Browse
Submit Data
Databases
API
Help

Dataset Information

19 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

A community-powered search of machine learning strategy space to find NMR property prediction models.

ABSTRACT: The rise of machine learning (ML) has created an explosion in the potential strategies for using data to make scientific predictions. For physical scientists wishing to apply ML strategies to a particular domain, it can be difficult to assess in advance what strategy to adopt within a vast space of possibilities. Here we outline the results of an online community-powered effort to swarm search the space of ML strategies and develop algorithms for predicting atomic-pairwise nuclear magnetic resonance (NMR) properties in molecules. Using an open-source dataset, we worked with Kaggle to design and host a 3-month competition which received 47,800 ML model predictions from 2,700 teams in 84 countries. Within 3 weeks, the Kaggle community produced models with comparable accuracy to our best previously published 'in-house' efforts. A meta-ensemble model constructed as a linear combination of the top predictions has a prediction accuracy which exceeds that of any individual model, 7-19x better than our previous state-of-the-art. The results highlight the potential of transformer architectures for predicting quantum mechanical (QM) molecular properties.

SUBMITTER: Bratholm LA

PROVIDER: S-EPMC8291653 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Comparison of Machine Learning Methods towards Developing Interpretable Polyamide Property Prediction.

Project description:Polyamides are often used for their superior thermal, mechanical, and chemical properties. They form a diverse set of materials that have a large variation in properties between linear to aromatic compounds, which renders the traditional quantitative structure-property relationship (QSPR) challenging. We use extended connectivity fingerprints (ECFP) and traditional QSPR fingerprints to develop machine learning models to perform high fidelity prediction of glass transition temperature (Tg), melting temperature (Tm), density (ρ), and tensile modulus (E). The non-linear model using random forest is in general found to be more accurate than linear regression; however, using feature selection or regularization, the accuracy of linear models is shown to be improved significantly to become comparable to the more complex nonlinear algorithm. We find that none of the models or fingerprints were able to accurately predict the tensile modulus E, which we hypothesize is due to heterogeneity in data and data sources, as well as inherent challenges in measuring it. Finally, QSPR models revealed that the fraction of rotatable bonds, and the rotational degree of freedom affects polyamide properties most profoundly and can be used for back of the envelope calculations for a quick estimate of the polymer attributes (glass transition temperature, melting temperature, and density). These QSPR models, although having slightly lower prediction accuracy, show the most promise for the polymer chemist seeking to develop an intuition of ways to modify the chemistry to enhance specific attributes.

| S-EPMC8587315 | biostudies-literature

Improving molecular property prediction through a task similarity enhanced transfer learning strategy.

Project description:Deeply understanding the properties (e.g., chemical or biological characteristics) of small molecules plays an essential role in drug development. A large number of molecular property datasets have been rapidly accumulated in recent years. However, most of these datasets contain only a limited amount of data, which hinders deep learning methods from making accurate predictions of the corresponding molecular properties. In this work, we propose a transfer learning strategy to alleviate such a data scarcity problem by exploiting the similarity between molecular property prediction tasks. We introduce an effective and interpretable computational framework, named MoTSE (Molecular Tasks Similarity Estimator), to provide an accurate estimation of task similarity. Comprehensive tests demonstrated that the task similarity derived from MoTSE can serve as useful guidance to improve the prediction performance of transfer learning on molecular properties. We also showed that MoTSE can capture the intrinsic relationships between molecular properties and provide meaningful interpretability for the derived similarity.

| S-EPMC9579493 | biostudies-literature

Advancing material property prediction: using physics-informed machine learning models for viscosity.

Project description:In materials science, accurately computing properties like viscosity, melting point, and glass transition temperatures solely through physics-based models is challenging. Data-driven machine learning (ML) also poses challenges in constructing ML models, especially in the material science domain where data is limited. To address this, we integrate physics-informed descriptors from molecular dynamics (MD) simulations to enhance the accuracy and interpretability of ML models. Our current study focuses on accurately predicting viscosity in liquid systems using MD descriptors. In this work, we curated a comprehensive dataset of over 4000 small organic molecules' viscosities from scientific literature, publications, and online databases. This dataset enabled us to develop quantitative structure-property relationships (QSPR) consisting of descriptor-based and graph neural network models to predict temperature-dependent viscosities for a wide range of viscosities. The QSPR models reveal that including MD descriptors improves the prediction of experimental viscosities, particularly at the small data set scale of fewer than a thousand data points. Furthermore, feature importance tools reveal that intermolecular interactions captured by MD descriptors are most important for viscosity predictions. Finally, the QSPR models can accurately capture the inverse relationship between viscosity and temperature for six battery-relevant solvents, some of which were not included in the original data set. Our research highlights the effectiveness of incorporating MD descriptors into QSPR models, which leads to improved accuracy for properties that are difficult to predict when using physics-based models alone or when limited data is available.

| S-EPMC10938832 | biostudies-literature

Application of machine learning models for property prediction to targeted protein degraders.

Project description:Machine learning (ML) systems can model quantitative structure-property relationships (QSPR) using existing experimental data and make property predictions for new molecules. With the advent of modalities such as targeted protein degraders (TPD), the applicability of QSPR models is questioned and ML usage in TPD-centric projects remains limited. Herein, ML models are developed and evaluated for TPDs' property predictions, including passive permeability, metabolic clearance, cytochrome P450 inhibition, plasma protein binding, and lipophilicity. Interestingly, performance on TPDs is comparable to that of other modalities. Predictions for glues and heterobifunctionals often yield lower and higher errors, respectively. For permeability, CYP3A4 inhibition, and human and rat microsomal clearance, misclassification errors into high and low risk categories are lower than 4% for glues and 15% for heterobifunctionals. For all modalities, misclassification errors range from 0.8% to 8.1%. Investigated transfer learning strategies improve predictions for heterobifunctionals. This is the first comprehensive evaluation of ML for the prediction of absorption, distribution, metabolism, and excretion (ADME) and physicochemical properties of TPD molecules, including heterobifunctional and molecular glue sub-modalities. Taken together, our investigations show that ML-based QSPR models are applicable to TPDs and support ML usage for TPDs' design, to potentially accelerate drug discovery.

| S-EPMC11233499 | biostudies-literature

Machine learning powered ellipsometry.

