Publications

@article{Pardo-Palacios2024,

title = {Systematic assessment of long-read RNA-seq methods for transcript identification and quantification},

author = {Francisco J. Pardo-Palacios and Dingjie Wang and Fairlie Reese and Mark Diekhans and Sílvia Carbonell-Sala and Brian Williams and Jane E. Loveland and Maite De María and Matthew S. Adams and Gabriela Balderrama-Gutierrez and Amit K. Behera and Jose M. Gonzalez Martinez and Toby Hunt and Julien Lagarde and Cindy E. Liang and Haoran Li and Marcus Jerryd Meade and David A. Moraga Amador and Andrey D. Prjibelski and Inanc Birol and Hamed Bostan and Ashley M. Brooks and Muhammed Hasan Çelik and Ying Chen and Mei R. M. Du and Colette Felton and Jonathan Göke and Saber Hafezqorani and Ralf Herwig and Hideya Kawaji and Joseph Lee and Jian-Liang Li and Matthias Lienhard and Alla Mikheenko and Dennis Mulligan and Ka Ming Nip and Mihaela Pertea and Matthew E. Ritchie and Andre D. Sim and Alison D. Tang and Yuk Kei Wan and Changqing Wang and Brandon Y. Wong and Chen Yang and If Barnes and Andrew E. Berry and Salvador Capella-Gutierrez and Alyssa Cousineau and Namrita Dhillon and Jose M. Fernandez-Gonzalez and Luis Ferrández-Peral and Natàlia Garcia-Reyero and Stefan Götz and Carles Hernández-Ferrer and Liudmyla Kondratova and Tianyuan Liu and Alessandra Martinez-Martin and Carlos Menor and Jorge Mestre-Tomás and Jonathan M. Mudge and Nedka G. Panayotova and Alejandro Paniagua and Dmitry Repchevsky and Xingjie Ren and Eric Rouchka and Brandon Saint-John and Enrique Sapena and Leon Sheynkman and Melissa Laird Smith and Marie-Marthe Suner and Hazuki Takahashi and Ingrid A. Youngworth and Piero Carninci and Nancy D. Denslow and Roderic Guigó and Margaret E. Hunter and Rene Maehr and Yin Shen and Hagen U. Tilgner and Barbara J. Wold and Christopher Vollmers and Adam Frankish and Kin Fai Au and Gloria M. Sheynkman and Ali Mortazavi and Ana Conesa and Angela N. Brooks},

doi = {10.1038/s41592-024-02298-3},

issn = {1548-7105},

year  = {2024},

date = {2024-06-07},

journal = {Nat Methods},

publisher = {Springer Science and Business Media LLC},

abstract = {AbstractThe Long-read RNA-Seq Genome Annotation Assessment Project Consortium was formed to evaluate the effectiveness of long-read approaches for transcriptome analysis. Using different protocols and sequencing platforms, the consortium generated over 427 million long-read sequences from complementary DNA and direct RNA datasets, encompassing human, mouse and manatee species. Developers utilized these data to address challenges in transcript isoform detection, quantification and de novo transcript detection. The study revealed that libraries with longer, more accurate sequences produce more accurate transcripts than those with increased read depth, whereas greater read depth improved quantification accuracy. In well-annotated genomes, tools based on reference sequences demonstrated the best performance. Incorporating additional orthogonal data and replicate samples is advised when aiming to detect rare and novel transcripts or using reference-free approaches. This collaborative study offers a benchmark for current practices and provides direction for future method development in transcriptome analysis.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Pardo-Palacios2024b,

title = {SQANTI3: curation of long-read transcriptomes for accurate identification of known and novel isoforms},

author = {Francisco J. Pardo-Palacios and Angeles Arzalluz-Luque and Liudmyla Kondratova and Pedro Salguero and Jorge Mestre-Tomás and Rocío Amorín and Eva Estevan-Morió and Tianyuan Liu and Adalena Nanni and Lauren McIntyre and Elizabeth Tseng and Ana Conesa},

doi = {10.1038/s41592-024-02229-2},

issn = {1548-7105},

year  = {2024},

date = {2024-05-00},

journal = {Nat Methods},

volume = {21},

number = {5},

pages = {793--797},

publisher = {Springer Science and Business Media LLC},

abstract = {AbstractSQANTI3 is a tool designed for the quality control, curation and annotation of long-read transcript models obtained with third-generation sequencing technologies. Leveraging its annotation framework, SQANTI3 calculates quality descriptors of transcript models, junctions and transcript ends. With this information, potential artifacts can be identified and replaced with reliable sequences. Furthermore, the integrated functional annotation feature enables subsequent functional iso-transcriptomics analyses.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Nanni2024,

title = {Nucleotide-level distance metrics to quantify alternative splicing implemented in \textit{TranD}},

author = {Adalena Nanni and James Titus-McQuillan and Kinfeosioluwa S Bankole and Francisco Pardo-Palacios and Sarah Signor and Srna Vlaho and Oleksandr Moskalenko and Alison M Morse and Rebekah L Rogers and Ana Conesa and Lauren M McIntyre},

