Table 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Identifying genes with essential roles in resisting environmental stress rates high in agronomic importance. Although massive DNA microarray gene expression data have been generated for plants, current computational approaches underutilize these data for studying genotype-trait relationships. Some advanced gene identification methods have been expl...
Similar publications
With the advent of modern imaging and measurement technology, complex phenotypes are increasingly represented by large numbers of measurements, which may not bear biological meaning one by one. For such multivariate phenotypes, studying the pairwise associations between all measurements and all alleles is highly inefficient and prevents insight into...
Citations
... Machine learning (ML) algorithms play a pivotal role in identifying stress resistance genes, aiding breeders and researchers in enhancing crop production. Liang et al. (2011) utilized a variant of the Support Vector Machine (SVM) algorithm to identify key genes associated with drought resistance in A. thaliana. Shikha et al. (2017) demonstrated the superior performance of Bayes algorithms, identifying critical SNPs for drought resistance in maize. ...
Plants intricately deploy defense systems to counter diverse biotic and abiotic stresses. Omics technologies, spanning genomics, transcriptomics, proteomics, and metabolomics, have revolutionized the exploration of plant defense mechanisms, unraveling molecular intricacies in response to various stressors. However, the complexity and scale of omics data necessitate sophisticated analytical tools for meaningful insights. This review delves into the application of artificial intelligence algorithms, particularly machine learning and deep learning, as promising approaches for deciphering complex omics data in plant defense research. The overview encompasses key omics techniques and addresses the challenges and limitations inherent in current AI-assisted omics approaches. Moreover, it contemplates potential future directions in this dynamic field. In summary, AI-assisted omics techniques present a robust toolkit, enabling a profound understanding of the molecular foundations of plant defense and paving the way for more effective crop protection strategies amidst climate change and emerging diseases.
... These algorithms use various evaluation criteria for classifying data and scoring the input features. In the area of plant stress, the effective use of machine learning and feature selection models for selecting gene features is reported in rice 21 , Arabidopsis 22 , potato 23 , and maize 24 . However, at the transcriptome level, the machine learning algorithms for identifying key signatures related to environmental stress have not been applied in Populus. ...
In Populus , drought is a major problem affecting plant growth and development which can be closely reflected by corresponding transcriptomic changes. Nevertheless, how these changes in Populus are not fully understood. Here, we first used meta-analysis and machine learning methods to identify water stress-responsive genes and then performed a systematic approach to discover important gene networks. Our analysis revealed that large transcriptional variations occur during drought stress. These changes were more associated with the response to stress, cellular catabolic process, metabolic pathways, and hormone-related genes. The differential gene coexpression analysis highlighted two acetyltransferase NATA1 -like and putative cytochrome P450 genes that have a special contribution in response to drought stress. In particular, the findings showed that MYBs and MAPKs have a prominent role in the drought stress response that could be considered to improve the drought tolerance of Populus . We also suggest ARF2 -like and PYL4 -like genes as potential markers for use in breeding programs. This study provides a better understanding of how Populus responses to drought that could be useful for improving tolerance to stress in Populus .
... We then opted for feature selection (i.e., filtering for the genes that best predict the phenotype) as an embedded method in the SVM iterations, because it is fast, better performing than univariate filter techniques (Saeys et al. 2007), and widely used in detection of loci associated with cancer (Abeel et al. 2010), plant drought-resistance (Liang et al. 2011), honey bee waggle dance (Veiner et al. 2022). We performed a leave-one-species-out iterative process, in which one species was chosen as the test dataset and the remaining five were used as the training set. ...
