biblio.bib

% Encoding: UTF-8

@Article{Lee2014-eterna100,
  author          = {Lee, Jeehyung and Kladwang, Wipapat and Lee, Minjae and Cantu, Daniel and Azizyan, Martin and Kim, Hanjoo and Limpaecher, Alex and Yoon, Sungroh and Treuille, Adrien and Das, Rhiju and EteRNA Participants},
  journal         = {Proceedings of the National Academy of Sciences of the United States of America},
  title           = {{RNA} design rules from a massive open laboratory},
  year            = {2014},
  issn            = {1091-6490},
  month           = feb,
  pages           = {2122--2127},
  volume          = {111},
  abstract        = {Self-assembling {RNA} molecules present compelling substrates for the rational interrogation and control of living systems. However, imperfect in silico models--even at the secondary structure level--hinder the design of new {RNA}s that function properly when synthesized. Here, we present a unique and potentially general approach to such empirical problems: the Massive Open Laboratory. The EteRNA project connects 37,000 enthusiasts to {RNA} design puzzles through an online interface. Uniquely, EteRNA participants not only manipulate simulated molecules but also control a remote experimental pipeline for high-throughput {RNA} synthesis and structure mapping. We show herein that the EteRNA community leveraged dozens of cycles of continuous wet laboratory feedback to learn strategies for solving in vitro {RNA} design problems on which automated methods fail. The top strategies--including several previously unrecognized negative design rules--were distilled by machine learning into an algorithm, EteRNABot. Over a rigorous 1-y testing phase, both the EteRNA community and EteRNABot significantly outperformed prior algorithms in a dozen {RNA} secondary structure design tests, including the creation of dendrimer-like structures and scaffolds for small molecule sensors. These results show that an online community can carry out large-scale experiments, hypothesis generation, and algorithm design to create practical advances in empirical science.},
  chemicals       = {RNA},
  citation-subset = {IM},
  completed       = {2014-05-15},
  country         = {United States},
  doi             = {10.1073/pnas.1313039111},
  issn-linking    = {0027-8424},
  keywords        = {Algorithms; Laboratories, organization & administration; Nucleic Acid Conformation; {RNA}, chemistry; Software; User-Computer Interface; {RNA} folding; citizen science; crowdsourcing; high-throughput experiments},
  nlm-id          = {7505876},
  owner           = {NLM},
  pii             = {1313039111},
  pmc             = {PMC3926058},
  pmid            = {24469816},
  pubmodel        = {Print-Electronic},
  pubstate        = {ppublish},
  revised         = {2018-11-13},
}

@article{Domin2017,
	author = {Domin, Gesine and Findei{\ss}, Sven and Wachsmuth, Manja and Will, Sebastian and Stadler, Peter F. and M{\ifmmode\ddot{o}\else\"{o}\fi}rl, Mario},
	title = {{Applicability of a computational design approach for synthetic riboswitches}},
	journal = {Nucleic Acids Res.},
	volume = {45},
	number = {7},
	pages = {4108},
	year = {2017},
	month = {Apr},
	publisher = {Oxford University Press},
	doi = {10.1093/nar/gkw1267}
}

@InProceedings{Yao2021,
	author = {Yao, Hua-Ting and Waldisp{\ifmmode\ddot{u}\else\"{u}\fi}hl, J{\ifmmode\acute{e}\else\'{e}\fi}r{\ifmmode\hat{o}\else\^{o}\fi}me and Ponty, Yann and Will, Sebastian},
	title = {{Taming Disruptive Base Pairs to Reconcile Positive and Negative Structural Design of RNA}},
	year = {2021},
	month = {Apr},
        booktitle = {Research in Computational Molecular Biology - 25nd Annual International Conference, {RECOMB} 2021},
}

@article{Andronescu2007,
	author = {Andronescu, Mirela and Condon, Anne and Hoos, Holger H. and Mathews, David H. and Murphy, Kevin P.},
	title = {{Efficient parameter estimation for RNA secondary structure prediction}},
	journal = {Bioinformatics},
	volume = {23},
	number = {13},
	pages = {i19--i28},
	year = {2007},
	month = {Jul},
	issn = {1367-4803},
	publisher = {Oxford Academic},
	doi = {10.1093/bioinformatics/btm223}
}

