Epigenetic Target Fishing with Accurate Machine Learning Models

Sánchez-Cruz, Norberto; Medina-Franco, José L.

doi:10.1021/acs.jmedchem.1c00020

Cited by 25 publications

(30 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a separate study, 14 we performed a comprehensive comparison of 15 machine learning models, derived from the combination of three different molecular fingerprints as compound representations and five different machine learning algorithms, for binary classification of compounds over 55 epigenetic targets, using a quantitative measure of biological activity cutoff of 10 μM (IC 50 , EC 50 , K i , or K d ). In that work, we found support vector machines (SVMs) trained on Morgan fingerprints of radius 2 (Morgan::SVM) and on RDK fingerprints (RDK::SVM) as the two best performing models for this task.…”

Section: ■ Approachmentioning

confidence: 99%

“…■ METHODS Data Sets. As described in our previous work, 14 55 epigenetic target-associated compound data sets were extracted from ChEMBL 27 20 and PubChem. 21 All 55 data sets including at least 30 compounds with a quantitative measure of biological activity (IC 50 , EC 50 , K i , or K d ) lower or equal to 10 μM and at least 30 compounds with a quantitative measure of biological activity higher than 10 μM.…”

Section: ■ Conclusionmentioning

confidence: 99%

“…Herein, we present Epigenetic Target Profiler (ETP), an easy-to-use and free web application for the prediction of the bioactivity profile of small molecules over a panel of 55 epigenetic targets. ETP implements the best performing model for epigenetic target prediction, as identified from a systematic comparison of machine learning models built on molecular fingerprints of different designs described in a separate work …”

Section: Introductionmentioning

confidence: 99%

“…ETP implements the best performing model for epigenetic target prediction, as identified from a systematic comparison of machine learning models built on molecular fingerprints of different designs described in a separate work. 14…”

Section: ■ Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Epigenetic Target Profiler: A Web Server to Predict Epigenetic Targets of Small Molecules

Sánchez-Cruz

Medina-Franco

2021

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

Motivation: The identification of protein targets of small molecules is essential for drug discovery. With the increasing amount of chemogenomic data in the public domain, multiple ligand-based models for target prediction have emerged. However, these models are generally biased by the number of known ligands for different targets, which involves an underrepresentation of epigenetic targets. Epigenetic drug discovery is of increasing importance but there are no open tools for epigenetic target prediction. Results: We introduce Epigenetic Target Profiler (ETP), a freely accessible and easy-to-use web application for the prediction of epigenetic targets of small molecules. For a query compound, ETP predicts its bioactivity profile over a panel of 55 different epigenetic targets. To that aim, ETP uses a consensus model based on two binary classification models for each target, relying on support vector machines and built on molecular fingerprints of different design. A distance-to-model parameter related to the reliability of the predictions is included to facilitate their interpretability and assist the identification of small molecules with potential epigenetic activity. File list (2)download file view on ChemRxiv Epigenetic_Target_Profiler_Manuscript.pdf (570.09 KiB) download file view on ChemRxiv Epigenetic_Target_Profiler_SuppInfo.pdf (440.45 KiB)

show abstract

Section: ■ Approachmentioning

confidence: 99%

Section: ■ Conclusionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: ■ Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Epigenetic Target Profiler: A Web Server to Predict Epigenetic Targets of Small Molecules

Sánchez-Cruz

Medina-Franco

2021

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Overexpression of GST is associated with tumor appearances and with resistance to cytostatic agents. Specifically the abnormal expression of the π-class of GST has been linked to the occurrence of tumor resistance to chemotherapy drugs [67] (Figure 9C). The prediction results for each ITCs are shown in Tables S3-S6 in the Supporting Information.…”

Section: Target Profiling and Prediction Of Activity Type Of Isothiocyanatesmentioning

confidence: 99%

Chemoinformatic Analysis of Isothiocyanates: Their Impact in Nature and Medicine

Guerrero-Alonso

Antúnez-Mojica

Medina-Franco

2021

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

Isothiocyanates (ITCs) have a significant impact on food and natural product chemistry. Several dietary components and food chemicals contain the isothiocyanate moiety. In addition, many ITCs interact with macromolecules of biological relevance, making these compounds relevant for potential therapeutic applications and disease prevention. However, there is a lack of systematic analysis of ITCs in chemical and biological databases. Herein, we conducted a comprehensive analysis of ITCs present in public domain databases, including natural products, food chemicals, macromolecular targets of drugs, and the Protein Data Bank. A total of 154 ITCs were found, which can be classified into seven categories: acyclic, cyclic, polycyclic, aromatic, polyaromatic, indolic, and glycosylated. 24 ITCs were reported in 18 vegetable sources, mainly in cruciferous vegetables (Brassica oleracea L.). Calculated properties of pharmaceutical relevance indicated that 11 % of the 154 ITCs would be suitable to be orally absorbed and 48 % permeate the blood-brain-barrier. It was also found that seven molecular targets have been co-crystallized with ITCs and the most frequent is the macrophage migration inhibitory factor. It is expected that this work will contribute to the sub-disciplines of natural products and food informatics.

show abstract

VDDB: A comprehensive resource and machine learning tool for antiviral drug discovery

Tao

Chen

et al. 2023

MedComm – Future Medicine

View full text Add to dashboard Cite

Virus infection is one of the major diseases that seriously threaten human health. To meet the growing demand for mining and sharing data resources related to antiviral drugs and to accelerate the design and discovery of new antiviral drugs, we presented an open‐access antiviral drug resource and machine learning platform (VDDB), which, to the best of our knowledge, is the first comprehensive dedicated resource for experimentally verified potential drugs/molecules based on manually curated data. Currently, VDDB highlights 848 clinical vaccines and 199 clinical antibodies, as well as over 710,000 small molecules targeting 39 medically important viruses including severe acute respiratory syndrome coronavirus 2. Furthermore, VDDB stores approximately three million records of pharmacological data for these collected potential antiviral drugs/molecules, involving 314 cell infection‐based phenotypic and 234 target‐based genotypic assays. Based on these annotated pharmacological data, VDDB allows users to browse, search, and download reliable information about these collects for various viruses of interest. In particular, VDDB also integrates 57 cell infection‐ and 117 target‐based associated high‐accuracy machine learning models to support various antivirals identification‐related tasks, such as compound activity prediction, virtual screening, drug repositioning, and target fishing. VDDB is freely accessible at https://vddb.idruglab.cn.

show abstract

Epigenetic Target Fishing with Accurate Machine Learning Models

Cited by 25 publications

References 61 publications

Epigenetic Target Profiler: A Web Server to Predict Epigenetic Targets of Small Molecules

Epigenetic Target Profiler: A Web Server to Predict Epigenetic Targets of Small Molecules

Chemoinformatic Analysis of Isothiocyanates: Their Impact in Nature and Medicine

VDDB: A comprehensive resource and machine learning tool for antiviral drug discovery

Contact Info

Product

Resources

About