Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Pushing the limits of solubility prediction via quality-oriented data selection.

ABSTRACT: Accurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved.

SUBMITTER: Sorkun MC

PROVIDER: S-EPMC7788089 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Pushing the limits of solubility prediction via quality-oriented data selection.

Sorkun Murat Cihan MC Koelman J M Vianney A JMVA Er Süleyman S

iScience 20201217 1

Accurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unrav ...[more]

PMID: 33437941

Similar Datasets

Introduction: airway surgery-pushing the limits.

Project description: Not available

| S-EPMC7656395 | biostudies-literature

Pushing property limits in materials discovery <i>via</i> boundless objective-free exploration.

Project description:Materials chemists develop chemical compounds to meet often conflicting demands of industrial applications. This process may not be properly modeled by black-box optimization because the target property is not well defined in some cases. Herein, we propose a new algorithm for automated materials discovery called BoundLess Objective-free eXploration (BLOX) that uses a novel criterion based on kernel-based Stein discrepancy in the property space. Unlike other objective-free exploration methods, a boundary for the materials properties is not needed; hence, BLOX is suitable for open-ended scientific endeavors. We demonstrate the effectiveness of BLOX by finding light-absorbing molecules from a drug database. Our goal is to minimize the number of density functional theory calculations required to discover out-of-trend compounds in the intensity-wavelength property space. Using absorption spectroscopy, we experimentally verified that eight compounds identified as outstanding exhibit the expected optical properties. Our results show that BLOX is useful for chemical repurposing, and we expect this search method to have numerous applications in various scientific disciplines.

| S-EPMC7409358 | biostudies-literature

Data of the maximum solid solubility limits of binary systems of elements.

Project description:This paper gives the available data for the maximum equilibrium solubility limits of each of the first 83 elements (H to Bi) of the periodic table in each of the others. This is expressed in the form of the maximum value of the equilibrium solid solubility for terminal solid solutions, expressed in atomic percentage (at%), occurring at any temperature where the room temperature phase of the pure element acting as the solvent is stable. The values thus represent the compatibility between different elements in the formation of alloys and similar combinations, and will be of use for research into fundamental solid state physics relating to elemental interactions, for the interpretation of phase structures in materials research and for the design of alloys and materials involving elemental mixing of the elements.

| S-EPMC6811886 | biostudies-literature

Pushing the limits of radiofrequency (RF) neuronal telemetry.

Project description:In a previous report it was shown that the channel capacity of an in vivo communication link using microscopic antennas at radiofrequency is severely limited by the requirement not to damage the tissue surrounding the antennas. For dipole-like antennas the strong electric field dissipates too much power into body tissues. Loop-type antennas have a strong magnetic near field and so dissipate much less power into the surrounding tissues but they require such a large current that the antenna temperature is raised to the thermal damage threshold of the tissue. The only solution was increasing the antenna size into hundreds of microns, which makes reporting on an individual neuron impossible. However, recently demonstrated true magnetic antennas offer an alternative not covered in the previous report. The near field of these antennas is dominated by the magnetic field yet they don't require large currents. Thus they combine the best characteristics of dipoles and loops. By calculating the coupling between identical magnetic antennas inside a model of the body medium we show an increase in the power transfer of up to 8 orders of magnitude higher than could be realized with the loops and dipoles, making the microscopic RF in-vivo transmitting antenna possible.

| S-EPMC4650618 | biostudies-other

Prediction-Oriented Marker Selection (PROMISE): With Application to High-Dimensional Regression.

Project description:In personalized medicine, biomarkers are used to select therapies with the highest likelihood of success based on an individual patient's biomarker/genomic profile. Two goals are to choose important biomarkers that accurately predict treatment outcomes and to cull unimportant biomarkers to reduce the cost of biological and clinical verifications. These goals are challenging due to the high dimensionality of genomic data. Variable selection methods based on penalized regression (e.g., the lasso and elastic net) have yielded promising results. However, selecting the right amount of penalization is critical to simultaneously achieving these two goals. Standard approaches based on cross-validation (CV) typically provide high prediction accuracy with high true positive rates but at the cost of too many false positives. Alternatively, stability selection (SS) controls the number of false positives, but at the cost of yielding too few true positives. To circumvent these issues, we propose prediction-oriented marker selection (PROMISE), which combines SS with CV to conflate the advantages of both methods. Our application of PROMISE with the lasso and elastic net in data analysis shows that, compared to CV, PROMISE produces sparse solutions, few false positives, and small type I + type II error, and maintains good prediction accuracy, with a marginal decrease in the true positive rates. Compared to SS, PROMISE offers better prediction accuracy and true positive rates. In summary, PROMISE can be applied in many fields to select regularization parameters when the goals are to minimize false positives and maximize prediction accuracy.

| S-EPMC5543994 | biostudies-literature

Pushing the limits for the surgical treatment of intrahepatic cholangiocarcinoma.

Project description: Not available

| S-EPMC9944536 | biostudies-literature

Pushing the limits of concertedness. A waltz of wandering carbocations.

