Find research datasets worth reusing

opencc-by-4.0Sep 2021View details →

Large CCS dataset (~90,000,000 molecules) predicted by SigmaCCS

We developed a model named SigmaCCS which can be used to predict CCS of compounds,and a dataset including CCS values of ~90,000,000 molecules from Pubchem was formed.For each molecules,there are "Pubchem ID","SMILES","InChi","Inchikey","Molecular Weight","Exact Mass","Formula"and predicted CCS values of three adduct ion type ([M+H]+,[M-H]-,[M+Na]+). We believe this dataset can unleash the true potential of IMS in molecule identification.

opencc-by-4.0Nov 2020View details →

Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections

A pre-trained model of the paper "Multimodal Trajectory Prediction via Topological Invariance for Navigation at Uncontrolled Intersections," CoRL 2020.

dryad40/100

Improving wheat yield prediction using secondary traits and high-density phenotyping under heat stressed environments

A primary selection target for wheat (Triticum aestivum) improvement is grain yield. However, the selection for yield is limited by the extent of field trials, fluctuating environments, and the time needed to obtain multiyear assessments. Secondary traits such as spectral reflectance and canopy temperature (CT), which can be rapidly measured many times throughout the growing season, are frequently correlated with grain yield and could be used for indirect selection in large populations particularly in earlier generations in the breeding cycle prior to replicated yield testing. While proximal sensing data collection is increasingly implemented with high-throughput platforms that provide powerful and affordable information, efficient and effective use of these data is challenging. The objective of this study was to monitor wheat growth and predict grain yield in wheat breeding trials using high-density proximal sensing measurements under extreme terminal heat stress that is common in Bangladesh. Over five growing seasons, we analyzed normalized difference vegetation index (NDVI) and CT measurements collected in elite breeding lines from the International Maize and Wheat Improvement Center at the Regional Agricultural Research Station, Jamalpur, Bangladesh. We explored several variable reduction and regularization techniques followed by using the combined secondary traits to predict grain yield. Across years, grain yield heritability ranged from 0.30 to 0.72, with variable secondary trait heritability (0.0–0.6), while the correlation between grain yield and secondary traits ranged from−0.5 to 0.5. The prediction accuracy was calculated by a cross-fold validation approach as the correlation between observed and predicted grain yield using univariate and multivariate models. We found that the multivariate models resulted in higher prediction accuracies for grain yield than the univariate models. Stepwise regression performed equal to, or better than, other models in predicting grain yield. When incorporating all secondary traits into the models, we obtained high prediction accuracies (0.58–0.68) across the five growing seasons. Our results show that the optimized phenotypic prediction models can leverage secondary traits to deliver accurate predictions of wheat grain yield, allowing breeding programs to make more robust and rapid selections.

opencc-zeroSep 2021View details →

Competition between predicting mathematical models and laboratory results for covid 19 after vaccination in Iran

All of us like to find a way to end Covid 19. Specially, economy confronts with many problems. In attached JPG, i bring two predictions for covid 19 pandemic in Iran. Mathematical model predicts that after a fall in figure we will have a peak. However, right now, most of people in Iran used of vaccines. In addition, government forced on all to get vaccine. Even, students with 12 to 18 years old get vaccine. It has been heard that soonly, kids with ages between 3-12 years old will receive vaccine. As a man or woman, all of us like that this program will response and vaccines work. However, predictions of math show reverse result. Although, maybe, we should enter the factor of vaccine in mathematical model. It is good opportunity for scientists to examine response of covid 19 to program of vaccine for all. Even if we have a peak, however its height be smaller, we can say that vaccines act. Hope for ending Covid 19 in all countries.

opencc-by-4.0Sep 2021View details →

Multivariate Spatial Predictions of Air Pollutants with INLA

Spatial predictions and uncertainty quantification for air pollutants: PM2.5, PM10, NO3−, NH4+, EC, OC, SO42− , CO, NOx, NO2, SO2 and O3 covering the continental US for the period 2005–2014. The daily prediction is at 12km spatial resolution.

