Improving QSAR Modeling for Predictive Toxicology using Publicly Aggregated Semantic Graph Data and Graph Neural Networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Romano JD
PROVIDER: S-EPMC8714189 | biostudies-literature | 2022
REPOSITORIES: biostudies-literature
Publications
Improving QSAR Modeling for Predictive Toxicology using Publicly Aggregated Semantic Graph Data and Graph Neural Networks.
Romano Joseph D JD Hao Yun Y Moore Jason H JH
Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing 20220101
Quantitative Structure-Activity Relationship (QSAR) modeling is a common computational technique for predicting chemical toxicity, but a lack of new methodological innovations has impeded QSAR performance on many tasks. We show that contemporary QSAR modeling for predictive toxicology can be substantially improved by incorporating semantic graph data aggregated from open-access public databases, and analyzing those data in the context of graph neural networks (GNNs). Furthermore, we introspect t ...[more]
Similar Datasets
Project description:Modern high-throughput sequencing technologies provide low-cost microbiome survey data across all habitats of life at unprecedented scale. At the most granular level, the primary data consist of sparse counts of amplicon sequence variants or operational taxonomic units that are associated with taxonomic and phylogenetic group information. In this contribution, we leverage the hierarchical structure of amplicon data and propose a data-driven and scalable tree-guided aggregation framework to associate microbial subcompositions with response variables of interest. The excess number of zero or low count measurements at the read level forces traditional microbiome data analysis workflows to remove rare sequencing variants or group them by a fixed taxonomic rank, such as genus or phylum, or by phylogenetic similarity. By contrast, our framework, which we call trac (tree-aggregation of compositional data), learns data-adaptive taxon aggregation levels for predictive modeling, greatly reducing the need for user-defined aggregation in preprocessing while simultaneously integrating seamlessly into the compositional data analysis framework. We illustrate the versatility of our framework in the context of large-scale regression problems in human gut, soil, and marine microbial ecosystems. We posit that the inferred aggregation levels provide highly interpretable taxon groupings that can help microbiome researchers gain insights into the structure and functioning of the underlying ecosystem of interest.
| S-EPMC8282688 | biostudies-literature
Project description:Malaria is a predominant infectious disease, with a global footprint, but especially severe in developing countries in the African subcontinent. In recent years, drug-resistant malaria has become an alarming factor, and hence the requirement of new and improved drugs is more crucial than ever before. One of the promising locations for antimalarial drug target is the apicoplast, as this organelle does not occur in humans. The apicoplast is associated with many unique and essential pathways in many Apicomplexan pathogens, including Plasmodium. The use of machine learning methods is now commonly available through open source programs. In the present work, we describe a standard protocol to develop molecular descriptor based predictive models (QSAR models), which can be further utilized for the screening of large chemical libraries. This protocol is used to build models using training data sourced from apicoplast specific bioassays. Multiple model building methods are used including Generalized Linear Models (GLM), Random Forest (RF), C5.0 implementation of a decision tree, Support Vector Machines (SVM), K-Nearest Neighbour and Naive Bayes. Methods to evaluate the accuracy of the model building method are included in the protocol. For the given dataset, the C5.0, SVM and RF perform better than other methods, with comparable accuracy over the test data.