doi = {10.1093/nar/gkae056},

issn = {1362-4962},

year  = {2024},

date = {2024-03-21},

volume = {52},

number = {5},

pages = {e28--e28},

publisher = {Oxford University Press (OUP)},

abstract = {Abstract

               Advances in affordable transcriptome sequencing combined with better exon and gene prediction has motivated many to compare transcription across the tree of life. We develop a mathematical framework to calculate complexity and compare transcript models. Structural features, i.e. intron retention (IR), donor/acceptor site variation, alternative exon cassettes, alternative 5′/3′ UTRs, are compared and the distance between transcript models is calculated with nucleotide level precision. All metrics are implemented in a PyPi package, TranD and output can be used to summarize splicing patterns for a transcriptome (1GTF) and between transcriptomes (2GTF). TranD output enables quantitative comparisons between: annotations augmented by empirical RNA-seq data and the original transcript models; transcript model prediction tools for longread RNA-seq (e.g. FLAIR versus Isoseq3); alternate annotations for a species (e.g. RefSeq vs Ensembl); and between closely related species. In C. elegans, Z. mays, D. melanogaster, D. simulans and H. sapiens, alternative exons were observed more frequently in combination with an alternative donor/acceptor than alone. Transcript models in RefSeq and Ensembl are linked and both have unique transcript models with empirical support. D. melanogaster and D. simulans, share many transcript models and long-read RNAseq data suggests that both species are under-annotated. We recommend combined references.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Mestre-Tomás2023,

title = {SQANTI-SIM: a simulator of controlled transcript novelty for lrRNA-seq benchmark},

author = {Jorge Mestre-Tomás and Tianyuan Liu and Francisco Pardo-Palacios and Ana Conesa},

doi = {10.1186/s13059-023-03127-0},

issn = {1474-760X},

year  = {2023},

date = {2023-12-00},

journal = {Genome Biol},

volume = {24},

number = {1},

publisher = {Springer Science and Business Media LLC},

abstract = {AbstractLong-read RNA sequencing has emerged as a powerful tool for transcript discovery, even in well-annotated organisms. However, assessing the accuracy of different methods in identifying annotated and novel transcripts remains a challenge. Here, we present SQANTI-SIM, a versatile tool that wraps around popular long-read simulators to allow precise management of transcript novelty based on the structural categories defined by SQANTI3. By selectively excluding specific transcripts from the reference dataset, SQANTI-SIM effectively emulates scenarios involving unannotated transcripts. Furthermore, the tool provides customizable features and supports the simulation of additional types of data, representing the first multi-omics simulation tool for the lrRNA-seq field.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{AmoríndeHegedüs2023,

title = {Integration of multi-omics data to elucidate keystone unknown taxa within microbialite-forming ecosystems},

author = {Rocío Amorín de Hegedüs and Ana Conesa and Jamie S. Foster},

doi = {10.3389/fmicb.2023.1174685},

issn = {1664-302X},

year  = {2023},

date = {2023-07-28},

journal = {Front. Microbiol.},

volume = {14},

publisher = {Frontiers Media SA},

abstract = {Microbes continually shape Earth’s biochemical and physical landscapes by inhabiting diverse metabolic niches. Despite the important role microbes play in ecosystem functioning, most microbial species remain unknown highlighting a gap in our understanding of structured complex ecosystems. To elucidate the relevance of these unknown taxa, often referred to as “microbial dark matter,” the integration of multiple high throughput sequencing technologies was used to evaluate the co-occurrence and connectivity of all microbes within the community. Since there are no standard methodologies for multi-omics integration of microbiome data, we evaluated the abundance of “microbial dark matter” in microbialite-forming communities using different types meta-omic datasets: amplicon, metagenomic, and metatranscriptomic sequencing previously generated for this ecosystem. Our goal was to compare the community structure and abundances of unknown taxa within the different data types rather than to perform a functional characterization of the data. Metagenomic and metatranscriptomic data were input into SortMeRNA to extract 16S rRNA gene reads. The output, as well as amplicon sequences, were processed through QIIME2 for taxonomy analysis. The R package mdmnets was utilized to build co-occurrence networks. Most hubs presented unknown classifications, even at the phyla level. Comparisons of the highest scoring hubs of each data type using sequence similarity networks allowed the identification of the most relevant hubs within the microbialite-forming communities. This work highlights the importance of unknown taxa in community structure and proposes that ecosystem network construction can be used on several types of data to identify keystone taxa and their potential function within microbial ecosystems.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36894419,

title = {Differences in uterine and serum metabolome associated with metritis in dairy cows},

author = {C C Figueiredo and L Balzano-Nogueira and D Z Bisinotto and A Revilla Ruiz and G A Duarte and A Conesa and K N Galvão and R S Bisinotto},

