Predictive Role of Cluster Bean (Cyamopsis tetragonoloba) Derived miRNAs in Human and Cattle Health.

MicroRNAs (miRNAs) are small non-coding conserved molecules with lengths varying between 18-25nt. Plants miRNAs are very stable, and probably they might have been transferred across kingdoms via food intake. Such miRNAs are also called exogenous miRNAs, which regulate the gene expression in host organisms. The miRNAs present in the cluster bean, a drought tolerant legume crop having high commercial value, might have also played a regulatory role for the genes involved in nutrients synthesis or disease pathways in animals including humans due to dietary intake of plant parts of cluster beans. However, the predictive role of miRNAs of cluster beans for gene-disease association across kingdoms such as cattle and humans are not yet fully explored. Thus, the aim of the present study is to (i) find out the cluster bean miRNAs (cb-miRs) functionally similar to miRNAs of cattle and humans and predict their target genes' involvement in the occurrence of complex diseases, and (ii) identify the role of cb-miRs that are functionally non-similar to the miRNAs of cattle and humans and predict their targeted genes' association with complex diseases in host systems. Here, we predicted a total of 33 and 15 functionally similar cb-miRs (fs-cb-miRs) to human and cattle miRNAs, respectively. Further, Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis revealed the participation of targeted genes of fs-cb-miRs in 24 and 12 different pathways in humans and cattle, respectively. Few targeted genes in humans like LCP2, GABRA6, and MYH14 were predicted to be associated with disease pathways of Yesinia infection (hsa05135), neuroactive ligand-receptor interaction (hsa04080), and pathogenic Escherichia coli infection (hsa05130), respectively. However, targeted genes of fs-cb-miRs in humans like KLHL20, TNS1, and PAPD4 are associated with Alzheimer's, malignant tumor of the breast, and hepatitis C virus infection disease, respectively. Similarly, in cattle, targeted genes like ATG2B and DHRS11 of fs-cb-miRs participate in the pathways of Huntington disease and steroid biosynthesis, respectively. Additionally, the targeted genes like SURF4 and EDME2 of fs-cb-miRs are associated with mastitis and bovine osteoporosis, respectively. We also found a few cb-miRs that do not have functional similarity with human and cattle miRNAs but are found to target the genes in the host organisms and as well being associated with human and cattle diseases. Interestingly, a few genes such as NRM, PTPRE and SUZ12 were observed to be associated with Rheumatoid Arthritis, Asthma and Endometrial Stromal Sarcoma diseases, respectively, in humans and genes like SCNN1B associated with renal disease in cattle.

Genome-wide identification of potassium channels in maize showed evolutionary patterns and variable functional responses to abiotic stresses.

Potassium (K) channels are essential components of plant biology, mediating not only K ion (K+) homeostasis but also regulating several physiological processes and stress tolerance. In the current investigation, we identified 27 K+ channels in maize and deciphered the evolution and divergence pattern with four monocots and five dicot species. Chromosomal localization and expansion of K+ channel genes showed uneven distribution and were independent of genome size. The dispersed duplication is the major force in expanding K+ channels in the target genomes. The mean Ka/Ks ratio of <0.5 in paralogs and orthologs indicates horizontal and vertical expansions of K+ channel genes under strong purifying selection. The one-to-one K+ channel orthologs were prominent among the closely related species, with higher synteny between maize and the rest of the monocots. Comprehensive K+ channels promoter analysis revealed various cis-regulatory elements mediating stress tolerance with the predominance of MYB and STRE binding sites. The regulatory network showed AP2-EREBP TFs, miR164 and miR399 are prominent regulatory elements of K+ channels. The qRT-PCR analysis of K+ channels and regulatory miRNAs showed significant expressions in response to drought and waterlogging stresses. The present study expanded the knowledge on K+ channels in maize and will serve as a basis for an in-depth functional analysis.

An Improved Machine Learning-Based Approach to Assess the Microbial Diversity in Major North Indian River Ecosystems.

