GitHub Repository Research Articles

QERaman: An open-source program for calculating resonance Raman spectra based on Quantum ESPRESSO

We present an open-source program QERaman that computes first-order resonance Raman spectroscopy of materials using the output data from Quantum ESPRESSO. Complex values of Raman tensors are calculated based on the quantum description of the Raman scattering from calculations of electron-photon and electron-phonon matrix elements, which are obtained by using the modified Quantum ESPRESSO. Our program also calculates the resonant Raman spectra as a function of incident laser energy for linearly- or circularly-polarized light. Hands-on tutorials for graphene and MoS2 are given to show how to run QERaman. All codes, examples, and scripts are available on the GitHub repository. Program summaryProgram Title:QERamanCPC Library link to program files:https://doi.org/10.17632/ddcrrrmxw9.1Developer's repository link:https://github.com/nguyen-group/QERamanLicensing provisions: GNU General Public Licence 3.0Programming language: FortranExternal routines:Quantum ESPRESSO v7.2Nature of problem: Resonance Raman spectra with first-principles calculations.Solution method: The Raman intensity formula is given by the quantum theory, in which the electron-photon and the electron-phonon matrix elements are obtained from the modified Quantum ESPRESSO package.

GeoDILI: A Robust and Interpretable Model for Drug-Induced Liver Injury Prediction Using Graph Neural Network-Based Molecular Geometric Representation.

Drug-induced liver injury (DILI) is a significant cause of drug failure and withdrawal due to liver damage. Accurate prediction of hepatotoxic compounds is crucial for safe drug development. Several DILI prediction models have been published, but they are built on different data sets, making it difficult to compare model performance. Moreover, most existing models are based on molecular fingerprints or descriptors, neglecting molecular geometric properties and lacking interpretability. To address these limitations, we developed GeoDILI, an interpretable graph neural network that uses a molecular geometric representation. First, we utilized a geometry-based pretrained molecular representation and optimized it on the DILI data set to improve predictive performance. Second, we leveraged gradient information to obtain high-precision atomic-level weights and deduce the dominant substructure. We benchmarked GeoDILI against recently published DILI prediction models, as well as popular GNN models and fingerprint-based machine learning models using the same data set, showing superior predictive performance of our proposed model. We applied the interpretable method in the DILI data set and derived seven precise and mechanistically elucidated structural alerts. Overall, GeoDILI provides a promising approach for accurate and interpretable DILI prediction with potential applications in drug discovery and safety assessment. The data and source code are available at GitHub repository (https://github.com/CSU-QJY/GeoDILI).

Particle-Picking in Cryo-Electron Microscopy Images with Online Resources

Aims: Use deep learning online resources to identify and pick single particle views in micrographs to enable high quality three-dimensional reconstruction for macromolecular structure determination. Study Design: Using the keyhole limpet hemocyanin dataset, a public cryo electron microscopy (cryo-EM) dataset containing two dimensional projections of the particles in two views (top and side) in several orientations, and a recent deep learning algorithm made available in a GitHub repository, we design the procedure to pick both views with high degree of confidence, using only online resources and running in a standard laptop. Methodology: The defocus images are subject to a pre-processing stage to increase its contrast and ameliorate its radiometric range. This is followed by a training stage, that needs a few images annotated with examples of both views of interest – top and side view – identified using user-friendly tools available online. The annotated subset of images is divided for train and validation purposes, and the algorithm runs to produce a set of weights, that can be used for inference in any other similar image, locating all the instances of the particles in both views in seconds. Results: From the 57 images used to evaluate the performance of the algorithm, 63% had both precision and recall better than 90%. The global precision on the test dataset was 91.6% and recall 98.1%. Considering each view separately, top views detections attain a precision of 91.7%, with 100% for recall; side views recall remains on 96.7%, while precision attain 91.5%. Conclusion: Deep learning methods are a promising tool for extracting large amounts of single particle views as needed for quality 3D structure reconstruction, as they can be implemented with minimal computer skills and trained to achieve state-of-the-art automatic discrimination, as described in this study.

