ProkDBP: Toward more precise identification of prokaryotic DNA binding proteins.

Prokaryotic DNA binding proteins (DBPs) play pivotal roles in governing gene regulation, DNA replication, and various cellular functions. Accurate computational models for predicting prokaryotic DBPs hold immense promise in accelerating the discovery of novel proteins, fostering a deeper understanding of prokaryotic biology, and facilitating the development of therapeutics targeting for potential disease interventions. However, existing generic prediction models often exhibit lower accuracy in predicting prokaryotic DBPs. To address this gap, we introduce ProkDBP, a novel machine learning-driven computational model for prediction of prokaryotic DBPs. For prediction, a total of nine shallow learning algorithms and five deep learning models were utilized, with the shallow learning models demonstrating higher performance metrics compared to their deep learning counterparts. The light gradient boosting machine (LGBM), coupled with evolutionarily significant features selected via random forest variable importance measure (RF-VIM) yielded the highest five-fold cross-validation accuracy. The model achieved the highest auROC (0.9534) and auPRC (0.9575) among the 14 machine learning models evaluated. Additionally, ProkDBP demonstrated substantial performance with an independent dataset, exhibiting higher values of auROC (0.9332) and auPRC (0.9371). Notably, when benchmarked against several cutting-edge existing models, ProkDBP showcased superior predictive accuracy. Furthermore, to promote accessibility and usability, ProkDBP (https://iasri-sg.icar.gov.in/prokdbp/) is available as an online prediction tool, enabling free access to interested users. This tool stands as a significant contribution, enhancing the repertoire of resources for accurate and efficient prediction of prokaryotic DBPs.

RBProkCNN: Deep learning on appropriate contextual evolutionary information for RNA binding protein discovery in prokaryotes.

RNA-binding proteins (RBPs) are central to key functions such as post-transcriptional regulation, mRNA stability, and adaptation to varied environmental conditions in prokaryotes. While the majority of research has concentrated on eukaryotic RBPs, recent developments underscore the crucial involvement of prokaryotic RBPs. Although computational methods have emerged in recent years to identify RBPs, they have fallen short in accurately identifying prokaryotic RBPs due to their generic nature. To bridge this gap, we introduce RBProkCNN, a novel machine learning-driven computational model meticulously designed for the accurate prediction of prokaryotic RBPs. The prediction process involves the utilization of eight shallow learning algorithms and four deep learning models, incorporating PSSM-based evolutionary features. By leveraging a convolutional neural network (CNN) and evolutionarily significant features selected through extreme gradient boosting variable importance measure, RBProkCNN achieved the highest accuracy in five-fold cross-validation, yielding 98.04% auROC and 98.19% auPRC. Furthermore, RBProkCNN demonstrated robust performance with an independent dataset, showcasing a commendable 95.77% auROC and 95.78% auPRC. Noteworthy is its superior predictive accuracy when compared to several state-of-the-art existing models. RBProkCNN is available as an online prediction tool (https://iasri-sg.icar.gov.in/rbprokcnn/), offering free access to interested users. This tool represents a substantial contribution, enriching the array of resources available for the accurate and efficient prediction of prokaryotic RBPs.

ASPTF: A computational tool to predict abiotic stress-responsive transcription factors in plants by employing machine learning algorithms.

BACKGROUND: Abiotic stresses pose serious threat to the growth and yield of crop plants. Several studies suggest that in plants, transcription factors (TFs) are important regulators of gene expression, especially when it comes to coping with abiotic stresses. Therefore, it is crucial to identify TFs associated with abiotic stress response for breeding of abiotic stress tolerant crop cultivars. METHODS: Based on a machine learning framework, a computational model was envisaged to predict TFs associated with abiotic stress response in plants. To numerically encode TF sequences, four distinct sequence derived features were generated. The prediction was performed using ten shallow learning and four deep learning algorithms. For prediction using more pertinent and informative features, feature selection techniques were also employed. RESULTS: Using the features chosen by the light-gradient boosting machine-variable importance measure (LGBM-VIM), the LGBM achieved the highest cross-validation performance metrics (accuracy: 86.81%, auROC: 92.98%, and auPRC: 94.03%). Further evaluation of the proposed model (LGBM prediction method + LGBM-VIM selected features) was also done using an independent test dataset, where the accuracy, auROC and auPRC were observed 81.98%, 90.65% and 91.30%, respectively. CONCLUSIONS: To facilitate the adoption of the proposed strategy by users, the approach was implemented as a prediction server called ASPTF, accessible at https://iasri-sg.icar.gov.in/asptf/. The developed approach and the corresponding web application are anticipated to supplement experimental methods in the identification of transcription factors (TFs) responsive to abiotic stress in plants.

