Browse
Submit Data
Databases
API
Help

Dataset Information

43 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Bioactivity descriptors for uncharacterized chemical compounds.

ABSTRACT: Chemical descriptors encode the physicochemical and structural properties of small molecules, and they are at the core of chemoinformatics. The broad release of bioactivity data has prompted enriched representations of compounds, reaching beyond chemical structures and capturing their known biological properties. Unfortunately, bioactivity descriptors are not available for most small molecules, which limits their applicability to a few thousand well characterized compounds. Here we present a collection of deep neural networks able to infer bioactivity signatures for any compound of interest, even when little or no experimental information is available for them. Our signaturizers relate to bioactivities of 25 different types (including target profiles, cellular response and clinical outcomes) and can be used as drop-in replacements for chemical descriptors in day-to-day chemoinformatics tasks. Indeed, we illustrate how inferred bioactivity signatures are useful to navigate the chemical space in a biologically relevant manner, unveiling higher-order organization in natural product collections, and to enrich mostly uncharacterized chemical libraries for activity against the drug-orphan target Snail1. Moreover, we implement a battery of signature-activity relationship (SigAR) models and show a substantial improvement in performance, with respect to chemistry-based classifiers, across a series of biophysics and physiology activity prediction benchmarks.

SUBMITTER: Bertoni M

PROVIDER: S-EPMC8225676 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

The Internal Relation between Quantum Chemical Descriptors and Empirical Constants of Polychlorinated Compounds.

Project description:Quantum chemical descriptors and empirical parameters are two different types of chemical parameters that play the fundamental roles in chemical reactivity and model development. However, previous studies have lacked detail regarding the relationship between quantum chemical descriptors and empirical constants. We selected polychlorinated biphenyls (PCBs) as an object to investigate the intrinsic correlation between 16 quantum chemical descriptors and Hammett constants. The results exhibited extremely high linearity for ? with Qxx/yy/zz, ? and EHOMO based on the meta-position grouping. Polychlorinated dibenzodioxins (PCDDs) and polychlorinated naphthalenes (PCNs) congeners, as two independent compounds, validated the reliability of the relationship. The meta-substituent grouping method between ? and ? was successfully used to predict the rate constant (k) for •OH oxidation of PCBs, as well as the octanol/water partition coefficient (logKOW) and aqueous solubility (-logSW) of PCDDs, and exhibited excellent agreement with experimental measurements. Revealing the intrinsic correlation underlying the empirical constant and quantum chemical descriptors can develop simpler and higher efficient model application in predicting the environmental behavior and chemical properties of compounds.

| S-EPMC6278375 | biostudies-literature

Bioactivity, Compounds Isolated, Chemical Qualitative, and Quantitative Analysis of Cymbaria daurica Extracts.

Project description:Cymbaria daurica L. is widely used in traditional Mongolian medicine for the treatment of impetigo, psoriasis, pruritus, fetotoxicity, and diabetes. Therefore, the anti-inflammatory and ?-glucosidase-inhibitory activities of four polar C. daurica extracts (water, n-butanol, ethyl acetate, and petroleum ether extract) were preliminarily evaluated to identify the active extracts. We also investigated the chemical composition of the active extracts by phytochemical analysis. The n-butanol and ethyl acetate extracts exhibited significant (p < 0.05) anti-inflammatory activities by inhibiting lipopolysaccharide-induced nitric oxide (NO) production in RAW 264.7 cells. None of the tested extracts exhibited cytotoxic effects at the effective concentrations. The ethyl acetate extract significantly inhibited ?-glucosidase activity, and the inhibition potency was equivalent to that of acarbose (p > 0.05). The n-Butanol extract presented the second highest inhibitory activity. As the n-butanol and ethyl acetate extracts were found to have potent anti-inflammatory and ?-glucosidase-inhibitory activities, we separated and identified 10 compounds from the extracts. Among them, vanillic acid, cistanoside F, echinacoside, arenarioside, verbascoside, isoacteoside, and tricin were isolated from C. daurica for the first time. Further, 30 compounds from the n-butanol and ethyl acetate extracts of C. daurica were identified using UHPLC-Q-Exactive. The present study demonstrates for the first time that C. daurica contains phenylethanoid glycosides. In addition, this novel HPLC method was subsequently used for simultaneous identification of five compounds in the n-butanol and ethyl acetate extracts of C. daurica. This study provides a chemical basis for further characterization and utilization of C. daurica, which could be a potential source of novel anti-diabetic and anti-inflammatory agents.

| S-EPMC7019114 | biostudies-literature

High-throughput metabolomic analysis predicts mode of action for uncharacterized antimicrobial compounds

Project description: Not available

| S-BSST113 | biostudies-other

Relating Chemical Structure to Cellular Response: An Integrative Analysis of Gene Expression, Bioactivity, and Structural Data Across 11,000 Compounds.