The rapidly evolving high-throughput sequencing (HTS) technologies generate voluminous genomic and metagenomic sequences, which can help classify the microbial communities with high accuracy in many ecosystems. Conventionally, the rule-based binning techniques are used to classify the contigs or scaffolds based on either sequence composition or sequence similarity. However, the accurate classification of the microbial communities remains a major challenge due to massive data volumes at hand as well as a requirement of efficient binning methods and classification algorithms. Therefore, we attempted here to implement iterative K-Means clustering for the initial binning of metagenomics sequences and applied various machine learning algorithms (MLAs) to classify the newly identified unknown microbes. The cluster annotation was achieved through the BLAST program of NCBI, which resulted in the grouping of assembled scaffolds into five classes, i.e., bacteria, archaea, eukaryota, viruses and others. The annotated cluster sequences were used to train machine learning algorithms (MLAs) to develop prediction models to classify unknown metagenomic sequences. In this study, we used metagenomic datasets of samples collected from the Ganga (Kanpur and Farakka) and the Yamuna (Delhi) rivers in India for clustering and training the MLA models. Further, the performance of MLAs was evaluated by 10-fold cross validation. The results revealed that the developed model based on the Random Forest had a superior performance compared to the other considered learning algorithms. The proposed method can be used for annotating the metagenomic scaffolds/contigs being complementary to existing methods of metagenomic data analysis. An offline predictor source code with the best prediction model is available at (https://github.com/Nalinikanta7/metagenomics).

ASLncR: a novel computational tool for prediction of abiotic stress-responsive long non-coding RNAs in plants.

Abiotic stresses are detrimental to plant growth and development and have a major negative impact on crop yields. A growing body of evidence indicates that a large number of long non-coding RNAs (lncRNAs) are key to many abiotic stress responses. Thus, identifying abiotic stress-responsive lncRNAs is essential in crop breeding programs in order to develop crop cultivars resistant to abiotic stresses. In this study, we have developed the first machine learning-based computational model for predicting abiotic stress-responsive lncRNAs. The lncRNA sequences which were responsive and non-responsive to abiotic stresses served as the two classes of the dataset for binary classification using the machine learning algorithms. The training dataset was created using 263 stress-responsive and 263 non-stress-responsive sequences, whereas the independent test set consists of 101 sequences from both classes. As the machine learning model can adopt only the numeric data, the Kmer features ranging from sizes 1 to 6 were utilized to represent lncRNAs in numeric form. To select important features, four different feature selection strategies were utilized. Among the seven learning algorithms, the support vector machine (SVM) achieved the highest cross-validation accuracy with the selected feature sets. The observed 5-fold cross-validation accuracy, AU-ROC, and AU-PRC were found to be 68.84, 72.78, and 75.86%, respectively. Furthermore, the robustness of the developed model (SVM with the selected feature) was evaluated using an independent test dataset, where the overall accuracy, AU-ROC, and AU-PRC were found to be 76.23, 87.71, and 88.49%, respectively. The developed computational approach was also implemented in an online prediction tool ASLncR accessible at https://iasri-sg.icar.gov.in/aslncr/ . The proposed computational model and the developed prediction tool are believed to supplement the existing effort for the identification of abiotic stress-responsive lncRNAs in plants.

ASmiR: a machine learning framework for prediction of abiotic stress-specific miRNAs in plants.

Abiotic stresses have become a major challenge in recent years due to their pervasive nature and shocking impacts on plant growth, development, and quality. MicroRNAs (miRNAs) play a significant role in plant response to different abiotic stresses. Thus, identification of specific abiotic stress-responsive miRNAs holds immense importance in crop breeding programmes to develop cultivars resistant to abiotic stresses. In this study, we developed a machine learning-based computational model for prediction of miRNAs associated with four specific abiotic stresses such as cold, drought, heat and salt. The pseudo K-tuple nucleotide compositional features of Kmer size 1 to 5 were used to represent miRNAs in numeric form. Feature selection strategy was employed to select important features. With the selected feature sets, support vector machine (SVM) achieved the highest cross-validation accuracy in all four abiotic stress conditions. The highest cross-validated prediction accuracies in terms of area under precision-recall curve were found to be 90.15, 90.09, 87.71, and 89.25% for cold, drought, heat and salt respectively. Overall prediction accuracies for the independent dataset were respectively observed 84.57, 80.62, 80.38 and 82.78%, for the abiotic stresses. The SVM was also seen to outperform different deep learning models for prediction of abiotic stress-responsive miRNAs. To implement our method with ease, an online prediction server "ASmiR" has been established at https://iasri-sg.icar.gov.in/asmir/ . The proposed computational model and the developed prediction tool are believed to supplement the existing effort for identification of specific abiotic stress-responsive miRNAs in plants.