Project description:Among the array of complex terpene-forming carbocation cyclization/rearrangement reactions, the so-called "triple shift" reactions are among the most unexpected. Such reactions involve the asynchronous combination of three 1,n-shifts into a concerted process, e.g., a 1,2-alkyl shift followed by a 1,3-hydride shift followed by a second 1,2-alkyl shift. This type of reaction so far has been proposed to occur during the biosynthesis of diterpenes and the sidechains of sterols. Here we describe efforts to push the limits of concertedness in this type of carbocation reaction by designing, and characterizing with quantum chemical computations, systems that could couple additional 1,n-shift events to a triple shift leading, in principle to quadruple, pentuple, etc. shifts. While our designs did not lead to clear-cut examples of quadruple, etc. shifts, they did lead to reactions with surprisingly flat energy surfaces where more than five chemical events connect reactants and plausible products. Ab initio molecular dynamics simulations demonstrate that the formal minima on these surfaces interchange on short timescales, both with each other and with additional unexpected structures, allowing us a glimpse into a very complex manifold that allows ready access to great structural diversity.

| S-EPMC6385557 | biostudies-literature

Pushing the limits of high-resolution polymer microscopy using antioxidants.

Project description:High-resolution transmission electron microscopy (HRTEM) has been transformative to the field of polymer science, enabling the direct imaging of molecular structures. Although some materials have remarkable stability under electron beams, most HRTEM studies are limited by the electron dose the sample can handle. Beam damage of conjugated polymers is not yet fully understood, but it has been suggested that the diffusion of secondary reacting species may play a role. As such, we examine the effect of the addition of antioxidants to a series of solution-processable conjugated polymers as an approach to mitigating beam damage. Characterizing the effects of beam damage by calculating critical dose DC values from the decay of electron diffraction peaks shows that beam damage of conjugated polymers in the TEM can be minimized by using antioxidants at room temperature, even if the antioxidant does not alter or incorporate into polymer crystals. As a consequence, the addition of antioxidants pushes the resolution limit of polymer microscopy, enabling imaging of a 3.6 Å lattice spacing in poly[(5,6-difluoro-2,1,3-benzothiadiazol-4,7-diyl)-alt-(3,3″'-di(2-octyldodecyl)-2,2';5',2″;5″,2″'-quaterthiophene-5,5″'-diyl)] (PffBT4T-2OD).

| S-EPMC7794589 | biostudies-literature

Double pancake bonds: pushing the limits of strong ?-? stacking interactions.

Project description:The concept of a double-bonded pancake bonding mechanism is introduced to explain the extremely short ?-? stacking contacts in dimers of dithiatriazines. While ordinary single pancake bonds occur between radicals and already display significantly shorter interatomic distances in comparison to van der Waals (vdW) contacts, the double-bonded pancake dimer is based on diradicaloid or antiaromatic molecules and exhibits even shorter and stronger intermolecular bonds that breach into the range of extremely stretched single bonds in terms of bond distances and binding energies. These properties give rise to promising possibilities in the design of new materials with high electrical conductivity and for the field of spintronics. The analysis of the double pancake bond is based on cutting edge electron correlation theory combining multireference (nondynamical) effects and dispersion (dynamical) contributions in a balanced way providing accurate interaction energies and distributions of unpaired spins. It is also shown that the present examples do not stand isolated but that similar mechanisms operate in several analogous nonradical molecular systems to form double-bonded ?-stacking pancake dimers. We report on the amazing properties of a new type of stacking interaction mechanism between ? conjugated molecules in the form of a "double pancake bond" which breaks the record for short intermolecular distances and provides formidable strength for some ?-? stacking interactions.

| S-EPMC4183611 | biostudies-literature

Pushing Stoichiometries of Lithium-Rich Layered Oxides Beyond Their Limits.

Project description:Lithium-rich layered oxides (LRLOs) are opening unexplored frontiers for high-capacity/high-voltage positive electrodes in Li-ion batteries (LIBs) to meet the challenges of green and safe transportation as well as cheap and sustainable stationary energy storage from renewable sources. LRLOs exploit the extra lithiation provided by the Li1.2TM0.8O2 stoichiometries (TM = a blend of transition metals with a moderate cobalt content) achievable by a layered structure to disclose specific capacities beyond 200-250 mA h g-1 and working potentials in the 3.4-3.8 V range versus Li. Here, we demonstrate an innovative paradigm to extend the LRLO concept. We have balanced the substitution of cobalt in the transition-metal layer of the lattice with aluminum and lithium, pushing the composition of LRLO to unexplored stoichiometries, that is, Li1.2+x (Mn,Ni,Co,Al)0.8-x O2-δ. The fine tuning of the composition of the metal blend results in an optimized layered material, that is, Li1.28Mn0.54Ni0.13Co0.02Al0.03O2-δ, with outstanding electrochemical performance in full LIBs, improved environmental benignity, and reduced manufacturing costs compared to the state-of-the-art.

| S-EPMC8889532 | 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