An extended B′ formulation for ablating-surface boundary conditions

The B′ formulation can be understood as a mass and energy conservation formalism at a reacting singular surface. In hypersonics applications, it is typically used to compute the chemical equilibrium properties of gaseous mixtures at ablating surfaces, and to estimate the recession velocity of the interface. In the first half of the paper, we derive the B′ formulation to emphasize first principles. In particular, while we eventually specialize to the commonly considered case of chemical equilibrium boundary layers that satisfy the heat and mass transfer analogy, we first derive a general interface jump condition that lets us highlight all the underlying assumptions of the well-known B′ equations. This procedure helps elucidate the nature of the B′ formalism and it also allows us to straightforwardly extend the original formulation. Specifically, when applied at the interface between a porous material and a boundary layer (as in thermal protection systems applications), the original formulation assumes unidirectional advective transport of gaseous species from the porous material to the boundary layer (i.e., blowing). However, under conditions that may appear in hypersonic flight or in ground-based wind tunnels, boundary layer gases can enter the porous material due to a favorable pressure gradient. We show that this scenario can be easily handled via a straightforward modification to the B′ formalism, and we demonstrate via examples that accounting for gas entering the material can impact the predicted recession velocity of ablating surfaces. In order to facilitate the implementation of the extended B′ formulation in existing material response codes, we present a short algorithm in section 5 and we also refer readers to a GitHub repository where the scripts used to generate the modified B′ tables are publicly available.

Blood DNA methylation signature of diet quality and association with cardiometabolic traits.

Diet quality might influence cardiometabolic health through epigenetic changes, but this has been little investigated in adults. Our aims were to identify cytosine-phosphate-guanine (CpG) dinucleotides associated with diet quality by conducting an epigenome-wide association study (EWAS) based on blood DNA methylation (DNAm) and to assess how diet-related CpGs associate with inherited susceptibility to cardiometabolic traits: body mass index (BMI), systolic blood pressure (SBP), triglycerides, type 2 diabetes (T2D), and coronary heart disease (CHD). Meta-EWAS including 5274 participants in four cohorts from Spain, the USA, and the UK. We derived three dietary scores (exposures) to measure adherence to a Mediterranean diet, to a healthy plant-based diet, and to the Dietary Approaches to Stop Hypertension. Blood DNAm (outcome) was assessed with the Infinium arrays Human Methylation 450K BeadChip and MethylationEPIC BeadChip. For each diet score, we performed linear EWAS adjusted for age, sex, blood cells, smoking and technical variables, and BMI in a second set of models. We also conducted Mendelian randomization analyses to assess the potential causal relationship between diet-related CpGs and cardiometabolic traits. We found 18 differentially methylated CpGs associated with dietary scores (P < 1.08 × 10-7; Bonferroni correction), of which 12 were previously associated with cardiometabolic traits. Enrichment analysis revealed overrepresentation of diet-associated genes in pathways involved in inflammation and cardiovascular disease. Mendelian randomization analyses suggested that genetically determined methylation levels corresponding to lower diet quality at cg02079413 (SNORA54), cg02107842 (MAST4), and cg23761815 (SLC29A3) were causally associated with higher BMI and at cg05399785 (WDR8) with greater SBP, and methylation levels associated with higher diet quality at cg00711496 (PRMT1) with lower BMI, T2D risk, and CHD risk and at cg0557921 (AHRR) with lower CHD risk. Diet quality in adults was related to differential methylation in blood at 18 CpGs, some of which related to cardiometabolic health.

The frequency modulation transfer function provides supplemental measures for the objective evaluation of pitch extractors

We propose to apply the frequency modulation transfer function as a supplemental measure for evaluating pitch extractors' performance. We introduced a new family of time-stretched-pulse for acoustic system analysis (Kawahara and Yatabe, ICASSP2021, called CAPRICEP). Composing a test signal using the CAPRICEP units by Walsh-Hadamard sequence enables simultaneous measurement of the linear-time-invariant, non-linear-time-invariant, and random-time-varying attributes. We applied the proposed analysis method to eighteen pitch extractors and visualized their behavior (represented more than five thousand plots) as a movie. The proposed procedure will be available as open-source tools in our GitHub repository.