Deciphering the mechanism of anhydrobiosis in the entomopathogenic nematode Heterorhabditis indica through comparative transcriptomics.

The entomopathogenic nematode, Heterorhabditis indica, is a popular biocontrol agent of high commercial significance. It possesses tremendous genetic architecture to survive desiccation stress by undergoing anhydrobiosis to increase its lifespan-an attribute exploited in the formulation technology. The comparative transcriptome of unstressed and anhydrobiotic H. indica revealed several previously concealed metabolic events crucial for adapting towards the moisture stress. During the induction of anhydrobiosis in the infective juveniles (IJ), 1584 transcripts were upregulated and 340 downregulated. As a strategy towards anhydrobiotic survival, the IJ showed activation of several genes critical to antioxidant defense, detoxification pathways, signal transduction, unfolded protein response and molecular chaperones and ubiquitin-proteasome system. Differential expression of several genes involved in gluconeogenesis - ß-oxidation of fatty acids, glyoxylate pathway; glyceroneogenesis; fatty acid biosynthesis; amino-acid metabolism - shikimate pathway, sachharopine pathway, kyneurine pathway, lysine biosynthesis; one-carbon metabolism-polyamine pathway, transsulfuration pathway, folate cycle, methionine cycle, nucleotide biosynthesis; mevalonate pathway; and glyceraldehyde-3-phosphate dehydrogenase were also observed. We report the role of shikimate pathway, sachharopine pathway and glyceroneogenesis in anhydrobiotes, and seven classes of repeat proteins, specifically in H. indica for the first time. These results provide insights into anhydrobiotic survival strategies which can be utilized to strengthen the development of novel formulations with enhanced and sustained shelf-life.

A comparative analysis of amino acid encoding schemes for the prediction of flexible length linear B-cell epitopes.

Linear B-cell epitopes have a prominent role in the development of peptide-based vaccines and disease diagnosis. High variability in the length of these epitopes is a major reason for low accuracy in their prediction. Most of the B-cell epitope prediction methods considered fixed length of epitope sequences and achieved good accuracy. Though a number of tools are available for the prediction of flexible length linear B-cell epitopes with reasonable accuracy, further improvement in the prediction performance is still expected. Thus, here we made an attempt to analyze the performance of machine learning approaches (MLA) with 18 different amino acid encoding schemes in the prediction of flexible length linear B-cell epitopes. We considered B-cell epitope sequences of variable lengths (11-56 amino acids) from well-established public resources. The performances of machine learning algorithms with the encoded epitope sequence datasets were evaluated. Besides, the feasible combinations of encoding schemes were also explored and analyzed. The results revealed that amino-acid composition (AC) and distribution component of composition-transition-distribution encoding schemes are suitable for heterogeneous epitope data, whereas amino-acid-anchoring-pair-composition (APC), dipeptide-composition and amino-acids-pair-propensity-scale (APP) are more appropriate for homogeneous data. Further, two combinations of peptide encoding schemes, i.e. APC + AC and APC + APP with random forest classifier were identified to have improved performance over the state-of-the-art tools for flexible length linear B-cell epitope prediction. The study also revealed better performance of random forest over other considered MLAs in the prediction of flexible length linear B-cell epitopes.

Single trait versus principal component based association analysis for flowering related traits in pigeonpea.

