@article{MTMT:32869275,
	title = {Maximizing the integration of virtual and experimental screening in hit discovery},
	url = {https://m2.mtmt.hu/api/publication/32869275},
	author = {Bajusz, Dávid and Keserű, György Miklós},
	doi = {10.1080/17460441.2022.2085685},
	journal-iso = {EXPERT OPIN DRUG DIS},
	journal = {EXPERT OPINION ON DRUG DISCOVERY},
	volume = {17},
	unique-id = {32869275},
	issn = {1746-0441},
	year = {2022},
	eissn = {1746-045X},
	pages = {629-640},
	orcid-numbers = {Bajusz, Dávid/0000-0003-4277-9481}
}

@article{MTMT:33147400,
	title = {Fingerprint-based deep neural networks can model thermodynamic and optical properties of eumelanin DHI dimers},
	url = {https://m2.mtmt.hu/api/publication/33147400},
	author = {Bosch, Daniel and Wang, Jun and Blancafort, Lluís},
	doi = {10.1039/D2SC02461F},
	journal-iso = {CHEM SCI},
	journal = {CHEMICAL SCIENCE},
	volume = {13},
	unique-id = {33147400},
	issn = {2041-6520},
	abstract = {Solving the challenge of melanin structure is important to realize its potential as smart biomaterial. By modeling the properties of eumelanin dimers we show that machine learning can be used to solve this problem.},
	year = {2022},
	eissn = {2041-6539},
	pages = {8942-8946},
	orcid-numbers = {Bosch, Daniel/0000-0003-1791-1129; Wang, Jun/0000-0003-0222-6380; Blancafort, Lluís/0000-0002-0003-5540}
}

@article{MTMT:33147402,
	title = {Artificial Intelligence-Based Toxicity Prediction of Environmental Chemicals: Future Directions for Chemical Management Applications},
	url = {https://m2.mtmt.hu/api/publication/33147402},
	author = {Jeong, Jaeseong and Choi, Jinhee},
	doi = {10.1021/acs.est.1c07413},
	journal-iso = {ENVIRON SCI TECHNOL},
	journal = {ENVIRONMENTAL SCIENCE & TECHNOLOGY},
	volume = {56},
	unique-id = {33147402},
	issn = {0013-936X},
	year = {2022},
	eissn = {1520-5851},
	pages = {7532-7543},
	orcid-numbers = {Jeong, Jaeseong/0000-0002-3860-0648; Choi, Jinhee/0000-0003-3393-7505}
}

@article{MTMT:32298744,
	title = {The role of quantum chemistry in covalent inhibitor design},
	url = {https://m2.mtmt.hu/api/publication/32298744},
	author = {Mihalovits, Levente Márk and Ferenczy, György and Keserű, György Miklós},
	doi = {10.1002/qua.26768},
	journal-iso = {INT J QUANTUM CHEM},
	journal = {INTERNATIONAL JOURNAL OF QUANTUM CHEMISTRY},
	volume = {122},
	unique-id = {32298744},
	issn = {0020-7608},
	abstract = {The recent ascent of targeted covalent inhibitors (TCI) in drug discovery brings new opportunities and challenges to quantum chemical reactivity calculations supporting discovery efforts. TCIs typically form a covalent bond with the targeted nucleophilic amino acid side chain. Their reactivity that can be both computed and experimentally measured is therefore one of the key factors in determining inhibitory potency. Calculation of relevant quantum chemical descriptors and corresponding reaction barriers of model reactions represent efficient ways to predict intrinsic reactivities of covalent ligands. A more comprehensive description of covalent ligand binding is offered by mixed quantum mechanical/molecular mechanical (QM/MM) potentials. Reaction mechanisms can be investigated by the exploration of the potential energy surface as a function of suitable reaction coordinates, and free energy surfaces can also be calculated with molecular dynamics based simulations. Here we review the methodological aspects and discuss applications with primary focus on high-end QM/MM simulations to illustrate the current status of quantum chemical support to covalent inhibitor design. Available QM approaches are suitable to identify likely reaction mechanisms and rate determining steps in the binding of covalent inhibitors. The efficient QM/MM prediction of ligand reactivities complemented with the computational description of the recognition step makes these computations highly useful in covalent drug discovery.},
	keywords = {MOLECULAR MECHANICS; REACTIVITY; quantum mechanics; free energy; Targeted covalent inhibitors; reaction barrier},
	year = {2022},
	eissn = {1097-461X},
	orcid-numbers = {Mihalovits, Levente Márk/0000-0003-1022-3294; Ferenczy, György/0000-0002-5771-4616}
}