Development and Application of a Data-Driven Signal Detection Method for Surveillance of Adverse Event Variability Across Manufacturing Lots of Biologics.

Postmarketing drug safety surveillance research has focused on the product-patient interaction as the primary source of variability in clinical outcomes. However, the inherent complexity of pharmaceutical manufacturing and distribution, especially of biologic drugs, also underscores the importance of risks related to variability in manufacturing and supply chain conditions that could potentially impact clinical outcomes. We propose a data-driven signal detection method called HMMScan to monitor for manufacturing lot-dependent changes in adverse event (AE) rates, and herein apply it to a biologic drug. The HMMScan method chooses the best-fitting candidate from a family of probabilistic Hidden Markov Models to detect temporal correlations in per lot AE rates that could signal clinically relevant variability in manufacturing and supply chain conditions. Additionally, HMMScan indicates the particular lots most likely to be related to risky states of the manufacturing or supply chain condition. The HMMScan method was validated on extensive simulated data and applied to three actual lot sequences of a major biologic drug by combining lot metadata from the manufacturer with AE reports from the US FDA Adverse Event Reporting System (FAERS). Extensive method validation on simulated data indicated that HMMScan is able to correctly detect the presence or absence of variable manufacturing and supply chain conditions for contiguous sequences of 100 lots or more when changes in these conditions have a meaningful impact on AE rates. Applying the HMMScan method to FAERS data, two of the three actual lot sequences examined exhibited evidence of potential manufacturing or supply chain-related variability. HMMScan could be utilized by both manufacturers and regulators to automate lot variability monitoring and inform targeted root-cause analysis. Broad application of HMMScan would rely on a well-developed data input pipeline. The proposed method is implemented in an open-source GitHub repository.

Predicting gene regulatory links from single-cell RNA-seq data using graph neural networks.

Single-cell RNA-sequencing (scRNA-seq) has emerged as a powerful technique for studying gene expression patterns at the single-cell level. Inferring gene regulatory networks (GRNs) from scRNA-seq data provides insight into cellular phenotypes from the genomic level. However, the high sparsity, noise and dropout events inherent in scRNA-seq data present challenges for GRN inference. In recent years, the dramatic increase in data on experimentally validated transcription factors binding to DNA has made it possible to infer GRNs by supervised methods. In this study, we address the problem of GRN inference by framing it as a graph link prediction task. In this paper, we propose a novel framework called GNNLink, which leverages known GRNs to deduce the potential regulatory interdependencies between genes. First, we preprocess the raw scRNA-seq data. Then, we introduce a graph convolutional network-based interaction graph encoder to effectively refine gene features by capturing interdependencies between nodes in the network. Finally, the inference of GRN is obtained by performing matrix completion operation on node features. The features obtained from model training can be applied to downstream tasks such as measuring similarity and inferring causality between gene pairs. To evaluate the performance of GNNLink, we compare it with six existing GRN reconstruction methods using seven scRNA-seq datasets. These datasets encompass diverse ground truth networks, including functional interaction networks, Loss of Function/Gain of Function data, non-specific ChIP-seq data and cell-type-specific ChIP-seq data. Our experimental results demonstrate that GNNLink achieves comparable or superior performance across these datasets, showcasing its robustness and accuracy. Furthermore, we observe consistent performance across datasets of varying scales. For reproducibility, we provide the data and source code of GNNLink on our GitHub repository: https://github.com/sdesignates/GNNLink.

Sequential stochastic and bootstrap methods to generate synthetic solar irradiance time series of high temporal resolution based on historical observations