doi = {10.3168/jds.2022-22552},

issn = {1525-3198},

year  = {2023},

date = {2023-05-01},

urldate = {2023-05-01},

journal = {J Dairy Sci},

volume = {106},

number = {5},

pages = {3525--3536},

abstract = {Objectives were to evaluate differences in the uterine and serum metabolomes associated with metritis in dairy cows. Vaginal discharge was evaluated using a Metricheck device (Simcro) at 5, 7, and 11 d in milk (DIM; herd 1) or 4, 6, 8, 10, and 12 DIM (herd 2). Cows with reddish or brownish, watery, and fetid discharge were diagnosed with metritis (n = 24). Cows with metritis were paired with herdmates without metritis (i.e., clear mucous vaginal discharge or clear lochia with ≤50% of pus) based on DIM and parity (n = 24). Day of metritis diagnosis was considered study d 0. All cows diagnosed with metritis received antimicrobial therapy. The metabolome of uterine lavage collected on d 0 and 5, and serum samples collected on d 0 were evaluated using untargeted gas chromatography time-of-flight mass spectrometry. Normalized data were subjected to multivariate canonical analysis of population using the MultBiplotR and MixOmics packages in R Studio. Univariate analyses including t-test, principal component analyses, partial least squares discriminant analyses, and pathway analyses were conducted using Metaboanalyst. The uterine metabolome differed between cows with and without metritis on d 0. Differences in the uterine metabolome associated with metritis on d 0 were related to the metabolism of butanoate, amino acids (i.e., glycine, serine, threonine, alanine, aspartate, and glutamate), glycolysis and gluconeogenesis, and the tricarboxylic acid cycle. No differences in the serum metabolome were observed between cows diagnosed with metritis and counterparts without metritis on d 0. Similarly, no differences in uterine metabolome were observed between cows with metritis and counterparts not diagnosed with metritis on d 5. These results indicate that the establishment of metritis in dairy cows is associated with local disturbances in amino acid, lipid, and carbohydrate metabolism in the uterus. The lack of differences in the uterine metabolome on d 5 indicates that processes implicated with the disease are reestablished by d 5 after diagnosis and treatment.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Thompson2023,

title = {Identification of food and nutrient components as predictors of Lactobacillus colonization},

author = {Sharon C. Thompson and Amanda L. Ford and Elijah J. Moothedan and Lauren S. Stafford and Timothy J. Garrett and Wendy J. Dahl and Ana Conesa and Claudio F. Gonzalez and Graciela L. Lorca},

doi = {10.3389/fnut.2023.1118679},

issn = {2296-861X},

year  = {2023},

date = {2023-04-21},

journal = {Front. Nutr.},

volume = {10},

publisher = {Frontiers Media SA},

abstract = {A previous double-blind, randomized clinical trial of 42 healthy individuals conducted with Lactobacillus johnsonii N6.2 found that the probiotic’s mechanistic tryptophan pathway was significantly modified when the data was stratified based on the individuals’ lactic acid bacteria (LAB) stool content. These results suggest that confounding factors such as dietary intake which impact stool LAB content may affect the response to the probiotic treatment. Using dietary intake, serum metabolite, and stool LAB colony forming unit (CFU) data from a previous clinical trial, the relationships between diet, metabolic response, and fecal LAB were assessed. The diets of subject groups with high vs. low CFUs of LAB/g of wet stool differed in their intakes of monounsaturated fatty acids, vegetables, proteins, and dairy. Individuals with high LAB consumed greater amounts of cheese, fermented meats, soy, nuts and seeds, alcoholic beverages, and oils whereas individuals with low LAB consumed higher amounts of tomatoes, starchy vegetables, and poultry. Several dietary variables correlated with LAB counts; positive correlations were determined for nuts and seeds, fish high in N-3 fatty acids, soy, and processed meats, and negative correlations to consumption of vegetables including tomatoes. Using machine learning, predictors of LAB count included cheese, nuts and seeds, fish high in N-3 fatty acids, and erucic acid. Erucic acid alone accurately predicted LAB categorization, and was shown to be utilized as a sole fatty acid source by several Lactobacillus species regardless of their mode of fermentation. Several metabolites were significantly upregulated in each group based on LAB titers, notably polypropylene glycol, caproic acid, pyrazine, and chondroitin sulfate; however, none were correlated with the dietary intake variables. These findings suggest that dietary variables may drive the presence of LAB in the human gastrointestinal tract and potentially impact response to probiotic interventions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36302651,

title = {Palmitate impairs circadian transcriptomics in muscle cells through histone modification of enhancers},

author = {Nicolas J Pillon and Laura Sardón Puig and Ali Altıntaş and Prasad G Kamble and Salvador Casaní-Galdón and Brendan M Gabriel and Romain Barrès and Ana Conesa and Alexander V Chibalin and Erik Näslund and Anna Krook and Juleen R Zierath},

doi = {10.26508/lsa.202201598},

issn = {2575-1077},

year  = {2023},

date = {2023-01-01},

journal = {Life Sci Alliance},

volume = {6},

number = {1},

abstract = {Obesity and elevated circulating lipids may impair metabolism by disrupting the molecular circadian clock. We tested the hypothesis that lipid overload may interact with the circadian clock and alter the rhythmicity of gene expression through epigenomic mechanisms in skeletal muscle. Palmitate reprogrammed the circadian transcriptome in myotubes without altering the rhythmic mRNA expression of core clock genes. Genes with enhanced cycling in response to palmitate were associated with post-translational modification of histones. The cycling of histone 3 lysine 27 acetylation (H3K27ac), a marker of active gene enhancers, was modified by palmitate treatment. Chromatin immunoprecipitation and sequencing confirmed that palmitate exposure altered the cycling of DNA regions associated with H3K27ac. The overlap between mRNA and DNA regions associated with H3K27ac and the pharmacological inhibition of histone acetyltransferases revealed novel cycling genes associated with lipid exposure of primary human myotubes. Palmitate exposure disrupts transcriptomic rhythmicity and modifies enhancers through changes in histone H3K27 acetylation in a circadian manner. Thus, histone acetylation is responsive to lipid overload and may redirect the circadian chromatin landscape, leading to the reprogramming of circadian genes and pathways involved in lipid biosynthesis in skeletal muscle.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37153913,

