Beyond Tripeptides Two-Step Active Machine Learning for Very Large Data sets.
Ontology highlight
ABSTRACT:
SUBMITTER: van Teijlingen A
PROVIDER: S-EPMC8278388 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:It is chemically intuitive that an optimal atom centered basis set must adapt to its atomic environment, for example by polarizing toward nearby atoms. Adaptive basis sets of small size can be significantly more accurate than traditional atom centered basis sets of the same size. The small size and well conditioned nature of these basis sets leads to large saving in computational cost, in particular in a linear scaling framework. Here, it is shown that machine learning can be used to predict such adaptive basis sets using local geometrical information only. As a result, various properties of standard DFT calculations can be easily obtained at much lower costs, including nuclear gradients. In our approach, a rotationally invariant parametrization of the basis is obtained by employing a potential anchored on neighboring atoms to ultimately construct a rotation matrix that turns a traditional atom centered basis set into a suitable adaptive basis set. The method is demonstrated using MD simulations of liquid water, where it is shown that minimal basis sets yield structural properties in fair agreement with basis set converged results, while reducing the computational cost in the best case by a factor of 200 and the required flops by 4 orders of magnitude. Already a very small training set yields satisfactory results as the variational nature of the method provides robustness.
| S-EPMC6096449 | biostudies-literature
Project description:Hematopoietic stem cells (HSCs) are an essential source and reservoir for normal hematopoiesis, and their function is compromised in many blood disorders. HSC research has benefitted from the recent development of single-cell molecular profiling technologies, where single-cell RNA sequencing (scRNA-seq) in particular has rapidly become an established method to profile HSCs and related hematopoietic populations. The classic definition of HSCs relies on transplantation assays, which have been used to validate HSC function for cell populations defined by flow cytometry. Flow cytometry information for single cells, however, is not available for many new high-throughput scRNA-seq methods, thus highlighting an urgent need for the establishment of alternative ways to pinpoint the likely HSCs within large scRNA-seq data sets. To address this, we tested a range of machine learning approaches and developed a tool, hscScore, to score single-cell transcriptomes from murine bone marrow based on their similarity to gene expression profiles of validated HSCs. We evaluated hscScore across scRNA-seq data from different laboratories, which allowed us to establish a robust method that functions across different technologies. To facilitate broad adoption of hscScore by the wider hematopoiesis community, we have made the trained model and example code freely available online. In summary, our method hscScore provides fast identification of mouse bone marrow HSCs from scRNA-seq measurements and represents a broadly useful tool for analysis of single-cell gene expression data.
| S-EPMC6900257 | biostudies-literature
Project description:Background As rare diseases (RDs) receive increasing attention, obtaining accurate RD incidence estimates has become an essential concern in public health. Since RDs are difficult to diagnose, include diverse types, and have scarce cases, traditional epidemiological methods are costly in RD registries. With the development of the internet, users have become accustomed to searching for disease-related information through search engines before seeking medical treatment. Therefore, online search data provide a new source for estimating RD incidences. Objective The aim of this study was to estimate the incidences of multiple RDs in distinct regions of China with online search data. Methods Our research scale included 15 RDs in China from 2016 to 2019. The online search data were obtained from Sogou, one of the top 3 commercial search engines in China. By matching to multilevel keywords related to 15 RDs during the 4 years, we retrieved keyword-matched RD-related queries. The queries used before and after the keyword-matched queries formed the basis of the RD-related search sessions. A two-step method was developed to estimate RD incidences with users’ intents conveyed by the sessions. In the first step, a combination of long short-term memory and multilayer perceptron algorithms was used to predict whether the intents of search sessions were RD-concerned, news-concerned, or others. The second step utilized a linear regression (LR) model to estimate the incidences of multiple RDs in distinct regions based on the RD- and news-concerned session numbers. For evaluation, the estimated incidences were compared with RD incidences collected from China’s national multicenter clinical database of RDs. The root mean square error (RMSE) and relative error rate (RER) were used as the evaluation metrics. Results The RD-related online data included 2,749,257 queries and 1,769,986 sessions from 1,380,186 users from 2016 to 2019. The best LR model with sessions as the input estimated the RD incidences with an RMSE of 0.017 (95% CI 0.016-0.017) and an RER of 0.365 (95% CI 0.341-0.388). The best LR model with queries as input had an RMSE of 0.023 (95% CI 0.017-0.029) and an RER of 0.511 (95% CI 0.377-0.645). Compared with queries, using session intents achieved an error decrease of 28.57% in terms of the RER (P=.01). Analysis of different RDs and regions showed that session input was more suitable for estimating the incidences of most diseases (14 of 15 RDs). Moreover, examples focusing on two RDs showed that news-concerned session intents reflected news of an outbreak and helped correct the overestimation of incidences. Experiments on RD types further indicated that type had no significant influence on the RD estimation task. Conclusions This work sheds light on a novel method for rapid estimation of RD incidences in the internet era, and demonstrates that search session intents were especially helpful for the estimation. The proposed two-step estimation method could be a valuable supplement to the traditional registry for understanding RDs, planning policies, and allocating medical resources. The utilization of search sessions in disease detection and estimation could be transferred to infoveillance of large-scale epidemics or chronic diseases.
