eMolFrag

If you use eFindSite, please cite the following papers:
1 Brylinski M, Feinstein WP. (2013) eFindSite: Improved prediction of ligand binding sites in protein models using meta-threading, machine learning and auxiliary ligands. J Comput Aided Mol Des 27 (6): 551-67.     
2 Feinstein WP, Brylinski M. (2014) eFindSite: Enhanced fingerprint-based virtual screening against predicted ligand binding sites in protein models. Mol Inf 33 (2): 135-50.     
If you use eThread, please cite the following papers:
1 Brylinski M, Lingam D. (2012) eThread: A highly optimized machine learning-based approach to meta-threading and the modeling of protein tertiary structures. PLoS ONE 7 (11): e50200.     
2 Brylinski M. (2013) Unleashing the power of meta-threading for evolution/structure-based function inference of proteins. Front Genet 4: 118.     
If you use eRankPPI, please cite the following papers:
1 Maheshwari S, Brylinski M. (2015) Predicted binding site information improves model ranking in protein docking using experimental and computer-generated target structures. BMC Struct Biol 15 (1): 23.     
2 Maheshwari S, Brylinski M. (2017) Across-proteome modeling of dimer structures for the bottom-up assembly of protein-protein interaction networks. BMC Bioinformatics 18 (1): 257.     
If you use eAromatic, please cite the following paper:
1 Brylinski M. (2018) Aromatic interactions at the ligand-protein interface: Implications for the development of docking scoring functions. Chem Biol Drug Des 91 (2): 380-90.     
If you use CMS, please cite the following paper:
1 Ding Y, Fang Y, Moreno J, Ramanujam J, Jarrell M, Brylinski M. (2016) Assessing the similarity of ligand binding conformations with the Contact Mode Score. Comput Biol Chem 64: 403-13.     
If you use GeauxDockd, please cite the following papers:
1 Ding Y, Fang Y, Feinstein WP, Ramanujam J, Koppelman DM, Moreno J, Brylinski M, Jarrell M. (2015) GeauxDock: A novel approach for mixed-resolution ligand docking using a descriptor-based force field. J Comput Chem 36 (27): 2013-26.     
2 Fang Y, Ding Y, Feinstein WP, Koppelman DM, Moreno J, Jarrell M, Ramanujam J, Brylinski M. (2016) GeauxDock: Accelerating structure-based virtual screening with heterogeneous computing. PLoS ONE 11 (7): e0158898.     
If you use eSynth, please cite the following paper:
1 Naderi M, Alvin C, Ding Y, Mukhopadhyay S, Brylinski M. (2016) A graph-based approach to construct target-focused libraries for virtual screening. J Cheminform 8: 14.     
If you use eBoxSize, please cite the following paper:
1 Feinstein WP, Brylinski M. (2015) Calculating an optimal box size for ligand docking and virtual screening against experimental and predicted binding pockets. J Cheminform 7 (1): 18.     
If you use the ACCase dataset, please cite the following paper:
1 Brylinski M, Waldrop GL. (2014) Computational redesign of bacterial biotin carboxylase inhibitors using structure-based virtual screening of combinatorial libraries. Molecules 19 (4): 4021-45.     
If you use eModel-BDB, please cite the following paper:
1 Naderi M, Govindaraj RG, Brylinski M. (2018) eModel-BDB: A database of comparative structure models of drug-target interactions from the Binding Database. GigaScience 7: 1-9.     
If you use eToxPred, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.     
If you use eFindSitePPI, please cite the following papers:
1 Maheshwari S, Brylinski M. (2015) Prediction of protein-protein interaction sites from weakly homologous template structures using meta-threading and machine learning. J Mol Recognit 28 (1): 35-48.     
2 Maheshwari S, Brylinski M. (2016) Template-based identification of protein-protein interfaces using eFindSite(PPI). Methods 93: 64-71.     
If you use TOUGH-D1, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.     
If you use TOUGH-D1, please cite the following paper:
1 Brylinski M. (2018) Aromatic interactions at the ligand-protein interface: Implications for the development of docking scoring functions. Chem Biol Drug Des 91 (2): 380-90.     
If you use TOUGH-M1, please cite the following paper:
1 Govindaraj RG, Brylinski M. (2018) Comparative assessment of strategies to identify similar ligand-binding pockets in proteins. BMC Bioinformatics 19 (1): 91.     
If you use eMatchSite, please cite the following papers:
1 Brylinski M. (2014) eMatchSite: sequence order-independent structure alignments of ligand binding pockets in protein models. PLoS Comput Biol 10 (9): e1003829.     
2 Brylinski M. (2017) Local alignment of ligand binding sites in proteins for polypharmacology and drug repositioning. Methods Mol Biol 1611: 109-22.     
If you use eMolFrag, please cite the following paper:
1 Liu T, Naderi M, Alvin C, Mukhopadhyay S, Brylinski M. (2017) Break down in order to build up: Decomposing small molecules for fragment-based drug design with eMolFrag. J Chem Inf Model 57 (4): 627-631.     
If you use eVolver, please cite the following papers:
1 Brylinski M. (2013) eVolver: an optimization engine for evolving protein sequences to stabilize the respective structures. BMC Res Notes 6 (1): 303.     
2 Brylinski M. (2013) The utility of artificially evolved sequences in protein threading and fold recognition. J Theor Biol 328: 77-88.     
If you use eRepo-ORP, please cite the following papers:
1 Govindaraj RG, Naderi M, Singha M, Lemoine J, Brylinski M. (2018) Large-scale computational drug repositioning to find treatments for rare diseases. NPJ Syst Biol Appl 4: 13.     
2 Brylinski M, Naderi M, Govindaraj RG, Lemoine J. (2018) eRepo-ORP: Exploring the opportunity space to combat orphan diseases with existing drugs. J Mol Biol 430 (15): 2266-2273.     
If you use eToxPred, please cite the following paper:
1 Pu L, Naderi M, Liu T, Wu HC, Mukhopadhyay S, Brylinski M. (2019) eToxPred: A machine learning-based approach to estimate the toxicity of drug candidates. BMC Pharmacol Toxicol 20 (1): 2.     
 