@article{MTMT:32867980,
	title = {Comparison of Descriptor- and Fingerprint Sets in Machine Learning Models for ADME-Tox Targets},
	url = {https://m2.mtmt.hu/api/publication/32867980},
	author = {Orosz, Álmos and Héberger, Károly and Rácz, Anita},
	doi = {10.3389/fchem.2022.852893},
	journal-iso = {FRONT CHEM},
	journal = {FRONTIERS IN CHEMISTRY},
	volume = {10},
	unique-id = {32867980},
	issn = {2296-2646},
	abstract = {The screening of compounds for ADME-Tox targets plays an important role in drug design. QSPR models can increase the speed of these specific tasks, although the performance of the models highly depends on several factors, such as the applied molecular descriptors. In this study, a detailed comparison of the most popular descriptor groups has been carried out for six main ADME-Tox classification targets: Ames mutagenicity, P-glycoprotein inhibition, hERG inhibition, hepatotoxicity, blood–brain-barrier permeability, and cytochrome P450 2C9 inhibition. The literature-based, medium-sized binary classification datasets (all above 1,000 molecules) were used for the model building by two common algorithms, XGBoost and the RPropMLP neural network. Five molecular representation sets were compared along with their joint applications: Morgan, Atompairs, and MACCS fingerprints, and the traditional 1D and 2D molecular descriptors, as well as 3D molecular descriptors, separately. The statistical evaluation of the model performances was based on 18 different performance parameters. Although all the developed models were close to the usual performance of QSPR models for each specific ADME-Tox target, the results clearly showed the superiority of the traditional 1D, 2D, and 3D descriptors in the case of the XGBoost algorithm. It is worth trying the classical tools in single model building because the use of 2D descriptors can produce even better models for almost every dataset than the combination of all the examined descriptor sets.},
	year = {2022},
	eissn = {2296-2646}
}

@article{MTMT:32741735,
	title = {Extended continuous similarity indices: theory and application for QSAR descriptor selection},
	url = {https://m2.mtmt.hu/api/publication/32741735},
	author = {Rácz, Anita and Dunn, Timothy B. and Bajusz, Dávid and Kim, Taewon D. and Miranda-Quintana, Ramón Alain and Héberger, Károly},
	doi = {10.1007/s10822-022-00444-7},
	journal-iso = {J COMPUT AID MOL DES},
	journal = {JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN},
	volume = {36},
	unique-id = {32741735},
	issn = {0920-654X},
	year = {2022},
	eissn = {1573-4951},
	pages = {157-173},
	orcid-numbers = {Bajusz, Dávid/0000-0003-4277-9481; Miranda-Quintana, Ramón Alain/0000-0003-2121-4449}
}

@article{MTMT:32089303,
	title = {Extended many-item similarity indices for sets of nucleotide and protein sequences},
	url = {https://m2.mtmt.hu/api/publication/32089303},
	author = {Bajusz, Dávid and Miranda-Quintana, Ramón Alain and Rácz, Anita and Héberger, Károly},
	doi = {10.1016/j.csbj.2021.06.021},
	journal-iso = {CSBJ},
	journal = {COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL},
	volume = {19},
	unique-id = {32089303},
	issn = {2001-0370},
	year = {2021},
	eissn = {2001-0370},
	pages = {3628-3639},
	orcid-numbers = {Bajusz, Dávid/0000-0003-4277-9481}
}

