Search

Your search keyword '"Francoeur, Paul"' showing total 22 results
Start Over Author "Francoeur, Paul"
22 results on '"Francoeur, Paul"'

3. Advancing Machine Learning for Small Molecule Property Prediction

Author

Francoeur, Paul Glidden and Francoeur, Paul Glidden

Abstract

Recently, machine learning (ML) models have rapidly become the state of the art at various molecular property prediction tasks. The speed of ML models, without sacrificing accuracy, makes them especially attractive in screening contexts, where a large number of potential molecules need to reduced to a number feasible for experimental testing. However, the black box nature and rapid advancement of ML models has resulted in a proliferation of input representations and model architectures. This makes selection of the ``best'' model architecture and input representation for a given task difficult. Additionally, while ML models thrive on having large datasets for training, the amount of labeled structures for properties like receptor-ligand binding affinity is small. This work sets out to help address these two problems with ML models for molecular property prediction. First, a wide variety of molecular input representations and ML model architectures were trained to predict calculated molecular properties. The characterization of both the performance of these models, and how well they utilize the training data, yields suggestions on how to best select a ML approach for more realistic property prediction tasks, given the amount of compute resources and training data available. Next, in order to address the lack of labeled structural data, a new dataset, CrossDocked2020, was created to expand the PDBbind dataset to expand the available binding pose classification data. By docking ligands into non-cognate, but similar, receptors we were able to expand the ~200,000 poses available from the PDBbind General set into ~22.5 million poses in CrossDocked2020. Various data imputation techniques were then explored to see if they could improve the binding affinity regression of a convolutional neural network (CNN) on CrossDocked2020. The utilization of an ensemble of CNN models to impute the missing binding affinity labels of complexes in CrossDocked2020 had a small, but significant

Published
2024

11. Additional file 1 of GNINA 1.0: molecular docking with deep learning

Author

McNutt, Andrew T., Francoeur, Paul, Aggarwal, Rishal, Masuda, Tomohide, Meli, Rocco, Ragoza, Matthew, Sunseri, Jocelyn, and Koes, David Ryan

Abstract

Additional file 1: Figure S1: Analyzing the effect on docking performance when downsampling the cross-docking dataset to include a fraction of the protein-ligand pairs per pocket. Figure S2: Comparison of the RMSD(Å) of the top 3 poses output by Gnina with no CNN in the docking pipeline and Smina. Figure S3: Comparison of the minimum and maximum RMSD(Å) poses output by Gnina with no CNN in the docking pipeline and Smina. Figure S4: Cross-docking results using a defined binding pocket. Figure S5: Evaluating different values of cnn emp weight on docking performance when using the Default Ensemble. Figure S6: Time to perform one docking run when using the Default Ensemble for “rescore” or refine” in comparison to only using the Vina scoring function. Figure S7: Evaluating the effect on docking performance when the value of autobox add is changed while using the Default Ensemble for rescoring. Figure S8: Evaluating the effect on docking performance when the value of cnn rotation is changed while using the Default Ensemble for rescoring. Figure S9: Evaluating the effect on docking performance when the value of min rmsd filter is changed while using the Default Ensemble for rescoring on both the redocking and cross-docking datasets. Figure S10: Cross-docking results using the whole protein as the defined binding pocket. Figure S1: Ligand RMSD distributions for the top pose in the cross-docking dataset, for both flexible and rigid docking. Figure S12: Thresholding the cross-docking results by CNNscore and evaluating Top1(%) per pocket. A pose is retained if the CNN score is greater than the value on the x-axis. Grey cells indicate that no poses are left in the pocket. Table S1: Optimal Model Ensemble Selection. Performance given by Top1, the percent of systems with RMSD less than 2 Å from the top pose to the known binding pose. Table S2: Average time to dock one protein-ligand system from the filtered PDBbind core set v.2016. Comparing runtime when GPU is used to when no GPU is used for docking. Table S3: Pocket, ligand and receptor identifiers for the systems excluded from the analysis of flexible docking, together with the reason for exclusion.

Published
2021
Full Text
View/download PDF

18. Abstract 1662: Development and validation of humanized mice models implanted with patient derived colorectal cancer xenografts

Author

Capasso, Anna, primary, Lang, Julie, additional, Pitts, Todd M., additional, Davis, Sarah Lindsey, additional, Lieu, Christopher, additional, Kopetz, Scott, additional, Bagby, Stacey, additional, Francoeur, Paul, additional, Tentler, John J., additional, Slansky, Jill, additional, Pelanda, Roberta, additional, and Eckhardt, Gail, additional

Published
2017
Full Text
View/download PDF

19. HDAC and PD-1 inhibition in humanized triple-negative breast cancer xenografts.

Author

Capasso, Anna, primary, Lang, Julie, additional, Pitts, Todd M., additional, Francoeur, Paul, additional, Davis, Sarah Lindsey, additional, Lieu, Christopher Hanyoung, additional, Bagby, Stacey M, additional, Tentler, John J., additional, Piscopio, Anthony d, additional, Diamond, Jennifer Robinson, additional, Pelanda, Roberta, additional, and Eckhardt, S. Gail, additional

Published
2017
Full Text
View/download PDF

20. BigBind: Learning from Nonstructural Data for Structure-Based Virtual Screening

Author

Brocidiacono, Michael, Francoeur, Paul, Aggarwal, Rishal, Popov, Konstantin I., Koes, David Ryan, and Tropsha, Alexander

Abstract

Deep learning methods that predict protein–ligand binding have recently been used for structure-based virtual screening. Many such models have been trained using protein–ligand complexes with known crystal structures and activities from the PDBBind data set. However, because PDBbind only includes 20K complexes, models typically fail to generalize to new targets, and model performance is on par with models trained with only ligand information. Conversely, the ChEMBL database contains a wealth of chemical activity information but includes no information about binding poses. We introduce BigBind, a data set that maps ChEMBL activity data to proteins from the CrossDocked data set. BigBind comprises 583 K ligand activities and includes 3D structures of the protein binding pockets. Additionally, we augmented the data by adding an equal number of putative inactives for each target. Using this data, we developed Banana(basic neural network for binding affinity), a neural network-based model to classify active from inactive compounds, defined by a 10 μM cutoff. Our model achieved an AUC of 0.72 on BigBind’s test set, while a ligand-only model achieved an AUC of 0.59. Furthermore, Bananaachieved competitive performance on the LIT-PCBA benchmark (median EF1% 1.81) while running 16,000 times faster than molecular docking with Gnina. We suggest that Banana, as well as other models trained on this data set, will significantly improve the outcomes of prospective virtual screening tasks.

Published
2024
Full Text
View/download PDF

22. MAIL BAG.

Author

Petrauskas, Edmundas, Crandall, Eve, Beagan, Catherine, Jacob, Maria, Stokes, Irene, Kutcher, Victor, Willis, Jim, Barrie, Susan, Meister, Don, Bishop Jr., Reginald, and Francoeur, Paul

Subjects
LETTERS to the editor, IMMIGRANTS, DEATH of teenagers, CRIMINALS
Abstract

Several letters to the editor are presented in response to articles in previous issues including "Do immigrants need rules? The debate rages on, " "The End," and "Release and catch." All three articles appeared in the March 5, 2007 issue.

Published
2007

Catalog

Books, media, physical & digital resources
See catalog results