Assuming that organic compounds are composed of sets of core fragments (bricks) connected by flexible linkers, a molecule can be decomposed into its building blocks tracking their atomic connectivity. eMolFrag is an automated method to extract molecular fragments from compound libraries.

Standalone

Available software:
Analysis of aromatic interactions in protein-ligand complexes.  
Calculation of the optimal box size for ligand docking.  
Protein-ligand complex (dis)similarity measure based on intermolecular contacts.  
Classification of drug binding sites with Deep Learning.   
Ligand binding site prediction and virtual screening.    
Prediction of protein binding sites and residues.  
Ultra-fast ligand docking with a hybrid force field.  
Sequence order-independent ligand binding site alignment.  
Extraction of molecular fragments from compound libraries.   
Ranking of dimer models with machine learning.  
Virtual synthesis of molecules from fragments with graph-based techniques.   
Template-based protein structure prediction with meta-threading and machine learning.  
Prediction of the toxicity and synthetic accessibility of small organic molecules.   
Optimization of synthetic protein sequences to stabilize the respective structures.  

Available datasets:
Docking of amino-oxazoles to bacterial biotin carboxylase isoforms.   
Comparative structure models of drug-target interactions from the Binding Database.    
Structure-based function annotation of the roundworm proteome.   
Structure-based function annotation of the human proteome.   
Structure-based function annotation of the fruitfly proteome.   
Structure-based function annotation of the proteomes of malaria parasites.   
Structure-based function annotation of the mouse proteome.   
Computational drug repositioning to find treatments for orphan diseases.   
Dataset to evaluate algorithms for binding site classification.   
Dataset to evaluate algorithms for ligand docking.   
Dataset to evaluate algorithms for binding site matching.   
Dataset to evaluate algorithms for binding site matching.   

Available gateways:
Ligand binding site prediction and virtual screening.    
Template-based protein structure prediction with meta-threading and machine learning.  

Available standalone software:
Analysis of aromatic interactions in protein-ligand complexes.  
Calculation of the optimal box size for ligand docking.  
Protein-ligand complex (dis)similarity measure based on intermolecular contacts.  
Classification of drug binding sites with Deep Learning.   
Ligand binding site prediction and virtual screening.    
Prediction of protein binding sites and residues.  
Ultra-fast ligand docking with a hybrid force field.  
Sequence order-independent ligand binding site alignment.  
Extraction of molecular fragments from compound libraries.   
Ranking of dimer models with machine learning.  
Virtual synthesis of molecules from fragments with graph-based techniques.   
Prediction of the toxicity and synthetic accessibility of small organic molecules.   
Optimization of synthetic protein sequences to stabilize the respective structures.  

Available datasets:
Docking of amino-oxazoles to bacterial biotin carboxylase isoforms.   
Comparative structure models of drug-target interactions from the Binding Database.    
Structure-based function annotation of the roundworm proteome.   
Structure-based function annotation of the human proteome.   
Structure-based function annotation of the fruitfly proteome.   
Structure-based function annotation of the proteomes of malaria parasites.   
Structure-based function annotation of the mouse proteome.   
Computational drug repositioning to find treatments for orphan diseases.   
Dataset to evaluate algorithms for binding site classification.   
Dataset to evaluate algorithms for ligand docking.   
Dataset to evaluate algorithms for binding site matching.   
Dataset to evaluate algorithms for binding site matching.   

Standalone software is hosted at GitHub.

Datasets

Available software:
Analysis of aromatic interactions in protein-ligand complexes.  
Calculation of the optimal box size for ligand docking.  
Protein-ligand complex (dis)similarity measure based on intermolecular contacts.  
Classification of drug binding sites with Deep Learning.   
Ligand binding site prediction and virtual screening.    
Prediction of protein binding sites and residues.  
Ultra-fast ligand docking with a hybrid force field.  
Sequence order-independent ligand binding site alignment.  
Extraction of molecular fragments from compound libraries.   
Ranking of dimer models with machine learning.  
Virtual synthesis of molecules from fragments with graph-based techniques.   
Template-based protein structure prediction with meta-threading and machine learning.  
Prediction of the toxicity and synthetic accessibility of small organic molecules.   
Optimization of synthetic protein sequences to stabilize the respective structures.  

Available datasets:
Docking of amino-oxazoles to bacterial biotin carboxylase isoforms.   
Comparative structure models of drug-target interactions from the Binding Database.    
Structure-based function annotation of the roundworm proteome.   
Structure-based function annotation of the human proteome.   
Structure-based function annotation of the fruitfly proteome.   
Structure-based function annotation of the proteomes of malaria parasites.   
Structure-based function annotation of the mouse proteome.   
Computational drug repositioning to find treatments for orphan diseases.   
Dataset to evaluate algorithms for binding site classification.   
Dataset to evaluate algorithms for ligand docking.   
Dataset to evaluate algorithms for binding site matching.   
Dataset to evaluate algorithms for binding site matching.   

Available gateways:
Ligand binding site prediction and virtual screening.    
Template-based protein structure prediction with meta-threading and machine learning.  