Pigeonpea, a tropical photosensitive crop, harbors significant diversity for days to flowering, but little is known about the genes that govern these differences. Our goal in the current study was to use genome wide association strategy to discover the loci that regulate days to flowering in pigeonpea. A single trait as well as a principal component based association study was conducted on a diverse collection of 142 pigeonpea lines for days to first and fifty percent of flowering over 3 years, besides plant height and number of seeds per pod. The analysis used seven association mapping models (GLM, MLM, MLMM, CMLM, EMLM, FarmCPU and SUPER) and further comparison revealed that FarmCPU is more robust in controlling both false positives and negatives as it incorporates multiple markers as covariates to eliminate confounding between testing marker and kinship. Cumulatively, a set of 22 SNPs were found to be associated with either days to first flowering (DOF), days to fifty percent flowering (DFF) or both, of which 15 were unique to trait based, 4 to PC based GWAS while 3 were shared by both. Because PC1 represents DOF, DFF and plant height (PH), four SNPs found associated to PC1 can be inferred as pleiotropic. A window of ± 2 kb of associated SNPs was aligned with available transcriptome data generated for transition from vegetative to reproductive phase in pigeonpea. Annotation analysis of these regions revealed presence of genes which might be involved in floral induction like Cytochrome p450 like Tata box binding protein, Auxin response factors, Pin like genes, F box protein, U box domain protein, chromatin remodelling complex protein, RNA methyltransferase. In summary, it appears that auxin responsive genes could be involved in regulating DOF and DFF as majority of the associated loci contained genes which are component of auxin signaling pathways in their vicinity. Overall, our findings indicates that the use of principal component analysis in GWAS is statistically more robust in terms of identifying genes and FarmCPU is a better choice compared to the other aforementioned models in dealing with both false positive and negative associations and thus can be used for traits with complex inheritance.

Whole-genome sequence analysis of Bipolaris sorokiniana infecting wheat in India and characterization of ToxA gene in different isolates as pathogenicity determinants.

Spot blotch disease of wheat caused by Bipolaris sorokiniana Boerma (Sacc.) is an emerging problem in South Asian countries. Whole genome of a highly virulent isolate of B. sorokiniana BS112 (BHU, Uttar Pradesh; Accession no. GCA_004329375.1) was sequenced using a hybrid assembly approach. Secreted proteins, virulence gene(s), pathogenicity-related gene(s) were identified and the role of ToxA gene present in this genome, in the development of disease was recognized. ToxA gene (535 bp) was analyzed and identified in the genome of B. sorokiniana (BS112) which revealed 100% homology with the ToxA gene of Pyrenophora tritici repentis (Accession no. MH017419). Furthermore, ToxA gene was amplified, sequenced and validated in 39 isolates of B. sorokiniana which confirmed the presence of ToxA gene in all the isolates taken for this study. All ToxA sequences were submitted in NCBI database (MN601358-MN601396). As ToxA gene interacts with Tsn1 gene of host, 13 wheat genotypes were evaluated out of which 5 genotypes (38.4%) were found to be Tsn1 positive with more severe necrotic lesions compared to Tsn1-negative wheat genotypes. In vitro expression analysis of ToxA gene in the pathogen B. sorokiniana using qPCR revealed maximum upregulation (14.67 fold) at 1st day after inoculation (DAI) in the medium. Furthermore, in planta expression analysis of ToxA gene in Tsn1-positive and Tsn1-negative genotypes, revealed maximum expression (7.89-fold) in Tsn1-positive genotype, Agra local at 5th DAI compared to Tsn1-negative genotype Chiriya 7 showing minimum expression (0.048-fold) at 5th DAI. In planta ToxA-Tsn1 interaction studies suggested that spot blotch disease is more severe in Tsn1-positive genotypes, which will be helpful in better understanding and management of spot blotch disease of wheat. Supplementary Information: The online version contains supplementary material available at 10.1007/s13205-022-03213-3.

Evolutionary and functional characterisation of glutathione peroxidases showed splicing mediated stress responses in Maize.