Project description:A central premise in systems pharmacology is that structurally similar compounds have similar cellular responses; however, this principle often does not hold. One of the most widely used measures of cellular response is gene expression. By integrating gene expression data from Library of Integrated Network-based Cellular Signatures (LINCS) with chemical structure and bioactivity data from PubChem, we performed a large-scale correlation analysis of chemical structures and gene expression profiles of over 11,000 compounds taking into account confounding factors such as biological conditions (e.g., cell line, dose) and bioactivities. We found that structurally similar compounds do indeed yield similar gene expression profiles. There is an ∼20% chance that two structurally similar compounds (Tanimoto Coefficient ≥ 0.85) share significantly similar gene expression profiles. Regardless of structural similarity, two compounds tend to share similar gene expression profiles in a cell line when they are administrated at a higher dose or when the cell line is sensitive to both compounds.

| S-EPMC4625862 | biostudies-literature

Physical and chemical descriptors for predicting interfacial thermal resistance.

Project description:Heat transfer at interfaces plays a critical role in material design and device performance. Higher interfacial thermal resistances (ITRs) affect the device efficiency and increase the energy consumption. Conversely, higher ITRs can enhance the figure of merit of thermoelectric materials by achieving ultra-low thermal conductivity via nanostructuring. This study proposes a dataset of descriptors for predicting the ITRs. The dataset includes two parts: one part consists of ITRs data collected from 87 experimental papers and the other part consists of the descriptors of 289 materials, which can construct over 80,000 pair-material systems for ITRs prediction. The former part is composed of over 1300 data points of metal/nonmetal, nonmetal/nonmetal, and metal/metal interfaces. The latter part consists of physical and chemical properties that are highly correlated to the ITRs. The synthesis method of the materials and the thermal measurement technique are also recorded in the dataset for further analyses. These datasets can be applied not only to ITRs predictions but also to thermal-property predictions or heat transfer on various material systems.

| S-EPMC6997172 | biostudies-literature

High-throughput metabolomic analysis predicts mode of action of uncharacterized antimicrobial compounds.

Project description:Rapidly spreading antibiotic resistance and the low discovery rate of new antimicrobial compounds demand more effective strategies for early drug discovery. One bottleneck in the drug discovery pipeline is the identification of the modes of action (MoAs) of new compounds. We have developed a rapid systematic metabolome profiling strategy to classify the MoAs of bioactive compounds. The method predicted MoA-specific metabolic responses in the nonpathogenic bacterium Mycobacterium smegmatis after treatment with 62 reference compounds with known MoAs and different metabolic and nonmetabolic targets. We then analyzed a library of 212 new antimycobacterial compounds with unknown MoAs from a drug discovery effort by the pharmaceutical company GlaxoSmithKline (GSK). More than 70% of these new compounds induced metabolic responses in M. smegmatis indicative of known MoAs, seven of which were experimentally validated. Only 8% (16) of the compounds appeared to target unconventional cellular processes, illustrating the difficulty in discovering new antibiotics with different MoAs among compounds used as monotherapies. For six of the GSK compounds with potentially new MoAs, the metabolome profiles suggested their ability to interfere with trehalose and lipid metabolism. This was supported by whole-genome sequencing of spontaneous drug-resistant mutants of the pathogen Mycobacterium tuberculosis and in vitro compound-proteome interaction analysis for one of these compounds. Our compendium of drug-metabolome profiles can be used to rapidly query the MoAs of uncharacterized antimicrobial compounds and should be a useful resource for the drug discovery community.

| S-EPMC6544516 | biostudies-literature

Distinguishing compounds with anticancer activity by ANN using inductive QSAR descriptors.