Available standalone software:
Analysis of aromatic interactions in protein-ligand complexes.  
Calculation of the optimal box size for ligand docking.  
Protein-ligand complex (dis)similarity measure based on intermolecular contacts.  
Classification of drug binding sites with Deep Learning.   
Ligand binding site prediction and virtual screening.    
Prediction of protein binding sites and residues.  
Ultra-fast ligand docking with a hybrid force field.  
Sequence order-independent ligand binding site alignment.  
Extraction of molecular fragments from compound libraries.   
Ranking of dimer models with machine learning.  
Virtual synthesis of molecules from fragments with graph-based techniques.   
Prediction of the toxicity and synthetic accessibility of small organic molecules.   
Optimization of synthetic protein sequences to stabilize the respective structures.  

Available datasets:
Docking of amino-oxazoles to bacterial biotin carboxylase isoforms.   
Comparative structure models of drug-target interactions from the Binding Database.    
Structure-based function annotation of the roundworm proteome.   
Structure-based function annotation of the human proteome.   
Structure-based function annotation of the fruitfly proteome.   
Structure-based function annotation of the proteomes of malaria parasites.   
Structure-based function annotation of the mouse proteome.   
Computational drug repositioning to find treatments for orphan diseases.   
Dataset to evaluate algorithms for binding site classification.   
Dataset to evaluate algorithms for ligand docking.   
Dataset to evaluate algorithms for binding site matching.   
Dataset to evaluate algorithms for binding site matching.   

Datasets are hosted at Open Science Framework and Dataverse.

Gateways

Available software:
Analysis of aromatic interactions in protein-ligand complexes.  
Calculation of the optimal box size for ligand docking.  
Protein-ligand complex (dis)similarity measure based on intermolecular contacts.  
Classification of drug binding sites with Deep Learning.   
Ligand binding site prediction and virtual screening.    
Prediction of protein binding sites and residues.  
Ultra-fast ligand docking with a hybrid force field.  
Sequence order-independent ligand binding site alignment.  
Extraction of molecular fragments from compound libraries.   
Ranking of dimer models with machine learning.  
Virtual synthesis of molecules from fragments with graph-based techniques.   
Template-based protein structure prediction with meta-threading and machine learning.  
Prediction of the toxicity and synthetic accessibility of small organic molecules.   
Optimization of synthetic protein sequences to stabilize the respective structures.  

Available datasets:
Docking of amino-oxazoles to bacterial biotin carboxylase isoforms.   
Comparative structure models of drug-target interactions from the Binding Database.    
Structure-based function annotation of the roundworm proteome.   
Structure-based function annotation of the human proteome.   
Structure-based function annotation of the fruitfly proteome.   
Structure-based function annotation of the proteomes of malaria parasites.   
Structure-based function annotation of the mouse proteome.   
Computational drug repositioning to find treatments for orphan diseases.   
Dataset to evaluate algorithms for binding site classification.   
Dataset to evaluate algorithms for ligand docking.   
Dataset to evaluate algorithms for binding site matching.   
Dataset to evaluate algorithms for binding site matching.   

Available gateways:
Ligand binding site prediction and virtual screening.    
Template-based protein structure prediction with meta-threading and machine learning.  

Available standalone software:
Analysis of aromatic interactions in protein-ligand complexes.  
Calculation of the optimal box size for ligand docking.  
Protein-ligand complex (dis)similarity measure based on intermolecular contacts.  
Classification of drug binding sites with Deep Learning.   
Ligand binding site prediction and virtual screening.    
Prediction of protein binding sites and residues.  
Ultra-fast ligand docking with a hybrid force field.  
Sequence order-independent ligand binding site alignment.  
Extraction of molecular fragments from compound libraries.   
Ranking of dimer models with machine learning.  
Virtual synthesis of molecules from fragments with graph-based techniques.   
Prediction of the toxicity and synthetic accessibility of small organic molecules.   
Optimization of synthetic protein sequences to stabilize the respective structures.  

Available datasets:
Docking of amino-oxazoles to bacterial biotin carboxylase isoforms.   
Comparative structure models of drug-target interactions from the Binding Database.    
Structure-based function annotation of the roundworm proteome.   
Structure-based function annotation of the human proteome.   
Structure-based function annotation of the fruitfly proteome.   
Structure-based function annotation of the proteomes of malaria parasites.   
Structure-based function annotation of the mouse proteome.   
Computational drug repositioning to find treatments for orphan diseases.   
Dataset to evaluate algorithms for binding site classification.   
Dataset to evaluate algorithms for ligand docking.   
Dataset to evaluate algorithms for binding site matching.   
Dataset to evaluate algorithms for binding site matching.   

Gateways are provided through SciGaP.