Maize (Zea mays L) is an important cereal with extensive adaptability and multifaceted usages. However, various abiotic and biotic stresses limit the productivity of maize across the globe. Exposure of plant to stresses disturb the balance between reactive oxygen species (ROS) production and scavenging, which subsequently increases cellular damage and death of plants. Tolerant genotypes have evolved higher output of scavenging antioxidative defence compounds (ADCs) during stresses as one of the protective mechanisms. The glutathione peroxidases (GPXs) are the broad class of ADCs family. The plant GPXs catalyse the reduction of hydrogen peroxide (H2O2), lipid hydroperoxides and organic hydroperoxides to the corresponding alcohol, and facilitate the regulation of stress tolerance mechanisms. The present investigation was framed to study the maize GPXs using evolutionary and functional analyses. Seven GPX genes with thirteen splice-variants and sixty-three types of cis-acting elements were identified through whole-genome scanning in maize. Evolutionary analysis of GPXs in monocots and dicots revealed mixed and lineage-specific grouping patterns in phylogeny. The expression of ZmGPX splice variants was studied in drought and waterlogging tolerant (L1621701) and sensitive (PML10) genotypes in root and shoot tissues. Further, the differential expression of splice variants of ZmGPX1, ZmGPX3, ZmGPX6 and ZmGPX7 and regulatory network analysis suggested the splicing and regulatory elements mediated stress responses. The present investigation suggests targeting the splicing machinery of GPXs as an approach to enhance the stress tolerance in maize.

ASRmiRNA: Abiotic Stress-Responsive miRNA Prediction in Plants by Using Machine Learning Algorithms with Pseudo K-Tuple Nucleotide Compositional Features.

MicroRNAs (miRNAs) play a significant role in plant response to different abiotic stresses. Thus, identification of abiotic stress-responsive miRNAs holds immense importance in crop breeding programmes to develop cultivars resistant to abiotic stresses. In this study, we developed a machine learning-based computational method for prediction of miRNAs associated with abiotic stresses. Three types of datasets were used for prediction, i.e., miRNA, Pre-miRNA, and Pre-miRNA + miRNA. The pseudo K-tuple nucleotide compositional features were generated for each sequence to transform the sequence data into numeric feature vectors. Support vector machine (SVM) was employed for prediction. The area under receiver operating characteristics curve (auROC) of 70.21, 69.71, 77.94 and area under precision-recall curve (auPRC) of 69.96, 65.64, 77.32 percentages were obtained for miRNA, Pre-miRNA, and Pre-miRNA + miRNA datasets, respectively. Overall prediction accuracies for the independent test set were 62.33, 64.85, 69.21 percentages, respectively, for the three datasets. The SVM also achieved higher accuracy than other learning methods such as random forest, extreme gradient boosting, and adaptive boosting. To implement our method with ease, an online prediction server "ASRmiRNA" has been developed. The proposed approach is believed to supplement the existing effort for identification of abiotic stress-responsive miRNAs and Pre-miRNAs.

mLoc-mRNA: predicting multiple sub-cellular localization of mRNAs using random forest algorithm coupled with feature selection via elastic net.

BACKGROUND: Localization of messenger RNAs (mRNAs) plays a crucial role in the growth and development of cells. Particularly, it plays a major role in regulating spatio-temporal gene expression. The in situ hybridization is a promising experimental technique used to determine the localization of mRNAs but it is costly and laborious. It is also a known fact that a single mRNA can be present in more than one location, whereas the existing computational tools are capable of predicting only a single location for such mRNAs. Thus, the development of high-end computational tool is required for reliable and timely prediction of multiple subcellular locations of mRNAs. Hence, we develop the present computational model to predict the multiple localizations of mRNAs. RESULTS: The mRNA sequences from 9 different localizations were considered. Each sequence was first transformed to a numeric feature vector of size 5460, based on the k-mer features of sizes 1-6. Out of 5460 k-mer features, 1812 important features were selected by the Elastic Net statistical model. The Random Forest supervised learning algorithm was then employed for predicting the localizations with the selected features. Five-fold cross-validation accuracies of 70.87, 68.32, 68.36, 68.79, 96.46, 73.44, 70.94, 97.42 and 71.77% were obtained for the cytoplasm, cytosol, endoplasmic reticulum, exosome, mitochondrion, nucleus, pseudopodium, posterior and ribosome respectively. With an independent test set, accuracies of 65.33, 73.37, 75.86, 72.99, 94.26, 70.91, 65.53, 93.60 and 73.45% were obtained for the respective localizations. The developed approach also achieved higher accuracies than the existing localization prediction tools. CONCLUSIONS: This study presents a novel computational tool for predicting the multiple localization of mRNAs. Based on the proposed approach, an online prediction server "mLoc-mRNA" is accessible at http://cabgrid.res.in:8080/mlocmrna/ . The developed approach is believed to supplement the existing tools and techniques for the localization prediction of mRNAs.

