and extensible. Therefore, users are strongly encouraged to extend it and develop new methods. We here present three use cases for ODDT in common tasks in computer-aided drug discovery. Open Drug Discovery Toolkit is released on a permissive 3-clause BSD license for both academic and industrial use. ODDT’s source code, additional examples and documentation are available on GitHub ( https://github.com/oddt/oddt ).
- 22 June 2015
- Published by Springer Nature in Journal of Cheminformatics
- Vol. 7 (1) , 26
Open AccessOpen Drug Discovery Toolkit (ODDT): a new open-source player in the drug discovery field
There has been huge progress in the open cheminformatics field in both methods and software development. Unfortunately, there has been little effort to unite those methods and software into one package. We here describe the Open Drug Discovery Toolkit (ODDT), which aims to fulfill the need for comprehensive and open source drug discovery software. The Open Drug Discovery Toolkit was developed as a free and open source tool for both computer aided drug discovery (CADD) developers and researchers. ODDT reimplements many state-of-the-art methods, such as machine learning scoring functions (RF-Score and NNScore) and wraps other external software to ease the process of developing CADD pipelines. ODDT is an out-of-the-box solution designed to be easily customizable and extensible. Therefore, users are strongly encouraged to extend it and develop new methods. We here present three use cases for ODDT in common tasks in computer-aided drug discovery. Open Drug Discovery Toolkit is released on a permissive 3-clause BSD license for both academic and industrial use. ODDT’s source code, additional examples and documentation are available on GitHub ( https://github.com/oddt/oddt ).
- Open Access
- 23 December 2013
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 54 (1) , 347-354
DiSCuS: An Open Platform for (Not Only) Virtual Screening Results Management
DiSCuS, a “Database System for Compound Selection”, has been developed. The primary goal of DiSCuS is to aid researchers in the steps subsequent to generating high-throughput virtual screening (HTVS) results, such as selection of compounds for further study, purchase, or synthesis. To do so, DiSCuS provides (1) a storage facility for ligand–receptor complexes (generated with external programs), (2) a number of tools for validating these complexes, such as scoring functions, potential energy contributions, and med-chem features with ligand similarity estimates, and (3) powerful searching and filtering options with logical operators. DiSCuS supports multiple receptor targets for a single ligand, so it can be used either to evaluate different variants of an active site or for selectivity studies. DiSCuS documentation, installation instructions, and source code can be found at http://discus.ibb.waw.pl.
- 23 December 2013
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 54 (1) , 347-354
Open AccessDiSCuS: An Open Platform for (Not Only) Virtual Screening Results Management
DiSCuS, a “Database System for Compound Selection”, has been developed. The primary goal of DiSCuS is to aid researchers in the steps subsequent to generating high-throughput virtual screening (HTVS) results, such as selection of compounds for further study, purchase, or synthesis. To do so, DiSCuS provides (1) a storage facility for ligand–receptor complexes (generated with external programs), (2) a number of tools for validating these complexes, such as scoring functions, potential energy contributions, and med-chem features with ligand similarity estimates, and (3) powerful searching and filtering options with logical operators. DiSCuS supports multiple receptor targets for a single ligand, so it can be used either to evaluate different variants of an active site or for selectivity studies. DiSCuS documentation, installation instructions, and source code can be found at http://discus.ibb.waw.pl.