@article{Bodini2010,
	author = {Bodini, Olivier and Ponty, Yann},
	title = {{Multi-dimensional Boltzmann Sampling of Languages}},
	journal = {Discrete Mathematics and Theoretical Computer Science},
	volume = {DMTCS Proceedings vol. AM, 21st International Meeting on Probabilistic, Combinatorial, and Asymptotic Methods in the Analysis of Algorithms (AofA'10)},
	pages = {49--64},
	year = {2010},
	month = {Jun},
	publisher = {Discrete Mathematics and Theoretical Computer Science},
	url = {https://hal.archives-ouvertes.fr/hal-00450763}
}

@PhdThesis{YPonty2006,
  author              = {{Ponty}, {Yann}},
  title               = {{Models for structured genomic sequences, random generation and applications}},
  school              = {{Université Paris Sud - Paris XI}},
  year                = {2006},
  type                = {Theses},
  month               = Nov,
  hal_id              = {tel-00144130},
  hal_local_reference = {No d'ordre 8480},
  hal_version         = {v2},
  keywords            = {Models for random sequences ; {RNA} structure ; Context-free grammars ; Random generation ; Enumerative combinatorics ; Modèles de séquences aléatoires ; Structure de l'ARN ; Grammaires hors-contexte pondérées ; Génération aléatoire ; Combinatoire énumérative},
  pdf                 = {https://tel.archives-ouvertes.fr/tel-00144130/file/these-ponty.pdf},
  url                 = {https://tel.archives-ouvertes.fr/tel-00144130},
}

@Article{Barcucci1994,
  author    = {Barcucci, Elena and Pinzani, Renzo and Sprugnoli, Renzo},
  title     = {The random generation of directed animals},
  journal   = {Theoretical Computer Science},
  year      = {1994},
  volume    = {127},
  number    = {2},
  pages     = {333--350},
  publisher = {Elsevier},
}

@Article{Nicaud2010,
  author    = {Nicaud, Cyril and Gouyou-Beauchamps, Dominique},
  title     = {Random Generation Using Binomial Approximations},
  journal   = {Discrete Mathematics \& Theoretical Computer Science},
  year      = {2010},
  publisher = {Episciences. org},
}

@Article{Flajolet1987,
  author  = {Philippe Flajolet},
  title   = {Analytic models and ambiguity of context-free languages},
  journal = {Theoretical Computer Science},
  year    = {1987},
  volume  = {49},
  pages   = {283--309},
  issn    = {0304-3975},
  doi     = {10.1016/0304-3975(87)90011-9},
}

@Article{Denise1999,
  author   = {Alain Denise and Paul Zimmermann},
  title    = {Uniform random generation of decomposable structures using floating-point arithmetic},
  journal  = {Theoretical Computer Science},
  year     = {1999},
  volume   = {218},
  number   = {2},
  pages    = {233 - 248},
  issn     = {0304-3975},
  abstract = {The recursive method formalized by Nijenhuis and Wilf (1998) and systematized by Flajolet, Van Cutsem and Zimmermann (1994), is extended here to floating-point arithmetic. The resulting ADZ method enables one to generate decomposable data structures — both labelled or unlabelled — uniformly at random, in expected O(n1 + ε) time and space, after a preprocessing phase of O(n2 + ε) time, which reduces to O(n1 + ε) for context-free grammars.
Résumé
La méthode récursive mise au point par Nijenhuis et Wilf (1998) et systématisée par Flajolet, Van Cutsem et Zimmermann (1994), est ici étendue à l'utilisation de nombres flottants. La méthode qui en découle, appelée ADZ, permet de générer aléatoirement et uniformément des structures décomposables — étiquetées ou non — en temps et espace moyens O(n1 + ε), après un précalcul de complexité en temps O(n2 + ε), se réduisant à O(n1 + ε) pour des grammaires algébriques.},
  doi      = {https://doi.org/10.1016/S0304-3975(98)00323-5},
  url      = {http://www.sciencedirect.com/science/article/pii/S0304397598003235},
}

@Article{Mishna2009,
  author    = {Mishna, Marni and Rechnitzer, Andrew},
  title     = {Two non-holonomic lattice walks in the quarter plane},
  journal   = {Theoretical Computer Science},
  year      = {2009},
  volume    = {410},
  number    = {38-40},
  pages     = {3616--3630},
  publisher = {Elsevier},
}