@article{MTMT:33147405,
	title = {Accelerating high-throughput virtual screening through molecular pool-based active learning},
	url = {https://m2.mtmt.hu/api/publication/33147405},
	author = {Graff, David E. and Shakhnovich, Eugene I. and Coley, Connor W.},
	doi = {10.1039/D0SC06805E},
	journal-iso = {CHEM SCI},
	journal = {CHEMICAL SCIENCE},
	volume = {12},
	unique-id = {33147405},
	issn = {2041-6520},
	abstract = {Bayesian optimization can accelerate structure-based virtual screening campaigns by minimizing the total number of simulations performed while still identifying the vast majority of computational hits.},
	year = {2021},
	eissn = {2041-6539},
	pages = {7866-7881},
	orcid-numbers = {Graff, David E./0000-0003-1250-3329; Coley, Connor W./0000-0002-8271-8723}
}

@article{MTMT:33147406,
	title = {Machine Learning Enables Highly Accurate Predictions of Photophysical Properties of Organic Fluorescent Materials: Emission Wavelengths and Quantum Yields},
	url = {https://m2.mtmt.hu/api/publication/33147406},
	author = {Ju, Cheng-Wei and Bai, Hanzhi and Li, Bo and Liu, Rizhang},
	doi = {10.1021/acs.jcim.0c01203},
	journal-iso = {J CHEM INF MODEL},
	journal = {JOURNAL OF CHEMICAL INFORMATION AND MODELING},
	volume = {61},
	unique-id = {33147406},
	issn = {1549-9596},
	year = {2021},
	eissn = {1549-960X},
	pages = {1053-1065},
	orcid-numbers = {Ju, Cheng-Wei/0000-0002-2250-8548}
}

@article{MTMT:32074659,
	title = {A corneal-PAMPA-based in silico model for predicting corneal permeability},
	url = {https://m2.mtmt.hu/api/publication/32074659},
	author = {Vincze, Anna and Dargó, Gergő and Rácz, Anita and Balogh, György Tibor},
	doi = {10.1016/j.jpba.2021.114218},
	journal-iso = {J PHARMACEUT BIOMED ANAL},
	journal = {JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS},
	volume = {203},
	unique-id = {32074659},
	issn = {0731-7085},
	year = {2021},
	eissn = {1873-264X},
	orcid-numbers = {Vincze, Anna/0000-0002-9756-574X; Dargó, Gergő/0000-0002-1141-8379; Balogh, György Tibor/0000-0003-3347-1880}
}

@article{MTMT:33147403,
	title = {Classification models and SAR analysis on CysLT1 receptor antagonists using machine learning algorithms},
	url = {https://m2.mtmt.hu/api/publication/33147403},
	author = {Wang, Hongzhao and Qin, Zijian and Yan, Aixia},
	doi = {10.1007/s11030-020-10165-4},
	journal-iso = {MOL DIVERS},
	journal = {MOLECULAR DIVERSITY},
	volume = {25},
	unique-id = {33147403},
	issn = {1381-1991},
	year = {2021},
	eissn = {1573-501X},
	pages = {1597-1616}
}

@article{MTMT:33147404,
	title = {Hydrogen Evolution Prediction for Alternating Conjugated Copolymers Enabled by Machine Learning with Multidimension Fragmentation Descriptors},
	url = {https://m2.mtmt.hu/api/publication/33147404},
	author = {Xu, Yuzhi and Ju, Cheng-Wei and Li, Bo and Ma, Qiu-Shi and Chen, Zhenyu and Zhang, Lianjie and Chen, Junwu},
	doi = {10.1021/acsami.1c05536},
	journal-iso = {ACS APPL MATER INTER},
	journal = {ACS APPLIED MATERIALS & INTERFACES},
	volume = {13},
	unique-id = {33147404},
	issn = {1944-8244},
	year = {2021},
	eissn = {1944-8252},
	pages = {34033-34042},
	orcid-numbers = {Ju, Cheng-Wei/0000-0002-2250-8548; Zhang, Lianjie/0000-0003-3555-4372; Chen, Junwu/0000-0003-0190-782X}
}