title = {Identification of food and nutrient components as predictors of  colonization},

author = {Sharon C Thompson and Amanda L Ford and Elijah J Moothedan and Lauren S Stafford and Timothy J Garrett and Wendy J Dahl and Ana Conesa and Claudio F Gonzalez and Graciela L Lorca},

doi = {10.3389/fnut.2023.1118679},

issn = {2296-861X},

year  = {2023},

date = {2023-01-01},

journal = {Front Nutr},

volume = {10},

pages = {1118679},

abstract = {A previous double-blind, randomized clinical trial of 42 healthy individuals conducted with  N6.2 found that the probiotic's mechanistic tryptophan pathway was significantly modified when the data was stratified based on the individuals' lactic acid bacteria (LAB) stool content. These results suggest that confounding factors such as dietary intake which impact stool LAB content may affect the response to the probiotic treatment. Using dietary intake, serum metabolite, and stool LAB colony forming unit (CFU) data from a previous clinical trial, the relationships between diet, metabolic response, and fecal LAB were assessed. The diets of subject groups with high vs. low CFUs of LAB/g of wet stool differed in their intakes of monounsaturated fatty acids, vegetables, proteins, and dairy. Individuals with high LAB consumed greater amounts of cheese, fermented meats, soy, nuts and seeds, alcoholic beverages, and oils whereas individuals with low LAB consumed higher amounts of tomatoes, starchy vegetables, and poultry. Several dietary variables correlated with LAB counts; positive correlations were determined for nuts and seeds, fish high in N-3 fatty acids, soy, and processed meats, and negative correlations to consumption of vegetables including tomatoes. Using machine learning, predictors of LAB count included cheese, nuts and seeds, fish high in N-3 fatty acids, and erucic acid. Erucic acid alone accurately predicted LAB categorization, and was shown to be utilized as a sole fatty acid source by several  species regardless of their mode of fermentation. Several metabolites were significantly upregulated in each group based on LAB titers, notably polypropylene glycol, caproic acid, pyrazine, and chondroitin sulfate; however, none were correlated with the dietary intake variables. These findings suggest that dietary variables may drive the presence of LAB in the human gastrointestinal tract and potentially impact response to probiotic interventions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid37577445,

title = {Integration of multi-omics data to elucidate keystone unknown taxa within microbialite-forming ecosystems},

author = {Rocío Amorín de Hegedüs and Ana Conesa and Jamie S Foster},

doi = {10.3389/fmicb.2023.1174685},

issn = {1664-302X},

year  = {2023},

date = {2023-01-01},

journal = {Front Microbiol},

volume = {14},

pages = {1174685},

abstract = {Microbes continually shape Earth's biochemical and physical landscapes by inhabiting diverse metabolic niches. Despite the important role microbes play in ecosystem functioning, most microbial species remain unknown highlighting a gap in our understanding of structured complex ecosystems. To elucidate the relevance of these unknown taxa, often referred to as "microbial dark matter," the integration of multiple high throughput sequencing technologies was used to evaluate the co-occurrence and connectivity of all microbes within the community. Since there are no standard methodologies for multi-omics integration of microbiome data, we evaluated the abundance of "microbial dark matter" in microbialite-forming communities using different types meta-omic datasets: amplicon, metagenomic, and metatranscriptomic sequencing previously generated for this ecosystem. Our goal was to compare the community structure and abundances of unknown taxa within the different data types rather than to perform a functional characterization of the data. Metagenomic and metatranscriptomic data were input into SortMeRNA to extract 16S rRNA gene reads. The output, as well as amplicon sequences, were processed through QIIME2 for taxonomy analysis. The R package mdmnets was utilized to build co-occurrence networks. Most hubs presented unknown classifications, even at the phyla level. Comparisons of the highest scoring hubs of each data type using sequence similarity networks allowed the identification of the most relevant hubs within the microbialite-forming communities. This work highlights the importance of unknown taxa in community structure and proposes that ecosystem network construction can be used on several types of data to identify keystone taxa and their potential function within microbial ecosystems.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36494864,

title = {New roles for AP-1/JUNB in cell cycle control and tumorigenic cell invasion via regulation of cyclin E1 and TGF-β2},

author = {Beatriz Pérez-Benavente and Alihamze Fathinajafabadi and Lorena de la Fuente and Carolina Gandía and Arantxa Martínez-Férriz and José Miguel Pardo-Sánchez and Lara Milián and Ana Conesa and Octavio A Romero and Julián Carretero and Rune Matthiesen and Isabelle Jariel-Encontre and Marc Piechaczyk and Rosa Farràs},

doi = {10.1186/s13059-022-02800-0},

issn = {1474-760X},

year  = {2022},

date = {2022-12-01},

journal = {Genome Biol},

volume = {23},

number = {1},

pages = {252},

abstract = {BACKGROUND: JUNB transcription factor contributes to the formation of the ubiquitous transcriptional complex AP-1 involved in the control of many physiological and disease-associated functions. The roles of JUNB in the control of cell division and tumorigenic processes are acknowledged but still unclear.