DBPMod: a supervised learning model for computational recognition of DNA-binding proteins in model organisms.

DNA-binding proteins (DBPs) play critical roles in many biological processes, including gene expression, DNA replication, recombination and repair. Understanding the molecular mechanisms underlying these processes depends on the precise identification of DBPs. In recent times, several computational methods have been developed to identify DBPs. However, because of the generic nature of the models, these models are unable to identify species-specific DBPs with higher accuracy. Therefore, a species-specific computational model is needed to predict species-specific DBPs. In this paper, we introduce the computational DBPMod method, which makes use of a machine learning approach to identify species-specific DBPs. For prediction, both shallow learning algorithms and deep learning models were used, with shallow learning models achieving higher accuracy. Additionally, the evolutionary features outperformed sequence-derived features in terms of accuracy. Five model organisms, including Caenorhabditis elegans, Drosophila melanogaster, Escherichia coli, Homo sapiens and Mus musculus, were used to assess the performance of DBPMod. Five-fold cross-validation and independent test set analyses were used to evaluate the prediction accuracy in terms of area under receiver operating characteristic curve (auROC) and area under precision-recall curve (auPRC), which was found to be ~89-92% and ~89-95%, respectively. The comparative results demonstrate that the DBPMod outperforms 12 current state-of-the-art computational approaches in identifying the DBPs for all five model organisms. We further developed the web server of DBPMod to make it easier for researchers to detect DBPs and is publicly available at https://iasri-sg.icar.gov.in/dbpmod/. DBPMod is expected to be an invaluable tool for discovering DBPs, supplementing the current experimental and computational methods.

RBPLight: a computational tool for discovery of plant-specific RNA-binding proteins using light gradient boosting machine and ensemble of evolutionary features.

RNA-binding proteins (RBPs) are essential for post-transcriptional gene regulation in eukaryotes, including splicing control, mRNA transport and decay. Thus, accurate identification of RBPs is important to understand gene expression and regulation of cell state. In order to detect RBPs, a number of computational models have been developed. These methods made use of datasets from several eukaryotic species, specifically from mice and humans. Although some models have been tested on Arabidopsis, these techniques fall short of correctly identifying RBPs for other plant species. Therefore, the development of a powerful computational model for identifying plant-specific RBPs is needed. In this study, we presented a novel computational model for locating RBPs in plants. Five deep learning models and ten shallow learning algorithms were utilized for prediction with 20 sequence-derived and 20 evolutionary feature sets. The highest repeated five-fold cross-validation accuracy, 91.24% AU-ROC and 91.91% AU-PRC, was achieved by light gradient boosting machine. While evaluated using an independent dataset, the developed approach achieved 94.00% AU-ROC and 94.50% AU-PRC. The proposed model achieved significantly higher accuracy for predicting plant-specific RBPs as compared to the currently available state-of-art RBP prediction models. Despite the fact that certain models have already been trained and assessed on the model organism Arabidopsis, this is the first comprehensive computer model for the discovery of plant-specific RBPs. The web server RBPLight was also developed, which is publicly accessible at https://iasri-sg.icar.gov.in/rbplight/, for the convenience of researchers to identify RBPs in plants.

PlDBPred: a novel computational model for discovery of DNA binding proteins in plants.

DNA-binding proteins (DBPs) play crucial roles in numerous cellular processes including nucleotide recognition, transcriptional control and the regulation of gene expression. Majority of the existing computational techniques for identifying DBPs are mainly applicable to human and mouse datasets. Even though some models have been tested on Arabidopsis, they produce poor accuracy when applied to other plant species. Therefore, it is imperative to develop an effective computational model for predicting plant DBPs. In this study, we developed a comprehensive computational model for plant specific DBPs identification. Five shallow learning and six deep learning models were initially used for prediction, where shallow learning methods outperformed deep learning algorithms. In particular, support vector machine achieved highest repeated 5-fold cross-validation accuracy of 94.0% area under receiver operating characteristic curve (AUC-ROC) and 93.5% area under precision recall curve (AUC-PR). With an independent dataset, the developed approach secured 93.8% AUC-ROC and 94.6% AUC-PR. While compared with the state-of-art existing tools by using an independent dataset, the proposed model achieved much higher accuracy. Overall results suggest that the developed computational model is more efficient and reliable as compared to the existing models for the prediction of DBPs in plants. For the convenience of the majority of experimental scientists, the developed prediction server PlDBPred is publicly accessible at https://iasri-sg.icar.gov.in/pldbpred/.The source code is also provided at https://iasri-sg.icar.gov.in/pldbpred/source_code.php for prediction using a large-size dataset.