Generating synthetic solar irradiance data through computational methods has become an attractive approach, especially when obtaining accurate measurements from historical observations or satellite-derived estimates is not feasible. Since solar photovoltaic energy production is influenced by variable weather conditions, having reliable solar irradiance data is crucial for evaluating the performance of photovoltaic systems accurately. In this paper, we propose two methods, namely stochastic method, and bootstrap method, to generate one-day synthetic solar irradiance data at a minimum 60-minute time resolution. Both techniques consider dynamic meteorological behavior and maintain the physical significance of the observed data, effectively capturing the intermittent nature of solar irradiance. Validations were performed for five sites with different climate conditions and significant geographical separation, and different time resolutions, through various metrics, including variability, statistical distribution, and energy production, which demonstrated mean average percentage errors as low as 2.1% for intraday irradiance fluctuations, statistical distribution goodness-of-fit up to 80%, and discrepancy for energy production close to 2.4%. results verify the applicability of the proposed methods regardless the time resolution, the location of the measured data and the procedure to record it (i.e., from ground weather stations or satellite-derived estimates). We also evaluated the computational performance of the proposed methods, synthetic, where the elapsed time to generate the synthetic data takes less than a minute to generate a hundred one-day solar irradiance time series. The novelty of the proposed methods is that it is only needed the information of a single month to generate representative synthetic solar irradiance one-day sequences generated for five climate conditions without the need of a training process (i.e., iterative adjustments of the parameters), being useful for pre-feasibility studies of the photovoltaic project and to train machine learning algorithms that deals with time series. To encourage the reproducibility of the research presented in this paper, the proposed methods to generate synthetic solar irradiance data are freely available in a well-documented GitHub repository from https://github.com/salazarna/synthetic-irradiance-sequence.

Rasgos‐CL: A functional trait database of Chilean woody plants

AbstractMotivationDue to language and networking barriers, global initiatives to compile trait data often fail to integrate data from sources in non‐English languages or scientists that largely speak and write in non‐English languages. To illustrate the potential for regional databases to fill gaps in trait data, and how such databases may fill critical gaps in global biodiversity databases, we built the Rasgos‐CL Database. Rasgos‐CL provides a comprehensive set of plant traits for the woody flora of Chile by mobilizing and standardizing unstructured data largely from the Spanish‐language literature. We quantified the gains in trait coverage compared to global trait databases and identified phylogenetic and geographic biases of trait data gaps.Main Types of Variables ContainedRasgos‐CL contains 25,174 trait records, including 2 continuous and 21 categorical traits for 662 woody species.Spatial Location and GrainNational coverage, with species that occur across all ecosystems in continental Chile.Time Period and GrainData were extracted from sources published between 1833 and 2023.Major Taxa and Level of MeasurementRasgos‐CL includes trait data aggregated at the species level for 662 tree and shrub species, and also provides trait records from individual data sources.Software FormatRasgos‐CL includes four csv files. A GitHub repository contains the csv files.

Implementation of deep neural networks and statistical methods to predict the resilient modulus of soils

ABSTRACT The Resilient Modulus (Mr) is perhaps the most relevant and widely used parameter to characterise the soil behaviour under repetitive loading for pavement applications. Accordingly, it is a crucial parameter controlling the mechanistic-empirical pavement design. Nonetheless, determining the Mr by laboratory tests is not always possible due to the high consumption of time and financial resources. Thus, developing new indirect approaches for estimating the MR is necessary. Precisely, this article investigates the application of Deep Neural Networks (DNNs) and statistical methods to predict the Mr of soils. For that purpose, the Long-Term Pavement Performance (LTPP) database was implemented. It includes 64 701 datasets resulting from coarse-grained and fine-grained soil samples considering a wide range of grain size distribution and subjected to different stress levels. The input parameters were the bulk stress, octahedral shear stress, and the percentage of soil particles passing through the different sieves (3”, 2”, 3/2”, 1”, 3/4”, 1/2”, 3/8”, No. 4, No. 10, No. 40, No. 80, and No. 200) and the output was the Mr. The results suggest that while conventional mathematical models are unable to predict the influence of the grain size distribution and stress level on the Mr, the proposed DNNs were able to reproduce very accurate predictions. Notably, the proposed computational models have been uploaded to a GitHub repository and have become a valuable tool for forecasting the Mr when experimental measurements are not feasible.

