How to Achieve Better Results Using PASS-Based Virtual Screening: Case Study for Kinase Inhibitors

Pogodin, Pavel V.; Lagunin, Alexey; Rudik, Anastasia V.; Филимонов, Д. А.; Druzhilovskiy, Dmitry S.; Nicklaus, Marc C.; Poroikov, Vladimir

doi:10.3389/fchem.2018.00133

Cited by 30 publications

(23 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the RF-TI model was generated from active and inactive compounds for Keap1/Nrf2 comprehensively collected from three public databases, the RF-PI model was from active compounds in the ChEMBL database and putative inactive compounds. The use of putative inactive compounds as negative training data is known as an alternative strategy for dataset preparation in LBVS 42 , 43 . Most compounds in large compound libraries are not tested for particular targets and are generally assumed to have a low likelihood of being active and are used as putative inactive compounds.…”

Section: Resultsmentioning

confidence: 99%

Identification of novel inhibitors of Keap1/Nrf2 by a promising method combining protein–protein interaction-oriented library and machine learning

Shimizu

Yonezawa

Sakamoto³

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Protein–protein interactions (PPIs) are prospective but challenging targets for drug discovery, because screening using traditional small-molecule libraries often fails to identify hits. Recently, we developed a PPI-oriented library comprising 12,593 small-to-medium-sized newly synthesized molecules. This study validates a promising combined method using PPI-oriented library and ligand-based virtual screening (LBVS) to discover novel PPI inhibitory compounds for Kelch-like ECH-associated protein 1 (Keap1) and nuclear factor erythroid 2-related factor 2 (Nrf2). We performed LBVS with two random forest models against our PPI library and the following time-resolved fluorescence resonance energy transfer (TR-FRET) assays of 620 compounds identified 15 specific hit compounds. The high hit rates for the entire PPI library (estimated 0.56–1.3%) and the LBVS (maximum 5.4%) compared to a conventional screening library showed the utility of the library and the efficiency of LBVS. All the hit compounds possessed novel structures with Tanimoto similarity ≤ 0.26 to known Keap1/Nrf2 inhibitors and aqueous solubility (AlogP < 5). Reasonable binding modes were predicted using 3D alignment of five hit compounds and a Keap1/Nrf2 peptide crystal structure. Our results represent a new, efficient method combining the PPI library and LBVS to identify novel PPI inhibitory ligands with expanded chemical space.

show abstract

Section: Resultsmentioning

confidence: 99%

Identification of novel inhibitors of Keap1/Nrf2 by a promising method combining protein–protein interaction-oriented library and machine learning

Shimizu

Yonezawa

Sakamoto³

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…al. 24 based on ChEMBL bioactivity data. 30 It contains 55,594 ligands with activities measured on 160 different human-protein kinases.…”

Section: Dataset and Processingmentioning

confidence: 99%

Using Domain-Specific Fingerprints Generated Through Neural Networks to Enhance Ligand-Based Virtual Screening

Menke

Koch

2021

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Molecular fingerprints are essential for different cheminformatics approaches like similarity-based virtual screening. In this work, the concept of neural (network) fingerprints in the context of similarity search is introduced in which the activation of the last hidden layer of a trained neural network represents the molecular fingerprint. The neural fingerprint performance of five different neural network architectures was analyzed and compared to the well-established Extended Connectivity Fingerprint (ECFP) and an autoencoder-based fingerprint. This is done using a published compound dataset with known bioactivity on 160 different kinase targets. We expect neural networks to combine information about the molecular space of already known bioactive compounds together with the information on the molecular structure of the query and by doing so enrich the fingerprint. The results show that indeed neural fingerprints can greatly improve the performance of similarity searches. Most importantly, it could be shown that the neural fingerprint performs well even for kinase targets that were not included in the training. Surprisingly, while Graph Neural Networks (GNNs) are thought to offer an advantageous alternative, the best performing neural fingerprints were based on traditional fully connected layers using the ECFP4 as input. The best performing kinase-specific neural fingerprint will be provided for public use.

show abstract

“…In order to determine the possible molecular mechanisms responsible for the observed activities of D2AAK1, we used the molecular similarity approach as incorporated in PASS software [ 23 ] to compare D2AAK1 structure with compound structures of known bioactivities. We found, that CaMKI kinase delta that regulates axonal extension and growth cone motility in hippocampal and cerebellar nerve cells may be one of molecular targets of D2AAK1 (P a , probability that the compound is active: 0.520; P i , probability that the compound is inactive: 0.084).…”

Section: Resultsmentioning

confidence: 99%

“…Although PASS software indicated D2AAK1 as an inhibitor of this kinase, this specific result can stem from a limited database of the software which may not contain activators of the enzyme. Therefore, it is imperative to experimentally verify if the predicted activity is indeed inhibitory and not activating, as recommended by the software developers [ 23 ].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

The Antipsychotic D2AAK1 as a Memory Enhancer for Treatment of Mental and Neurodegenerative Diseases

Koszła

Sołek

Woźniak

et al. 2020

IJMS

View full text Add to dashboard Cite

The treatment of memory impairments associated with the central nervous system diseases remains an unmet medical need with social and economic implications. Here we show, that a multi-target ligand of aminergic G protein-coupled receptors with antipsychotic activity in vivo (D2AAK1) stimulates neuron growth and survival and promotes neuron integrity. We focused on the multilevel evaluation of the D2AAK1-related effects on neurons in terms of behavioral, cellular, molecular, and biochemical features in vivo and in vitro, such as memory-related responses, locomotor activity, tissue sections analysis, metabolic activity, proliferation level, neurons morphology, and proteins level involved in intracellular signaling pathways. In silico studies indicate that activation of calcium/calmodulin-dependent protein kinase I (CaMKI) may underline some of the observed activities of the compound. Furthermore, the compound increases hippocampal neuron proliferation via the activation of neurotrophic factors and cooperating signals responsible for cell growth and proliferation. D2AAK1 improves memory and learning processes in mice after both acute and chronic administration. D2AAK1 also causes an increase in the number of hippocampal pyramidal neurons after chronic administration. Because of its neuroprotective properties and pro-cognitive activity in behavioral studies D2AAK1 has the potential for the treatment of memory disturbances in neurodegenerative and mental diseases.

show abstract

How to Achieve Better Results Using PASS-Based Virtual Screening: Case Study for Kinase Inhibitors

Cited by 30 publications

References 75 publications

Identification of novel inhibitors of Keap1/Nrf2 by a promising method combining protein–protein interaction-oriented library and machine learning

Identification of novel inhibitors of Keap1/Nrf2 by a promising method combining protein–protein interaction-oriented library and machine learning

Using Domain-Specific Fingerprints Generated Through Neural Networks to Enhance Ligand-Based Virtual Screening

The Antipsychotic D2AAK1 as a Memory Enhancer for Treatment of Mental and Neurodegenerative Diseases

Contact Info

Product

Resources

About