Kinome‐Wide Profiling Prediction of Small Molecules

Sorgenfrei, Frieda A.; Merget, Benjamin

doi:10.1002/cmdc.201700180

Cited by 32 publications

(30 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we will elaborate on how our strategy was implemented and was evaluated from various perspectives. It is worth noting that each prediction model in our research was assessed with a rigorous four-level (CV1 − CV4) validation strategy [40] ( Figure S3).…”

Section: Resultsmentioning

confidence: 99%

WITHDRAWN: Exploration and Augmentation of Pharmacological Space via Adversarial Auto-encoder Model for Facilitating Kinase-centric Drug Development

Bai

Yin

2020

Preprint

View full text Add to dashboard Cite

Predicting drug-protein interactions (DPIs) is of great importance for drug discovery and repositioning, yet still challenging mainly due to the sparse nature of DPI matrixes, resulting in poor generalization performance. Hence, unlike typical DPI prediction models which focused on representation learning or model selection, we propose a deep neural network-based strategy, PCM_AAE, that re-explores and augments the pharmacological space of kinase inhibitors by introducing adversarial auto-encoder model (AAE) to improve the generalization of the prediction model. To complete the pharmacological space, we constructed Ensemble of PCM-AAE (EPA), an ensemble model that quickly and accurately yields quantitative predictions of binding affinity between any human kinase and inhibitor. In rigorous internal validation, EPA showed excellent performance, consistently outperforming the model trained with the imbalanced set, especially for targets with relatively fewer training data points. Improved prediction accuracy of EPA to external datasets again demonstrated enhanced generalization ability of EPA that could gracefully handle previously unseen kinases or inhibitors. Further analysis showed promising potential when EPA was directly applied to virtual screening and off-target prediction, exhibiting the practicality of the EPA model in hit prediction. Our strategy is expected to facilitate kinase-centric drug development, as well as to solve more challenging prediction problems with insufficient data points.

show abstract

Section: Resultsmentioning

confidence: 99%

WITHDRAWN: Exploration and Augmentation of Pharmacological Space via Adversarial Auto-encoder Model for Facilitating Kinase-centric Drug Development

Bai

Yin

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Representations: Three mathematical representations are employed for the polymer structures, including MF, ME and MG. MF, also known as extended-connectivity fingerprints, is the most commonly used mathematical representation in organic molecular activity predictions. [31][32][33][34][35][36][37] To generate a MF, all substructures around all non-hydrogen atoms of a molecule within a defined radius are generated and converted to unique identifiers. [31] These identifiers are then usually hashed to high-dimensional and sparse vectors with a fixed length.…”

Section: Datasetmentioning

confidence: 99%

Evaluating Polymer Representations via Quantifying Structure-Property Relationships

Ma¹,

Liu²,

Zhang³

et al. 2019

Preprint

View full text Add to dashboard Cite

Machine learning techniques are being applied in quantifying structure-property relationships for a wide variety of materials, where the properly representing materials plays key roles. Although algorithms for representation learning are extensively studied, their applications to domain-specific areas, such as polymer, are limited largely due to the lack of benchmark databases. In this work, we investigate different types of polymer representations, including Morgan Fingerprint (MF), molecular embedding (ME) and molecular graph (MG), based on a benchmark database from a subset of PolyInfo. We evaluate the quality of different polymer representations via quantifying the relationships between the representations and polymer properties, including density, melting temperature and glass transition temperature. Different representation learning schemes, such as supervised learning, semi-supervised learning and transfer learning, are investigated. It is found that ME outperforms the other representations for structure-property relationship quantification in all cases studied, and MG is shown to be much inferior than ME and MF, likely due to the relatively small volumes of training data available. For MEs, it is found that the similarities of substructure MEs under different learning schemes (e.g., SL, SSL and TL) are differently estimated, thus leading to different performance scores in structure-property relation quantification. Several ME mixtures have shown to outperform the single MEs in the corresponding regression tasks, and this is attributed to the information gain when mixing different ME.

show abstract

“…Most commonly used representations include Morgan FPs (also known as extended-connectivity fingerprints (ECFP)) 1 as they often outperform other types of FPs in similarity search and virtual screening tasks 2,3 and are also successfully used for molecular activity predictions. [4][5][6][7] To generate a Morgan FP, all substructures around all heavy atoms of a molecule within a defined radius are generated and assigned to a unique identifier (called Morgen identifier below). These identifiers are then usually hashed to a vector with fixed length.…”

Section: Introductionmentioning

confidence: 99%

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

Jaeger

Fulle

Turk

2018

J. Chem. Inf. Model.

Self Cite

486

477

View full text Add to dashboard Cite

Inspired by natural language processing techniques, we here introduce Mol2vec, which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Like the Word2vec models, where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that point in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing the vectors of the individual substructures and, for instance, be fed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pretrained once, yields dense vector representations, and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as a reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment-independent and thus can also be easily used for proteins with low sequence similarities.

show abstract

Kinome‐Wide Profiling Prediction of Small Molecules

Cited by 32 publications

References 38 publications

WITHDRAWN: Exploration and Augmentation of Pharmacological Space via Adversarial Auto-encoder Model for Facilitating Kinase-centric Drug Development

WITHDRAWN: Exploration and Augmentation of Pharmacological Space via Adversarial Auto-encoder Model for Facilitating Kinase-centric Drug Development

Evaluating Polymer Representations via Quantifying Structure-Property Relationships

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

Contact Info

Product

Resources

About