RESULTS: Here, we report the results of combined transcriptomic, genomic, and functional studies showing that JUNB promotes cell cycle progression via induction of cyclin E1 and repression of transforming growth factor (TGF)-β2 genes. We also show that high levels of JUNB switch the response of TGF-β2 stimulation from an antiproliferative to a pro-invasive one, induce endogenous TGF-β2 production by promoting TGF-β2 mRNA translation, and enhance tumor growth and metastasis in mice. Moreover, tumor genomic data indicate that JUNB amplification associates with poor prognosis in breast and ovarian cancer patients.



CONCLUSIONS: Our results reveal novel functions for JUNB in cell proliferation and tumor aggressiveness through regulation of cyclin E1 and TGF-β2 expression, which might be exploited for cancer prognosis and therapy.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36097183,

title = {Independent phenotypic plasticity axes define distinct obesity sub-types},

author = {Chih-Hsiang Yang and Luca Fagnocchi and Stefanos Apostle and Vanessa Wegert and Salvador Casaní-Galdón and Kathrin Landgraf and Ilaria Panzeri and Erez Dror and Steffen Heyne and Till Wörpel and Darrell P Chandler and Di Lu and Tao Yang and Elizabeth Gibbons and Rita Guerreiro and Jose Bras and Martin Thomasen and Louise G Grunnet and Allan A Vaag and Linn Gillberg and Elin Grundberg and Ana Conesa and Antje Körner and  and J Andrew Pospisilik},

doi = {10.1038/s42255-022-00629-2},

issn = {2522-5812},

year  = {2022},

date = {2022-09-01},

journal = {Nat Metab},

volume = {4},

number = {9},

pages = {1150--1165},

abstract = {Studies in genetically 'identical' individuals indicate that as much as 50% of complex trait variation cannot be traced to genetics or to the environment. The mechanisms that generate this 'unexplained' phenotypic variation (UPV) remain largely unknown. Here, we identify neuronatin (NNAT) as a conserved factor that buffers against UPV. We find that Nnat deficiency in isogenic mice triggers the emergence of a bi-stable polyphenism, where littermates emerge into adulthood either 'normal' or 'overgrown'. Mechanistically, this is mediated by an insulin-dependent overgrowth that arises from histone deacetylase (HDAC)-dependent β-cell hyperproliferation. A multi-dimensional analysis of monozygotic twin discordance reveals the existence of two patterns of human UPV, one of which (Type B) phenocopies the NNAT-buffered polyphenism identified in mice. Specifically, Type-B monozygotic co-twins exhibit coordinated increases in fat and lean mass across the body; decreased NNAT expression; increased HDAC-responsive gene signatures; and clinical outcomes linked to insulinemia. Critically, the Type-B UPV signature stratifies both childhood and adult cohorts into four metabolic states, including two phenotypically and molecularly distinct types of obesity.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36066904,

title = {The absence of the queuosine tRNA modification leads to pleiotropic phenotypes revealing perturbations of metal and oxidative stress homeostasis in Escherichia coli K12},

author = {Leticia Pollo-Oliveira and Nick K Davis and Intekhab Hossain and Peiying Ho and Yifeng Yuan and Pedro Salguero García and Cécile Pereira and Shane R Byrne and Jiapeng Leng and Melody Sze and Crysten E Blaby-Haas and Agnieszka Sekowska and Alvaro Montoya and Thomas Begley and Antoine Danchin and Daniel P Aalberts and Alexander Angerhofer and John Hunt and Ana Conesa and Peter C Dedon and Valérie de Crécy-Lagard},

doi = {10.1093/mtomcs/mfac065},

issn = {1756-591X},

year  = {2022},

date = {2022-09-01},

journal = {Metallomics},

volume = {14},

number = {9},

abstract = {Queuosine (Q) is a conserved hypermodification of the wobble base of tRNA containing GUN anticodons but the physiological consequences of Q deficiency are poorly understood in bacteria. This work combines transcriptomic, proteomic and physiological studies to characterize a Q-deficient Escherichia coli K12 MG1655 mutant. The absence of Q led to an increased resistance to nickel and cobalt, and to an increased sensitivity to cadmium, compared to the wild-type (WT) strain. Transcriptomic analysis of the WT and Q-deficient strains, grown in the presence and absence of nickel, revealed that the nickel transporter genes (nikABCDE) are downregulated in the Q- mutant, even when nickel is not added. This mutant is therefore primed to resist to high nickel levels. Downstream analysis of the transcriptomic data suggested that the absence of Q triggers an atypical oxidative stress response, confirmed by the detection of slightly elevated reactive oxygen species (ROS) levels in the mutant, increased sensitivity to hydrogen peroxide and paraquat, and a subtle growth phenotype in a strain prone to accumulation of ROS.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid36046619,

title = {Reference-based comparison of adaptive immune receptor repertoires},

author = {Cédric R Weber and Teresa Rubio and Longlong Wang and Wei Zhang and Philippe A Robert and Rahmad Akbar and Igor Snapkov and Jinghua Wu and Marieke L Kuijjer and Sonia Tarazona and Ana Conesa and Geir K Sandve and Xiao Liu and Sai T Reddy and Victor Greiff},