A Web Tool for Consensus Gene Regulatory Network Construction.

Gene regulatory network (GRN) construction involves various steps of complex computational steps. This step-by-step procedure requires prior knowledge of programming languages such as R. Development of a web tool may reduce this complexity in the analysis steps which can be easy accessible for the user. In this study, a web tool for constructing consensus GRN by combining the outcomes obtained from four methods, namely, correlation, principal component regression, partial least square, and ridge regression, has been developed. We have designed the web tool with an interactive and user-friendly web page using the php programming language. We have used R script for the analysis steps which run in the background of the user interface. Users can upload gene expression data for constructing consensus GRN. The output obtained from analysis will be available in downloadable form in the result window of the web tool.

Nitrogen Use Efficiency Phenotype and Associated Genes: Roles of Germination, Flowering, Root/Shoot Length and Biomass.

Crop improvement for Nitrogen Use Efficiency (NUE) requires a well-defined phenotype and genotype, especially for different N-forms. As N-supply enhances growth, we comprehensively evaluated 25 commonly measured phenotypic parameters for N response using 4 N treatments in six indica rice genotypes. For this, 32 replicate potted plants were grown in the green-house on nutrient-depleted sand. They were fertilized to saturation with media containing either nitrate or urea as the sole N source at normal (15 mM N) or low level (1.5 mM N). The variation in N-response among genotypes differed by N form/dose and increased developmentally from vegetative to reproductive parameters. This indicates survival adaptation by reinforcing variation in every generation. Principal component analysis segregated vegetative parameters from reproduction and germination. Analysis of variance revealed that relative to low level, normal N facilitated germination, flowering and vegetative growth but limited yield and NUE. Network analysis for the most connected parameters, their correlation with yield and NUE, ranking by Feature selection and validation by Partial least square discriminant analysis enabled shortlisting of eight parameters for NUE phenotype. It constitutes germination and flowering, shoot/root length and biomass parameters, six of which were common to nitrate and urea. Field-validation confirmed the NUE differences between two genotypes chosen phenotypically. The correspondence between multiple approaches in shortlisting parameters for NUE makes it a novel and robust phenotyping methodology of relevance to other plants, nutrients or other complex traits. Thirty-Four N-responsive genes associated with the phenotype have also been identified for genotypic characterization of NUE.

Phenotyping for Nitrogen Use Efficiency: Rice Genotypes Differ in N-Responsive Germination, Oxygen Consumption, Seed Urease Activities, Root Growth, Crop Duration, and Yield at Low N.

The biological improvement of fertilizer nitrogen use efficiency (NUE) is hampered by the poor characterization of the phenotype and genotype for crop N response and NUE. In an attempt to identify phenotypic traits for N-response and NUE in the earliest stages of plant growth, we analyzed the N-responsive germination, respiration, urease activities, and root/shoot growth of 21 Indica genotypes of rice (Oryza sativa var. indica). We found that N delays germination from 0 to 12 h in a genotype-dependent and source-dependent manner, especially with urea and nitrate. We identified contrasting groups of fast germinating genotypes such as Aditya, Nidhi, and Swarnadhan, which were also least delayed by N and slow germinating genotypes such as Panvel 1, Triguna, and Vikramarya, which were also most delayed by N. Oxygen uptake measurements in the seeds of contrasting genotypes revealed that they were affected by N source in accordance with germination rates, especially with urea. Germinating seeds were found to have endogenous urease activity, indicating the need to explore genotypic differences in the effective urea uptake and metabolism, which remain unexplored so far. Urea was found to significantly inhibit early root growth in all genotypes but not shoot growth. Field evaluation of 15 of the above genotypes clearly showed that germination rates, crop duration, and yield are linked to NUE. Slow germinating genotypes had longer crop duration and higher yield even at lower N, indicating their higher NUE, relative to fast germinating or short duration genotypes. Moreover, longer duration genotypes suffered lesser yield losses at reduced N levels as compared to short duration genotypes, which is also a measure of their NUE. Together, these results indicate the potential of germination rates, crop duration, urea utilization and its effect on root growth in the development of novel phenotypic traits for screening genotypes and crop improvement for NUE, at least in rice.