Computational insights into RNAi-based therapeutics for foot and mouth disease of Bos taurus.

Foot-and-mouth disease (FMD) endangers a large number of livestock populations across the globe being a highly contagious viral infection in wild and domestic cloven-hoofed animals. It adversely affects the socioeconomic status of millions of households. Vaccination has been used to protect animals against FMD virus (FMDV) to some extent but the effectiveness of available vaccines has been decreased due to high genetic variability in the FMDV genome. Another key aspect that the current vaccines are not favored is they do not provide the ability to differentiate between infected and vaccinated animals. Thus, RNA interference (RNAi) being a potential strategy to control virus replication, has opened up a new avenue for controlling the viral transmission. Hence, an attempt has been made here to establish the role of RNAi in therapeutic developments for FMD by computationally identifying (i) microRNA (miRNA) targets in FMDV using target prediction algorithms, (ii) targetable genomic regions in FMDV based on their dissimilarity with the host genome and, (iii) plausible anti-FMDV miRNA-like simulated nucleotide sequences (SNSs). The results revealed 12 mature host miRNAs that have 284 targets in 98 distinct FMDV genomic sequences. Wet-lab validation for anti-FMDV properties of 8 host miRNAs was carried out and all were observed to confer variable magnitude of antiviral effect. In addition, 14 miRBase miRNAs were found with better target accessibility in FMDV than that of Bos taurus. Further, 8 putative targetable regions having sense strand properties of siRNAs were identified on FMDV genes that are highly dissimilar with the host genome. A total of 16 SNSs having > 90% identity with mature miRNAs were also identified that have targets in FMDV genes. The information generated from this study is populated at http://bioinformatics.iasri.res.in/fmdisc/ to cater the needs of biologists, veterinarians and animal scientists working on FMD.

Metagenomic Analysis Reveals Bacterial and Fungal Diversity and Their Bioremediation Potential From Sediments of River Ganga and Yamuna in India.

In this study, we report the presence of a microbial community of bioremediation potential in terms of relative abundance and taxonomic biodiversity in sediment samples of river Ganga and Yamuna, India at nine different sites. Metagenomic libraries were constructed using TruSeq Nano DNA Library Prep Kit and sequenced on NextSeq 500 by Illumina Next Generation Sequencing (NGS) technology. Bioremediation bacteria belong to 45 genera with 92 species and fungi belong to 13 genera with 24 species have been classified using Kaiju taxonomical classification. The study revealed that Proteobacteria was the most dominant bacterial flora, followed by Actinobacteria, Firmicutes, and Deinococcus-Thermus. PCA analysis revealed that bioremediation bacteria viz. Streptomyces bikiniensis, Rhodococcus qingshengii, Bacillus aerophilus, Pseudomonas veronii, etc., were more dominant in highly polluted river stretch as compared to less polluted river stretch. Similarly, the relative abundance of bioremediation fungi viz. Phanerochaete chrysosporium and Rhizopus oryzae, etc., were significantly correlated with the polluted Kanpur stretch of river Ganga. Several protein domains, which play a pivotal role in bioremediation in the polluted environments, including urea ABC transporter, UrtA, UrtD, UrtE, zinc/cadmium/mercury/lead-transporting ATPase, etc., were identified using protein domain analysis. The protein domains involved in pesticide biodegradation viz. P450, short-chain dehydrogenases/reductases (SDR), etc., were also discovered in river sediment metagenomics data. This is the first report on the richness of bioremediation microbial communities in the Ganga and Yamuna riverine ecosystems, highlighting their importance in aquatic pollution management.

