Browse
Submit Data
Databases
API
Help

Dataset Information

7 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

MetaClass, a Comprehensive Classification System for Predicting the Occurrence of Metabolic Reactions Based on the MetaQSAR Database.

ABSTRACT: (1) Background: Machine learning algorithms are finding fruitful applications in predicting the ADME profile of new molecules, with a particular focus on metabolism predictions. However, the development of comprehensive metabolism predictors is hampered by the lack of highly accurate metabolic resources. Hence, we recently proposed a manually curated metabolic database (MetaQSAR), the level of accuracy of which is well suited to the development of predictive models. (2) Methods: MetaQSAR was used to extract datasets to predict the metabolic reactions subdivided into major classes, classes and subclasses. The collected datasets comprised a total of 3788 first-generation metabolic reactions. Predictive models were developed by using standard random forest algorithms and sets of physicochemical, stereo-electronic and constitutional descriptors. (3) Results: The developed models showed satisfactory performance, especially for hydrolyses and conjugations, while redox reactions were predicted with greater difficulty, which was reasonable as they depend on many complex features that are not properly encoded by the included descriptors. (4) Conclusions: The generated models allowed a precise comparison of the propensity of each metabolic reaction to be predicted and the factors affecting their predictability were discussed in detail. Overall, the study led to the development of a freely downloadable global predictor, MetaClass, which correctly predicts 80% of the reported reactions, as assessed by an explorative validation analysis on an external dataset, with an overall MCC = 0.44.

SUBMITTER: Mazzolari A

PROVIDER: S-EPMC8512547 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

iProClass: an integrated, comprehensive and annotated protein classification database.

Project description:The iProClass database is an integrated resource that provides comprehensive family relationships and structural and functional features of proteins, with rich links to various databases. It is extended from ProClass, a protein family database that integrates PIR superfamilies and PROSITE motifs. The iProClass currently consists of more than 200,000 non-redundant PIR and SWISS-PROT proteins organized with more than 28,000 superfamilies, 2600 domains, 1300 motifs, 280 post-translational modification sites and links to more than 30 databases of protein families, structures, functions, genes, genomes, literature and taxonomy. Protein and family summary reports provide rich annotations, including membership information with length, taxonomy and keyword statistics, full family relationships, comprehensive enzyme and PDB cross-references and graphical feature display. The database facilitates classification-driven annotation for protein sequence databases and complete genomes, and supports structural and functional genomic research. The iProClass is implemented in Oracle 8i object-relational system and available for sequence search and report retrieval at http://pir.georgetown.edu/iproclass/.

| S-EPMC29833 | biostudies-literature

The Comprehensive AOCMF Classification System: Classification and Documentation within AOCOIAC Software.

Project description:The AOCMF Classification Group developed a hierarchical three-level craniomaxillofacial (CMF) fracture classification system. The fundamental level 1 distinguishes four major anatomical units including the mandible (code 91), midface (code 92), skull base (code 93) and cranial vault (code 94); level 2 relates to the location of the fractures within defined topographical regions within each units; level 3 relates to fracture morphology in these regions regarding fragmentation, displacement, and bone defects, as well as the involvement of specific anatomical structures. The resulting CMF classification system has been implemented into AO comprehensive injury automatic classifier (AOCOIAC) software allowing for fracture classification as well as clinical documentation of individual cases including a selected sample of diagnostic images. This tutorial highlights the main features of the software. In addition, a series of illustrative case examples is made available electronically for viewing and editing.

| S-EPMC4251723 | biostudies-other

A comprehensive database of squirrel distribution and occurrence in South Asia.

Project description:BackgroundThe Squirrels of South Asia (SOSA) database compiles comprehensive distribution and occurrence information on all squirrel species that occur in this region (34 species). These 34 squirrel species, including tree, flying and ground squirrels, represent 14% of global sciurid diversity. The database collates curated data from various sources such as museums, literature, primary fieldwork, citizen science and social media platforms and covers the entire distributional ranges of the target species, including countries in Central Asia and Southeast Asia when required. The SOSA database enhances our understanding of squirrel distribution, population dynamics and their conservation needs in South Asia by consolidating information. It aims to be a valuable resource for researchers, conservationists and wildlife enthusiasts.New informationAs of March 2023, the database comprises over 40,000 records of 34 species in over 30 countries globally. Spending an average of 334 hours on each species, more than 20 data collectors put in over 10,000 hours to gather, curate and build this database. The database has resulted in novel records of species occurrence in regions and countries that are poorly represented in currently available global data repositories. The current version which has been made public via GBIF comprises of 1187 records of all 34 species across multiple sources. This is a subset of the SOSA database.

| S-EPMC10838086 | biostudies-literature

Development of a Comprehensive Database System for Safety Analyst.