| S-EPMC10182453 | biostudies-literature
Project description:Experimental search for high-temperature ferroelectric perovskites is a challenging task due to the vast chemical space and lack of predictive guidelines. Here, we demonstrate a two-step machine learning approach to guide experiments in search of xBi[Formula: see text]O3-(1 - x)PbTiO3-based perovskites with high ferroelectric Curie temperature. These involve classification learning to screen for compositions in the perovskite structures, and regression coupled to active learning to identify promising perovskites for synthesis and feedback. The problem is challenging because the search space is vast, spanning ~61,500 compositions and only 167 are experimentally studied. Furthermore, not every composition can be synthesized in the perovskite phase. In this work, we predict x, y, Me', and Me″ such that the resulting compositions have both high Curie temperature and form in the perovskite structure. Outcomes from both successful and failed experiments then iteratively refine the machine learning models via an active learning loop. Our approach finds six perovskites out of ten compositions synthesized, including three previously unexplored {Me'Me″} pairs, with 0.2Bi(Fe0.12Co0.88)O3-0.8PbTiO3 showing the highest measured Curie temperature of 898 K among them.
| S-EPMC5920103 | biostudies-literature
Project description:Machine learning methods have proven invaluable for increasing the sensitivity of peptide detection in proteomics experiments. Most modern tools, such as Percolator and PeptideProphet, use semisupervised algorithms to learn models directly from the data sets that they analyze. Although these methods are effective for many proteomics experiments, we suspected that they may be suboptimal for experiments of smaller scale. In this work, we found that the power and consistency of Percolator results were reduced as the size of the experiment was decreased. As an alternative, we propose a different operating mode for Percolator: learn a model with Percolator from a large data set and use the learned model to evaluate the small-scale experiment. We call this a "static modeling" approach, in contrast to Percolator's usual "dynamic model" that is trained anew for each data set. We applied this static modeling approach to two settings: small, gel-based experiments and single-cell proteomics. In both cases, static models increased the yield of detected peptides and eliminated the model-induced variability of the standard dynamic approach. These results suggest that static models are a powerful tool for bringing the full benefits of Percolator and other semisupervised algorithms to small-scale experiments.
| S-EPMC8455073 | biostudies-literature
Project description:Due to their multiple beneficial effects, antioxidant peptides have attracted increasing interest. Currently, the screening and identification of bioactive peptides, including antioxidative peptides based on wet-chemistry methods are time-consuming and highly rely on many advanced instruments and trained personnel. Quantitative structure-activity relationship (QSAR) analysis as an in silico method can be more efficient and cost-effective. However, model performance of QSAR studies on antioxidant peptides was still poor due to limited attempts in model development approaches. The objective of this study was to compare popular machine learning methods for antioxidant activity modeling and screening of tripeptides and identify the critical amino acid features that determine the antioxidant activity. 533 numerical indices of amino acids were adopted to characterize 130 tripeptides with known antioxidant activity from the published literature, and then 7 feature selection strategies plus pairwise correlation were used to screen the most important indices for antioxidant activity and model building. 14 machine learning methods were used to build models based on the feature selection strategies, respectively. Among the 98 models, non-linear regression methods tended to perform better, and the best model with an R 2 Test of 0.847 and RMSETest of 0.627 for tripeptide antioxidants was obtained by combining random forest for feature selection and tree-based extreme gradient boost regression for model development. Based on the predicted antioxidant values of 7870 unknown tripeptides, potentially high antioxidant activity tripeptides all have a tyrosine, tryptophan, or cysteine residue at the C-terminal position. Furthermore, the predicted antioxidant activity of six synthesized tripeptides was confirmed through experimental determination, and for the first time, the cysteine or tyrosine residue at the C-terminal was found to be critical to the antioxidant activity based on both QSAR models and experimental observations.
