February 7, 2023
NodeCoder: a graph-based machine learning platform to predict active sites of modeled protein structures
Nasim Abdollahi, Seyed Ali Madani Tonekaboni, Jay Huang, Bo Wang, and Stephen MacKinnon.
January 23, 2023
Synthesis of Carvone Derivatives and In Silico and In Vitro Screening of Anti-Inflammatory Activity in Murine Macrophages*
Gabriela Moço, Cátia Sousa, Ana Capitão, Stephen Scott MacKinnon, Alcino Jorge Leitão, and Alexandrina Ferreira Mendes.
December 2, 2021
Novel structural-related analogs of PFI-3 (SRAPs) that target the BRG1 catalytic subunit of the SWI/SNF complex increase the activity of temozolomide in glioblastoma cells*
Yali He, Chuanhe Yang, Yinan Wang, Joshua R. Sacher, Michelle M. Sims, Lawrence M. Pfeffer, and Duane D. Miller.
December 2, 2021
Multiscale interactome analysis coupled with off-target drug predictions reveals drug repurposing candidates for human coronavirus disease*
Michael G. Sugiyama, Haotian Cui, Dar’ya S. Redka, Mehran Karimzadeh, Edurne Rujas, Hassaan Maan, Sikander Hayat, Kyle Cheung, Rahul Misra, Joseph B. McPhee, Russell D. Viirre, Andrew Haller, Roberto J. Botelho, Raffi Karshafian, Sarah A. Sabatinos, Gregory D. Fairn, Seyed Ali Madani Tonekaboni, Andreas Windemuth, Jean-Philippe Julien, Vijay Shahani, Stephen S. MacKinnon, Bo Wang, and Costin N. Antonescu.
November 23, 2021
Proteome-Scale Drug-Target Interaction Predictions: Approaches and Applications*
Stephen Scott MacKinnon, S. A. Madani Tonekaboni, and Andreas Windemuth.
June 28, 2021
Genetic variability of the SARS-CoV-2 pocketome*
Setayesh Yazdani, Nicola De Maio, Yining Ding, Vijay Shahani, Nick Goldman, and Matthieu Schapira.
April 13, 2021
Multiscale interactome analysis coupled with off-target drug predictions reveals drug repurposing candidates for human coronavirus disease
Michael G. Sugiyama, Haotian Cui, Dar’ya S. Redka, Mehran Karimzadeh, Edurne Rujas, Hassaan Maan, Sikander Hayat, Kyle Cheung, … (+15 more).
August 17, 2020
Assessing methods and obstacles in chemical space exploration*
Shawn Reeves, Benjamin DiFrancesco, Vijay Shahani, Stephen MacKinnon, Andreas Windemuth, and Andrew Brereton.
June 3, 2020
Learning across label confidence distributions using Filtered Transfer Learning*
Seyed Ali Madani Tonekaboni, Andrew E. Brereton, Zhaleh Safikhani, Andreas Windemuth, Benjamin Haibe-Kains, and Stephen MacKinnon.
May 19, 2020
Predicting drug properties with parameter-free machine learning: Pareto-Optimal Embedded Modeling (POEM)*
Andrew E. Brereton, Stephen MacKinnon, Zhaleh Safikhani, Shawn Reeves, Sana Alwash, Vijay Shahani, and Andreas Windemuth.
April 6, 2020
PolypharmDB quickly identifies repurposed drug candidates for COVID-19
Dar’ya S. Redka, Stephen S. MacKinnon, Melissa Landon, AndreasWindemuth, Naheed Kurji, and Vijay Shahani.
March 23, 2018
Structural pharmacogenomics identifies putative binding sites*
Steven V. Molinski, Vijay M. Shahani, Adithya S. Subramanian, Stephen S. MacKinnon, Geoffrey Woollard, Marcon Laforet, Onofrio Laselva, Leonard D. Morayniss, Christine E. Bear, and Andreas Windemuth.