doi = {10.1016/j.crmeth.2022.100269},

issn = {2667-2375},

year  = {2022},

date = {2022-08-01},

journal = {Cell Rep Methods},

volume = {2},

number = {8},

pages = {100269},

abstract = {B and T cell receptor (immune) repertoires can represent an individual's immune history. While current repertoire analysis methods aim to discriminate between health and disease states, they are typically based on only a limited number of parameters. Here, we introduce immuneREF: a quantitative multidimensional measure of adaptive immune repertoire (and transcriptome) similarity that allows interpretation of immune repertoire variation by relying on both repertoire features and cross-referencing of simulated and experimental datasets. To quantify immune repertoire similarity landscapes across health and disease, we applied immuneREF to >2,400 datasets from individuals with varying immune states (healthy, [autoimmune] disease, and infection). We discovered, in contrast to the current paradigm, that blood-derived immune repertoires of healthy and diseased individuals are highly similar for certain immune states, suggesting that repertoire changes to immune perturbations are less pronounced than previously thought. In conclusion, immuneREF enables the population-wide study of adaptive immune response similarity across immune states.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid35961013,

title = {A roadmap for the functional annotation of protein families: a community perspective},

author = {Valérie de Crécy-Lagard and Rocio Amorin de Hegedus and Cecilia Arighi and Jill Babor and Alex Bateman and Ian Blaby and Crysten Blaby-Haas and Alan J Bridge and Stephen K Burley and Stacey Cleveland and Lucy J Colwell and Ana Conesa and Christian Dallago and Antoine Danchin and Anita de Waard and Adam Deutschbauer and Raquel Dias and Yousong Ding and Gang Fang and Iddo Friedberg and John Gerlt and Joshua Goldford and Mark Gorelik and Benjamin M Gyori and Christopher Henry and Geoffrey Hutinet and Marshall Jaroch and Peter D Karp and Liudmyla Kondratova and Zhiyong Lu and Aron Marchler-Bauer and Maria-Jesus Martin and Claire McWhite and Gaurav D Moghe and Paul Monaghan and Anne Morgat and Christopher J Mungall and Darren A Natale and William C Nelson and Seán O'Donoghue and Christine Orengo and Katherine H O'Toole and Predrag Radivojac and Colbie Reed and Richard J Roberts and Dmitri Rodionov and Irina A Rodionova and Jeffrey D Rudolf and Lana Saleh and Gloria Sheynkman and Francoise Thibaud-Nissen and Paul D Thomas and Peter Uetz and David Vallenet and Erica Watson Carter and Peter R Weigele and Valerie Wood and Elisha M Wood-Charlson and Jin Xu},

doi = {10.1093/database/baac062},

issn = {1758-0463},

year  = {2022},

date = {2022-08-01},

journal = {Database (Oxford)},

volume = {2022},

abstract = {Over the last 25 years, biology has entered the genomic era and is becoming a science of 'big data'. Most interpretations of genomic analyses rely on accurate functional annotations of the proteins encoded by more than 500 000 genomes sequenced to date. By different estimates, only half the predicted sequenced proteins carry an accurate functional annotation, and this percentage varies drastically between different organismal lineages. Such a large gap in knowledge hampers all aspects of biological enterprise and, thereby, is standing in the way of genomic biology reaching its full potential. A brainstorming meeting to address this issue funded by the National Science Foundation was held during 3-4 February 2022. Bringing together data scientists, biocurators, computational biologists and experimentalists within the same venue allowed for a comprehensive assessment of the current state of functional annotations of protein families. Further, major issues that were obstructing the field were identified and discussed, which ultimately allowed for the proposal of solutions on how to move forward.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rubio2022-sg,

title = {A Nextflow pipeline for T-cell receptor repertoire  reconstruction and analysis from RNA sequencing data},

author = {Teresa Rubio and Maria Chernigovskaya and Susanna Marquez and Cristina Marti and Paula Izquierdo-Altarejos and Amparo Urios and Carmina Montoliu and Vicente Felipo and Ana Conesa and Victor Greiff and Sonia Tarazona},

url = {https://www.immunoinformaticsjournal.com/action/showPdf?pii=S2667-1190%2822%2900004-0},

doi = {10.1016/j.immuno.2022.100012},

year  = {2022},

date = {2022-06-01},

urldate = {2022-06-01},

journal = {ImmunoInformatics},

volume = {6},

pages = {100012},

publisher = {Elsevier},

abstract = {T-cell receptor (TCR) analysis is relevant for the study of immune system diseases. The expression of TCRs is usually measured with targeted sequencing approaches where TCR genes are selectively amplified. However, many non-targeted RNA-seq experiments also contain reads of TCR genes, which could be leveraged for TCR expression analysis while reducing sample requirements and costs. Moreover, a step-by-step pipeline for the processing of transcriptome RNA-seq reads to deliver immune repertoire data is missing, and these types of analyses are usually not included in RNA-seq studies of immunological conditions. This represents a missed opportunity for complementing them with the analysis of the immune repertoire.