TOUGH-D1

If you use eFindSite, please cite the following papers:
1 Brylinski M, Feinstein WP. (2013) eFindSite: Improved prediction of ligand binding sites in protein models using meta-threading, machine learning and auxiliary ligands. J Comput Aided Mol Des 27 (6): 551-67.     
2 Feinstein WP, Brylinski M. (2014) eFindSite: Enhanced fingerprint-based virtual screening against predicted ligand binding sites in protein models. Mol Inf 33 (2): 135-50.     
If you use eThread, please cite the following papers:
1 Brylinski M, Lingam D. (2012) eThread: A highly optimized machine learning-based approach to meta-threading and the modeling of protein tertiary structures. PLoS ONE 7 (11): e50200.     
2 Brylinski M. (2013) Unleashing the power of meta-threading for evolution/structure-based function inference of proteins. Front Genet 4: 118.     
If you use eRankPPI, please cite the following papers:
1 Maheshwari S, Brylinski M. (2015) Predicted binding site information improves model ranking in protein docking using experimental and computer-generated target structures. BMC Struct Biol 15 (1): 23.     
2 Maheshwari S, Brylinski M. (2017) Across-proteome modeling of dimer structures for the bottom-up assembly of protein-protein interaction networks. BMC Bioinformatics 18 (1): 257.     
If you use eAromatic, please cite the following paper:
1 Brylinski M. (2018) Aromatic interactions at the ligand-protein interface: Implications for the development of docking scoring functions. Chem Biol Drug Des 91 (2): 380-90.     
If you use CMS, please cite the following paper:
1 Ding Y, Fang Y, Moreno J, Ramanujam J, Jarrell M, Brylinski M. (2016) Assessing the similarity of ligand binding conformations with the Contact Mode Score. Comput Biol Chem 64: 403-13.     
If you use GeauxDockd, please cite the following papers:
1 Ding Y, Fang Y, Feinstein WP, Ramanujam J, Koppelman DM, Moreno J, Brylinski M, Jarrell M. (2015) GeauxDock: A novel approach for mixed-resolution ligand docking using a descriptor-based force field. J Comput Chem 36 (27): 2013-26.     
2 Fang Y, Ding Y, Feinstein WP, Koppelman DM, Moreno J, Jarrell M, Ramanujam J, Brylinski M. (2016) GeauxDock: Accelerating structure-based virtual screening with heterogeneous computing. PLoS ONE 11 (7): e0158898.     
If you use eSynth, please cite the following paper:
1 Naderi M, Alvin C, Ding Y, Mukhopadhyay S, Brylinski M. (2016) A graph-based approach to construct target-focused libraries for virtual screening. J Cheminform 8: 14.     
If you use eBoxSize, please cite the following paper:
1 Feinstein WP, Brylinski M. (2015) Calculating an optimal box size for ligand docking and virtual screening against experimental and predicted binding pockets. J Cheminform 7 (1): 18.     
If you use the ACCase dataset, please cite the following paper:
1 Brylinski M, Waldrop GL. (2014) Computational redesign of bacterial biotin carboxylase inhibitors using structure-based virtual screening of combinatorial libraries. Molecules 19 (4): 4021-45.     
If you use eModel-BDB, please cite the following paper:
1 Naderi M, Govindaraj RG, Brylinski M. (2018) eModel-BDB: A database of comparative structure models of drug-target interactions from the Binding Database. GigaScience 7: 1-9.     
If you use eToxPred, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.     
If you use eFindSitePPI, please cite the following papers:
1 Maheshwari S, Brylinski M. (2015) Prediction of protein-protein interaction sites from weakly homologous template structures using meta-threading and machine learning. J Mol Recognit 28 (1): 35-48.     
2 Maheshwari S, Brylinski M. (2016) Template-based identification of protein-protein interfaces using eFindSite(PPI). Methods 93: 64-71.     
If you use TOUGH-D1, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.     
If you use TOUGH-D1, please cite the following paper:
1 Brylinski M. (2018) Aromatic interactions at the ligand-protein interface: Implications for the development of docking scoring functions. Chem Biol Drug Des 91 (2): 380-90.     
If you use TOUGH-M1, please cite the following paper:
1 Govindaraj RG, Brylinski M. (2018) Comparative assessment of strategies to identify similar ligand-binding pockets in proteins. BMC Bioinformatics 19 (1): 91.     
If you use eMatchSite, please cite the following papers:
1 Brylinski M. (2014) eMatchSite: sequence order-independent structure alignments of ligand binding pockets in protein models. PLoS Comput Biol 10 (9): e1003829.     
2 Brylinski M. (2017) Local alignment of ligand binding sites in proteins for polypharmacology and drug repositioning. Methods Mol Biol 1611: 109-22.     
If you use eMolFrag, please cite the following paper:
1 Liu T, Naderi M, Alvin C, Mukhopadhyay S, Brylinski M. (2017) Break down in order to build up: Decomposing small molecules for fragment-based drug design with eMolFrag. J Chem Inf Model 57 (4): 627-631.     
If you use eVolver, please cite the following papers:
1 Brylinski M. (2013) eVolver: an optimization engine for evolving protein sequences to stabilize the respective structures. BMC Res Notes 6 (1): 303.     
2 Brylinski M. (2013) The utility of artificially evolved sequences in protein threading and fold recognition. J Theor Biol 328: 77-88.     
If you use eRepo-ORP, please cite the following papers:
1 Govindaraj RG, Naderi M, Singha M, Lemoine J, Brylinski M. (2018) Large-scale computational drug repositioning to find treatments for rare diseases. NPJ Syst Biol Appl 4: 13.     
2 Brylinski M, Naderi M, Govindaraj RG, Lemoine J. (2018) eRepo-ORP: Exploring the opportunity space to combat orphan diseases with existing drugs. J Mol Biol 430 (15): 2266-2273.     
If you use eToxPred, please cite the following paper:
1 Pu L, Naderi M, Liu T, Wu HC, Mukhopadhyay S, Brylinski M. (2019) eToxPred: A machine learning-based approach to estimate the toxicity of drug candidates. BMC Pharmacol Toxicol 20 (1): 2.     
 

Aromatic stacking has long been recognized as one of key constituents of drug-protein interfaces. The dataset comprises the experimental structures of 3,079 ligand-protein complexes forming a total number of 8,148 interactions between 4,967 aromatic rings of organic ligands and 5,961 protein residues.