FIELDimageR.Extra: Advancing user experience and computational efficiency for analysis of orthomosaic from agricultural field trials

AbstractFieldimageR.Extra is an advanced R package that enhances user experience and computational efficiency in analyzing orthomosaic images from agricultural field trials. Through the integration of modern GIS libraries like terra, stars, and sf, it surpasses traditional packages like raster and sp. The FieldimageR.Extra offers interactive visualization, vector feature creation, and spatial data editing within the R environment through the integration of mapview and mapedit packages. Notably, FieldimageR.Extra introduces new functions like fieldShape_render and fieldShape_edit, enabling flexible plot grid generation and editing capabilities. Comparative evaluations demonstrate the superior performance of FieldimageR.Extra in handling spatial data, crop and extract operations, and plot grid generation. With its comprehensive features, FieldimageR.Extra stands as a valuable addition to the FieldimageR R package, offering researchers efficient tools for unmanned aerial vehicle‐based orthomosaic image analysis in agricultural research. FIELDimageR.Extra is publicly available as a GitHub repository (https://github.com/filipematias23/FIELDimageR.Extra).

GENII: A graph neural network-based model for citywide litter prediction leveraging crowdsensing data

Plastic litter and its associated environmental hazards have garnered global attention in recent years, highlighting the need for effective management. Improper handling of plastic litter can lead to environmental degradation, making it crucial to address this issue. In this paper, we propose an innovative approach to predict the spatial distribution and quantity of plastic litter at the city level by leveraging crowd-sensing data and designing a graph neural network-based model. Meteorological data is specifically used to enhance temporal correlation, while the spatial distribution of litter is clustered using the K-means method to capture spatial correlation. For each cluster, multiple graphs are constructed based on the points of interest (POIs) and litter distribution within the cluster. Graph attention neural networks and heterogeneous graph attention networks are then utilized to aggregate the adjacency information and overall structural information of these graphs, respectively. Finally, the litter prediction results are obtained through multiple fully connected layers. Real-world experiments convincingly demonstrate the high effectiveness of our proposed model in predicting city-wide litter, surpassing multiple comparative models. All the code and datasets can be accessed from the GitHub repository at https://github.com/ZJUDataIntelligence/Genii.

FrameD: Framework for DNA-based Data Storage Design, Verification, and Validation.

DNA-based data storage is a quickly growing field that hopes to harness the massive theoretical information density of DNA molecules to produce a competitive next-generation storage medium suitable for archival data. In recent years, many DNA-based storage system designs have been proposed. Given that no common infrastructure exists for simulating these storage systems, comparing many different designs along with many different error models is increasingly difficult. To address this challenge we introduce FrameD, a simulation infrastructure for DNA storage systems that leverages the underlying modularity of DNA storage system designs to provide a framework to express different designs while being able to reuse common components. We demonstrate the utility of FrameD and the need for a common simulation platform using a case study. Our case study compares designs that utilize strand copies differently, some that align strand copies using Multiple Sequence Alignment (MSA) algorithms and others that do not. We found that the choice to include MSA in the pipeline is dependent on the error rate and the type of errors being injected and is not always beneficial. In addition to supporting a wide range of designs, FrameD provides the user with transparent parallelism to deal with a large number of reads from sequencing and the need for many fault injection iterations. We believe that FrameD fills a void in the tools publicly available to the DNA storage community by providing a modular and extensible framework with support for massive parallelism. As a result, it will help accelerate the design process of future DNA-based storage systems. The source code for FrameD along with the data generated during the demonstration of FrameD is available in a public Github repository at https://github.com/dna-storage/framed (10.5281/zenodo.7757762).

Gradient-Based Metrics for the Evaluation of Image Defogging

Fog, haze, or smoke are standard atmospheric phenomena that dramatically compromise the overall visibility of any scene, critically affecting features such as the illumination, contrast, and contour detection of objects. The decrease in visibility compromises the performance of computer vision algorithms such as pattern recognition and segmentation, some of which are very relevant to decision-making in the field of autonomous vehicles. Several dehazing methods have been proposed that either need to estimate fog parameters through physical models or are statistically based. But physical parameters greatly depend on the scene conditions, and statistically based methods require large datasets of natural foggy images together with the original images without fog, i.e., the ground truth, for evaluation. Obtaining proper fog-less ground truth images for pixel-to-pixel evaluation is costly and time-consuming, and this fact hinders progress in the field. This paper aims to tackle this issue by proposing gradient-based metrics for image defogging evaluation that do not require a ground truth image without fog or a physical model. A comparison of the proposed metrics with metrics already used in the NTIRE 2018 defogging challenge as well as several state-of-the-art defogging evaluation metrics is performed to prove its effectiveness in a general situation, showing comparable results to conventional metrics and an improvement in the no-reference scene. A Matlab implementation of the proposed metrics has been developed and it is open-sourced in a public GitHub repository.