We present a Nextflow pipeline for T-cell receptor repertoire reconstruction and analysis from RNA sequencing data. We used a case study where TCR repertoire profiles were recovered from bulk RNA-seq of isolated CD4 T cells from control patients, cirrhotic patients without and with Minimal Hepatic Encephalopathy (MHE). MHE is a neuropsychiatric syndrome, mediated by peripheral inflammation, that may affect cirrhotic patients. After the recovery of 498-1,114 distinct TCR beta chains per patient, repertoire analysis of patients resulted in few public clones, high diversity and elevated within-repertoire sequence similarity, independently of immune status. Additionally, TCRs associated with celiac disease and inflammatory bowel disease were significantly overrepresented in MHE patient repertoires. The provided computational pipeline functions as a resource to facilitate TCR profiling from RNA-seq data boosting immunophenotype analyses of immunological diseases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid35579358,

title = {Variation in leaf transcriptome responses to elevated ozone corresponds with physiological sensitivity to ozone across maize inbred lines},

author = {Adalena V Nanni and Alison M Morse and Jeremy R B Newman and Nicole E Choquette and Jessica M Wedow and Zihao Liu and Andrew D B Leakey and Ana Conesa and Elizabeth A Ainsworth and Lauren M McIntyre},

doi = {10.1093/genetics/iyac080},

issn = {1943-2631},

year  = {2022},

date = {2022-05-01},

journal = {Genetics},

abstract = {We examine the impact of sustained elevated ozone concentration on the leaf transcriptome of 5 diverse maize inbred genotypes, which vary in physiological sensitivity to ozone (B73, Mo17, Hp301, C123, NC338), using long reads to assemble transcripts and short reads to quantify expression of these transcripts. More than 99% of the long reads, 99% of the assembled transcripts, and 97% of the short reads map to both B73 and Mo17 reference genomes. Approximately 95% of the genes with assembled transcripts belong to known B73-Mo17 syntenic loci and 94% of genes with assembled transcripts are present in all temperate lines in the NAM pan-genome. While there is limited evidence for alternative splicing in response to ozone stress, there is a difference in the magnitude of differential expression among the 5 genotypes. The transcriptional response to sustained ozone stress in the ozone resistant B73 genotype (151 genes) was modest, while more than 3,300 genes were significantly differentially expressed in the more sensitive NC338 genotype. There is the potential for tandem duplication in 30% of genes with assembled transcripts, but there is no obvious association between potential tandem duplication and differential expression. Genes with a common response across the 5 genotypes (83 genes) were associated with photosynthesis, in particular photosystem I. The functional annotation of genes not differentially expressed in B73 but responsive in the other 4 genotypes (789) identifies reactive oxygen species. This suggests that B73 has a different response to long term ozone exposure than the other 4 genotypes. The relative magnitude of the genotypic response to ozone, and the enrichment analyses are consistent regardless of whether aligning short reads to: long read assembled transcripts; the B73 reference; the Mo17 reference. We find that prolonged ozone exposure directly impacts the photosynthetic machinery of the leaf.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pmid35609982,

title = {PaintOmics 4: new tools for the integrative analysis of multi-omics datasets supported by multiple pathway databases},

author = {Tianyuan Liu and Pedro Salguero and Marko Petek and Carlos Martinez-Mira and Leandro Balzano-Nogueira and Živa Ramšak and Lauren McIntyre and Kristina Gruden and Sonia Tarazona and Ana Conesa},

doi = {10.1093/nar/gkac352},

issn = {1362-4962},

year  = {2022},

date = {2022-05-01},

journal = {Nucleic Acids Res},

abstract = {PaintOmics is a web server for the integrative analysis and visualisation of multi-omics datasets using biological pathway maps. PaintOmics 4 has several notable updates that improve and extend analyses. Three pathway databases are now supported: KEGG, Reactome and MapMan, providing more comprehensive pathway knowledge for animals and plants. New metabolite analysis methods fill gaps in traditional pathway-based enrichment methods. The metabolite hub analysis selects compounds with a high number of significant genes in their neighbouring network, suggesting regulation by gene expression changes. The metabolite class activity analysis tests the hypothesis that a metabolic class has a higher-than-expected proportion of significant elements, indicating that these compounds are regulated in the experiment. Finally, PaintOmics 4 includes a regulatory omics module to analyse the contribution of trans-regulatory layers (microRNA and transcription factors, RNA-binding proteins) to regulate pathways. We show the performance of PaintOmics 4 on both mouse and plant data to highlight how these new analysis features provide novel insights into regulatory biology. PaintOmics 4 is available at https://paintomics.org/.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ugidos2022-sk,

title = {MultiBaC: An R package to remove batch effects in multi-omic  experiments},

author = {Manuel Ugidos and María José Nueda and José M Prats-Montalbán and Alberto Ferrer and Ana Conesa and Sonia Tarazona},

