Optimizing Computer-Aided Diagnosis with Cost-Aware Deep Learning Models.

Classical machine learning and deep learning models for Computer-Aided Diagnosis (CAD) commonly focus on overall classification performance, treating misclassification errors (false negatives and false positives) equally during training. This uniform treatment overlooks the distinct costs associated with each type of error, leading to suboptimal decision-making, particularly in the medical domain where it is important to improve the prediction sensitivity without significantly compromising overall accuracy. This study introduces a novel deep learning-based CAD system that incorporates a cost-sensitive parameter into the activation function. By applying our methodologies to two medical imaging datasets, our proposed study shows statistically significant increases of 3.84% and 5.4% in sensitivity while maintaining overall accuracy for Lung Image Database Consortium (LIDC) and Breast Cancer Histological Database (BreakHis), respectively. Our findings underscore the significance of integrating cost-sensitive parameters into future CAD systems to optimize performance and ultimately reduce costs and improve patient outcomes.

The Gossypium herbaceum L. Wagad genome as a resource for understanding cotton domestication.

Gossypium herbaceum is a species of cotton native to Africa and Asia that is one of the 2 domesticated diploids. Together with its sister-species G. arboreum, these A-genome taxa represent models of the extinct A-genome donor of modern polyploid cotton, which provide about 95% of cotton grown worldwide. As part of a larger effort to characterize variation and improve resources among diverse diploid and polyploid cotton genomes, we sequenced and assembled the genome of G. herbaceum cultivar (cv.) Wagad, representing the first domesticated accession for this species. This chromosome-level genome was generated using a combination of PacBio long-read technology, HiC, and Bionano optical mapping and compared to existing genome sequences in cotton. We compare the genome of this cultivar to the existing genome of wild G. herbaceum subspecies africanum to elucidate changes in the G. herbaceum genome concomitant with domestication and extend these analyses to gene expression using available RNA-seq. Our results demonstrate the utility of the G. herbaceum cv. Wagad genome in understanding domestication in the diploid species, which could inform modern breeding programs.

Dual Domestication, Diversity, and Differential Introgression in Old World Cotton Diploids.

Domestication in the cotton genus is remarkable in that it has occurred independently four different times at two different ploidy levels. Relatively little is known about genome evolution and domestication in the cultivated diploid species Gossypium herbaceum and Gossypium arboreum, due to the absence of wild representatives for the latter species, their ancient domestication, and their joint history of human-mediated dispersal and interspecific gene flow. Using in-depth resequencing of a broad sampling from both species, we provide support for their independent domestication, as opposed to a progenitor-derivative relationship, showing that diversity (mean π = 6 × 10-3) within species is similar, and that divergence between species is modest (FST = 0.413). Individual accessions were homozygous for ancestral single-nucleotide polymorphisms at over half of variable sites, while fixed, derived sites were at modest frequencies. Notably, two chromosomes with a paucity of fixed, derived sites (i.e., chromosomes 7 and 10) were also strongly implicated as having experienced high levels of introgression. Collectively, these data demonstrate variable permeability to introgression among chromosomes, which we propose is due to divergent selection under domestication and/or the phenomenon of F2 breakdown in interspecific crosses. Our analyses provide insight into the evolutionary forces that shape diversity and divergence in the diploid cultivated species and establish a foundation for understanding the contribution of introgression and/or strong parallel selection to the extensive morphological similarities shared between species.

Three Strains of Tobacco etch virus Distinctly Alter the Transcriptome of Apical Stem Tissue in Capsicum annuum during Infection.