TOUGH-M1

If you use eFindSite, please cite the following papers:
1 Brylinski M, Feinstein WP. (2013) eFindSite: Improved prediction of ligand binding sites in protein models using meta-threading, machine learning and auxiliary ligands. J Comput Aided Mol Des 27 (6): 551-67.     
2 Feinstein WP, Brylinski M. (2014) eFindSite: Enhanced fingerprint-based virtual screening against predicted ligand binding sites in protein models. Mol Inf 33 (2): 135-50.     
If you use eThread, please cite the following papers:
1 Brylinski M, Lingam D. (2012) eThread: A highly optimized machine learning-based approach to meta-threading and the modeling of protein tertiary structures. PLoS ONE 7 (11): e50200.     
2 Brylinski M. (2013) Unleashing the power of meta-threading for evolution/structure-based function inference of proteins. Front Genet 4: 118.     
If you use eRankPPI, please cite the following papers:
1 Maheshwari S, Brylinski M. (2015) Predicted binding site information improves model ranking in protein docking using experimental and computer-generated target structures. BMC Struct Biol 15 (1): 23.     
2 Maheshwari S, Brylinski M. (2017) Across-proteome modeling of dimer structures for the bottom-up assembly of protein-protein interaction networks. BMC Bioinformatics 18 (1): 257.     
If you use eAromatic, please cite the following paper:
1 Brylinski M. (2018) Aromatic interactions at the ligand-protein interface: Implications for the development of docking scoring functions. Chem Biol Drug Des 91 (2): 380-90.     
If you use CMS, please cite the following paper:
1 Ding Y, Fang Y, Moreno J, Ramanujam J, Jarrell M, Brylinski M. (2016) Assessing the similarity of ligand binding conformations with the Contact Mode Score. Comput Biol Chem 64: 403-13.     
If you use GeauxDockd, please cite the following papers:
1 Ding Y, Fang Y, Feinstein WP, Ramanujam J, Koppelman DM, Moreno J, Brylinski M, Jarrell M. (2015) GeauxDock: A novel approach for mixed-resolution ligand docking using a descriptor-based force field. J Comput Chem 36 (27): 2013-26.     
2 Fang Y, Ding Y, Feinstein WP, Koppelman DM, Moreno J, Jarrell M, Ramanujam J, Brylinski M. (2016) GeauxDock: Accelerating structure-based virtual screening with heterogeneous computing. PLoS ONE 11 (7): e0158898.     
If you use eSynth, please cite the following paper:
1 Naderi M, Alvin C, Ding Y, Mukhopadhyay S, Brylinski M. (2016) A graph-based approach to construct target-focused libraries for virtual screening. J Cheminform 8: 14.     
If you use eBoxSize, please cite the following paper:
1 Feinstein WP, Brylinski M. (2015) Calculating an optimal box size for ligand docking and virtual screening against experimental and predicted binding pockets. J Cheminform 7 (1): 18.     
If you use the ACCase dataset, please cite the following paper:
1 Brylinski M, Waldrop GL. (2014) Computational redesign of bacterial biotin carboxylase inhibitors using structure-based virtual screening of combinatorial libraries. Molecules 19 (4): 4021-45.     
If you use eModel-BDB, please cite the following paper:
1 Naderi M, Govindaraj RG, Brylinski M. (2018) eModel-BDB: A database of comparative structure models of drug-target interactions from the Binding Database. GigaScience 7: 1-9.     
If you use eToxPred, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.     
If you use eFindSitePPI, please cite the following papers:
1 Maheshwari S, Brylinski M. (2015) Prediction of protein-protein interaction sites from weakly homologous template structures using meta-threading and machine learning. J Mol Recognit 28 (1): 35-48.     
2 Maheshwari S, Brylinski M. (2016) Template-based identification of protein-protein interfaces using eFindSite(PPI). Methods 93: 64-71.     
If you use TOUGH-D1, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.     
If you use TOUGH-D1, please cite the following paper:
1 Brylinski M. (2018) Aromatic interactions at the ligand-protein interface: Implications for the development of docking scoring functions. Chem Biol Drug Des 91 (2): 380-90.     
If you use TOUGH-M1, please cite the following paper:
1 Govindaraj RG, Brylinski M. (2018) Comparative assessment of strategies to identify similar ligand-binding pockets in proteins. BMC Bioinformatics 19 (1): 91.     
If you use eMatchSite, please cite the following papers:
1 Brylinski M. (2014) eMatchSite: sequence order-independent structure alignments of ligand binding pockets in protein models. PLoS Comput Biol 10 (9): e1003829.     
2 Brylinski M. (2017) Local alignment of ligand binding sites in proteins for polypharmacology and drug repositioning. Methods Mol Biol 1611: 109-22.     
If you use eMolFrag, please cite the following paper:
1 Liu T, Naderi M, Alvin C, Mukhopadhyay S, Brylinski M. (2017) Break down in order to build up: Decomposing small molecules for fragment-based drug design with eMolFrag. J Chem Inf Model 57 (4): 627-631.     
If you use eVolver, please cite the following papers:
1 Brylinski M. (2013) eVolver: an optimization engine for evolving protein sequences to stabilize the respective structures. BMC Res Notes 6 (1): 303.     
2 Brylinski M. (2013) The utility of artificially evolved sequences in protein threading and fold recognition. J Theor Biol 328: 77-88.     
If you use eRepo-ORP, please cite the following papers:
1 Govindaraj RG, Naderi M, Singha M, Lemoine J, Brylinski M. (2018) Large-scale computational drug repositioning to find treatments for rare diseases. NPJ Syst Biol Appl 4: 13.     
2 Brylinski M, Naderi M, Govindaraj RG, Lemoine J. (2018) eRepo-ORP: Exploring the opportunity space to combat orphan diseases with existing drugs. J Mol Biol 430 (15): 2266-2273.     
If you use eToxPred, please cite the following paper:
1 Pu L, Naderi M, Liu T, Wu HC, Mukhopadhyay S, Brylinski M. (2019) eToxPred: A machine learning-based approach to estimate the toxicity of drug candidates. BMC Pharmacol Toxicol 20 (1): 2.     
 