| S-EPMC5498782 | biostudies-other
Project description:BackgroundThe OpenTox Framework, developed by the partners in the OpenTox project (http://www.opentox.org), aims at providing a unified access to toxicity data, predictive models and validation procedures. Interoperability of resources is achieved using a common information model, based on the OpenTox ontologies, describing predictive algorithms, models and toxicity data. As toxicological data may come from different, heterogeneous sources, a deployed ontology, unifying the terminology and the resources, is critical for the rational and reliable organization of the data, and its automatic processing.ResultsThe following related ontologies have been developed for OpenTox: a) Toxicological ontology - listing the toxicological endpoints; b) Organs system and Effects ontology - addressing organs, targets/examinations and effects observed in in vivo studies; c) ToxML ontology - representing semi-automatic conversion of the ToxML schema; d) OpenTox ontology- representation of OpenTox framework components: chemical compounds, datasets, types of algorithms, models and validation web services; e) ToxLink-ToxCast assays ontology and f) OpenToxipedia community knowledge resource on toxicology terminology.OpenTox components are made available through standardized REST web services, where every compound, data set, and predictive method has a unique resolvable address (URI), used to retrieve its Resource Description Framework (RDF) representation, or to initiate the associated calculations and generate new RDF-based resources.The services support the integration of toxicity and chemical data from various sources, the generation and validation of computer models for toxic effects, seamless integration of new algorithms and scientifically sound validation routines and provide a flexible framework, which allows building arbitrary number of applications, tailored to solving different problems by end users (e.g. toxicologists).AvailabilityThe OpenTox toxicological ontology projects may be accessed via the OpenTox ontology development page http://www.opentox.org/dev/ontology; the OpenTox ontology is available as OWL at http://opentox.org/api/1 1/opentox.owl, the ToxML - OWL conversion utility is an open source resource available at http://ambit.svn.sourceforge.net/viewvc/ambit/branches/toxml-utils/
| S-EPMC3337268 | biostudies-literature
Project description:Exponential random graph models (ERGMs), also known as p* models, have been utilized extensively in the social science literature to study complex networks and how their global structure depends on underlying structural components. However, the literature on their use in biological networks (especially brain networks) has remained sparse. Descriptive models based on a specific feature of the graph (clustering coefficient, degree distribution, etc.) have dominated connectivity research in neuroscience. Corresponding generative models have been developed to reproduce one of these features. However, the complexity inherent in whole-brain network data necessitates the development and use of tools that allow the systematic exploration of several features simultaneously and how they interact to form the global network architecture. ERGMs provide a statistically principled approach to the assessment of how a set of interacting local brain network features gives rise to the global structure. We illustrate the utility of ERGMs for modeling, analyzing, and simulating complex whole-brain networks with network data from normal subjects. We also provide a foundation for the selection of important local features through the implementation and assessment of three selection approaches: a traditional p-value based backward selection approach, an information criterion approach (AIC), and a graphical goodness of fit (GOF) approach. The graphical GOF approach serves as the best method given the scientific interest in being able to capture and reproduce the structure of fitted brain networks.
| S-EPMC3102079 | biostudies-other
Project description:Semantic processing (SP) is one of the critical abilities of humans for representing and manipulating conceptual and meaningful information. Neuroimaging studies of SP typically collapse data from many subjects, but its neural organization and behavioral performance vary between individuals. It is not yet understood whether and how the individual variabilities in neural network organizations contribute to the individual differences in SP behaviors. We aim to identify the neural signatures underlying SP variabilities by analyzing functional connectivity (FC) patterns based on a large-sample Human Connectome Project (HCP) dataset and rigorous predictive modeling. We used a two-stage predictive modeling approach to build an internally cross-validated model and to test the model's generalizability with unseen data from different HCP samples and other out-of-sample datasets. FC patterns within a putative semantic brain network were significantly predictive of individual SP scores summarized from five SP-related behavioral tests. This cross-validated model can be used to predict unseen HCP data. The model generalizability was enhanced in the language task compared with other tasks used during scanning and was better for females than males. The model constructed from the HCP dataset can be partially generalized to two independent cohorts that participated in different semantic tasks. FCs connecting to the Perisylvian language network show the most reliable contributions to predictive modeling and the out-of-sample generalization. These findings contribute to our understanding of the neural sources of individual differences in SP, which potentially lay the foundation for personalized education for healthy individuals and intervention for SP and language deficits patients.
| S-EPMC9435002 | biostudies-literature
Project description:BackgroundBirth defects are functional and structural abnormalities that impact about 1 in 33 births in the United States. They have been attributed to genetic and other factors such as drugs, cosmetics, food, and environmental pollutants during pregnancy, but for most birth defects there are no known causes.MethodsTo further characterize associations between small molecule compounds and their potential to induce specific birth abnormalities, we gathered knowledge from multiple sources to construct a reproductive toxicity Knowledge Graph (ReproTox-KG) with a focus on associations between birth defects, drugs, and genes. Specifically, we gathered data from drug/birth-defect associations from co-mentions in published abstracts, gene/birth-defect associations from genetic studies, drug- and preclinical-compound-induced gene expression changes in cell lines, known drug targets, genetic burden scores for human genes, and placental crossing scores for small molecules.ResultsUsing ReproTox-KG and semi-supervised learning (SSL), we scored >30,000 preclinical small molecules for their potential to cross the placenta and induce birth defects, and identified >500 birth-defect/gene/drug cliques that can be used to explain molecular mechanisms for drug-induced birth defects. The ReproTox-KG can be accessed via a web-based user interface available at https://maayanlab.cloud/reprotox-kg . This site enables users to explore the associations between birth defects, approved and preclinical drugs, and all human genes.ConclusionsReproTox-KG provides a resource for exploring knowledge about the molecular mechanisms of birth defects with the potential of predicting the likelihood of genes and preclinical small molecules to induce birth defects.
