Browse
Submit Data
Databases
API
Help

Dataset Information

22 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Modelling compound cytotoxicity using conformal prediction and PubChem HTS data.

ABSTRACT: The assessment of compound cytotoxicity is an important part of the drug discovery process. Accurate predictions of cytotoxicity have the potential to expedite decision making and save considerable time and effort. In this work we apply class conditional conformal prediction to model the cytotoxicity of compounds based on 16 high throughput cytotoxicity assays from PubChem. The data span 16 cell lines and comprise more than 440 000 unique compounds. The data sets are heavily imbalanced with only 0.8% of the tested compounds being cytotoxic. We trained one classification model for each cell line and validated the performance with respect to validity and accuracy. The generated models deliver high quality predictions for both toxic and non-toxic compounds despite the imbalance between the two classes. On external data collected from the same assay provider as one of the investigated cell lines the model had a sensitivity of 74% and a specificity of 65% at the 80% confidence level among the compounds assigned to a single class. Compared to previous approaches for large scale cytotoxicity modelling, this represents a balanced performance in the prediction of the toxic and non-toxic classes. The conformal prediction framework also allows the modeller to control the error frequency of the predictions, allowing predictions of cytotoxicity outcomes with confidence.

SUBMITTER: Svensson F

PROVIDER: S-EPMC6061930 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Dynamic applicability domain (dAD): compound-target binding affinity estimates with local conformal prediction.

Project description:MotivationIncreasing efforts are being made in the field of machine learning to advance the learning of robust and accurate models from experimentally measured data and enable more efficient drug discovery processes. The prediction of binding affinity is one of the most frequent tasks of compound bioactivity modelling. Learned models for binding affinity prediction are assessed by their average performance on unseen samples, but point predictions are typically not provided with a rigorous confidence assessment. Approaches, such as the conformal predictor framework equip conventional models with a more rigorous assessment of confidence for individual point predictions. In this article, we extend the inductive conformal prediction framework for interaction data, in particular the compound-target binding affinity prediction task. The new framework is based on dynamically defined calibration sets that are specific for each testing pair and provides prediction assessment in the context of calibration pairs from its compound-target neighbourhood, enabling improved estimates based on the local properties of the prediction model.ResultsThe effectiveness of the approach is benchmarked on several publicly available datasets and tested in realistic use-case scenarios with increasing levels of difficulty on a complex compound-target binding affinity space. We demonstrate that in such scenarios, novel approach combining applicability domain paradigm with conformal prediction framework, produces superior confidence assessment with valid and more informative prediction regions compared to other 'state-of-the-art' conformal prediction approaches.Availability and implementationDataset and the code are available on GitHub (https://github.com/mlkr-rbi/dAD).

| S-EPMC10457664 | biostudies-literature

Predicting adverse drug reactions using publicly available PubChem BioAssay data.

Project description:Adverse drug reactions (ADRs) can have severe consequences, and therefore the ability to predict ADRs prior to market introduction of a drug is desirable. Computational approaches applied to preclinical data could be one way to inform drug labeling and marketing with respect to potential ADRs. Based on the premise that some of the molecular actors of ADRs involve interactions that are detectable in large, and increasingly public, compound screening campaigns, we generated logistic regression models that correlate postmarketing ADRs with screening data from the PubChem BioAssay database. These models analyze ADRs at the level of organ systems, using the system organ classes (SOCs). Of the 19 SOCs under consideration, nine were found to be significantly correlated with preclinical screening data. With regard to six of the eight established drugs for which we could retropredict SOC-specific ADRs, prior knowledge was found that supports these predictions. We conclude this paper by predicting that SOC-specific ADRs will be associated with three unapproved or recently introduced drugs.

| S-EPMC3464971 | biostudies-literature

Maximizing gain in high-throughput screening using conformal prediction.

Project description:Iterative screening has emerged as a promising approach to increase the efficiency of screening campaigns compared to traditional high throughput approaches. By learning from a subset of the compound library, inferences on what compounds to screen next can be made by predictive models, resulting in more efficient screening. One way to evaluate screening is to consider the cost of screening compared to the gain associated with finding an active compound. In this work, we introduce a conformal predictor coupled with a gain-cost function with the aim to maximise gain in iterative screening. Using this setup we were able to show that by evaluating the predictions on the training data, very accurate predictions on what settings will produce the highest gain on the test data can be made. We evaluate the approach on 12 bioactivity datasets from PubChem training the models using 20% of the data. Depending on the settings of the gain-cost function, the settings generating the maximum gain were accurately identified in 8-10 out of the 12 datasets. Broadly, our approach can predict what strategy generates the highest gain based on the results of the cost-gain evaluation: to screen the compounds predicted to be active, to screen all the remaining data, or not to screen any additional compounds. When the algorithm indicates that the predicted active compounds should be screened, our approach also indicates what confidence level to apply in order to maximize gain. Hence, our approach facilitates decision-making and allocation of the resources where they deliver the most value by indicating in advance the likely outcome of a screening campaign.

| S-EPMC5821614 | biostudies-literature

Modelling of free-form conformal metasurfaces.