@article{MTMT:31430558,
	title = {One molecular fingerprint to rule them all: drugs, biomolecules, and the metabolome},
	url = {https://m2.mtmt.hu/api/publication/31430558},
	author = {Capecchi, Alice and Probst, Daniel and Reymond, Jean-Louis},
	doi = {10.1186/s13321-020-00445-4},
	journal-iso = {J CHEMINFORMATICS},
	journal = {JOURNAL OF CHEMINFORMATICS},
	volume = {12},
	unique-id = {31430558},
	issn = {1758-2946},
	abstract = {Background Molecular fingerprints are essential cheminformatics tools for virtual screening and mapping chemical space. Among the different types of fingerprints, substructure fingerprints perform best for small molecules such as drugs, while atom-pair fingerprints are preferable for large molecules such as peptides. However, no available fingerprint achieves good performance on both classes of molecules. Results Here we set out to design a new fingerprint suitable for both small and large molecules by combining substructure and atom-pair concepts. Our quest resulted in a new fingerprint called MinHashed atom-pair fingerprint up to a diameter of four bonds (MAP4). In this fingerprint the circular substructures with radii ofr = 1 andr = 2 bonds around each atom in an atom-pair are written as two pairs of SMILES, each pair being combined with the topological distance separating the two central atoms. These so-called atom-pair molecular shingles are hashed, and the resulting set of hashes is MinHashed to form the MAP4 fingerprint. MAP4 significantly outperforms all other fingerprints on an extended benchmark that combines the Riniker and Landrum small molecule benchmark with a peptide benchmark recovering BLAST analogs from either scrambled or point mutation analogs. MAP4 furthermore produces well-organized chemical space tree-maps (TMAPs) for databases as diverse as DrugBank, ChEMBL, SwissProt and the Human Metabolome Database (HMBD), and differentiates between all metabolites in HMBD, over 70% of which are indistinguishable from their nearest neighbor using substructure fingerprints. Conclusion MAP4 is a new molecular fingerprint suitable for drugs, biomolecules, and the metabolome and can be adopted as a universal fingerprint to describe and search chemical space. The source code is available atand interactive MAP4 similarity search tools and TMAPs for various databases are accessible atand.},
	keywords = {Databases; Virtual screening; chemical space; molecular fingerprints; Locality sensitive hashing},
	year = {2020},
	eissn = {1758-2946},
	orcid-numbers = {Reymond, Jean-Louis/0000-0003-2724-2942}
}

@article{MTMT:31252936,
	title = {Striking essential oil: tapping into a largely unexplored source for drug discovery},
	url = {https://m2.mtmt.hu/api/publication/31252936},
	author = {Feyaerts, A.F. and Luyten, W. and Van, Dijck P.},
	doi = {10.1038/s41598-020-59332-5},
	journal-iso = {SCI REP},
	journal = {SCIENTIFIC REPORTS},
	volume = {10},
	unique-id = {31252936},
	year = {2020},
	eissn = {2045-2322}
}

@article{MTMT:31024118,
	title = {The Symbiotic Relationship Between Drug Discovery and Organic Chemistry},
	url = {https://m2.mtmt.hu/api/publication/31024118},
	author = {Grygorenko, Oleksandr O. and Volochnyuk, Dmitriy M. and Ryabukhin, Sergey and Judd, Duncan B.},
	doi = {10.1002/chem.201903232},
	journal-iso = {CHEM-EUR J},
	journal = {CHEMISTRY-A EUROPEAN JOURNAL},
	volume = {26},
	unique-id = {31024118},
	issn = {0947-6539},
	abstract = {All pharmaceutical products contain organic molecules; the source may be a natural product or a fully synthetic molecule, or a combination of both. Thus, it follows that organic chemistry underpins both existing and upcoming pharmaceutical products. The reverse relationship has also affected organic synthesis, changing its landscape towards increasingly complex targets. This Review article sets out to give a concise appraisal of this symbiotic relationship between organic chemistry and drug discovery, along with a discussion of the design concepts and highlighting key milestones along the journey. In particular, criteria for a high-quality compound library design enabling efficient virtual navigation of chemical space, as well as rise and fall of concepts for its synthetic exploration (such as combinatorial chemistry; diversity-, biology-, lead-, or fragment-oriented syntheses; and DNA-encoded libraries) are critically surveyed.},
	keywords = {combinatorial chemistry; natural products; DRUG DISCOVERY; Chemoinformatics; organic synthesis},
	year = {2020},
	eissn = {1521-3765},
	pages = {1196-1237}
}