The evolution of eusociality requires that individuals forgo some or all their own reproduction to assist the reproduction of others in their group, such as a primary egg-laying queen. A major open question is how genes and genetic pathways sculpt the evolution of eusociality, especially in rudimentary forms of sociality – those with smaller cooperative nests as compared with species such as honeybees that possess large societies. We lack comprehensive comparative studies examining shared patterns and processes across multiple social lineages. Here we examine the mechanisms of molecular convergence across two lineages of bees and wasps exhibiting such rudimentary societies. These societies consist of few individuals and their life histories range from facultative to obligately social. Using six species across four independent origins of sociality, we conduct a comparative meta-analysis of publicly available transcriptomes. Standard methods detected little similarity in patterns of differential gene expression in brain transcriptomes among reproductive and non-reproductive individuals across species. By contrast, both supervised machine learning and consensus co-expression network approaches uncovered sets of genes with conserved expression patterns among reproductive and non-reproductive phenotypes across species. These sets overlap substantially, and may comprise a shared genetic “toolkit” for sociality across the distantly related taxa of bees and wasps and independently evolved lineages of sociality. We also found many lineage-specific genes and co-expression modules associated with social phenotypes and possible signatures of shared life-history traits. These results reveal how taxon-specific molecular mechanisms complement a core toolkit of molecular processes in sculpting traits related to the evolution of eusociality.
... In this regard, volcano plot method (Cui and Churchill 2003) is quite popular among the researchers in which genes are selected by considering their relevance with their classes. However, such method may not be sufficient to discover some complex relationships among genes for a certain trait or condition (Liang et al. 2011). Besides, several statistical and machine learning methods, viz., t-score, F-score, information gain (IG) measure, random forest (RF), and support vector machine-recursive feature elimination (SVM-RFE) (Mao et al. 2006;Forman 2003;Díaz-Uriarte and de Andrés 2006;Lai et al. 2011;Guoyon and Elisseeff 2003), have also been used for gene selection. ...
Currently, soybean (Glycine max (L.) Merrill), a Leguminosae family member, has become one of the main economical oilseed beans. It is being cultivated nowadays in all major areas of the world including China, Japan, Brazil, the USA, and Korea as well as in many South and Midwest countries for several uses. The reason lies in the introduction of multiple local varieties, efficient seed supply, and timely technology transfer, participation of the public sector as well as large international capital groups, and large-scale introduction of new soy foods. It is primarily being cultivated as a substitute for high-protein meat and a source of vegetable oil. Furthermore, the availability of many bioactive compounds has also increased the interest of various researchers toward this bean which originated from northeast China. As a result, it has emerged somewhere as one of the nutritious cum economical parts of the vegan diet. Due to its nutritive value, this “yellow meat of the field” is touted by many as a potential weapon against global hunger. Next to diet, soybean and related greater market value products are being employed either directly or as an ingredient in making cheese, spreads, paints, fertilizers, adhesives, fire extinguisher fluids, animal feed, etc. Due to all these applications, soybean was cultivated on nearly 125 million hectares of the area resulting in 348.7 million tons of harvest in the year 2018. This quantity of production is projected to increase in the near future with a parallel surge in purchasing demand of the every second increasing population. However, there are still many “yield limiters” that uneven the soybean production at both pilot and global scales by nearly 50%. In order to tackle all these soybean yield limiters in a highly efficient manner, various techniques including cross hybridization, molecular marker-assisted breeding, transgenic breeding, tilling, microbiome engineering, and genome editing are being employed by various research groups. Therefore, in the present chapter, the focus is solely on how with time the soybean has proved its strong candidature as a key player for global food security. Furthermore, the production trends at the world and Indian scale are also highlighted. Additionally, the present chapter is an attempt to provide a streamlined overview of all these soybean yield limiters and employed technologies, in brief, to pave the way for the readers for other chapters in the book.KeywordsSoybeanChinaNutritionYieldYield limiters
... There is, therefore, a need to prioritize the development of drought-tolerant varieties of G. gynandra. Since information on the genetic control of drought is not available in G. gynandra, Sogbohossou et al. (2018) suggested the use of information from well-studied sister species, such as A. thaliana (Bouchabke et al., 2008;Liang et al., 2011) and Brassica spp. (Wu et al., 2012;Zhang et al., 2014) to facilitate the genetic characterization for drought. ...