Metagenome analysis from the sediment of river Ganga and Yamuna: In search of beneficial microbiome.

Beneficial microbes are all around us and it remains to be seen, whether all diseases and disorders can be prevented or treated with beneficial microbes. In this study, the presence of various beneficial bacteria were identified from the sediments of Indian major Rivers Ganga and Yamuna from nine different sites using a metagenomic approach. The metagenome sequence analysis using the Kaiju Web server revealed the presence of 69 beneficial bacteria. Phylogenetic analysis among these bacterial species revealed that they were highly diverse. Relative abundance analysis of these bacterial species is highly correlated with different pollution levels among the sampling sites. The PCA analysis revealed that Lactobacillus spp. group of beneficial bacteria are more associated with sediment sampling sites, KAN-2 and ND-3; whereas Bacillus spp. are more associated with sites, FAR-2 and ND-2. This is the first report revealing the richness of beneficial bacteria in the Indian rivers, Ganga and Yamuna. The study might be useful in isolating different important beneficial microorganisms from these river sediments, for possible industrial applications.

Inferring Relationship of Blood Metabolic Changes and Average Daily Gain With Feed Conversion Efficiency in Murrah Heifers: Machine Learning Approach.

Machine learning algorithms were employed for predicting the feed conversion efficiency (FCE), using the blood parameters and average daily gain (ADG) as predictor variables in buffalo heifers. It was observed that isotonic regression outperformed other machine learning algorithms used in study. Further, we also achieved the best performance evaluation metrics model with additive regression as the meta learner and isotonic regression as the base learner on 10-fold cross-validation and leaving-one-out cross-validation tests. Further, we created three separate partial least square regression (PLSR) models using all 14 parameters of blood and ADG as independent (explanatory) variables and FCE as the dependent variable, to understand the interactions of blood parameters, ADG with FCE each by inclusion of all FCE values (i), only higher FCE values (negative RFI) (ii), and inclusion of only lower FCE (positive RFI) values (iii). The PLSR model including only the higher FCE values was concluded the best, based on performance evaluation metrics as compared to PLSR models developed by inclusion of the lower FCE values and all types of FCE values. IGF1 and its interactions with the other blood parameters were found highly influential for higher FCE measures. The strength of the estimated interaction effects of the blood parameter in relation to FCE may facilitate understanding of intricate dynamics of blood parameters for growth.

miRNALoc: predicting miRNA subcellular localizations based on principal component scores of physico-chemical properties and pseudo compositions of di-nucleotides.

MicroRNAs (miRNAs) are one kind of non-coding RNA, play vital role in regulating several physiological and developmental processes. Subcellular localization of miRNAs and their abundance in the native cell are central for maintaining physiological homeostasis. Besides, RNA silencing activity of miRNAs is also influenced by their localization and stability. Thus, development of computational method for subcellular localization prediction of miRNAs is desired. In this work, we have proposed a computational method for predicting subcellular localizations of miRNAs based on principal component scores of thermodynamic, structural properties and pseudo compositions of di-nucleotides. Prediction accuracy was analyzed following fivefold cross validation, where ~ 63-71% of AUC-ROC and ~ 69-76% of AUC-PR were observed. While evaluated with independent test set, > 50% localizations were found to be correctly predicted. Besides, the developed computational model achieved higher accuracy than the existing methods. A user-friendly prediction server "miRNALoc" is freely accessible at https://cabgrid.res.in:8080/mirnaloc/ , by which the user can predict localizations of miRNAs.

SpikeSegNet-a deep learning approach utilizing encoder-decoder network with hourglass for spike segmentation and counting in wheat plant from visual imaging.