@{MTMT:33147407,
	title = {10. A primer on natural product-based virtual screening},
	url = {https://m2.mtmt.hu/api/publication/33147407},
	author = {Koulouridi, Eleni and Valli, Marilia and Ntie-Kang, Fidele and Silva Bolzani, Vanderlan da},
	booktitle = {Fundamental Concepts},
	doi = {10.1515/9783110579352-011},
	unique-id = {33147407},
	year = {2020},
	pages = {251-290}
}

@article{MTMT:31429933,
	title = {Large-scale evaluation of cytochrome P450 2C9 mediated drug interaction potential with machine learning-based consensus modeling},
	url = {https://m2.mtmt.hu/api/publication/31429933},
	author = {Rácz, Anita and Keserű, György Miklós},
	doi = {10.1007/s10822-020-00308-y},
	journal-iso = {J COMPUT AID MOL DES},
	journal = {JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN},
	volume = {34},
	unique-id = {31429933},
	issn = {0920-654X},
	abstract = {Cytochrome P450 (CYP) enzymes play an important role in the metabolism of xenobiotics. Since they are connected to drug interactions, screening for potential inhibitors is of utmost importance in drug discovery settings. Our study provides an extensive classification model for P450-drug interactions with one of the most prominent members, the 2C9 isoenzyme. Our model involved the largest set of 45,000 molecules ever used for developing prediction models. The models are based on three different types of descriptors, (a) typical one, two and three dimensional molecular descriptors, (b) chemical and pharmacophore fingerprints and (c) interaction fingerprints with docking scores. Two machine learning algorithms, the boosted tree and the multilayer feedforward of resilient backpropagation network were used and compared based on their performances. The models were validated both internally and using external validation sets. The results showed that the consensus voting technique with custom probability thresholds could provide promising results even in large-scale cases without any restrictions on the applicability domain. Our best model was capable to predict the 2C9 inhibitory activity with the area under the receiver operating characteristic curve (AUC) of 0.85 and 0.84 for the internal and the external test sets, respectively. The chemical space covered with the largest available dataset has reached its limit encompassing publicly available bioactivity data for the 2C9 isoenzyme.},
	keywords = {CLASSIFICATION; machine learning; Cytochrome P450; ADME-Tox},
	year = {2020},
	eissn = {1573-4951},
	pages = {831-839}
}

@article{MTMT:31433852,
	title = {What place does molecular topology have in today’s drug discovery?},
	url = {https://m2.mtmt.hu/api/publication/31433852},
	author = {Zanni, Riccardo and Galvez-Llompart, Maria and Garcia-Domenech, Ramon and Galvez, Jorge},
	doi = {10.1080/17460441.2020.1770223},
	journal-iso = {EXPERT OPIN DRUG DIS},
	journal = {EXPERT OPINION ON DRUG DISCOVERY},
	volume = {15},
	unique-id = {31433852},
	issn = {1746-0441},
	year = {2020},
	eissn = {1746-045X},
	pages = {1133-1144}
}

@article{MTMT:30807381,
	title = {A primer on natural product-based virtual screening},
	url = {https://m2.mtmt.hu/api/publication/30807381},
	author = {Koulouridi, Eleni and Valli, Marilia and Ntie-Kang, Fidele and Bolzani, Vanderlan da Silva},
	doi = {10.1515/psr-2018-0105},
	journal-iso = {PHYS SCI REV},
	journal = {PHYSICAL SCIENCES REVIEWS},
	volume = {4},
	unique-id = {30807381},
	issn = {2365-6581},
	year = {2019},
	eissn = {2365-659X},
	pages = {2365659X}
}