Vegetation Stratum Occupancy Prediction from Airborne LiDAR 3D Point Clouds

Our proposed dataset comprises 199 cylindrical plots of 10 m radius corresponding to typical pasture land parcels in South-Eastern France. Each plot contains between 3000 and 17000 3D points, and each point is attributed with a total of 10 features: (i) absolute 3D coordinates, (ii) RGB and Near-InfraRed reflectance obtained with aerial cameras, (iii) uncalibrated laser intensity, return number and number of returns provided by the aerial LiDAR. This dataset can be used as training data for our model deep learning model "Vegetation Stratum Occupancy Prediction from Airborne LiDAR 3D Point Clouds" available on <a href="https://github.com/ekalinicheva/plot_vegetation_coverage">https://github.com/ekalinicheva/plot_vegetation_coverage</a>

Predicting Response: Waste-based biopolymer slurry recipe for 3d-printing

Waste-based biopolymer slurry recipe preparation description for 3d-printing. It combines cellulose floc fibers and xanthan gum.  This recipe has been used for the print experiment in the paper: Rossi G., Chiujdea R., Colmo C., ElAlami C., Nicholas P., Tamke M., Ramsgaard Thomsen M. (2021)  A material monitoring framework: tracking the curing of 3d printed cellulose-based biopolymers. In Acadia 2021 Realignments.

opencc-zeroOct 2021View details →

dryad40/100

Airflow modelling predicts seabird breeding habitat across islands

Wind is fundamentally related to shelter and flight performance: two factors that are critical for birds at their nest sites. Despite this, airflows have never been fully integrated into models of breeding habitat selection, even for well-studied seabirds. Here we use computational fluid dynamics to provide the first assessment of whether flow characteristics (including wind speed and turbulence) predict the distribution of seabird colonies, taking common guillemots (Uria aalge) breeding on Skomer island as our study system. This demonstrates that occupancy is driven by the need to shelter from both wind and rain/ wave action, rather than airflow characteristics alone. Models of airflows and cliff orientation both performed well in predicting high quality habitat in our study site, identifying 80% of colonies and 93% of avoided sites, as well as 73% of the largest colonies on a neighbouring island. This suggests generality in the mechanisms driving breeding distributions, and provides an approach for identifying habitat for seabird reintroductions considering current and projected wind speeds and directions.

opencc-by-4.0Sep 2021View details →

Supplementary material for: RSAT variation-tools: An accessible and flexible framework to predict the impact of regulatory variants on transcription factor binding

Supplementary Material for the Article Santana-Garcia, W., Rocha-Acevedo, M., Ramirez-Navarro, L., Mbouamboua, Y., Thieffry, D., Thomas-Chollier, M., Contreras-Moreira, B., van Helden, J., Medina-Rivera, A., 2019. RSAT variation-tools: An accessible and flexible framework to predict the impact of regulatory variants on transcription factor binding. Comput. Struct. Biotechnol. J. 17, 1415–1428.

Assessment of Non-Invasive Blood Pressure Prediction from PPG and rPPG Signals Using Deep Learning

This dataset is a subset of the MIMIC-III dataset used for non-invasive blood pressure prediction. PPG and ABP data were divided into windows of  7s length (875 data points). Systolic and diastolic blood pressure values were derived from the ABP windows. Each sample of the dataset consists of a PPG signal and blood pressure values as well as a unique subject identifier.  The file consists of three datasets: <ul> <li>PPG: PPG data of size 905,400 x 875</li> <li>label: BP data of size 905,400 x 2</li> <li>subject_idx: subject affiliation of each sample (size 905,400 x 1)</li> </ul> Furthermore, this submission contains the following models: <ul> <li>AlexNet</li> <li>ResNet50</li> <li>LSTM</li> <li>Architecture published by Slapnicar et al. 2019</li> </ul> The architectures were trained using a non-mixed dataset derived from the MIMIC-III waveform database. Samples were divided between training, validation and test set based on their subject affiliation preventing contamination of validation and test sets with samples from subjects used for training.

opencc-by-4.0Dec 2018View details →

On the Performance of Method-Level Bug Prediction: A Negative Result. Appendix

Abstract Bug prediction is aimed at identifying software artifacts that are more likely to be defective. Most approaches defined so far target the prediction of bugs at class/file level. Nevertheless, past research has provided evidence that this granularity might be too coarse-grained, thus reducing the usability of bug prediction in practice. As a consequence, researchers have started proposing defect prediction models targeting a finer granularity, particularly targeting methods, providing promising evidence that it is possible to operate at this granularity. Particularly, models based on a mixture of product and process metrics provided the best results.  In this paper, we first replicate previous research on method-level bug- prediction using different systems and timespans. Afterward, based on the limitations of existing research, we (1) re-evaluate method-level bug prediction models more realistically and (2) analyze the whether textual features— previously shown as valuable sources of information for the evaluation of software quality (yet surprisingly unexplored in this research field)—can be exploited to improve method-level bug prediction abilities. Key results of our study include that (1) the performance of the previously proposed models, tested using the same strategy but with different systems/timespans, is con- firmed. However, (2) when evaluated with a more realistic strategy all the models show a dramatic drop in performance exhibiting results close to that of a random classifier. In addition, we find that (3) the contribution of textual features within such models is limited and unable to improve the prediction capabilities significantly. As a consequence, our replication and negative results indicate that method-level bug prediction is still an open challenge.