A non-redundant and representative dataset of ligand-binding pockets extracted from proteins with globally unrelated sequences and structures. The dataset comprises 7,524 experimental structures of protein-ligand complexes with pockets predicted by Fpocket. It is divided into two subsets, 505,116 pairs of pockets binding chemically similar molecules and 556,810 pairs of pockets binding different ligands.

Software and datasets

Available software:
Analysis of aromatic interactions in protein-ligand complexes.  
Calculation of the optimal box size for ligand docking.  
Protein-ligand complex (dis)similarity measure based on intermolecular contacts.  
Classification of drug binding sites with Deep Learning.   
Ligand binding site prediction and virtual screening.    
Prediction of protein binding sites and residues.  
Ultra-fast ligand docking with a hybrid force field.  
Sequence order-independent ligand binding site alignment.  
Extraction of molecular fragments from compound libraries.   
Ranking of dimer models with machine learning.  
Virtual synthesis of molecules from fragments with graph-based techniques.   
Template-based protein structure prediction with meta-threading and machine learning.  
Prediction of the toxicity and synthetic accessibility of small organic molecules.   
Optimization of synthetic protein sequences to stabilize the respective structures.  

Available datasets:
Docking of amino-oxazoles to bacterial biotin carboxylase isoforms.   
Comparative structure models of drug-target interactions from the Binding Database.    
Structure-based function annotation of the roundworm proteome.   
Structure-based function annotation of the human proteome.   
Structure-based function annotation of the fruitfly proteome.   
Structure-based function annotation of the proteomes of malaria parasites.   
Structure-based function annotation of the mouse proteome.   
Computational drug repositioning to find treatments for orphan diseases.   
Dataset to evaluate algorithms for binding site classification.   
Dataset to evaluate algorithms for ligand docking.   
Dataset to evaluate algorithms for binding site matching.   
Dataset to evaluate algorithms for binding site matching.   

Available gateways:
Ligand binding site prediction and virtual screening.    
Template-based protein structure prediction with meta-threading and machine learning.  

Available standalone software:
Analysis of aromatic interactions in protein-ligand complexes.  
Calculation of the optimal box size for ligand docking.  
Protein-ligand complex (dis)similarity measure based on intermolecular contacts.  
Classification of drug binding sites with Deep Learning.   
Ligand binding site prediction and virtual screening.    
Prediction of protein binding sites and residues.  
Ultra-fast ligand docking with a hybrid force field.  
Sequence order-independent ligand binding site alignment.  
Extraction of molecular fragments from compound libraries.   
Ranking of dimer models with machine learning.  
Virtual synthesis of molecules from fragments with graph-based techniques.   
Prediction of the toxicity and synthetic accessibility of small organic molecules.   
Optimization of synthetic protein sequences to stabilize the respective structures.  

Available datasets:
Docking of amino-oxazoles to bacterial biotin carboxylase isoforms.   
Comparative structure models of drug-target interactions from the Binding Database.    
Structure-based function annotation of the roundworm proteome.   
Structure-based function annotation of the human proteome.   
Structure-based function annotation of the fruitfly proteome.   
Structure-based function annotation of the proteomes of malaria parasites.   
Structure-based function annotation of the mouse proteome.   
Computational drug repositioning to find treatments for orphan diseases.   
Dataset to evaluate algorithms for binding site classification.   
Dataset to evaluate algorithms for ligand docking.   
Dataset to evaluate algorithms for binding site matching.   
Dataset to evaluate algorithms for binding site matching.   
   