Tobacco etch virus (TEV; genus Potyvirus) is flexuous rod shaped with a single molecule of single-stranded RNA and causes serious yield losses in species in the Solanaceae. Three TEV strains (HAT, Mex21, and N) are genetically distinct and cause different disease symptoms in plants. Here, a transcriptomic RNA sequencing approach was taken for each TEV strain to evaluate gene expression of the apical stem segment of pepper plants during two stages of disease development. Distinct profiles of Differentially Expressed Genes (DEGs) were identified for each TEV strain. DEG numbers increased with degree of symptom severity: 24 from HAT, 1190 from Mex21, and 4010 from N. At 7 days post-inoculation (dpi), when systemic symptoms were similar, there were few DEGs for HAT- and Mex21-infected plants, whereas N-infected plants had 2516 DEGs. DEG patterns from 7 to 14 dpi corresponded to severity of disease symptoms: milder disease with smaller DEG changes for HAT and Mex21 and severe disease with larger DEG changes for N. Strikingly, in each of these comparisons, there are very few overlapping DEGs among the TEV strains, including no overlapping DEGs between all three strains at 7 or 14 dpi.

Transcriptional changes and preservation of bone mass in hibernating black bears.

Physical inactivity leads to losses of bone mass and strength in most mammalian species. In contrast, hibernating bears show no bone loss over the prolonged periods (4-6 months) of immobility during winter, which suggests that they have adaptive mechanisms to preserve bone mass. To identify transcriptional changes that underlie molecular mechanisms preventing disuse osteoporosis, we conducted a large-scale gene expression screening in the trabecular bone and bone marrow, comparing hibernating and summer active bears through sequencing of the transcriptome. Gene set enrichment analysis showed a coordinated down-regulation of genes involved in bone resorption, osteoclast differentiation and signaling, and apoptosis during hibernation. These findings are consistent with previous histological findings and likely contribute to the preservation of bone during the immobility of hibernation. In contrast, no significant enrichment indicating directional changes in gene expression was detected in the gene sets of bone formation and osteoblast signaling in hibernating bears. Additionally, we revealed significant and coordinated transcriptional induction of gene sets involved in aerobic energy production including fatty acid beta oxidation, tricarboxylic acid cycle, oxidative phosphorylation, and mitochondrial metabolism. Mitochondrial oxidation was likely up-regulated by transcriptionally induced AMPK/PGC1α pathway, an upstream stimulator of mitochondrial function.

Corrigendum: Novel Meiotic miRNAs and Indications for a Role of PhasiRNAs in Meiosis.

[This corrects the article DOI: 10.3389/fpls.2016.00762.].

The Genome Sequence of Gossypioides kirkii Illustrates a Descending Dysploidy in Plants.

One of the extraordinary aspects of plant genome evolution is variation in chromosome number, particularly that among closely related species. This is exemplified by the cotton genus (Gossypium) and its relatives, where most species and genera have a base chromosome number of 13. The two exceptions are sister genera that have n = 12 (the Hawaiian Kokia and the East African and Madagascan Gossypioides). We generated a high-quality genome sequence of Gossypioides kirkii (n = 12) using PacBio, Bionano, and Hi-C technologies, and compared this assembly to genome sequences of Kokia (n = 12) and Gossypium diploids (n = 13). Previous analysis demonstrated that the directionality of their reduced chromosome number was through large structural rearrangements. A series of structural rearrangements were identified comparing the de novo G. kirkii genome sequence to genome sequences of Gossypium, including chromosome fusions and inversions. Genome comparison between G. kirkii and Gossypium suggests that multiple steps are required to generate the extant structural differences.

Janthinobacterium CG23_2: Comparative Genome Analysis Reveals Enhanced Environmental Sensing and Transcriptional Regulation for Adaptation to Life in an Antarctic Supraglacial Stream.