Agronomic improvements can make future cereal systems in South Asia far more productive and result in a lower environmental footprint.

South Asian countries will have to double their food production by 2050 while using resources more efficiently and minimizing environmental problems. Transformative management approaches and technology solutions will be required in the major grain-producing areas that provide the basis for future food and nutrition security. This study was conducted in four locations representing major food production systems of densely populated regions of South Asia. Novel production-scale research platforms were established to assess and optimize three futuristic cropping systems and management scenarios (S2, S3, S4) in comparison with current management (S1). With best agronomic management practices (BMPs), including conservation agriculture (CA) and cropping system diversification, the productivity of rice- and wheat-based cropping systems of South Asia increased substantially, whereas the global warming potential intensity (GWPi) decreased. Positive economic returns and less use of water, labor, nitrogen, and fossil fuel energy per unit food produced were achieved. In comparison with S1, S4, in which BMPs, CA and crop diversification were implemented in the most integrated manner, achieved 54% higher grain energy yield with a 104% increase in economic returns, 35% lower total water input, and a 43% lower GWPi. Conservation agriculture practices were most suitable for intensifying as well as diversifying wheat-rice rotations, but less so for rice-rice systems. This finding also highlights the need for characterizing areas suitable for CA and subsequent technology targeting. A comprehensive baseline dataset generated in this study will allow the prediction of extending benefits to a larger scale.

QTL analysis of novel genomic regions associated with yield and yield related traits in new plant type based recombinant inbred lines of rice (Oryza sativa L.).

BACKGROUND: Rice is staple food for more than half of the world's population including two billion Asians, who obtain 60-70% of their energy intake from rice and its derivatives. To meet the growing demand from human population, rice varieties with higher yield potential and greater yield stability need to be developed. The favourable alleles for yield and yield contributing traits are distributed among two subspecies i.e., indica and japonica of cultivated rice (Oryza sativa L.). Identification of novel favourable alleles in indica/japonica will pave way to marker-assisted mobilization of these alleles in to a genetic background to break genetic barriers to yield. RESULTS: A new plant type (NPT) based mapping population of 310 recombinant inbred lines (RILs) was used to map novel genomic regions and QTL hotspots influencing yield and eleven yield component traits. We identified major quantitative trait loci (QTLs) for days to 50% flowering (R2 = 25%, LOD = 14.3), panicles per plant (R2 = 19%, LOD = 9.74), flag leaf length (R2 = 22%, LOD = 3.05), flag leaf width (R2 = 53%, LOD = 46.5), spikelets per panicle (R2 = 16%, LOD = 13.8), filled grains per panicle (R2 = 22%, LOD = 15.3), percent spikelet sterility (R2 = 18%, LOD = 14.24), thousand grain weight (R2 = 25%, LOD = 12.9) and spikelet setting density (R2 = 23%, LOD = 15) expressing over two or more locations by using composite interval mapping. The phenotypic variation (R2) ranged from 8 to 53% for eleven QTLs expressing across all three locations. 19 novel QTLs were contributed by the NPT parent, Pusa1266. 15 QTL hotpots on eight chromosomes were identified for the correlated traits. Six epistatic QTLs effecting five traits at two locations were identified. A marker interval (RM3276-RM5709) on chromosome 4 harboring major QTLs for four traits was identified. CONCLUSIONS: The present study reveals that favourable alleles for yield and yield contributing traits were distributed among two subspecies of rice and QTLs were co-localized in different genomic regions. QTL hotspots will be useful for understanding the common genetic control mechanism of the co-localized traits and selection for beneficial allele at these loci will result in a cumulative increase in yield due to the integrative positive effect of various QTLs. The information generated in the present study will be useful to fine map and to identify the genes underlying major robust QTLs and to transfer all favourable QTLs to one genetic background to break genetic barriers to yield for sustained food security.

Controlled release formulations of metribuzin: release kinetics in water and soil.