| S-EPMC9330208 | biostudies-literature
Project description:The sequence kernel association test (SKAT) is widely used to test for associations between a phenotype and a set of genetic variants that are usually rare. Evaluating tail probabilities or quantiles of the null distribution for SKAT requires computing the eigenvalues of a matrix related to the genotype covariance between markers. Extracting the full set of eigenvalues of this matrix (an n×n matrix, for n subjects) has computational complexity proportional to n3 . As SKAT is often used when n>104 , this step becomes a major bottleneck in its use in practice. We therefore propose fastSKAT, a new computationally inexpensive but accurate approximations to the tail probabilities, in which the k largest eigenvalues of a weighted genotype covariance matrix or the largest singular values of a weighted genotype matrix are extracted, and a single term based on the Satterthwaite approximation is used for the remaining eigenvalues. While the method is not particularly sensitive to the choice of k, we also describe how to choose its value, and show how fastSKAT can automatically alert users to the rare cases where the choice may affect results. As well as providing faster implementation of SKAT, the new method also enables entirely new applications of SKAT that were not possible before; we give examples grouping variants by topologically associating domains, and comparing chromosome-wide association by class of histone marker.
| S-EPMC6129408 | biostudies-literature
Project description:The chemical sciences are producing an unprecedented amount of large, high-dimensional data sets containing chemical structures and associated properties. However, there are currently no algorithms to visualize such data while preserving both global and local features with a sufficient level of detail to allow for human inspection and interpretation. Here, we propose a solution to this problem with a new data visualization method, TMAP, capable of representing data sets of up to millions of data points and arbitrary high dimensionality as a two-dimensional tree (http://tmap.gdb.tools). Visualizations based on TMAP are better suited than t-SNE or UMAP for the exploration and interpretation of large data sets due to their tree-like nature, increased local and global neighborhood and structure preservation, and the transparency of the methods the algorithm is based on. We apply TMAP to the most used chemistry data sets including databases of molecules such as ChEMBL, FDB17, the Natural Products Atlas, DSSTox, as well as to the MoleculeNet benchmark collection of data sets. We also show its broad applicability with further examples from biology, particle physics, and literature.
| S-EPMC7015965 | biostudies-literature
Project description:Hydrodynamic theories effectively describe many-body systems out of equilibrium in terms of a few macroscopic parameters. However, such parameters are difficult to determine from microscopic information. Seldom is this challenge more apparent than in active matter, where the hydrodynamic parameters are in fact fields that encode the distribution of energy-injecting microscopic components. Here, we use active nematics to demonstrate that neural networks can map out the spatiotemporal variation of multiple hydrodynamic parameters and forecast the chaotic dynamics of these systems. We analyze biofilament/molecular-motor experiments with microtubule/kinesin and actin/myosin complexes as computer vision problems. Our algorithms can determine how activity and elastic moduli change as a function of space and time, as well as adenosine triphosphate (ATP) or motor concentration. The only input needed is the orientation of the biofilaments and not the coupled velocity field which is harder to access in experiments. We can also forecast the evolution of these chaotic many-body systems solely from image sequences of their past using a combination of autoencoders and recurrent neural networks with residual architecture. In realistic experimental setups for which the initial conditions are not perfectly known, our physics-inspired machine-learning algorithms can surpass deterministic simulations. Our study paves the way for artificial-intelligence characterization and control of coupled chaotic fields in diverse physical and biological systems, even in the absence of knowledge of the underlying dynamics.
| S-EPMC7958379 | biostudies-literature
Project description:Prediction is one of the last frontiers in ecology. Indeed, predicting fine-scale species composition in natural systems is a complex challenge as multiple abiotic and biotic processes operate simultaneously to determine local species abundances. On the one hand, species intrinsic performance and their tolerance limits to different abiotic pressures modulate species abundances. On the other hand, there is growing recognition that species interactions play an equally important role in limiting or promoting such abundances within ecological communities. Here, we present a joint effort between ecologists and data scientists to use data-driven models to predict species abundances using reasonably easy to obtain data. We propose a sequential data-driven modeling approach that in a first step predicts the potential species abundances based on abiotic variables, and in a second step uses these predictions to model the realized abundances once accounting for species competition. Using a curated data set over five years we predict fine-scale species abundances in a highly diverse annual plant community. Our models show a remarkable spatial predictive accuracy using only easy-to-measure variables in the field, yet such predictive power is lost when temporal dynamics are taken into account. This result suggests that predicting future abundances requires longer time series analysis to capture enough variability. In addition, we show that these data-driven models can also suggest how to improve mechanistic models by adding missing variables that affect species performance such as particular soil conditions (e.g. carbonate availability in our case). Robust models for predicting fine-scale species composition informed by the mechanistic understanding of the underlying abiotic and biotic processes can be a pivotal tool for conservation, especially given the human-induced rapid environmental changes we are experiencing. This objective can be achieved by promoting the knowledge gained with classic modelling approaches in ecology and recently developed data-driven models.
| S-EPMC8675934 | biostudies-literature