@article{MTMT:30791108,
	title = {On the impossibility of unambiguously selecting the best model for fitting data},
	url = {https://m2.mtmt.hu/api/publication/30791108},
	author = {Miranda-Quintana, Ramon Alain and Kim, Taewon David and Heidar-Zadeh, Farnaz and Ayers, Paul W.},
	doi = {10.1007/s10910-019-01035-y},
	journal-iso = {J MATH CHEM},
	journal = {JOURNAL OF MATHEMATICAL CHEMISTRY},
	volume = {57},
	unique-id = {30791108},
	issn = {0259-9791},
	abstract = {We analyze the problem of selecting the model that best describes a given dataset. We focus on the case where the best model is the one with the smallest error, respect to the reference data. To select the best model, we consider two components: (a) an error measure to compare individual data points, and (b) a function that combines the individual errors for all the points. We show that working with the most general definition of consistency, it is impossible to extend individual error measures in a way that provides a unanimous consensus about which is the best model. We also prove that, in the best case, modifying the notion of consistency leads to expressions that are too ill-behaved to be of any practical utility. These results show that selecting the model that best describes a dataset depends heavily on the way one measures the individual errors, even if these measures are consistent.},
	keywords = {CONSISTENCY; Model selection; Comparisons; error assessment},
	year = {2019},
	eissn = {1572-8897},
	pages = {1755-1769}
}

@article{MTMT:30622971,
	title = {Intercorrelation Limits in Molecular Descriptor Preselection for QSAR/QSPR},
	url = {https://m2.mtmt.hu/api/publication/30622971},
	author = {Rácz, Anita and Bajusz, Dávid and Héberger, Károly},
	doi = {10.1002/minf.201800154},
	journal-iso = {MOL INFORM},
	journal = {MOLECULAR INFORMATICS},
	volume = {38},
	unique-id = {30622971},
	issn = {1868-1743},
	year = {2019},
	eissn = {1868-1751},
	orcid-numbers = {Bajusz, Dávid/0000-0003-4277-9481}
}

@article{MTMT:30807382,
	title = {Steroids-specific target library for steroids target prediction},
	url = {https://m2.mtmt.hu/api/publication/30807382},
	author = {Dang, Xiaoxue and Liu, Zheng and Zhou, Yanzhuo and Chen, Peizi and Liu, Jiyuan and Yao, Xiaojun and Lei, Beilei},
	doi = {10.1016/j.steroids.2018.10.002},
	journal-iso = {STEROIDS},
	journal = {STEROIDS},
	volume = {140},
	unique-id = {30807382},
	issn = {0039-128X},
	year = {2018},
	eissn = {1878-5867},
	pages = {83-91}
}

@article{MTMT:3408640,
	title = {Modeling methods and cross-validation variants in QSAR modeling: A multi-level analysis},
	url = {https://m2.mtmt.hu/api/publication/3408640},
	author = {Rácz, Anita and Bajusz, Dávid and Héberger, Károly},
	doi = {10.1080/1062936X.2018.1505778},
	journal-iso = {SAR QSAR ENVIRON RES},
	journal = {SAR AND QSAR IN ENVIRONMENTAL RESEARCH},
	volume = {29},
	unique-id = {3408640},
	issn = {1062-936X},
	year = {2018},
	eissn = {1029-046X},
	pages = {661-674},
	orcid-numbers = {Bajusz, Dávid/0000-0003-4277-9481}
}

@article{MTMT:30310783,
	title = {Life beyond the Tanimoto coefficient: similarity measures for interaction fingerprints},
	url = {https://m2.mtmt.hu/api/publication/30310783},
	author = {Rácz, Anita and Bajusz, Dávid and Héberger, Károly},
	doi = {10.1186/s13321-018-0302-y},
	journal-iso = {J CHEMINFORMATICS},
	journal = {JOURNAL OF CHEMINFORMATICS},
	volume = {10},
	unique-id = {30310783},
	issn = {1758-2946},
	year = {2018},
	eissn = {1758-2946},
	orcid-numbers = {Bajusz, Dávid/0000-0003-4277-9481}
}