T9GPred: A Comprehensive Computational Tool for the Prediction of Type 9 Secretion System, Gliding Motility, and the Associated Secreted Proteins.

Type 9 secretion system (T9SS) is one of the least characterized secretion systems exclusively found in the Bacteroidetes phylum, which comprises various environmental and economically relevant bacteria. While T9SS plays a central role in bacterial movement termed gliding motility, survival, and pathogenicity, there is an unmet need for a comprehensive tool that predicts T9SS, gliding motility, and proteins secreted via T9SS. In this study, we develop such a computational tool, Type 9 secretion system and Gliding motility Prediction (T9GPred). To build this tool, we manually curated published experimental evidence and identified mandatory components for T9SS and gliding motility prediction. We also compiled experimentally characterized proteins secreted via T9SS and determined the presence of three unique types of C-terminal domain signals, and these insights were leveraged to predict proteins secreted via T9SS. Notably, using recently published experimental evidence, we show that T9GPred has high predictive power. Thus, we used T9GPred to predict the presence of T9SS, gliding motility, and associated secreted proteins across 693 completely sequenced Bacteroidetes strains. T9GPred predicted 402 strains to have T9SS, of which 327 strains are also predicted to exhibit gliding motility. Further, T9GPred also predicted putative secreted proteins for the 402 strains. In a nutshell, T9GPred is a novel computational tool for systems-level prediction of T9SS and streamlining future experimentation. The source code of the computational tool is available in our GitHub repository: https://github.com/asamallab/T9GPred. The tool and its predicted results are compiled in a web server available at: https://cb.imsc.res.in/t9gpred/.

LOGICS: Learning optimal generative distribution for designing de novo chemical structures

In recent years, the field of computational drug design has made significant strides in the development of artificial intelligence (AI) models for the generation of de novo chemical compounds with desired properties and biological activities, such as enhanced binding affinity to target proteins. These high-affinity compounds have the potential to be developed into more potent therapeutics for a broad spectrum of diseases. Due to the lack of data required for the training of deep generative models, however, some of these approaches have fine-tuned their molecular generators using data obtained from a separate predictor. While these studies show that generative models can produce structures with the desired target properties, it remains unclear whether the diversity of the generated structures and the span of their chemical space align with the distribution of the intended target molecules. In this study, we present a novel generative framework, LOGICS, a framework for Learning Optimal Generative distribution Iteratively for designing target-focused Chemical Structures. We address the exploration—exploitation dilemma, which weighs the choice between exploring new options and exploiting current knowledge. To tackle this issue, we incorporate experience memory and employ a layered tournament selection approach to refine the fine-tuning process. The proposed method was applied to the binding affinity optimization of two target proteins of different protein classes, κ-opioid receptors, and PIK3CA, and the quality and the distribution of the generative molecules were evaluated. The results showed that LOGICS outperforms competing state-of-the-art models and generates more diverse de novo chemical structures with optimized properties. The source code is available at the GitHub repository (https://github.com/GIST-CSBL/LOGICS).

A blockchain-based framework for effective monitoring of EU Green Bonds

The EU recognises green bonds as a critical financing tool for climate and environmental projects. However, there is a pressing need to ensure that these bonds genuinely support green growth instead of allowing greenwashing, where entities present themselves as environmentally friendly without the evidence to support their claims. Greenwashing undermines the credibility of the market and can have a significantly negative environmental impact. To address this issue, a proposed blockchain-based framework called EUGBS-Chain has been introduced to increase transparency and accountability in the EUGB market. The framework utilises blockchain technology to record transactions in a tamper-proof, decentralised ledger that is accessible and verifiable by all stakeholders. With EUGBS-Chain, the EU can ensure that green bonds are used for genuine green growth projects and not just as marketing tools for companies. The proposed framework is open-source and available on the GitHub repository.