As many bacteria detected in Antarctic environments are neither true psychrophiles nor endemic species, their proliferation in spite of environmental extremes gives rise to genome adaptations. Janthinobacterium sp. CG23_2 is a bacterial isolate from the Cotton Glacier stream, Antarctica. To understand how Janthinobacterium sp. CG23_2 has adapted to its environment, we investigated its genomic traits in comparison to genomes of 35 published Janthinobacterium species. While we hypothesized that genome shrinkage and specialization to narrow ecological niches would be energetically favorable for dwelling in an ephemeral Antarctic stream, the genome of Janthinobacterium sp. CG23_2 was on average 1.7 ± 0.6 Mb larger and predicted 1411 ± 499 more coding sequences compared to the other Janthinobacterium spp. Putatively identified horizontal gene transfer events contributed 0.92 Mb to the genome size expansion of Janthinobacterium sp. CG23_2. Genes with high copy numbers in the species-specific accessory genome of Janthinobacterium sp. CG23_2 were associated with environmental sensing, locomotion, response and transcriptional regulation, stress response, and mobile elements-functional categories which also showed molecular adaptation to cold. Our data suggest that genome plasticity and the abundant complementary genes for sensing and responding to the extracellular environment supported the adaptation of Janthinobacterium sp. CG23_2 to this extreme environment.

De Novo Genome Sequence Assemblies of Gossypium raimondii and Gossypium turneri.

Cotton is an agriculturally important crop. Because of its importance, a genome sequence of a diploid cotton species (Gossypium raimondii, D-genome) was first assembled using Sanger sequencing data in 2012. Improvements to DNA sequencing technology have improved accuracy and correctness of assembled genome sequences. Here we report a new de novo genome assembly of G. raimondii and its close relative G. turneri The two genomes were assembled to a chromosome level using PacBio long-read technology, HiC, and Bionano optical mapping. This report corrects some minor assembly errors found in the Sanger assembly of G. raimondii We also compare the genome sequences of these two species for gene composition, repetitive element composition, and collinearity. Most of the identified structural rearrangements between these two species are due to intra-chromosomal inversions. More inversions were found in the G. turneri genome sequence than the G. raimondii genome sequence. These findings and updates to the D-genome sequence will improve accuracy and translation of genomics to cotton breeding and genetics.

Exploring Frequented Regions in Pan-Genomic Graphs.

We consider the problem of identifying regions within a pan-genome De Bruijn graph that are traversed by many sequence paths. We define such regions and the subpaths that traverse them as frequented regions (FRs). In this work, we formalize the FR problem and describe an efficient algorithm for finding FRs. Subsequently, we propose some applications of FRs based on machine-learning and pan-genome graph simplification. We demonstrate the effectiveness of these applications using data sets for the organisms Staphylococcus aureus (bacterium) and Saccharomyces cerevisiae (yeast). We corroborate the biological relevance of FRs such as identifying introgressions in yeast that aid in alcohol tolerance, and show that FRs are useful for classification of yeast strains by industrial use and visualizing pan-genomic space.

Genome and evolution of the arbuscular mycorrhizal fungus Diversispora epigaea (formerly Glomus versiforme) and its bacterial endosymbionts.

Arbuscular mycorrhizal (AM) fungi form endosymbioses with most plants, and they themselves are hosts for Mollicutes/Mycoplasma-related endobacteria (MRE). Despite their significance, genomic information for AM fungi and their MRE are relatively sparse, which hinders our understanding of their biology and evolution. We assembled the genomes of the AM fungus Diversispora epigaea (formerly Glomus versiforme) and its MRE and performed comparative genomics and evolutionary analyses. The D. epigaea genome showed a pattern of substantial gene duplication and differential evolution of gene families, including glycosyltransferase family 25, whose activities are exclusively lipopolysaccharide biosynthesis. Genes acquired by horizontal transfer from bacteria possibly function in defense against foreign DNA or viruses. The MRE population was diverse, with multiple genomes displaying characteristics of differential evolution and encoding many MRE-specific genes as well as genes of AM fungal origin. Gene family expansion in D. epigaea may enhance adaptation to both external and internal environments, such as expansion of kinases for signal transduction upon external stimuli and expansion of nucleoside salvage pathway genes potentially for competition with MRE, whose genomes lack purine and pyrimidine biosynthetic pathways. Collectively, this metagenome provides high-quality references and begins to reveal the diversity within AM fungi and their MRE.

Cranberry-derived proanthocyanidins induce a differential transcriptomic response within Candida albicans urinary biofilms.