November 14, 2017
Giving drugs a second chance: Overcoming regulatory and financial hurdles in repurposing approved drugs as cancer therapeutics*
J. Javier Hernandez, Michael Pryszlak, Lindsay Smith, Connor Yanchus, Naheed Kurji, Vijay M. Shahani, and Steven V. Molinski.
September 21, 2017
The antiretroviral agent nelfinavir mesylate: A potential therapy for systemic sclerosis*
Cecilia G. Sanchez, Steven V. Molinski, Rafael Gongora, Meredith Sosulski, Taylor Fuselier, Stephen S. MacKinnon, Debasis Mondal, and Joseph A. Lasky.
August 23, 2017
Structural coverage of the proteome for pharmaceutical applications*
Joseph C. Somody, Stephen S. MacKinnon, and Andreas Windemuth.
December 17, 2016
Computational proteome-wide screening predicts neurotoxic drug-protein interactome for the investigational analgesic BIA 10-2474*
Steven V. Molinski, Vijay M. Shahani, Stephen S. MacKinnon, Leonard D. Morayniss, Marc Laforet, Geoffrey Woollard, Naheed Kurji, Cecilia G. Sanchez, Shoshana J. Wodak, and Andreas Windemuth.
April 19, 2023
Cyclica’s MatchMaker™ complements DNA Encoded Library (DEL) experimental techniques for predicting drug discovery targets
This study aimed to understand the strengths and synergies between DNA encoded libraries (DEL) technology and Cyclica’s MatchMaker™ for improving the drug discovery process.
White paper | November 3, 2022
Exploring the unexplored, drugging the undrugged: How Cyclica is opening new frontiers in drug discovery
By exploring the entire protein universe, Cyclica is industrializing drug discovery by creating a large, sustainable, and risk-adjusted portfolio of drug programs.
April 28, 2022
Designing chemical probes for DCAF1 using MatchMaker™
Cyclica partnered with the Structural Genomics Consortium (SGC) to design a chemical probe for DCAF1, a low data WDR protein.
July 28, 2021
Cyclica’s Ligand Design platform identifies active molecules for repurposing which can be used to treat Parkinson’s
Cyclica partners with Kalia labs to accelerate the discovery of critical medicines for patients suffering from neurodegenerative diseases.
June 29, 2021
Comparison of MatchMaker to DeepConv-DTI reveals superior performance and compute efficiency for predicting drug-target interactions
Cyclica’s MatchMaker deep learning engine excels at dataless protein targets.
June 25, 2021
MatchMaker™ Validation on newly published protein-ligand interaction dataset
Proteome screening, powered by Cyclica’s MatchMaker deep learning engine, predicts primary protein targets of newly published ligands.
April 1, 2021
MatchMaker Proteome Screening identified more drug-target interactions than CETSA® MS, KiNativ™ or affinity purification
MatchMaker compared with experimental approaches for target deconvolution.
Predicting hERG channel liabilities
POEM, Cyclica’s supervised machine learning algorithm, predicts hERG activity for small molecules.
Rapid discovery of a sirtuin 2 inhibitor using Ligand Design
Ligand Design leverages polypharmacology to find both specific and multi-targeted hits through the exploration of a commercial library.
Proteome Screening with MatchMaker achieves performance comparable to experimental techniques
MatchMaker-powered Proteome Screening identifies more known binders of methotrexate, dasatinib, and panobinostat compared to thermal proteome profiling (TPP).
Evaluating Cyclica’s AI-based ADMET Prediction tool
The ADMET Prediction tool consistently outperforms traditional QSAR approaches for predicting pharmacokinetic and toxicity properties.
The Ligand Express™ platform guides drug repurposing study
Top drug repositioning candidates selected by anticipating the biological consequences of predicted ligand-protein interactions.
MatchMaker: A leap forward in proteome screening beyond molecular docking
MatchMaker combines molecular biophysics and deep learning to predict binding of new drug molecules to all proteins with high speed, accuracy, and generalizability, moving beyond the reliance of molecular docking.