Project description:Artificial electromagnetic surfaces, metasurfaces, control light in the desired manner through the introduction of abrupt changes of electromagnetic fields at interfaces. Current modelling of metasurfaces successfully exploits generalised sheet transition conditions (GSTCs), a set of boundary conditions that account for electric and magnetic metasurface-induced optical responses. GSTCs are powerful theoretical tools but they are not readily applicable for arbitrarily shaped metasurfaces. Accurate and computationally efficient algorithms capable of implementing artificial boundary conditions are highly desired for designing free-form photonic devices. To address this challenge, we propose a numerical method based on conformal boundary optics with a modified finite difference time-domain (FDTD) approach which accurately calculates the electromagnetic fields across conformal metasurfaces. Illustrative examples of curved meta-optics are presented, showing results in good agreement with theoretical predictions. This method can become a powerful tool for designing and predicting optical functionalities of conformal metasurfaces for new lightweight, flexible and wearable photonic devices.

| S-EPMC6113266 | biostudies-literature

Automated evaluation of consistency within the PubChem Compound database.

Project description:Identification of discrepant data in aggregated databases is a key step in data curation and remediation. We have applied the ALATIS approach, which is based on the international chemical shift identifier (InChI) model, to the full PubChem Compound database to generate unique and reproducible compound and atom identifiers for all entries for which three-dimensional structures were available. This exercise also served to identify entries with discrepancies between structures and chemical formulas or InChI strings. The use of unique compound identifiers and atom nomenclature should support more rigorous links between small-molecule databases including those containing atom-specific information of the type available from crystallography and spectroscopy. The comprehensive results from this analysis are publicly available through our webserver [http://alatis.nmrfam.wisc.edu/].

| S-EPMC6380220 | biostudies-other

Predicting Off-Target Binding Profiles With Confidence Using Conformal Prediction.

Project description:Ligand-based models can be used in drug discovery to obtain an early indication of potential off-target interactions that could be linked to adverse effects. Another application is to combine such models into a panel, allowing to compare and search for compounds with similar profiles. Most contemporary methods and implementations however lack valid measures of confidence in their predictions, and only provide point predictions. We here describe a methodology that uses Conformal Prediction for predicting off-target interactions, with models trained on data from 31 targets in the ExCAPE-DB dataset selected for their utility in broad early hazard assessment. Chemicals were represented by the signature molecular descriptor and support vector machines were used as the underlying machine learning method. By using conformal prediction, the results from predictions come in the form of confidence p-values for each class. The full pre-processing and model training process is openly available as scientific workflows on GitHub, rendering it fully reproducible. We illustrate the usefulness of the developed methodology on a set of compounds extracted from DrugBank. The resulting models are published online and are available via a graphical web interface and an OpenAPI interface for programmatic access.

| S-EPMC6233526 | biostudies-literature

PubChemRDF: towards the semantic annotation of PubChem compound and substance databases.

Project description:BackgroundPubChem is an open repository for chemical structures, biological activities and biomedical annotations. Semantic Web technologies are emerging as an increasingly important approach to distribute and integrate scientific data. Exposing PubChem data to Semantic Web services may help enable automated data integration and management, as well as facilitate interoperable web applications.DescriptionThis work, one of a series covering the PubChemRDF project, describes an approach to translate PubChem Substance and Compound information into Resource Description Framework (RDF) format. Basic examples are provided to demonstrate its use. The aim of this effort is to provide two new primary benefits to researchers in a cost-effective manner. Firstly, we aim to remove the inherent limitations of using the web-based resource PubChem by allowing a researcher to use readily available semantic technologies (namely, RDF triple stores and their corresponding SPARQL query engines) to query and analyze PubChem data on local computing resources. Secondly, this work intends to help improve data sharing, analysis, and integration of PubChem data to resources external to NCBI and across scientific domains, by means of the association of PubChem data to existing ontological frameworks, including CHEMical INFormation ontology, Semanticscience Integrated Ontology, and others.ConclusionsWith the goal of semantically describing information available in the PubChem archive, pre-existing ontological frameworks were used, rather than creating new ones. Semantic relationships between compounds and substances, chemical descriptors associated with compounds and substances, interrelationships between chemicals, as well as provenance and attribute metadata of substances are described. Graphical abstract:Schematic representation of the semantic links for PubChem compounds and substances.