Candida albicans is one of the most common causes of hospital-acquired urinary tract infections (UTIs). However, azoles are poorly active against biofilms, echinocandins do not achieve clinically useful urinary concentrations, and amphotericin B exhibits severe toxicities. Thus, novel strategies are needed to prevent Candida UTIs, which are often associated with urinary catheter biofilms. We previously demonstrated that cranberry-derived proanthocyanidins (PACs) prevent C. albicans biofilm formation in an in vitro urinary model. To elucidate functional pathways unique to urinary biofilm development and PAC inhibition, we investigated the transcriptome of C. albicans in artificial urine (AU), with and without PACs. C. albicans biofilm and planktonic cells were cultivated with or without PACs. Genome-wide expression analysis was performed by RNA sequencing. Differentially expressed genes were determined using DESeq2 software; pathway analysis was performed using Cytoscape. Approximately 2,341 of 6,444 total genes were significantly expressed in biofilm relative to planktonic cells. Functional pathway analysis revealed that genes involved in filamentation, adhesion, drug response and transport were up-regulated in urinary biofilms. Genes involved in carbon and nitrogen metabolism and nutrient response were down-regulated. In PAC-treated urinary biofilms compared to untreated control biofilms, 557 of 6,444 genes had significant changes in gene expression. Genes downregulated in PAC-treated biofilms were implicated in iron starvation and adhesion pathways. Although urinary biofilms share key features with biofilms formed in other environments, many genes are uniquely expressed in urinary biofilms. Cranberry-derived PACs interfere with the expression of iron acquisition and adhesion genes within urinary biofilms.

Histone Citrullination Represses MicroRNA Expression, Resulting in Increased Oncogene mRNAs in Somatolactotrope Cells.

Peptidylarginine deiminase (PAD) enzymes convert histone arginine residues into citrulline to modulate chromatin organization and gene expression. Although PADs are expressed in anterior pituitary gland cells, their functional role and expression in pituitary adenomas are unknown. To begin to address these issues, we first examined normal human pituitaries and pituitary adenomas and found that PAD2, PAD4, and citrullinated histones are highest in prolactinomas and somatoprolactinomas. In the somatoprolactinoma-derived GH3 cell line, PADs citrullinate histone H3, which is attenuated by a pan-PAD inhibitor. RNA sequencing and chromatin immunoprecipitation (ChIP) studies show that the expression of microRNAs (miRNAs) let-7c-2, 23b, and 29c is suppressed by histone citrullination. Our studies demonstrate that these miRNAs directly target the mRNA of the oncogenes encoding HMGA, insulin-like growth factor 1 (IGF-1), and N-MYC, which are highly implicated in human prolactinoma/somatoprolactinoma pathogenesis. Our results are the first to define a direct role for PAD-catalyzed histone citrullination in miRNA expression, which may underlie the etiology of prolactinoma and somatoprolactinoma tumors through regulation of oncogene expression.

Use of a draft genome of coffee (Coffea arabica) to identify SNPs associated with caffeine content.

Arabica coffee (Coffea arabica) has a small gene pool limiting genetic improvement. Selection for caffeine content within this gene pool would be assisted by identification of the genes controlling this important trait. Sequencing of DNA bulks from 18 genotypes with extreme high- or low-caffeine content from a population of 232 genotypes was used to identify linked polymorphisms. To obtain a reference genome, a whole genome assembly of arabica coffee (variety K7) was achieved by sequencing using short read (Illumina) and long-read (PacBio) technology. Assembly was performed using a range of assembly tools resulting in 76 409 scaffolds with a scaffold N50 of 54 544 bp and a total scaffold length of 1448 Mb. Validation of the genome assembly using different tools showed high completeness of the genome. More than 99% of transcriptome sequences mapped to the C. arabica draft genome, and 89% of BUSCOs were present. The assembled genome annotated using AUGUSTUS yielded 99 829 gene models. Using the draft arabica genome as reference in mapping and variant calling allowed the detection of 1444 nonsynonymous single nucleotide polymorphisms (SNPs) associated with caffeine content. Based on Kyoto Encyclopaedia of Genes and Genomes pathway-based analysis, 65 caffeine-associated SNPs were discovered, among which 11 SNPs were associated with genes encoding enzymes involved in the conversion of substrates, which participate in the caffeine biosynthesis pathways. This analysis demonstrated the complex genetic control of this key trait in coffee.