BACKGROUND: High throughput non-destructive phenotyping is emerging as a significant approach for phenotyping germplasm and breeding populations for the identification of superior donors, elite lines, and QTLs. Detection and counting of spikes, the grain bearing organs of wheat, is critical for phenomics of a large set of germplasm and breeding lines in controlled and field conditions. It is also required for precision agriculture where the application of nitrogen, water, and other inputs at this critical stage is necessary. Further, counting of spikes is an important measure to determine yield. Digital image analysis and machine learning techniques play an essential role in non-destructive plant phenotyping analysis. RESULTS: In this study, an approach based on computer vision, particularly object detection, to recognize and count the number of spikes of the wheat plant from the digital images is proposed. For spike identification, a novel deep-learning network, SpikeSegNet, has been developed by combining two proposed feature networks: Local Patch extraction Network (LPNet) and Global Mask refinement Network (GMRNet). In LPNet, the contextual and spatial features are learned at the local patch level. The output of LPNet is a segmented mask image, which is further refined at the global level using GMRNet. Visual (RGB) images of 200 wheat plants were captured using LemnaTec imaging system installed at Nanaji Deshmukh Plant Phenomics Centre, ICAR-IARI, New Delhi. The precision, accuracy, and robustness (F1 score) of the proposed approach for spike segmentation are found to be 99.93%, 99.91%, and 99.91%, respectively. For counting the number of spikes, "analyse particles"-function of imageJ was applied on the output image of the proposed SpikeSegNet model. For spike counting, the average precision, accuracy, and robustness are 99%, 95%, and 97%, respectively. SpikeSegNet approach is tested for robustness with illuminated image dataset, and no significant difference is observed in the segmentation performance. CONCLUSION: In this study, a new approach called as SpikeSegNet has been proposed based on combined digital image analysis and deep learning techniques. A dedicated deep learning approach has been developed to identify and count spikes in the wheat plants. The performance of the approach demonstrates that SpikeSegNet is an effective and robust approach for spike detection and counting. As detection and counting of wheat spikes are closely related to the crop yield, and the proposed approach is also non-destructive, it is a significant step forward in the area of non-destructive and high-throughput phenotyping of wheat.

Evaluating the performance of sequence encoding schemes and machine learning methods for splice sites recognition.

Identification of splice sites is imperative for prediction of gene structure. Machine learning-based approaches (MLAs) have been reported to be more successful than the rule-based methods for identification of splice sites. However, the strings of alphabets should be transformed into numeric features through sequence encoding before using them as input in MLAs. In this study, we evaluated the performances of 8 different sequence encoding schemes i.e., Bayes kernel, density and sparse (DS), distribution of tri-nucleotide and 1st order Markov model (DM), frequency difference distance measure (FDDM), paired-nucleotide frequency difference between true and false sites (FDTF), 1st order Markov model (MM1), combination of both 1st and 2nd order Markov model (MM1 + MM2) and 2nd order Markov model (MM2) in respect of predicting donor and acceptor splice sites using 5 supervised learning methods (ANN, Bagging, Boosting, RF and SVM). The encoding schemes and machine learning methods were first evaluated in 4 species i.e., A. thaliana, C. elegans, D. melanogaster and H. sapiens, and then performances were validated with another four species i.e., Ciona intestinalis, Dictyostelium discoideum, Phaeodactylum tricornutum and Trypanosoma brucei. In terms of ROC (receiver-operating-characteristics) and PR (precision-recall) curves, FDTF encoding approach achieved higher accuracy followed by either MM2 or FDDM. Further, SVM was found to achieve higher accuracy (in terms of ROC and PR curves) followed by RF across encoding schemes and species. In terms of prediction accuracy across species, the SVM-FDTF combination was optimum than other combinations of classifiers and encoding schemes. Further, splice site prediction accuracies were observed higher for the species with low intron density. To our limited knowledge, this is the first attempt as far as comprehensive evaluation of sequence encoding schemes for prediction of splice sites is concerned. We have also developed an R-package EncDNA (https://cran.r-project.org/web/packages/EncDNA/index.html) for encoding of splice site motifs with different encoding schemes, which is expected to supplement the existing nucleotide sequence encoding approaches. This study is believed to be useful for the computational biologists for predicting different functional elements on the genomic DNA.