Controlled release (CR) formulations of metribuzin in Polyvinyl chloride [(PVC) (emulsion)], carboxy methyl cellulose (CMC), and carboxy methyl cellulose-kaolinite composite (CMC-KAO), are reported. Kinetics of its release in water and soil was studied in comparison with the commercial formulation (75 DF). Metribuzin from the commercial formulation became non-detectable after 35 days whereas it attained maxima between 35-49 days and became non-detectable after 63 days in the developed products. Amongst the CR formulations, the release in both water and soil was the fastest in CMC and slowest in PVC. The CMC-KAO composite reduced the rate of release as compared to CMC alone. The diffusion exponent (n value) of metribuzin in water and soil ranged from 0.515 to 0.745 and 0.662 to 1.296, respectively in the various formulations. The release was diffusion controlled with half release time (t(1/2)) from different controlled release matrices of 12.98 to 47.63 days in water and 16.90 to 51.79 days in soil. It was 3.25 and 4.66 days, respectively in the commercial formulation. The period of optimum availability of metribuzin in water and soil from controlled released formulations ranged from 15.09 to 31.68 and 17.99 to 34.72 days as against 5.03 and 8.80 days in the commercial formulation.

Pesticidal seed coats based on azadirachtin-A: release kinetics, storage life and performance.

BACKGROUND: Infestation of seeds by pests during storage leads to deterioration in quality. Seed coating is an effective option to overcome the menace. Unlike synthetic fungicidal seed coats, little is known of those based on botanicals. This study aims at developing azadirachtin-A-based pesticidal seed coats to maintain seed quality during storage. RESULTS: Polymer- and clay-based coats containing azadirachtin-A were prepared and evaluated for quality maintenance of soybean seed during storage. Gum acacia, gum tragacanth, rosin, ethyl cellulose, hydroxyethyl cellulose, polyethyl methacrylate, methyl cellulose, polyethylene glycol, polyvinyl chloride, polyvinyl acetate, polyvinyl pyrrolidone and Agrimer VA 6 polymers and the clay bentonite were used as carriers. The time for 50% release (t(1/2)) of azadirachtin-A into water from the seeds coated with the different coats ranged from 8.02 to 21.36 h. The half-life (T(1/2)) of azadirachtin-A in the coats on seed ranged from 4.37 to 11.22 months, as compared with 3.45 months in azadirachtin-A WP, showing an increase by a factor of nearly 1.3-3.3 over the latter. The coats apparently acted as a barrier to moisture to reduce azadirachtin-A degradation and prevented proliferation of storage fungi. Polyethyl methacrylate, polyvinyl acetate and polyvinyl pyrrolidone were significantly superior to the other polymers. Azadirachtin-A showed a significant positive correlation with seed germination and vigour, and negative correlation with moisture content. CONCLUSION: Effective polymeric carriers for seed coats based on azadirachtin-A are reported. These checked seed deterioration during storage by acting as a barrier to moisture and reduced the degradation of azadirachtin-A.

Development of controlled release formulations of carbofuran and evaluation of their efficacy against Meloidogyne incognita.

Controlled release (CR) formulations of the insecti-nematicide carbofuran have been prepared using commercially available rosin, sodium carboxymethylcellulose and sodium carboxymethylcellulose with clay (bentonite, kaolinite, and Fuller's earth). The kinetics of carbofuran release in soil from the different formulations were studied in comparison with that of the commercially available granules (3G). Release from the commercial formulation was faster than with the new CR formulations. Addition of clay in the biodegradable polymer matrix reduced the rate of release. The diffusion exponent (n value) of carbofuran in soil ranged from 0.462 to 0.740 in the tested formulations. The half-release (t1/2) values ranged between 4.79 and 25.11 days, and the period of optimum availability (POA) of carbofuran ranged from 15.10 to 43.97 days. The mean EC50 of the commercial formulation against Meloidogyne incognita was quite high as compared to those of CR formulations. The effective duration (te) of carbofuran from the CR and commercial formulations was predicted by fitting the mean EC50 values of test formulations in the model (M(infinity) - Me)/M(infinity) = Kdte. It was 0.7 day in commercial 3G in comparison with 17.8 days for CMC-bentonite. The bioassay studies revealed that with the rosin-yellow polymer, the dose of carbofuran could be reduced to half of its recommended dose for nematode control. Overall, a comparison of CR formulations with the commercial one showed an earlier degradation of carbofuran in the latter and relatively prolonged activity in the former.