@article{zin_borrel_fourches_2020, title={Benchmarking 2D/3D/MD-QSAR Models for Imatinib Derivatives: How Far Can We Predict?}, volume={60}, ISSN={["1549-960X"]}, DOI={10.1021/acs.jcim.0c00200}, abstractNote={Imatinib, a 2-phenylaminopyridine-based BCR-ABL tyrosine kinase inhibitor, is a highly effective drug for treating Chronic Myeloid Leukemia (CML). However, cases of drug resistance are constantly emerging due to various mutations in the ABL kinase domain; thus, it is crucial to identify novel bioactive analogues. Reliable QSAR models and molecular docking protocols have been shown to facilitate the discovery of new compounds from chemical libraries prior to experimental testing. However, as the vast majority of QSAR models strictly relies on 2D descriptors, the rise of 3D descriptors directly computed from molecular dynamics simulations offers new opportunities to potentially augment the reliability of QSAR models. Herein, we employed molecular docking and molecular dynamics on a large series of Imatinib derivatives and developed an ensemble of QSAR models relying on deep neural nets (DNN) and hybrid sets of 2D/3D/MD descriptors in order to predict the binding affinity and inhibition potencies of those compounds. Through rigorous validation tests, we showed that our DNN regression models achieved excellent external prediction performances for the pKi data set (n = 555, R2 ≥ 0.71. and MAE ≤ 0.85), and the pIC50 data set (n = 306, R2 ≥ 0.54. and MAE ≤ 0.71) with strict validation protocols based on external test sets and 10-fold native and nested cross validations. Interestingly, the best DNN and random forest models performed similarly across all descriptor sets. In fact, for this particular series of compounds, our external test results suggest that incorporating additional 3D protein-ligand binding site fingerprint, descriptors, or even MD time-series descriptors did not significantly improve the overall R2 but lowered the MAE of DNN QSAR models. Those augmented models could still help in identifying and understanding the key dynamic protein-ligand interactions to be optimized for further molecular design.}, number={7}, journal={JOURNAL OF CHEMICAL INFORMATION AND MODELING}, author={Zin, Phyo Phyo Kyaw and Borrel, Alexandre and Fourches, Denis}, year={2020}, month={Jul}, pages={3342–3360} }
 @article{zin_williams_ekins_2020, title={Cheminformatics Analysis and Modeling with MacrolactoneDB}, volume={10}, ISSN={2045-2322}, url={http://dx.doi.org/10.1038/s41598-020-63192-4}, DOI={10.1038/s41598-020-63192-4}, abstractNote={Abstract}, number={1}, journal={Scientific Reports}, publisher={Springer Science and Business Media LLC}, author={Zin, Phyo Phyo Kyaw and Williams, Gavin J. and Ekins, Sean}, year={2020}, month={Apr} }
 @article{kuenemann_zin_kuchibhotla_fourches_2020, title={Cheminformatics Modeling of Closantel Analogues for Treating River Blindness}, volume={1}, url={https://doi.org/10.26434/chemrxiv.11606019.v1}, DOI={10.26434/chemrxiv.11606019.v1}, abstractNote={Onchocerciasis (also known as river blindness) is a neglected tropical disease caused by the Onchocerca volvulus parasitic nematode. Currently, the only approved drug for treating this disease is ivermectin, which is a broad-spectrum antiparasitic agent. However, signs of resistance towards ivermectin have started to emerge. New therapeutic agents are thus urgently needed. The OvCHT1 chitinase enzyme from O. volvulus has been established as a relevant biological target for combatting river blindness. The veterinary anthelmintic drug closantel has been found to be a potent, micro-molar OvCHT1 inhibitor. Herein, we investigated the chemical space of closantel and all its synthesized analogues, focusing on the analysis of their potential binding modes towards OvCHT1. First, we conducted an unsupervised hierarchical clustering to group highly similar analogues and explore structure-activity relationships. Second, we conducted a structure-based molecular docking to predict and study the binding modes of all 57 closantel analogues in the active site of OvCHT1. Third, we screened more than 4 million lead-like compounds from the ZINC library to identify other structurally similar ligands that could potentially bind to OvCHT1. The cheminformatics analysis of the closantel analogues illustrated how minor structural changes in closantel analogues can impact their OvCHT1 activity.}, publisher={American Chemical Society (ACS)}, author={Kuenemann, Melaine A. and Zin, Phyo Phyo and Kuchibhotla, Sravya and Fourches, Denis}, year={2020}, month={Jan} }
