SwissTargetPrediction: updated data and new features for efficient prediction of protein targets of small molecules

Daina, Antoine; Michielin, Olivier; Zoete, Vincent

doi:10.1093/nar/gkz382

Cited by 2,154 publications

(1,529 citation statements)

References 20 publications

(26 reference statements)

Supporting

Mentioning

1,518

Contrasting

Unclassified

Order By: Relevance

“…30 Preliminary ADME-tox computational studies of the designed compounds were carried out using SwissADME. 31 For all our compounds, a high gastrointestinal absorption was predicted, which is an important factor for oral bioavailability.…”

Section: Compound Designmentioning

confidence: 88%

Structure-activity relationships and mechanistic studies of novel mitochondria-targeted, leishmanicidal derivatives of the 4-aminostyrylquinoline scaffold

Staderini

Piquero

Abengózar

et al. 2019

European Journal of Medicinal Chemistry

View full text Add to dashboard Cite

show abstract

Section: Compound Designmentioning

confidence: 88%

Structure-activity relationships and mechanistic studies of novel mitochondria-targeted, leishmanicidal derivatives of the 4-aminostyrylquinoline scaffold

Staderini

Piquero

Abengózar

et al. 2019

European Journal of Medicinal Chemistry

View full text Add to dashboard Cite

show abstract

“…The molecular docking study was performed to assess the interaction of the poncirin with the various molecular targets. The Swiss Target Prediction version-2019 was used to study the interaction of the poncirin with the cytochrome p450, adenosine receptor A1, sodium/ glucose transporter1/2, low affinity sodium/glucose cotransporter [37].…”

Section: Molecular Docking Studymentioning

confidence: 99%

Poncirin attenuates CCL4-induced liver injury through inhibition of oxidative stress and inflammatory cytokines in mice

Ullah

Khan

Baig

et al. 2020

BMC Complement Med Ther

View full text Add to dashboard Cite

Background: In the present study, the poncirin which is flavonoid-7-o-glycosides (isolated from the Poncirus trifoliata) in nature was evaluated against the Carbon tetra chloride (CCL4)-induced liver injury. The poncirin have been reported for various anti-inflammatory, analgesic activity etc. Based on the previous studies it was anticipated that the poncirin will ameliorate CCL4-induced liver injury.Methods: The CCL4-induced acute and chronic liver injury model (albino BALB/c mice) was used. Following the induction of the liver injury various parameters such as food and water intake, body weight and weight to dry ratio changes were assessed. Furthermore, various hematological, biochemical parameters and histological studies such as hemotoxylin and eosin (H and E) staining were performed. The poncirin treatment was also evaluated against the pro-inflammatory cytokines such as interleukin-1β (IL-1β), interleukin-6 (IL-6) and tumor necrosis factor-α (TNF-α) using enzyme link immunosorbant assay (ELISA). The Swiss Target prediction software was used to investigate interaction of the poncirin on the various hepatic enzymes. Results: The poncirin treatment markedly improved the behavioral parameters such as food and water intake. The liver weight variation was attenuated and total body was improved markedly. The hematological and biochemical parameters were significantly improved compared to the CCL4 treated groups. The anti-oxidants were induced, while oxidative stress markers were reduced promisingly. The H and E staining showed that poncirin treatment significantly improved the histology of liver compared to the CCL4 treated group. Furthermore, the poncirin treatment also evidently decreased the inflammatory mediators. Conclusions: The poncirin treatment showed marked improvement in behavioral, biochemical and histological parameters following CCL4-induced liver injury. Additionally, the poncirin treatment also markedly improved the antioxidant enzymes, attenuated the oxidative stress markers and inflammatory cytokines.

show abstract

“…For each of the target identification methods (Similarity Ensemble Approach (SEA) [76], SwissTargetPrediction [77,78], and PharmMapper [79,80]), we used the corresponding web servers to generate predictions for AC6.…”

Section: Novelty Of Ac6 As An Ache Inhibitormentioning

confidence: 99%

Machine learning classification can reduce false positives in structure-based virtual screening

Adeshina

Deeds

Karanicolas

2020

Preprint

View full text Add to dashboard Cite

With the recent explosion in the size of libraries available for screening, virtual screening is positioned to assume a more prominent role in early drug discovery's search for active chemical matter.Modern virtual screening methods are still, however, plagued with high false positive rates: typically, only about 12% of the top-scoring compounds actually show activity when tested in biochemical assays.We argue that most scoring functions used for this task have been developed with insufficient thoughtfulness into the datasets on which they are trained and tested, leading to overly simplistic models and/or overtraining. These problems are compounded in the literature because none of the studies reporting new scoring methods have validated their model prospectively within the same study. Here, we report a new strategy for building a training dataset (D-COID) that aims to generate highly-compelling decoy complexes that are individually matched to available active complexes. Using this dataset, we train a general-purpose classifier for virtual screening (vScreenML) that is built on the XGBoost framework of gradient-boosted decision trees. In retrospective benchmarks, our new classifier shows outstanding performance relative to other scoring functions. We additionally evaluate the classifier in a prospective context, by screening for new acetylcholinesterase inhibitors. Remarkably, we find that nearly all compounds selected by vScreenML show detectable activity at 50 µM, with 10 of 23 providing greater than 50% inhibition at this concentration. Without any medicinal chemistry optimization, the most potent hit from this initial screen has an IC50 of 280 nM, corresponding to a Ki value of 173 nM. These results support using the D-COID strategy for training classifiers in other computational biology tasks, and for vScreenML in virtual screening campaigns against other protein targets. Both D-COID and vScreenML are freely distributed to facilitate such efforts.

show abstract

SwissTargetPrediction: updated data and new features for efficient prediction of protein targets of small molecules

Cited by 2,154 publications

References 20 publications

Structure-activity relationships and mechanistic studies of novel mitochondria-targeted, leishmanicidal derivatives of the 4-aminostyrylquinoline scaffold

Structure-activity relationships and mechanistic studies of novel mitochondria-targeted, leishmanicidal derivatives of the 4-aminostyrylquinoline scaffold

Poncirin attenuates CCL4-induced liver injury through inhibition of oxidative stress and inflammatory cytokines in mice

Machine learning classification can reduce false positives in structure-based virtual screening

Contact Info

Product

Resources

About