url = {https://watermark.silverchair.com/btac132.pdf?token=AQECAHi208BE49Ooan9kkhW_Ercy7Dm3ZL_9Cf3qfKAc485ysgAAAzEwggMtBgkqhkiG9w0BBwagggMeMIIDGgIBADCCAxMGCSqGSIb3DQEHATAeBglghkgBZQMEAS4wEQQMeEcUTCRMnmsoFyy8AgEQgIIC5JWHJW_tG0ZfXPRWz1anVh55AhxVg26g2g9wdqQAgT7LBtdVIlHfR_v5GbzIud725UlWMpSwL-oFFwiYCDSoGweumU1IH6_XhfgfUfI-AFBEuQDXTRYjtTpSoH1VlIXMsXd1OtVdfE6aj8zG1iNSSirVljWzpRdJfZolvD1GoqXOySVndzFgV4FEC2eHxbvABFV8bVpqO9T6QWxgwy_5qY1faQ9XUsywBxq3SbGV1uKhqrcSEOePoLYUIXCRLnYaIXfsbZIKxHd4JWHYSUPzHfgH-tSUTkCZjqfv0PI1DNj9vXhsHL0eMSEdtSc2Kdh1h06r7Y0ShpDcDzv1d77wtlX00r6npnlnVwv8XKJURx8kY_vkVOJO5XFPqyl4JQm4Nd6r0kvuBPJ9p0JUTpz5kJOxrtfcS96Ql5YPC8p-5qccBtVbWzaApqdubHm1o7D7z9X3rKA3053pPoQ8HuEsPqe7Keuoqvo1gpYbJICPDm7-raQj7YIwFS9iZBCAphwsp4MXpOhEKA23vBdpv4b_pMANVBHHq33WVFJjBneTeJliYFv_Ynk6W1KrbgTqel8f0mF9knfrOhftEB-Eod3uj0nrCkmB31jwlGC0A6jaF_mJ06WY7hekKmrAki07356jI2cc5VGyGGfD8uRvuBV2wPxXTlkZfq9vwLZbX9qNuhSg14aTUXvW89nbF4uNI3h8dowM7bvUV6Qdf2eabAoBg7cYervp5twQLlMHfSmcwMnvB4Oit4w9UD3xaed-osA1o6jYVCofUN0Qcq9oeeutC9NxYpmziEcVXu4Uz5aIgpakIaHcUvYHtySGrk85Pu9-CmrY-Ek6M3OXJHV7drvq_8dfKKrlj-5xDoulwdRjCwOYkLr88o-r38-QfEsanwmjEqFjZH93e0Rm3wNZVn1j1NRGLrdzclEldx_DXTd3vuh6jxv-CrtRxQ9pK-n73Kq4msmTKiHV6Ubg-qcYREbMZ1e4NpKp},

doi = {10.1093/bioinformatics/btac132},

year  = {2022},

date = {2022-03-01},

urldate = {2022-03-01},

journal = {Bioinformatics},

publisher = {Öxford University Press (OUP)},

abstract = {MOTIVATION: Batch effects in omics datasets are usually a source 

 of technical noise that masks the biological signal and hampers 

 data analysis. Batch effect removal has been widely addressed 

 for individual omics technologies. However, multi-omic datasets 

 may combine data obtained in different batches where omics type 

 and batch are often confounded. Moreover, systematic biases may 

 be introduced without notice during data acquisition, which 

 creates a hidden batch effect. Current methods fail to address 

 batch effect correction in these cases. RESULTS: In this paper 

 we introduce the MultiBaC R package, a tool for batch effect 

 removal in multi-omics and hidden batch effect scenarios. The 

 package includes a diversity of graphical outputs for model 

 validation and assessment of the batch effect correction. 

 AVAILABILITY: MultiBaC package is available on Bioconductor 

 (https://www.bioconductor.org/packages/release/bioc/html/MultiBaC.html) 

 and GitHub (https://github.com/ConesaLab/MultiBaC.git). 

 SUPPLEMENTARY INFORMATION: Supplementary data are available at 

 Bioinformatics online.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Miller2022-sz,

title = {Enhanced protein isoform characterization through long-read  proteogenomics},

author = {Rachel M Miller and Ben T Jordan and Madison M Mehlferber and Erin D Jeffery and Christina Chatzipantsiou and Simi Kaur and Robert J Millikin and Yunxiang Dai and Simone Tiberi and Peter J Castaldi and Michael R Shortreed and Chance John Luckey and Ana Conesa and Lloyd M Smith and Anne Deslattes Mays and Gloria M Sheynkman},

url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8892804/pdf/13059_2022_Article_2624.pdf},

doi = {10.1186/s13059-022-02624-y},

year  = {2022},

date = {2022-03-01},

urldate = {2022-03-01},

journal = {Genome Biol.},

volume = {23},

number = {1},

pages = {69},

publisher = {Springer Science and Business Media LLC},

abstract = {BACKGROUND: The detection of physiologically relevant protein 

 isoforms encoded by the human genome is critical to biomedicine. 

 Mass spectrometry (MS)-based proteomics is the preeminent method 

 for protein detection, but isoform-resolved proteomic analysis 

 relies on accurate reference databases that match the sample; 

 neither a subset nor a superset database is ideal. Long-read RNA 

 sequencing (e.g., PacBio or Oxford Nanopore) provides 

 full-length transcripts which can be used to predict full-length 

 protein isoforms. RESULTS: We describe here a long-read 

 proteogenomics approach for integrating sample-matched long-read 

 RNA-seq and MS-based proteomics data to enhance isoform 

 characterization. We introduce a classification scheme for 

 protein isoforms, discover novel protein isoforms, and present 

 the first protein inference algorithm for the direct 

 incorporation of long-read transcriptome data to enable 

 detection of protein isoforms previously intractable to MS-based 

 detection. We have released an open-source Nextflow pipeline 

 that integrates long-read sequencing in a proteomic workflow for 

 isoform-resolved analysis. CONCLUSIONS: Our work suggests that 

 the incorporation of long-read sequencing and proteomic data can 

 facilitate improved characterization of human protein isoform 

 diversity. Our first-generation pipeline provides a strong 

 foundation for future development of long-read proteogenomics 

 and its adoption for both basic and translational research.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}