Project description:This study addressed barriers associated with the use of Safety Analyst, a state-of-the-art tool that has been developed to assist during the entire Traffic Safety Management process but that is not widely used due to a number of challenges as described in this paper. As part of this study, a comprehensive database system and tools to provide data to multiple traffic safety applications, with a focus on Safety Analyst, were developed. A number of data management tools were developed to extract, collect, transform, integrate, and load the data. The system includes consistency-checking capabilities to ensure the adequate insertion and update of data into the database. This system focused on data from roadways, ramps, intersections, and traffic characteristics for Safety Analyst. To test the proposed system and tools, data from Clark County, which is the largest county in Nevada and includes the cities of Las Vegas, Henderson, Boulder City, and North Las Vegas, was used. The database and Safety Analyst together help identify the sites with the potential for safety improvements. Specifically, this study examined the results from two case studies. The first case study, which identified sites having a potential for safety improvements with respect to fatal and all injury crashes, included all roadway elements and used default and calibrated Safety Performance Functions (SPFs). The second case study identified sites having a potential for safety improvements with respect to fatal and all injury crashes, specifically regarding intersections; it used default and calibrated SPFs as well. Conclusions were developed for the calibration of safety performance functions and the classification of site subtypes. Guidelines were provided about the selection of a particular network screening type or performance measure for network screening.

| S-EPMC4475753 | biostudies-other

MetaSpot: A General Approach for Recognizing the Reactive Atoms Undergoing Metabolic Reactions Based on the MetaQSAR Database.

Project description:The prediction of drug metabolism is attracting great interest for the possibility of discarding molecules with unfavorable ADME/Tox profile at the early stage of the drug discovery process. In this context, artificial intelligence methods can generate highly performing predictive models if they are trained by accurate metabolic data. MetaQSAR-based datasets were collected to predict the sites of metabolism for most metabolic reactions. The models were based on a set of structural, physicochemical, and stereo-electronic descriptors and were generated by the random forest algorithm. For each considered biotransformation, two types of models were developed: the first type involved all non-reactive atoms and included atom types among the descriptors, while the second type involved only non-reactive centers having the same atom type(s) of the reactive atoms. All the models of the first type revealed very high performances; the models of the second type show on average worst performances while being almost always able to recognize the reactive centers; only conjugations with glucuronic acid are unsatisfactorily predicted by the models of the second type. Feature evaluation confirms the major role of lipophilicity, self-polarizability, and H-bonding for almost all considered reactions. The obtained results emphasize the possibility of recognizing the sites of metabolism by classification models trained on MetaQSAR database. The two types of models can be synergistically combined since the first models identify which atoms can undergo a given metabolic reactions, while the second models detect the truly reactive centers. The generated models are available as scripts for the VEGA program.

| S-EPMC10341931 | biostudies-literature

The Comprehensive AOCMF Classification System: Midface Fractures - Level 2 Tutorial.

Project description:The AOCMF Classification Group developed a hierarchical three-level craniomaxillofacial classification system with increasing level of complexity and details. The highest level 1 system distinguish four major anatomical units including the mandible (code 91), midface (code 92), skull base (code 93), and cranial vault (code 94). This tutorial presents the level 2 system for the midface unit that concentrates on the location of the fractures within defined regions in the central (upper, intermediate, and lower) and lateral (zygoma, pterygoid) midface, as well as the internal orbit and palate. The level 2 midface fracture location outlines the topographic boundaries of the anatomical regions. The common nasoorbitoethmoidal and zygoma en bloc fracture patterns, as well as the time-honored Le Fort classification are taken into account. This tutorial is organized in a sequence of sections dealing with the description of the classification system with illustrations of the topographical cranial midface regions along with rules for fracture location and coding, a series of case examples with clinical imaging and a general discussion on the design of this classification. Individual fracture mapping in these regions regarding severity, fragmentation, displacement of the fragment or bone defect is addressed in a more detailed level 3 system in the subsequent articles.

| S-EPMC4251720 | biostudies-other

The Comprehensive AOCMF Classification System: Radiological Issues and Systematic Approach.