| S-EPMC10352311 | biostudies-literature
Project description:In the past few years, the study of therapeutic RNA nanotechnology has expanded tremendously to encompass a large group of interdisciplinary sciences. It is now evident that rationally designed programmable RNA nanostructures offer unique advantages in addressing contemporary therapeutic challenges such as distinguishing target cell types and ameliorating disease. However, to maximize the therapeutic benefit of these nanostructures, it is essential to understand the immunostimulatory aptitude of such tools and identify potential complications. This paper presents a set of 16 nanoparticle platforms that are highly configurable. These novel nucleic acid based polygonal platforms are programmed for controllable self-assembly from RNA and/or DNA strands via canonical Watson-Crick interactions. It is demonstrated that the immunostimulatory properties of these particular designs can be tuned to elicit the desired immune response or lack thereof. To advance the current understanding of the nanoparticle properties that contribute to the observed immunomodulatory activity and establish corresponding designing principles, quantitative structure-activity relationship modeling is conducted. The results demonstrate that molecular weight, together with melting temperature and half-life, strongly predicts the observed immunomodulatory activity. This framework provides the fundamental guidelines necessary for the development of a new library of nanoparticles with predictable immunomodulatory activity.
| S-EPMC6258062 | biostudies-literature
Project description:Graph neural networks (GNNs) have proven to be effective in the prediction of chemical reaction yields. However, their performance tends to deteriorate when they are trained using an insufficient training dataset in terms of quantity or diversity. A promising solution to alleviate this issue is to pre-train a GNN on a large-scale molecular database. In this study, we investigate the effectiveness of GNN pre-training in chemical reaction yield prediction. We present a novel GNN pre-training method for performance improvement.Given a molecular database consisting of a large number of molecules, we calculate molecular descriptors for each molecule and reduce the dimensionality of these descriptors by applying principal component analysis. We define a pre-text task by assigning a vector of principal component scores as the pseudo-label to each molecule in the database. A GNN is then pre-trained to perform the pre-text task of predicting the pseudo-label for the input molecule. For chemical reaction yield prediction, a prediction model is initialized using the pre-trained GNN and then fine-tuned with the training dataset containing chemical reactions and their yields. We demonstrate the effectiveness of the proposed method through experimental evaluation on benchmark datasets.
| S-EPMC10905905 | biostudies-literature
Project description:Linking distal enhancers to genes and modeling their impact on target gene expression are longstanding unresolved problems in regulatory genomics and critical for interpreting noncoding genetic variation. Here, we present a new deep learning approach called GraphReg that exploits 3D interactions from chromosome conformation capture assays to predict gene expression from 1D epigenomic data or genomic DNA sequence. By using graph attention networks to exploit the connectivity of distal elements up to 2 Mb away in the genome, GraphReg more faithfully models gene regulation and more accurately predicts gene expression levels than the state-of-the-art deep learning methods for this task. Feature attribution used with GraphReg accurately identifies functional enhancers of genes, as validated by CRISPRi-FlowFISH and TAP-seq assays, outperforming both convolutional neural networks (CNNs) and the recently proposed activity-by-contact model. Sequence-based GraphReg also accurately predicts direct transcription factor (TF) targets as validated by CRISPRi TF knockout experiments via in silico ablation of TF binding motifs. GraphReg therefore represents an important advance in modeling the regulatory impact of epigenomic and sequence elements.
| S-EPMC9104700 | biostudies-literature
Project description:Simple physico-chemical properties, like logD, solubility, or melting point, can reveal a great deal about how a compound under development might later behave. These data are typically measured for most compounds in drug discovery projects in a medium throughput fashion. Collecting and assembling all the Bayer in-house data related to these properties allowed us to apply powerful machine learning techniques to predict the outcome of those assays for new compounds. In this paper, we report our finding that, especially for predicting physicochemical ADMET endpoints, a multitask graph convolutional approach appears a highly competitive choice. For seven endpoints of interest, we compared the performance of that approach to fully connected neural networks and different single task models. The new model shows increased predictive performance compared to previous modeling methods and will allow early prioritization of compounds even before they are synthesized. In addition, our model follows the generalized solubility equation without being explicitly trained under this constraint.
| S-EPMC6982787 | biostudies-literature