opencc-by-4.0Aug 2022View details →

Prediction of metabolites associated with somatic mutations in cancers

<ul> <li>GEMs_AML: 16 acute myeloid leukemia (AML) patient-specific genome-scale metabolic models (GEMs) reconstructed using their corresponding RNA-seq data and Recon 2M.2</li> <li>GEMs_PCAWG: 943 cancer patient-specific GEMs for 24 different cancer types reconstructed using the Pan-Cancer Analysis of Whole Genomes (PCAWG) RNA-seq data and generic human GEM 'Recon 2M.2'</li> <li>GEMs_RCC: 20 renal cell carcinoma (RCC) patient-specific GEMs reconstructed using their corresponding RNA-seq data and Recon 2M.2</li> <li>GEMs_TCGA_LAML: 113 AML patient-specific GEMs reconstructed using The Cancer Genome Atlas (TCGA) LAML RNA-seq data and Recon 2M.2</li> </ul>

opencc-by-4.0Mar 2022View details →

Robust group- but limited individual-level (longitudinal) reliability and insights into cross-phases response prediction of conditioned fear

Here we follow the call to target measurement reliability as a key prerequisite for individual-level predictions in translational neuroscience by investigating i) longitudinal reliability at the individual and ii) group level, iii) internal consistency and iv) response predictability across experimental phases. 120 individuals performed a fear conditioning paradigm twice six months apart. Analyses of skin conductance responses, fear ratings and blood oxygen level dependent functional magnetic resonance imaging (BOLD fMRI) with different data transformations and included numbers of trials were conducted. While longitudinal reliability was rather limited at the individual level, it was comparatively higher for acquisition but not extinction at the group-level. Internal consistency was satisfactory. Higher responding in preceding phases predicted higher responding in subsequent experimental phases at a weak to moderate level depending on data specifications. In sum, the results suggest that while individual-level predictions are meaningful for (very) short time frames, they also call for more attention to measurement properties in the field.

dryad40/100

Data for: Modeling the transition of death assemblages through the mixed layer predicts a downcore increase in time averaging

Understanding how time averaging changes during the burial is essential for using Holocene and Anthropocene cores to analyze ecosystem change, given the many ways in which the time averaging affects biodiversity measures. Here, we use transition-rate matrices to explore how time averaging changes downcore when shells transit through a taphonomically-complex mixed layer into permanently-buried historical layers: this is a null model, without any temporal changes in rates of sedimentation or bioturbation, to contrast with downcore patterns that might be produced by human activity. Assuming stochastic burial and exhumation movements of shells between increments within the mixed layer and stochastic disintegration within increments, almost all combinations of net sedimentation, mixing, and disintegration produce a downcore increase in time averaging (interquartile range, IQR), typically associated with a decrease in kurtosis and skewness and with a shift from right-skewed to symmetrical age distributions. A downcore increase in time averaging is a null expectation wherever bioturbation generates an internally-structured mixed layer (i.e., a surface well-mixed layer is underlain by an incompletely-mixed layer), so that shells are mixed throughout the entire mixed layer at slower rate than they are buried below it by sedimentation. This downcore trend created by mixing is further amplified by the downcore decline in disintegration rate. Using data from the southern California shelf, we find that transition-rate matrices accurately reproduce the downcore changes in IQR, skewness, and kurtosis observed in sediment cores. The right-skewed distributions typical of surface death assemblages – the focus of most actualistic research – might be fossilized under exceptional conditions of episodic anoxia or sudden burial. However, such right-skewed assemblages will not typically transfer into subsurface historical layers and thus will be geologically transient. The deep-time fossil record will be dominated instead by more time-averaged assemblages with weakly skewed age distributions that form in the lower parts of the mixed layer.

opencc-zeroNov 2022View details →

FIGURE 3 in Ecological conditions predict the intensity of Hendra virus excretion over space and time from bat reservoir hosts

FIGURE 3 Variation in HeV AUC from flying foxes. (A) The forest plot displays annual estimates and 95% confidence intervals ordered by latitude and year; points are scaled by the inverse sampling variance. The horizontal axis uses a modulus transformation to accommodate wide upper bounds of some confidence intervals. (B) Fitted values and 95% confidence intervals for the top GAM, with raw data (scaled by inverse sampling variance) and modelled means coloured by roost type. Transparency denotes AUC derived from truncated time series (≤20 weeks)