Spider plant ( Gynandropsis gynandra (L.) Briq .) is among the most important African Leafy Vegetables (ALVs) as a source of essential nutrients with the potential of contributing significantly to household food and nutritional security and mitigation of hidden hunger. Nevertheless, the vegetable is considered an orphan crop and its production is challenged by inadequate research to identify and improve traits preferred by smallholder farmers. The research was conducted to identify the main challenges impacting the production of spider plants and identify traits preferred by smallholder farmers in northern Namibia and central Malawi for use in demand-led crop improvement. Semi-structured interviews involving a random selection of 197 farming households from five regions of northern Namibia and three districts of central Malawi were conducted. In addition, six key informant interviews and four focus group discussions were conducted to triangulate the findings. Data were analyzed using IBM SPSS version 20. Fischer's exact test was used to test for independence in the ranking of production constraints and agronomic traits, while Kendall's Coefficient of Concordance (W) was used to measure agreement levels in the ranking across the countries. Farmers indicated lack of seed, poor soil fertility, poor seed germination and drought as the main production challenges across the two countries. Production constraints were ranked differently ( p < 0.001) across the study sites suggesting the influence of biophysical and socio-economic factors associated with production. High yield and drought tolerance were considered the most important agronomic traits among the smallholder farmers in both countries. The findings of this study are useful for designing demand-driven pre-breeding trials that prioritize the needs of the end-users. Demand-led breeding has the potential to stimulate the production and utilization of spider plant, hence contributing to household food and nutritional security.
... With the open access to the massive gene expression data and bioinformatic tool for predicting key genes involved in water stress genes were confirmed to related to known biological processes involved in imparting resistance to drought (Liang et al. 2011). A number of genes (about 500) were identified to be linked to the stress response and the ABA response (Liang et al. 2011). ...
... With the open access to the massive gene expression data and bioinformatic tool for predicting key genes involved in water stress genes were confirmed to related to known biological processes involved in imparting resistance to drought (Liang et al. 2011). A number of genes (about 500) were identified to be linked to the stress response and the ABA response (Liang et al. 2011). In another attempt, overexpression of an ethylene-responsive factor (ERF) from B. rapa (BrERF4) increased Arabidopsis resistance to salt and drought stresses. ...
Castor, Ricinus communis, is one of the top ten oil crops in the world. It has been paid more and more attention because of its high economic value. In the process of growth and development, it is subjected to a variety of abiotic stresses from the environment. In this chapter, the stresses on castor are discussed in consideration of heat tolerances, cold tolerance, drought tolerance, flooding and submergence tolerance, nutrient use efficiency, water use efficiency, salt-alkali stress and metal ion toxicity. It is suggested that more attention should be paid to the physiological adaptation mechanisms of castor to these stresses.
... With the open access to the massive gene expression data and bioinformatic tool for predicting key genes involved in water stress genes were confirmed to related to known biological processes involved in imparting resistance to drought (Liang et al. 2011). A number of genes (about 500) were identified to be linked to the stress response and the ABA response (Liang et al. 2011). ...
... With the open access to the massive gene expression data and bioinformatic tool for predicting key genes involved in water stress genes were confirmed to related to known biological processes involved in imparting resistance to drought (Liang et al. 2011). A number of genes (about 500) were identified to be linked to the stress response and the ABA response (Liang et al. 2011). In another attempt, overexpression of an ethylene-responsive factor (ERF) from B. rapa (BrERF4) increased Arabidopsis resistance to salt and drought stresses. ...
