ChemoPy: freely available python package for computational biology and chemoinformatics

Cao, Dong‐Sheng; Xu, Qingsong; Hu, Qian-Nan; Liang, Yi‐Zeng

doi:10.1093/bioinformatics/btt105

Cited by 204 publications

(122 citation statements)

References 32 publications

Supporting

Mentioning

122

Contrasting

Order By: Relevance

“…Since static features are defined a priori, the number of static features that represent a molecule is fixed. For the static features, DeepTox calculates a number of numerical features based on the topological and physical properties of each compound using off-the-shelf software (Cao et al, 2013). These static features include weight, Van der Waals volume, and partial charge information.…”

Section: Chemical Descriptorsmentioning

confidence: 99%

DeepTox: Toxicity Prediction using Deep Learning

Mayr

Klambauer

Unterthiner

et al. 2016

Front. Environ. Sci.

796

697

View full text Add to dashboard Cite

The Tox21 Data Challenge has been the largest effort of the scientific community to compare computational methods for toxicity prediction. This challenge comprised 12,000 environmental chemicals and drugs which were measured for 12 different toxic effects by specifically designed assays. We participated in this challenge to assess the performance of Deep Learning in computational toxicity prediction. Deep Learning has already revolutionized image processing, speech recognition, and language understanding but has not yet been applied to computational toxicity. Deep Learning is founded on novel algorithms and architectures for artificial neural networks together with the recent availability of very fast computers and massive datasets. It discovers multiple levels of distributed representations of the input, with higher levels representing more abstract concepts. We hypothesized that the construction of a hierarchy of chemical features gives Deep Learning the edge over other toxicity prediction methods. Furthermore, Deep Learning naturally enables multi-task learning, that is, learning of all toxic effects in one neural network and thereby learning of highly informative chemical features. In order to utilize Deep Learning for toxicity prediction, we have developed the DeepTox pipeline. First, DeepTox normalizes the chemical representations of the compounds. Then it computes a large number of chemical descriptors that are used as input to machine learning methods. In its next step, DeepTox trains models, evaluates them, and combines the best of them to ensembles. Finally, DeepTox predicts the toxicity of new compounds. In the Tox21 Data Challenge, DeepTox had the highest performance of all computational methods winning the grand challenge, the nuclear receptor panel, the stress response panel, and six single assays (teams "Bioinf@JKU"). We found that Deep Learning excelled in toxicity prediction and outperformed many other computational approaches like naive Bayes, support vector machines, and random forests.

show abstract

Section: Chemical Descriptorsmentioning

confidence: 99%

DeepTox: Toxicity Prediction using Deep Learning

Mayr

Klambauer

Unterthiner

et al. 2016

Front. Environ. Sci.

796

697

View full text Add to dashboard Cite

show abstract

“…We focused on three diverse DUD datasets (details are shown in Table 1) that cover kinases, nuclear hormone receptors and other enzymes such as TK, which corresponds to thymidine kinase (from PDB 1KIM), MR, which corresponds to mineralocorticoid receptor (from PDB 2AA2), and GPB, which corresponds to the enzyme glycogen phosphorylase (from PDB 1A8I). Next, using the ChemoPy package (Cao et al, 2013) we calculated for all ligands of the TK, MR and GPB sets a diverse of molecular properties derived from the set of constitutional, CPSA (charged partial surface area) and fragment/fingerprint-based descriptors, as described in Table 2. Constitutional properties depend on very simple descriptors of the molecule that can be easily calculated just counting the number of molecular elements such as atoms, types of atoms, bonds, rings, etc.…”

Section: Ligand Databases and Molecular Propertiesmentioning

confidence: 99%

Improving drug discovery using hybrid softcomputing methods

Pérez‐Sánchez

Cano

García-Rodríguez

2014

Applied Soft Computing

View full text Add to dashboard Cite

Abstract. Virtual Screening (VS) methods can considerably aid clinical research, predicting how ligands interact with drug targets. Most VS methods suppose a unique binding site for the target, but it has been demonstrated that diverse ligands interact with unrelated parts of the target and many VS methods do not take into account this relevant fact. This problem is circumvented by a novel VS methodology named BINDSURF that scans the whole protein surface in order to find new hotspots, where ligands might potentially interact with, and which is implemented in last generation massively parallel GPU hardware, allowing fast processing of large ligand databases. BINDSURF can thus be used in drug discovery, drug design, drug repurposing and therefore helps considerably in clinical research. However, the accuracy of most VS methods and concretely BINDSURF is constrained by limitations in the scoring function that describes biomolecular interactions, and even nowadays these uncertainties are not completely understood. In order to improve accuracy of the scoring functions used in BINDSURF we propose a hybrid novel approach where neural networks (NNET) and support vector machines (SVM) methods are trained with databases of known active (drugs) and inactive compounds, being this information exploited afterwards to improve BINDSURF VS predictions.

show abstract

“…Both the definitions of FP4 and MACCS substructure patterns are available from OpenBabel (version 2.3.0, http://openbabel.org/, accessed October, 2010). All calculations for three fingerprints are performed by the ChemoPy package, developed by our group [43].…”

Section: Datasets and Molecular Descriptionmentioning

confidence: 99%