Correction to: The transcriptome landscape of early maize meiosis.

CORRECTION: Following publication of the original article [1], the authors reported that the number of genes overlaying the bar graph in Fig. 3A were incorrectly counted and inserted (i.e. including a title tile, and in inverse order). The corrected numbers are below and match with the listed genes supplied in Additional File: Table S2.

Salt and oxidative stresses uniquely regulate tomato cytokinin levels and transcriptomic response.

Cytokinins are well-known to be involved in processes responsible for plant growth and development. More recently, these hormones have begun to be associated with stress responses as well. However, it is unclear how changes in cytokinin biosynthesis, signaling, or transport relate to stress effects. This study examines in parallel how two different stresses, salt, and oxidative stress, affect changes in both cytokinin levels and whole plant transcriptome response. Solanum lycopersicum seedlings were given a short-term (6 hr) exposure to either salt (150 mM NaCl) or oxidative (20 mM H2O2) stress and then examined to determine both changes in cytokinin levels and transcriptome. LC-MS/MS was used to determine the levels of 22 different types of cytokinins in tomato plants including precursors, active, transported, and conjugated forms. When examining cytokinin levels we found that salt treatment caused an increase in both active and inactive cytokinin levels and oxidative stress caused a decrease in these levels. RNA-sequencing analyses of these same stress-treated tissues revealed 6,643 significantly differentially expressed genes (DEGs). Although many DEGs are similar between the two stresses, approximately one-third of the DEGs in each treatment were unique to that stress. Several cytokinin-related genes were among the DEGs. Examination of photosystem II efficiency revealed that cytokinins affect physiological response to stress in tomato, further validating the changes in cytokinin levels seen in planta.

Comparative Genomics of an Unusual Biogeographic Disjunction in the Cotton Tribe (Gossypieae) Yields Insights into Genome Downsizing.

Long-distance insular dispersal is associated with divergence and speciation because of founder effects and strong genetic drift. The cotton tribe (Gossypieae) has experienced multiple transoceanic dispersals, generating an aggregate geographic range that encompasses much of the tropics and subtropics worldwide. Two genera in the Gossypieae, Kokia and Gossypioides, exhibit a remarkable geographic disjunction, being restricted to the Hawaiian Islands and Madagascar/East Africa, respectively. We assembled and use de novo genome sequences to address questions regarding the divergence of these two genera from each other and from their sister-group, Gossypium. In addition, we explore processes underlying the genome downsizing that characterizes Kokia and Gossypioides relative to other genera in the tribe. Using 13,000 gene orthologs and synonymous substitution rates, we show that the two disjuncts last shared a common ancestor ∼5 Ma, or half as long ago as their divergence from Gossypium. We report relative stasis in the transposable element fraction. In comparison to Gossypium, there is loss of ∼30% of the gene content in the two disjunct genera and a history of genome-wide accumulation of deletions. In both genera, there is a genome-wide bias toward deletions over insertions, and the number of gene losses exceeds the number of gains by ∼2- to 4-fold. The genomic analyses presented here elucidate genomic consequences of the demographic and biogeographic history of these closest relatives of Gossypium, and enhance their value as phylogenetic outgroups.

Strategies for optimizing BioNano and Dovetail explored through a second reference quality assembly for the legume model, Medicago truncatula.