Project description:The AOCMF Classification Group developed a hierarchical three-level craniomaxillofacial (CMF) classification system with increasing level of complexity and details. The basic level 1 system differentiates fracture location in the mandible (code 91), midface (code 92), skull base (code 93), and cranial vault (code 94); the levels 2 and 3 focus on defining fracture location and morphology within more detailed regions and subregions. Correct imaging acquisition, systematic analysis, and interpretation according to the anatomic and surgical relevant structures in the CMF regions are essential for an accurate, reproducible, and comprehensive diagnosis of CMF fractures using that system. Basic principles for radiographic diagnosis are based on conventional plain films, multidetector computed tomography, and magnetic resonance imaging. In this tutorial, the radiological issues according to each level of the classification are described.

| S-EPMC4251726 | biostudies-other

The Comprehensive AOCMF Classification System: Mandible Fractures-Level 3 Tutorial.

Project description:This tutorial outlines the details of the AOCMF image-based classification system for fractures of the mandibular arch (i.e. the non-condylar mandible) at the precision level 3. It is the logical expansion of the fracture allocation to topographic mandibular sites outlined in level 2, and is based on three-dimensional (3D) imaging techniques/computed tomography (CT)/cone beam CT). Level 3 allows an anatomical description of the individual conditions of the mandibular arch such as the preinjury dental state and the degree of alveolar atrophy. Trauma sequelae are then addressed: (1) tooth injuries and periodontal trauma, (2) fracture involvement of the alveolar process, (3) the degree of fracture fragmentation in three categories (none, minor, and major), and (4) the presence of bone loss. The grading of fragmentation needs a 3D evaluation of the fracture area, allowing visualization of the outer and inner mandibular cortices. To document these fracture features beyond topography the alphanumeric codes are supplied with distinctive appendices. This level 3 tutorial is accompanied by a brief survey of the peculiarities of the edentulous atrophic mandible. Illustrations and a few case examples serve as instruction and reference to improve the understanding and application of the presented features.

| S-EPMC4251719 | biostudies-other

The Comprehensive AOCMF Classification System: Orbital Fractures - Level 3 Tutorial.

Project description:The AOCMF Classification Group developed a hierarchical three-level craniomaxillofacial classification system with increasing level of complexity and details. Within the midface (level 1 code 92), the level 2 system describes the location of the fractures within defined regions in the central and lateral midface including the internal orbit. This tutorial outlines the level 3 detailed classification system for fractures of the orbit. It depicts the orbital fractures according to the subregions defined as orbital rims, anterior orbital walls, midorbit, and apex. The system allows documentation of the involvement of specific orbital structures such as inferior orbital fissure, internal orbital buttress, the greater wing of sphenoid, lacrimal bone, superior orbital fissure, and optic canal. The classification system is presented along with rules for fracture location and coding, a series of case examples with clinical imaging and a general discussion on the design of this classification.

| S-EPMC4251722 | biostudies-other

The Comprehensive AOCMF Classification System: Mandible Fractures- Level 2 Tutorial.

Project description:This tutorial outlines the details of the AOCMF image-based classification system for fractures of the mandible at the precision level 2 allowing description of their topographical distribution. A short introduction about the anatomy is made. Mandibular fractures are classified by the anatomic regions involved. For this purpose, the mandible is delineated into an array of nine regions identified by letters: the symphysis/parasymphysis region anteriorly, two body regions on each lateral side, combined angle and ascending ramus regions, and finally the condylar and coronoid processes. A precise definition of the demarcation lines between these regions is given for the unambiguous allocation of fractures. Four transition zones allow an accurate topographic assignment if fractures end up in or run across the borders of anatomic regions. These zones are defined between angle/ramus and body, and between body and symphysis/parasymphysis. A fracture is classified as "confined" as long as it is located within a region, in contrast to a fracture being "nonconfined" when it extents to an adjoining region. Illustrations and case examples of mandible fractures are presented to become familiar with the classification procedure in daily routine.

| S-EPMC4251718 | biostudies-other

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