Project description:This article describes a method developed for predicting anticancer/non-anticancer drugs using artificial neural network (ANN). The ANN used in this study is a feed-forward neural network with a standard back-propagation training algorithm. Using 30 'inductive' QSAR descriptors alone, we have been able to achieve 84.28% accuracy for correct separation of compounds with- and without anticancer activity. For the complete set of 30 inductive QSAR descriptors, ANN based method reveals a superior model (accuracy = 84.28%, Q(pred) = 74.28%, sensitivity = 0.9285, specificity = 0.7857, Matthews correlation coefficient (MCC) = 0.6998). The method was trained and tested on a non redundant data set of 380 drugs (122 anticancer and 258 non-anticancer). The elaborated QSAR model based on the Artificial Neural Networks approach has been extensively validated and has confidently assigned anticancer character to a number of trial anticancer drugs from the literature.

| S-EPMC2561164 | biostudies-literature

Theoretical prediction of hydrogen-bond basicity pKBHX using quantum chemical topology descriptors.

Project description:Hydrogen bonding plays an important role in the interaction of biological molecules and their local environment. Hydrogen-bond strengths have been described in terms of basicities by several different scales. The pKBHX scale has been developed with the interests of medicinal chemists in mind. The scale uses equilibrium constants of acid···base complexes to describe basicity and is therefore linked to Gibbs free energy. Site specific data for polyfunctional bases are also available. The pKBHX scale applies to all hydrogen-bond donors (HBDs) where the HBD functional group is either OH, NH, or NH+. It has been found that pKBHX can be described in terms of a descriptor defined by quantum chemical topology, ΔE(H), which is the change in atomic energy of the hydrogen atom upon complexation. Essentially the computed energy of the HBD hydrogen atom correlates with a set of 41 HBAs for five common HBDs, water (r2=0.96), methanol (r2=0.95), 4-fluorophenol (r2=0.91), serine (r2=0.93), and methylamine (r2=0.97). The connection between experiment and computation was strengthened with the finding that there is no relationship between ΔE(H) and pKBHX when hydrogen fluoride was used as the HBD. Using the methanol model, pKBHX predictions were made for an external set of bases yielding r2=0.90. Furthermore, the basicities of polyfunctional bases correlate with ΔE(H), giving r2=0.93. This model is promising for the future of computation in fragment-based drug design. Not only has a model been established that links computation to experiment, but the model may also be extrapolated to predict external experimental pKBHX values.

| S-EPMC4004274 | biostudies-other

Pyrrole and Fused Pyrrole Compounds with Bioactivity against Inflammatory Mediators.

Project description:A new series of pyrrolopyridines and pyrrolopyridopyrimidines have been synthesized from aminocyanopyrroles. The synthesized compounds have been characterized by FTIR, ¹H-NMR and mass spectroscopy. The final compounds have been screened for in vitro pro-inflammatory cytokine inhibitory and in vivo anti-inflammatory activity. The biological results revealed that among all tested compounds some fused pyrroles, namely the pyrrolopyridines 3i and 3l, show promising activity. A docking study of the active synthesized molecules confirmed the biological results and revealed a new binding pose in the COX-2 binding site.

| S-EPMC6155178 | biostudies-literature

Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations.

Project description:There has been a recent surge of interest in using machine learning across chemical space in order to predict properties of molecules or design molecules and materials with the desired properties. Most of this work relies on defining clever feature representations, in which the chemical graph structure is encoded in a uniform way such that predictions across chemical space can be made. In this work, we propose to exploit the powerful ability of deep neural networks to learn a feature representation from low-level encodings of a huge corpus of chemical structures. Our model borrows ideas from neural machine translation: it translates between two semantically equivalent but syntactically different representations of molecular structures, compressing the meaningful information both representations have in common in a low-dimensional representation vector. Once the model is trained, this representation can be extracted for any new molecule and utilized as a descriptor. In fair benchmarks with respect to various human-engineered molecular fingerprints and graph-convolution models, our method shows competitive performance in modelling quantitative structure-activity relationships in all analysed datasets. Additionally, we show that our descriptor significantly outperforms all baseline molecular fingerprints in two ligand-based virtual screening tasks. Overall, our descriptors show the most consistent performances in all experiments. The continuity of the descriptor space and the existence of the decoder that permits deducing a chemical structure from an embedding vector allow for exploration of the space and open up new opportunities for compound optimization and idea generation.

| S-EPMC6368215 | 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