| S-EPMC4500850 | biostudies-literature

PubChem Protein, Gene, Pathway, and Taxonomy Data Collections: Bridging Biology and Chemistry through Target-Centric Views of PubChem Data.

Project description:PubChem (https://pubchem.ncbi.nlm.nih.gov) is a public chemical database at the U.S. National Institutes of Health. Visited by millions of users every month, it plays a role as a key chemical information resource for biomedical research communities. Data in PubChem is from hundreds of contributors and organized into multiple collections by record type. Among these are the Protein, Gene, Pathway, and Taxonomy data collections. Records in these collections contain information on chemicals related to a given biological target (i.e., protein, gene, pathway, or taxon), helping users to analyze and interpret the biological activity data of molecules. In addition, annotations about the biological targets are collected from authoritative or curated data sources and integrated into the four collections. The content can be programmatically accessed through PubChem's web service interfaces (including PUG View). A machine-readable representation of this content is also provided within PubChemRDF.

| S-EPMC9177802 | biostudies-literature

Discovery of Novel eEF2K Inhibitors Using HTS Fingerprint Generated from Predicted Profiling of Compound-Protein Interactions.

Project description:Background: Eukaryotic elongation factor 2 kinase (eEF2K) regulates the elongation stage of protein synthesis by phosphorylating eEF2, a process related to various diseases including cancer and cardiovascular and neurodegenerative diseases. In this study, we describe the identification of novel eEF2K inhibitors using high-throughput screening fingerprints (HTSFP) generated from predicted profiling of compound-protein interactions (CPIs). Methods: We utilized computationally generated HTSFPs referred to as chemical genomics-based fingerprint (CGBFP). Generally, HTSFPs are generated from multiple biochemical or cell-based assay data. On the other hand, CGBFPs are generated from computational prediction of CPIs using the Chemical Genomics-Based Virtual Screening (CGBVS) method. Therefore, CGBFPs do not have missing information mainly caused by the absence of assay data. Results: Chemogenomics-Based Similarity Profiling (CGBSP) of the screening library (2.6 million compounds) yielded 27 compounds which were evaluated for in vitro eEF2K inhibitory activity. Three compounds with interesting results were identified. Compounds 2 (IC50 = 11.05 μM) and 4 (IC50 = 43.54 μM) are thieno[2,3-b]pyridine derivatives that have the same scaffolds with a known eEF2K inhibitor, while compound 13 (IC50 = 70.13 μM) was a new thiophene-2-amine-type eEF2K inhibitor. Conclusions: CGBSP supplied an efficient strategy in the identification of novel eEF2K inhibitors and provided useful scaffolds for optimization.

| S-EPMC8161098 | biostudies-literature

Estimating diagnostic uncertainty in artificial intelligence assisted pathology using conformal prediction.

Project description:Unreliable predictions can occur when an artificial intelligence (AI) system is presented with data it has not been exposed to during training. We demonstrate the use of conformal prediction to detect unreliable predictions, using histopathological diagnosis and grading of prostate biopsies as example. We digitized 7788 prostate biopsies from 1192 men in the STHLM3 diagnostic study, used for training, and 3059 biopsies from 676 men used for testing. With conformal prediction, 1 in 794 (0.1%) predictions is incorrect for cancer diagnosis (compared to 14 errors [2%] without conformal prediction) while 175 (22%) of the predictions are flagged as unreliable when the AI-system is presented with new data from the same lab and scanner that it was trained on. Conformal prediction could with small samples (N = 49 for external scanner, N = 10 for external lab and scanner, and N = 12 for external lab, scanner and pathology assessment) detect systematic differences in external data leading to worse predictive performance. The AI-system with conformal prediction commits 3 (2%) errors for cancer detection in cases of atypical prostate tissue compared to 44 (25%) without conformal prediction, while the system flags 143 (80%) unreliable predictions. We conclude that conformal prediction can increase patient safety of AI-systems.

| S-EPMC9755280 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data