eFindSitePPI

If you use eFindSite, please cite the following papers:
1 Brylinski M, Feinstein WP. (2013) eFindSite: Improved prediction of ligand binding sites in protein models using meta-threading, machine learning and auxiliary ligands. J Comput Aided Mol Des 27 (6): 551-67.     
2 Feinstein WP, Brylinski M. (2014) eFindSite: Enhanced fingerprint-based virtual screening against predicted ligand binding sites in protein models. Mol Inf 33 (2): 135-50.     
If you use eThread, please cite the following papers:
1 Brylinski M, Lingam D. (2012) eThread: A highly optimized machine learning-based approach to meta-threading and the modeling of protein tertiary structures. PLoS ONE 7 (11): e50200.     
2 Brylinski M. (2013) Unleashing the power of meta-threading for evolution/structure-based function inference of proteins. Front Genet 4: 118.     
If you use eRankPPI, please cite the following papers:
1 Maheshwari S, Brylinski M. (2015) Predicted binding site information improves model ranking in protein docking using experimental and computer-generated target structures. BMC Struct Biol 15 (1): 23.     
2 Maheshwari S, Brylinski M. (2017) Across-proteome modeling of dimer structures for the bottom-up assembly of protein-protein interaction networks. BMC Bioinformatics 18 (1): 257.     
If you use eAromatic, please cite the following paper:
1 Brylinski M. (2018) Aromatic interactions at the ligand-protein interface: Implications for the development of docking scoring functions. Chem Biol Drug Des 91 (2): 380-90.     
If you use CMS, please cite the following paper:
1 Ding Y, Fang Y, Moreno J, Ramanujam J, Jarrell M, Brylinski M. (2016) Assessing the similarity of ligand binding conformations with the Contact Mode Score. Comput Biol Chem 64: 403-13.     
If you use GeauxDockd, please cite the following papers:
1 Ding Y, Fang Y, Feinstein WP, Ramanujam J, Koppelman DM, Moreno J, Brylinski M, Jarrell M. (2015) GeauxDock: A novel approach for mixed-resolution ligand docking using a descriptor-based force field. J Comput Chem 36 (27): 2013-26.     
2 Fang Y, Ding Y, Feinstein WP, Koppelman DM, Moreno J, Jarrell M, Ramanujam J, Brylinski M. (2016) GeauxDock: Accelerating structure-based virtual screening with heterogeneous computing. PLoS ONE 11 (7): e0158898.     
If you use eSynth, please cite the following paper:
1 Naderi M, Alvin C, Ding Y, Mukhopadhyay S, Brylinski M. (2016) A graph-based approach to construct target-focused libraries for virtual screening. J Cheminform 8: 14.     
If you use eBoxSize, please cite the following paper:
1 Feinstein WP, Brylinski M. (2015) Calculating an optimal box size for ligand docking and virtual screening against experimental and predicted binding pockets. J Cheminform 7 (1): 18.     
If you use the ACCase dataset, please cite the following paper:
1 Brylinski M, Waldrop GL. (2014) Computational redesign of bacterial biotin carboxylase inhibitors using structure-based virtual screening of combinatorial libraries. Molecules 19 (4): 4021-45.     
If you use eModel-BDB, please cite the following paper:
1 Naderi M, Govindaraj RG, Brylinski M. (2018) eModel-BDB: A database of comparative structure models of drug-target interactions from the Binding Database. GigaScience 7: 1-9.     
If you use eToxPred, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.     
If you use eFindSitePPI, please cite the following papers:
1 Maheshwari S, Brylinski M. (2015) Prediction of protein-protein interaction sites from weakly homologous template structures using meta-threading and machine learning. J Mol Recognit 28 (1): 35-48.     
2 Maheshwari S, Brylinski M. (2016) Template-based identification of protein-protein interfaces using eFindSite(PPI). Methods 93: 64-71.     
If you use TOUGH-D1, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.     
If you use TOUGH-D1, please cite the following paper:
1 Brylinski M. (2018) Aromatic interactions at the ligand-protein interface: Implications for the development of docking scoring functions. Chem Biol Drug Des 91 (2): 380-90.     
If you use TOUGH-M1, please cite the following paper:
1 Govindaraj RG, Brylinski M. (2018) Comparative assessment of strategies to identify similar ligand-binding pockets in proteins. BMC Bioinformatics 19 (1): 91.     
If you use eMatchSite, please cite the following papers:
1 Brylinski M. (2014) eMatchSite: sequence order-independent structure alignments of ligand binding pockets in protein models. PLoS Comput Biol 10 (9): e1003829.     
2 Brylinski M. (2017) Local alignment of ligand binding sites in proteins for polypharmacology and drug repositioning. Methods Mol Biol 1611: 109-22.     
If you use eMolFrag, please cite the following paper:
1 Liu T, Naderi M, Alvin C, Mukhopadhyay S, Brylinski M. (2017) Break down in order to build up: Decomposing small molecules for fragment-based drug design with eMolFrag. J Chem Inf Model 57 (4): 627-631.     
If you use eVolver, please cite the following papers:
1 Brylinski M. (2013) eVolver: an optimization engine for evolving protein sequences to stabilize the respective structures. BMC Res Notes 6 (1): 303.     
2 Brylinski M. (2013) The utility of artificially evolved sequences in protein threading and fold recognition. J Theor Biol 328: 77-88.     
If you use eRepo-ORP, please cite the following papers:
1 Govindaraj RG, Naderi M, Singha M, Lemoine J, Brylinski M. (2018) Large-scale computational drug repositioning to find treatments for rare diseases. NPJ Syst Biol Appl 4: 13.     
2 Brylinski M, Naderi M, Govindaraj RG, Lemoine J. (2018) eRepo-ORP: Exploring the opportunity space to combat orphan diseases with existing drugs. J Mol Biol 430 (15): 2266-2273.     
If you use eToxPred, please cite the following paper:
1 Pu L, Naderi M, Liu T, Wu HC, Mukhopadhyay S, Brylinski M. (2019) eToxPred: A machine learning-based approach to estimate the toxicity of drug candidates. BMC Pharmacol Toxicol 20 (1): 2.     
 

A program to detect protein binding sites and residues with meta-threading. eFindSitePPI also predicts interfacial geometry and specific interactions stabilizing protein-protein complexes, such as hydrogen bonds, salt bridges, aromatic and hydrophobic interactions.