FIGURE 2 Fitted HeV urine pool prevalence and 95 in Ecological conditions predict the intensity of Hendra virus excretion over space and time from bat reservoir hosts

FIGURE 2 Fitted HeV urine pool prevalence and 95% confidence intervals from the most parsimonious GAMM with week, seasonal interactions with roost type and previous food shortages, and an adjustment for relative abundance of Pteropus alecto. Weekly data are overlaid, coloured by roost type, and sized by corresponding P. alecto relative abundance. Thin lines show the fitted curves from the random factor smooth including each roost per year

FIGURE 1 in Ecological conditions predict the intensity of Hendra virus excretion over space and time from bat reservoir hosts

FIGURE 1 Spatiotemporal variation in HeV shedding for the nine Australian flying fox roosts sampled from 2012 through 2014. Curve height indicates the weekly proportion of HeV-positive urine pools, with roosts shown in order of latitude and coloured by roost type. Ticks show sampling time points. Dark grey shading indicates regional acute food shortage events, and dashed lines with light grey shading indicate the Austral winter (i.e. June through August)

FIGURE 4 in Ecological conditions predict the intensity of Hendra virus excretion over space and time from bat reservoir hosts

FIGURE 4 Spatiotemporal variation in regional HeV spillover events during the flying fox surveillance period (2012–2014) and its relationship with HeV AUC. (a) Maps display the annual distributions of spillovers (coloured by year) in relation to the nine analysed roosts. (b) Modelled relationships between AUC and spillover counts are shown with fitted values and 95% confidence intervals from GAMs for 50, 100, 200, 300, 400 and 500 km buffers of each roost. Raw data are overlaid and scaled by the inverse of the sampling variance for AUC

opencc-by-4.0Aug 2020View details →

Neural Networks for Structure-Informed Prediction of Formation Energy (employed in SIPFENN)

pySIPFENN Documentation: <a href="https://pysipfenn.org">pysipfenn.org</a> pySIPFENN GitHub: <a href="https://github.com/PhasesResearchLab/pySIPFENN">git.pysipfenn.org</a> Original SIPFENN Paper: <a href="https://doi.org/10.1016/j.commatsci.2022.111254">10.1016/j.commatsci.2022.111254</a>   Network Changelog: V 0.10 - All models moved to the open ONNX format for improved interchangeability; NN30 neural network similar to NN20 but accepting the new KS2022 feature vector; Python code migrated to public GitHub repository. V 0.9 - Python code updated to the release version; paper published V 0.8 - Python code (beta) to run models included V 0.7 - Original upload of development models    Selected works with SIPFENN alongside DFT and experiments: - <a href="https://doi.org/10.1016/j.actamat.2021.117448">10.1016/j.actamat.2021.117448</a> - <a href="https://doi.org/10.1038/s41598-021-03578-0">10.1038/s41598-021-03578-0</a>   SIPFENN Abstract (original publication, 2021): In recent years, numerous studies have employed machine learning (ML) techniques to enable orders of magnitude faster high-throughput materials discovery by augmentation of existing methods or as standalone tools. In this paper, we introduce a new neural network-based tool for the prediction of formation energies based on elemental and structural features of Voronoi-tessellated materials. We provide a self-contained overview of the ML techniques used. Of particular importance is the connection between the ML and the true material-property relationship, how to improve the generalization accuracy by reducing overfitting, and how new data can be incorporated into the model to tune it to a specific material system.          In the course of this work, over 30 novel neural network architectures were designed and tested. This lead to three final models optimized for (1) highest test accuracy on the Open Quantum Materials Database (OQMD), (2) performance in the discovery of new materials, and (3) performance at a low computational cost. On a test set of 21,800 compounds randomly selected from OQMD, they achieve mean average error (MAE) of 28, 40, and 42 meV/atom respectively. The second model provides better predictions on materials far from ones reported in OQMD, while the third reduces the computational cost by a factor of 8.          We collect our results in a new open-source tool called SIPFENN (Structure-Informed Prediction of Formation Energy using Neural Networks). SIPFENN not only improves the accuracy beyond existing models but also ships in a ready-to-use form with pre-trained neural networks and a user interface.    Contacts: - Adam Krajewski: ak@psu.edu - Prof. Zi-Kui Liu: zxl15@psu.edu