BACKGROUND: Third generation sequencing technologies, with sequencing reads in the tens- of kilo-bases, facilitate genome assembly by spanning ambiguous regions and improving continuity. This has been critical for plant genomes, which are difficult to assemble due to high repeat content, gene family expansions, segmental and tandem duplications, and polyploidy. Recently, high-throughput mapping and scaffolding strategies have further improved continuity. Together, these long-range technologies enable quality draft assemblies of complex genomes in a cost-effective and timely manner. RESULTS: Here, we present high quality genome assemblies of the model legume plant, Medicago truncatula (R108) using PacBio, Dovetail Chicago (hereafter, Dovetail) and BioNano technologies. To test these technologies for plant genome assembly, we generated five assemblies using all possible combinations and ordering of these three technologies in the R108 assembly. While the BioNano and Dovetail joins overlapped, they also showed complementary gains in continuity and join numbers. Both technologies spanned repetitive regions that PacBio alone was unable to bridge. Combining technologies, particularly Dovetail followed by BioNano, resulted in notable improvements compared to Dovetail or BioNano alone. A combination of PacBio, Dovetail, and BioNano was used to generate a high quality draft assembly of R108, a M. truncatula accession widely used in studies of functional genomics. As a test for the usefulness of the resulting genome sequence, the new R108 assembly was used to pinpoint breakpoints and characterize flanking sequence of a previously identified translocation between chromosomes 4 and 8, identifying more than 22.7 Mb of novel sequence not present in the earlier A17 reference assembly. CONCLUSIONS: Adding Dovetail followed by BioNano data yielded complementary improvements in continuity over the original PacBio assembly. This strategy proved efficient and cost-effective for developing a quality draft assembly compared to traditional reference assemblies.

Hybrid assembly with long and short reads improves discovery of gene family expansions.

BACKGROUND: Long-read and short-read sequencing technologies offer competing advantages for eukaryotic genome sequencing projects. Combinations of both may be appropriate for surveys of within-species genomic variation. METHODS: We developed a hybrid assembly pipeline called "Alpaca" that can operate on 20X long-read coverage plus about 50X short-insert and 50X long-insert short-read coverage. To preclude collapse of tandem repeats, Alpaca relies on base-call-corrected long reads for contig formation. RESULTS: Compared to two other assembly protocols, Alpaca demonstrated the most reference agreement and repeat capture on the rice genome. On three accessions of the model legume Medicago truncatula, Alpaca generated the most agreement to a conspecific reference and predicted tandemly repeated genes absent from the other assemblies. CONCLUSION: Our results suggest Alpaca is a useful tool for investigating structural and copy number variation within de novo assemblies of sampled populations.

Crude oil impairs immune function and increases susceptibility to pathogenic bacteria in southern flounder.

Exposure to crude oil or its individual constituents can have detrimental impacts on fish species, including impairment of the immune response. Increased observations of skin lesions in northern Gulf of Mexico fish during the 2010 Deepwater Horizon oil spill indicated the possibility of oil-induced immunocompromisation resulting in bacterial or viral infection. This study used a full factorial design of oil exposure and bacterial challenge to examine how oil exposure impairs southern flounder (Paralichthys lethostigma) immune function and increases susceptibility to the bacteria Vibrio anguillarum, a causative agent of vibriosis. Fish exposed to oil prior to bacterial challenge exhibited 94.4% mortality within 48 hours of bacterial exposure. Flounder challenged with V. anguillarum without prior oil exposure had <10% mortality. Exposure resulted in taxonomically distinct gill and intestine bacterial communities. Mortality strongly correlated with V. anguillarum levels, where it comprised a significantly higher percentage of the microbiome in Oil/Pathogen challenged fish and was nearly non-existent in the No Oil/Pathogen challenged fish bacterial community. Elevated V. anguillarum levels were a direct result of oil exposure-induced immunosuppression. Oil-exposure reduced expression of immunoglobulin M, the major systemic fish antibody, and resulted in an overall downregulation in transcriptome response, particularly in genes related to immune function, response to stimulus and hemostasis. Ultimately, sediment-borne oil exposure impairs immune function, leading to increased incidences of bacterial infections. This type of sediment-borne exposure may result in long-term marine ecosystem effects, as oil-bound sediment in the northern Gulf of Mexico will likely remain a contamination source for years to come.