  

eFindSite

If you use eFindSite, please cite the following papers:
1 Brylinski M, Feinstein WP. (2013) eFindSite: Improved prediction of ligand binding sites in protein models using meta-threading, machine learning and auxiliary ligands. J Comput Aided Mol Des 27 (6): 551-67.     
2 Feinstein WP, Brylinski M. (2014) eFindSite: Enhanced fingerprint-based virtual screening against predicted ligand binding sites in protein models. Mol Inf 33 (2): 135-50.     
If you use eThread, please cite the following papers:
1 Brylinski M, Lingam D. (2012) eThread: A highly optimized machine learning-based approach to meta-threading and the modeling of protein tertiary structures. PLoS ONE 7 (11): e50200.     
2 Brylinski M. (2013) Unleashing the power of meta-threading for evolution/structure-based function inference of proteins. Front Genet 4: 118.     
If you use eRankPPI, please cite the following papers:
1 Maheshwari S, Brylinski M. (2015) Predicted binding site information improves model ranking in protein docking using experimental and computer-generated target structures. BMC Struct Biol 15 (1): 23.     
2 Maheshwari S, Brylinski M. (2017) Across-proteome modeling of dimer structures for the bottom-up assembly of protein-protein interaction networks. BMC Bioinformatics 18 (1): 257.     
If you use eAromatic, please cite the following paper:
1 Brylinski M. (2018) Aromatic interactions at the ligand-protein interface: Implications for the development of docking scoring functions. Chem Biol Drug Des 91 (2): 380-90.     
If you use CMS, please cite the following paper:
1 Ding Y, Fang Y, Moreno J, Ramanujam J, Jarrell M, Brylinski M. (2016) Assessing the similarity of ligand binding conformations with the Contact Mode Score. Comput Biol Chem 64: 403-13.     
If you use GeauxDockd, please cite the following papers:
1 Ding Y, Fang Y, Feinstein WP, Ramanujam J, Koppelman DM, Moreno J, Brylinski M, Jarrell M. (2015) GeauxDock: A novel approach for mixed-resolution ligand docking using a descriptor-based force field. J Comput Chem 36 (27): 2013-26.     
2 Fang Y, Ding Y, Feinstein WP, Koppelman DM, Moreno J, Jarrell M, Ramanujam J, Brylinski M. (2016) GeauxDock: Accelerating structure-based virtual screening with heterogeneous computing. PLoS ONE 11 (7): e0158898.     
If you use eSynth, please cite the following paper:
1 Naderi M, Alvin C, Ding Y, Mukhopadhyay S, Brylinski M. (2016) A graph-based approach to construct target-focused libraries for virtual screening. J Cheminform 8: 14.     
If you use eBoxSize, please cite the following paper:
1 Feinstein WP, Brylinski M. (2015) Calculating an optimal box size for ligand docking and virtual screening against experimental and predicted binding pockets. J Cheminform 7 (1): 18.     
If you use the ACCase dataset, please cite the following paper:
1 Brylinski M, Waldrop GL. (2014) Computational redesign of bacterial biotin carboxylase inhibitors using structure-based virtual screening of combinatorial libraries. Molecules 19 (4): 4021-45.     
If you use eModel-BDB, please cite the following paper:
1 Naderi M, Govindaraj RG, Brylinski M. (2018) eModel-BDB: A database of comparative structure models of drug-target interactions from the Binding Database. GigaScience 7: 1-9.     
If you use eToxPred, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.     
If you use eFindSitePPI, please cite the following papers:
1 Maheshwari S, Brylinski M. (2015) Prediction of protein-protein interaction sites from weakly homologous template structures using meta-threading and machine learning. J Mol Recognit 28 (1): 35-48.     
2 Maheshwari S, Brylinski M. (2016) Template-based identification of protein-protein interfaces using eFindSite(PPI). Methods 93: 64-71.     
If you use TOUGH-D1, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.     
If you use TOUGH-D1, please cite the following paper:
1 Brylinski M. (2018) Aromatic interactions at the ligand-protein interface: Implications for the development of docking scoring functions. Chem Biol Drug Des 91 (2): 380-90.     
If you use TOUGH-M1, please cite the following paper:
1 Govindaraj RG, Brylinski M. (2018) Comparative assessment of strategies to identify similar ligand-binding pockets in proteins. BMC Bioinformatics 19 (1): 91.     
If you use eMatchSite, please cite the following papers:
1 Brylinski M. (2014) eMatchSite: sequence order-independent structure alignments of ligand binding pockets in protein models. PLoS Comput Biol 10 (9): e1003829.     
2 Brylinski M. (2017) Local alignment of ligand binding sites in proteins for polypharmacology and drug repositioning. Methods Mol Biol 1611: 109-22.     
If you use eMolFrag, please cite the following paper:
1 Liu T, Naderi M, Alvin C, Mukhopadhyay S, Brylinski M. (2017) Break down in order to build up: Decomposing small molecules for fragment-based drug design with eMolFrag. J Chem Inf Model 57 (4): 627-631.     
If you use eVolver, please cite the following papers:
1 Brylinski M. (2013) eVolver: an optimization engine for evolving protein sequences to stabilize the respective structures. BMC Res Notes 6 (1): 303.     
2 Brylinski M. (2013) The utility of artificially evolved sequences in protein threading and fold recognition. J Theor Biol 328: 77-88.     
If you use eRepo-ORP, please cite the following papers:
1 Govindaraj RG, Naderi M, Singha M, Lemoine J, Brylinski M. (2018) Large-scale computational drug repositioning to find treatments for rare diseases. NPJ Syst Biol Appl 4: 13.     
2 Brylinski M, Naderi M, Govindaraj RG, Lemoine J. (2018) eRepo-ORP: Exploring the opportunity space to combat orphan diseases with existing drugs. J Mol Biol 430 (15): 2266-2273.     
If you use eToxPred, please cite the following paper:
1 Pu L, Naderi M, Liu T, Wu HC, Mukhopadhyay S, Brylinski M. (2019) eToxPred: A machine learning-based approach to estimate the toxicity of drug candidates. BMC Pharmacol Toxicol 20 (1): 2.     
 

A ligand-binding site prediction and virtual screening algorithm detecting common ligand-binding sites in a set of evolutionarily related proteins identified with threading/fold recognition. eFindSite also performs ligand-based virtual screening against identified pockets.

  
Subscribe to