Flooding-based MobileNet to identify cucumber diseases from leaf images in natural scenes

Cucumber production in China is declining due to various pathologic diseases, but the technology for plant disease detection is not mature and requires high labor costs. Moreover, since planting sites are typically high-density scenes, most photos are shot from various angles with messy backgrounds, resulting in poor classification reliability. In this paper, batches of cucumber leaf image data are collected from agricultural websites and then preprocessed through the image size normalization. A mobile-based recognition algorithm is proposed to identify cucumber diseases from leaf images in natural scenes, enabling farmers to detect diseases more quickly. The proposed algorithm allows farmers to upload cucumber pictures, and rapidly and accurately classify them with high accuracy. With a improved network based on MobileNet V3, the classification of seven kinds of cucumber leaf diseases can be quickly and accurately completed. The network model is achieved by selecting appropriate parameters, optimizers, and batch capacity using the single-variable method. Additionally, a new training strategy called the flooding method is applied in the model, replacing the traditional strategy that relies solely on loss decline. An accuracy of 83.3% is achieved on our custom dataset. Finally, two public datasets, namely PlantVillage and Apple Disease, are selected for migration experiments. The achieved accuracy rates for these datasets are 99% and 98.1% respectively, demonstrating the universality of the proposed strategy. The code for all the experiments will be made available for reference on the GitHub repository at https://github.com/YiQuanMarx/Agricultural_Diseases_Dentification.

Promoting High-Quality Data in OBIS: Insights from the OBIS Data Quality Assessment and Enhancement Project Team

The Ocean Biodiversity Information System (OBIS) (Klein et al. 2019) is a global database of marine biodiversity and associated environmental data, which provides critical information to researchers and policymakers worldwide. Ensuring the accuracy and consistency of the data in OBIS is essential for its usefulness and value, not only to the scientific community but also to the science-policy interface. The OBIS Data Quality Assessment and Enhancement Project Team (QCPT), formed in 2019 by the OBIS steering group, aims to assess and enhance data quality. It has been working on three categories of activities for this purpose: Data quality enhancement and management The OBIS QCPT organized data laundry events to identify and address data quality issues of published OBIS datasets. Furthermore, individual OBIS nodes were invited to give their data-processing presentations in the monthly meetings to foster knowledge sharing and collaborative problem-solving focused on data quality. Data quality issues and solutions highlighted in the presentations and data laundry events were documented in a dedicated GitHub repository as GitHub issues. The solutions for data quality issues and marine-specific pre-publication quality control tools, designed to identify the data quality issues, were provided as feedback to the OBIS Capacity Development Task Team. These inputs were used to create training resources (see OBIS manual, upcoming OBIS training course hosted on OceanTeacher Global Academy) aimed at preventing these issues. Standardization of OBIS data processing pipeline As OBIS uses the Darwin Core standard (Wieczorek et al. 2012), the use of standardized tests and assertions in the data processing pipeline is encouraged. To achieve this, the OBIS QCPT aligned OBIS quality checks with a subset of core tests and assertions (Chapman et al. 2020) developed by the Biodiversity Information Standards (TDWG) Biodiversity Data Quality (BDQ) Task Group 2 (TG2) (Chapman et al. 2020) as tracked in this GitHub issue. Not all default parameters of the core tests and assertions are optimal for marine biodiversity data. The OBIS QCPT met monthly to determine suitable parameters for customizing the tests. The pipeline produces a data quality report for each dataset with quality flags that indicate potential data quality issues, enabling node managers and data providers to review the flagged records. Community engagement The OBIS QCPT led a survey among data users to gather insights into OBIS data quality issues and bridge the gap between the current implementation and user expectations. The survey findings enabled OBIS to prioritize issues to be addressed, as summarized in Section 2.2.2 of the 11th OBIS Steering Group meeting report. In addition to engaging with data users, the OBIS QCPT also served as a platform to discuss questions related to the use of Darwin Core from the nodes and provided feedback for the term discussions. In summary, the OBIS QCPT improves marine species data reliability and usability through transparent and participatory approaches, fostering continuous improvement. Collaborative efforts, standardized procedures, and knowledge sharing advance OBIS' mission of providing high quality biodiversity data for research, conservation, and ocean management.