Brassica species were domesticated as oil producing crops during different periods at many sites throughout the world. Animal fat being pricier, the poor used vegetable oil as a source of their nutrition. Accordingly, world production of vegetable oil has been incremental chiefly due to increased production of soybean, palm and oilseed rape. Rapeseed (Brassica napus L.), also known as Canola or Oilseed rape, has thus become an important source of vegetable oil worldwide, and ranks third after soybean and palm. The world population is expected to cross the 9 billion mark by 2050, and to assure food and nutritional security for our soaring future generations, we need to necessarily double the production of food crops by then. However, various environmental stresses negate the realization of this target. Rapeseed thrives very well in countries of the northern hemisphere of the planet having cool and humid climates, making it a very important oil- and protein-crop, since no other crop can produce such high yields of both oil and protein under these climatic conditions. In the coming decades, it has the potential of achieving the rank numero uno as the cheapest source of nutritious vegetable oil for the impoverished of the world. Nevertheless, it is prone to various abiotic stresses which not only affect normal growth rate of the plant but also decrease crop productivity by alarming proportions. It is, therefore, imperative to develop new stress tolerant varieties having higher productivity and better adaptation to the abiotic stresses abounding because of climate change. This chapter summarizes the various abiotic stresses afflicting rapeseed; the classical, genetic and molecular approaches that have been employed for breeding for abiotic stress tolerance, together with biotechnological and synthetic biology research breakthroughs aimed at creating abiotic stress-resistant climate-resilient varieties. The combination of classical and molecular breeding, being assisted by integrated omics and genome editing breakthroughs, can lead to speed up breeding of the crop and alter the rate of production of rapeseed worldwide, making it feasible to achieve the target of being number one in meeting the demands for vegetable oil of a soaring population.Keywords
Brassica napus
Oilseed rapeRapeseedCanolaAbiotic stressTemperature stressDrought stressSalt stress
... With the open access to the massive gene expression data and bioinformatic tool for predicting key genes involved in water stress genes were confirmed to related to known biological processes involved in imparting resistance to drought (Liang et al. 2011). A number of genes (about 500) were identified to be linked to the stress response and the ABA response (Liang et al. 2011). ...
... With the open access to the massive gene expression data and bioinformatic tool for predicting key genes involved in water stress genes were confirmed to related to known biological processes involved in imparting resistance to drought (Liang et al. 2011). A number of genes (about 500) were identified to be linked to the stress response and the ABA response (Liang et al. 2011). In another attempt, overexpression of an ethylene-responsive factor (ERF) from B. rapa (BrERF4) increased Arabidopsis resistance to salt and drought stresses. ...
... As to wrapper methods, varying classification algorithms are often used as a fitness evaluation to determine the subset of genes and the selected genes can in turn enhance the classification performance [2,[49][50][51][52][53][54][55][56]. In general, wrapper methods can obtain better results than filter methods, but bring more expensive computational cost. ...
The microarray cancer data obtained by DNA microarray technology play an important role for cancer prevention, diagnosis, and treatment. However, predicting the different types of tumors is a challenging task since the sample size in microarray data is often small but the dimensionality is very high. Gene selection, which is an effective means, is aimed at mitigating the curse of dimensionality problem and can boost the classification accuracy of microarray data. However, many of previous gene selection methods focus on model design, but neglect the correlation between different genes. In this paper, we introduce a novel unsupervised gene selection method by taking the gene correlation into consideration, named gene correlation guided gene selection (G3CS). Specifically, we calculate the covariance of different gene dimension pairs and embed it into our unsupervised gene selection model to regularize the gene selection coefficient matrix. In such a manner, redundant genes can be effectively excluded. In addition, we utilize a matrix factorization term to exploit the cluster structure of original microarray data to assist the learning process. We design an iterative updating algorithm with convergence guarantee to solve the resultant optimization problem. Experimental results on six publicly available microarray datasets are conducted to validate the efficacy of our proposed method.
... Liang et al. developed a Support Vector Machine-Recursive Feature Elimination (SVM-RFE) feature selection method to compute the ranking of the features based on their importance to accuracy by training SVM, and then recursively removed the feature with the lowest ranking [4]. In another study [5], Zhang et al. present a two-stage selection method by combing ReliefF and minimal-redundancymaximal-relevance (mRMR). ...
The advancement of Omics technology has led to a surge in molecular and cell profiling data for mechanism study. Large amount of data and complex data structure pose a great challenge to data analysis. Modern machine learning methods such as deep learning are expected to take advantage such big data for accurate disease prediction or other related tasks. However, large feature number may bring large amount redundant information and adversely affect the accuracy of a classifier. To this end, feature selection methods can remove redundant information and help the model achieve higher accuracy by selecting informative features. In this paper, we propose a two-step deep learning-based method combining stacked denoising autoencoders (SDAE) with SVM-RFE to accomplish the task of feature selection. We compared our method with other related methods and the results showed that our approach achieved a better performance than other methods when using the TCGA datasets.