Project description:Ellipsometry is a powerful method for determining both the optical constants and thickness of thin films. For decades, solutions to ill-posed inverse ellipsometric problems require substantial human-expert intervention and have become essentially human-in-the-loop trial-and-error processes that are not only tedious and time-consuming but also limit the applicability of ellipsometry. Here, we demonstrate a machine learning based approach for solving ellipsometric problems in an unambiguous and fully automatic manner while showing superior performance. The proposed approach is experimentally validated by using a broad range of films covering categories of metals, semiconductors, and dielectrics. This method is compatible with existing ellipsometers and paves the way for realizing the automatic, rapid, high-throughput optical characterization of films.

| S-EPMC7952555 | biostudies-literature

Game-powered machine learning.

Project description:Searching for relevant content in a massive amount of multimedia information is facilitated by accurately annotating each image, video, or song with a large number of relevant semantic keywords, or tags. We introduce game-powered machine learning, an integrated approach to annotating multimedia content that combines the effectiveness of human computation, through online games, with the scalability of machine learning. We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the "wisdom of the crowds." Second, these annotated examples are used to train a supervised machine learning system. Third, the machine learning system actively directs the annotation games to collect new data that will most benefit future model iterations. Once trained, the system can automatically annotate a corpus of music much larger than what could be labeled using human computation alone. Automatically annotated songs can be retrieved based on their semantic relevance to text-based queries (e.g., "funky jazz with saxophone," "spooky electronica," etc.). Based on the results presented in this paper, we find that actively coupling annotation games with machine learning provides a reliable and scalable approach to making searchable massive amounts of multimedia data.

| S-EPMC3340027 | biostudies-literature

Topology-Based Machine Learning Strategy for Cluster Structure Prediction.

Project description:In cluster physics, the determination of the ground-state structure of medium-sized and large-sized clusters is a challenge due to the number of local minimal values on the potential energy surface growing exponentially with cluster size. Although machine learning approaches have had much success in materials sciences, their applications in clusters are often hindered by the geometric complexity clusters. Persistent homology provides a new topological strategy to simplify geometric complexity while retaining important chemical and physical information without having to "downgrade" the original data. We further propose persistent pairwise independence (PPI) to enhance the predictive power of persistent homology. We construct topology-based machine learning models to reveal hidden structure-energy relationships in lithium (Li) clusters. We integrate the topology-based machine learning models, a particle swarm optimization algorithm, and density functional theory calculations to accelerate the search of the globally stable structure of clusters.

| S-EPMC7351018 | biostudies-literature

Spectral prediction features as a solution for the search space size problem in proteogenomics

Project description:Proteogenomics approaches often struggle with the distinction between right and false peptide-to-spectrum matches as the database size enlarges. However, features extracted from tandem mass spectrometry intensity predictors can enhance the peptide identification rate and can provide extra confidence for spectral matching in a proteogenomic context. To that end, features from the spectral intensity pattern predictors MS2PIP and Prosit were combined with the canonical scores from MaxQuant in the Percolator post-processing tool for protein databases constructed from RNA-seq and ribosome profiling analyses. The presented results provide evidence that this approach enhances the peptide identification power in a proteogenomic setting and in the meantime they lead to the validation of new proteoforms with elevated stringency. In this online repository, we submitted the conventional proteomic search results with MaxQuant against the custom nanopore RNA-seq-based search space. All other results can be found in the supplemental materials of the manuscript, in SRA (sequencing data) or under ProteomeXChange Project PXD011353 (as this is original data from a previuos paper).

2021-03-26 | PXD022280 | Pride

Spectral Prediction Features as a Solution for the Search Space Size Problem in Proteogenomics.

Project description:Proteogenomics approaches often struggle with the distinction between true and false peptide-to-spectrum matches as the database size enlarges. However, features extracted from tandem mass spectrometry intensity predictors can enhance the peptide identification rate and can provide extra confidence for peptide-to-spectrum matching in a proteogenomics context. To that end, features from the spectral intensity pattern predictors MS2PIP and Prosit were combined with the canonical scores from MaxQuant in the Percolator postprocessing tool for protein sequence databases constructed out of ribosome profiling and nanopore RNA-Seq analyses. The presented results provide evidence that this approach enhances both the identification rate as well as the validation stringency in a proteogenomic setting.

| S-EPMC8214147 | biostudies-literature

Scatter-search with support vector machine for prediction of relative solvent accessibility.

Project description:Proteins have vital roles in the living cells. The protein function is almost completely dependent on protein structure. The prediction of relative solvent accessibility gives helpful information for the prediction of tertiary structure of a protein. In recent years several relative solvent accessibility (RSA) prediction methods including those that generate real values and those that predict discrete states have been developed. The proposed method consists of two main steps: the first one, provided subset selection of quantitative features based on selected qualitative features and the second, dedicated to train a model with selected quantitative features for RSA prediction. The results show that the proposed method has an improvement in average prediction accuracy and training time. The proposed method can dig out all the valuable knowledge about which physicochemical features of amino acids are deemed more important in prediction of RSA without human supervision, which is of great importance for biologists and their future researches.

| S-EPMC4531788 | 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