 @article{makarov_salina_reynolds_zin_ekins_2020, title={Molecule Property Analyses of Active Compounds for Mycobacterium tuberculosis}, volume={63}, ISSN={["1520-4804"]}, DOI={10.1021/acs.jmedchem.9b02075}, abstractNote={Tuberculosis (TB) continues to claim the lives of around 1.7 million people per year. Most concerning are the reports of multidrug drug resistance. Paradoxically, this global health pandemic is demanding new therapies when resources and interest are waning. However, continued tuberculosis drug discovery is critical to address the global health need and burgeoning multidrug resistance. Many diverse classes of antitubercular compounds have been identified with activity in vitro and in vivo. Our analyses of over 100 active leads are representative of thousands of active compounds generated over the past decade suggesting they come from few chemical classes or natural product sources. We are therefore repeatedly identifying compounds that are similar to those that preceded them. Our molecule-centred cheminformatics analyses points to the need to dramatically increase the diversity of chemical libraries tested and get outside of the historic Mtb property space if we are to generate novel improved antitubercular leads.}, number={17}, journal={JOURNAL OF MEDICINAL CHEMISTRY}, author={Makarov, Vadim and Salina, Elena and Reynolds, Robert C. and Zin, Phyo Phyo Kyaw and Ekins, Sean}, year={2020}, month={Sep}, pages={8917–8955} }
 @article{zin_williams_fourches_2020, title={SIME: synthetic insight-based macrolide enumerator to generate the V1B library of 1 billion macrolides}, volume={12}, ISSN={1758-2946}, url={http://dx.doi.org/10.1186/s13321-020-00427-6}, DOI={10.1186/s13321-020-00427-6}, abstractNote={Abstract}, number={1}, journal={Journal of Cheminformatics}, publisher={Springer Science and Business Media LLC}, author={Zin, Phyo Phyo Kyaw and Williams, Gavin and Fourches, Denis}, year={2020}, month={Apr} }
 @article{odenkirk_zin_ash_reif_fourches_baker_2020, title={Structural-based connectivity and omic phenotype evaluations (SCOPE): a cheminformatics toolbox for investigating lipidomic changes in complex systems}, volume={145}, ISSN={["1364-5528"]}, DOI={10.1039/d0an01638a}, abstractNote={SCOPE is a toolbox for expanding upon lipid data interpretation capabilities. Herein we utilize SCOPE to explore how lipid structure, biological connections and metadata linkages contribute to the results observed from lipidomic experiments.}, number={22}, journal={ANALYST}, author={Odenkirk, Melanie T. and Zin, Phyo Phyo K. and Ash, Jeremy R. and Reif, David M. and Fourches, Denis and Baker, Erin S.}, year={2020}, month={Nov}, pages={7197–7209} }
 @article{zin_williams_fourches_2018, title={Cheminformatics-based enumeration and analysis of large libraries of macrolide scaffolds}, volume={10}, ISSN={1758-2946}, url={http://dx.doi.org/10.1186/s13321-018-0307-6}, DOI={10.1186/s13321-018-0307-6}, abstractNote={We report on the development of a cheminformatics enumeration technology and the analysis of a resulting large dataset of virtual macrolide scaffolds. Although macrolides have been shown to have valuable biological properties, there is no ready-to-screen virtual library of diverse macrolides in the public domain. Conducting molecular modeling (especially virtual screening) of these complex molecules is highly relevant as the organic synthesis of these compounds, when feasible, typically requires many synthetic steps, and thus dramatically slows the discovery of new bioactive macrolides. Herein, we introduce a cheminformatics approach and associated software that allows for designing and generating libraries of virtual macrocycle/macrolide scaffolds with user-defined constitutional and structural constraints (e.g., types and numbers of structural motifs to be included in the macrocycle, ring size, maximum number of compounds generated). To study the chemical diversity of such generated molecules, we enumerated V1M (Virtual 1 million Macrolide scaffolds) library, each containing twelve common structural motifs. For each macrolide scaffold, we calculated several key properties, such as molecular weight, hydrogen bond donors/acceptors, topological polar surface area. In this study, we discuss (1) the initial concept and current features of our PKS (polyketides) Enumerator software, (2) the chemical diversity and distribution of structural motifs in V1M library, and (3) the unique opportunities for future virtual screening of such enumerated ensembles of macrolides. Importantly, V1M is provided in the Supplementary Material of this paper allowing other researchers to conduct any type of molecular modeling and virtual screening studies. Therefore, this technology for enumerating extremely large libraries of macrolide scaffolds could hold a unique potential in the field of computational chemistry and drug discovery for rational designing of new antibiotics and anti-cancer agents.}, number={1}, journal={Journal of Cheminformatics}, publisher={Springer Science and Business Media LLC}, author={Zin, Phyo Phyo Kyaw and Williams, Gavin and Fourches, Denis}, year={2018}, month={Nov} }