@InProceedings{Bendkowski2018,
  author       = {Bendkowski, Maciej and Bodini, Olivier and Dovgal, Sergey},
  title        = {Polynomial tuning of multiparametric combinatorial samplers},
  booktitle    = {2018 Proceedings of the Fifteenth Workshop on Analytic Algorithmics and Combinatorics (ANALCO)},
  year         = {2018},
  pages        = {92--106},
  organization = {SIAM},
}

@Book{Nesterov1994,
  title     = {Interior-point polynomial algorithms in convex programming},
  publisher = {Siam},
  year      = {1994},
  author    = {Nesterov, Yurii and Nemirovskii, Arkadii},
  volume    = {13},
}

@Article{Duchon2004,
  author    = {Duchon, Philippe and Flajolet, Philippe and Louchard, Guy and Schaeffer, Gilles},
  title     = {Boltzmann samplers for the random generation of combinatorial structures},
  journal   = {Combinatorics, Probability and Computing},
  year      = {2004},
  volume    = {13},
  number    = {4-5},
  pages     = {577--625},
  publisher = {Cambridge University Press},
}

@Article{Altschul1985,
  author          = {Altschul, Stephen F and Erickson, Blake W},
  title           = {Significance of nucleotide sequence alignments: a method for random sequence permutation that preserves dinucleotide and codon usage.},
  journal         = {Molecular biology and evolution},
  year            = {1985},
  volume          = {2},
  pages           = {526--538},
  month           = nov,
  issn            = {0737-4038},
  abstract        = {The similarity of two nucleotide sequences is often expressed in terms of evolutionary distance, a measure of the amount of change needed to transform one sequence into the other. Given two sequences with a small distance between them, can their similarity be explained by their base composition alone? The nucleotide order of these sequences contributes to their similarity if the distance is much smaller than their average permutation distance, which is obtained by calculating the distances for many random permutations of these sequences. To determine whether their similarity can be explained by their dinucleotide and codon usage, random sequences must be chosen from the set of permuted sequences that preserve dinucleotide and codon usage. The problem of choosing random dinucleotide and codon-preserving permutations can be expressed in the language of graph theory as the problem of generating random Eulerian walks on a directed multigraph. An efficient algorithm for generating such walks is described. This algorithm can be used to choose random sequence permutations that preserve (1) dinucleotide usage, (2) dinucleotide and trinucleotide usage, or (3) dinucleotide and codon usage. For example, the similarity of two 60-nucleotide DNA segments from the human beta-1 interferon gene (nucleotides 196-255 and 499-558) is not just the result of their nonrandom dinucleotide and codon usage.},
  chemicals       = {Codon, Interferon Type I},
  citation-subset = {IM},
  completed       = {1988-06-20},
  country         = {United States},
  doi             = {10.1093/oxfordjournals.molbev.a040370},
  issn-linking    = {0737-4038},
  issue           = {6},
  keywords        = {Base Sequence; Biological Evolution; Codon, genetics; Humans; Interferon Type I, genetics; Models, Genetic; Molecular Sequence Data; Sequence Homology, Nucleic Acid},
  nlm-id          = {8501455},
  owner           = {NLM},
  pmid            = {3870875},
  pubmodel        = {Print},
  pubstatus       = {ppublish},
  revised         = {2018-01-09},
}

@Article{Hurst2001,
  author          = {Hurst, L D and Merchant, A R},
  title           = {High guanine-cytosine content is not an adaptation to high temperature: a comparative analysis amongst prokaryotes.},
  journal         = {Proceedings. Biological sciences},
  year            = {2001},
  volume          = {268},
  pages           = {493--497},
  month           = mar,
  issn            = {0962-8452},
  abstract        = {The causes of the variation between genomes in their guanine (G) and cytosine (C) content is one of the central issues in evolutionary genomics. The thermal adaptation hypothesis conjectures that, as G:C pairs in DNA are more thermally stable than adenonine:thymine pairs, high GC content may he a selective response to high temperature. A compilation of data on genomic GC content and optimal growth temperature for numerous prokaryotes failed to demonstrate the predicted correlation. By contrast, the GC content of Structural {RNA}s is higher at high temperatures. The issue that we address here is whether more freely evolving sites in exons (i.e. codonic third positions) evolve in the same manner as genomic DNA as a whole, Showing no correlated response, or like structural {RNA}s showing a strong correlation. The latter pattern would provide strong support for the thermal adaptation hypothesis, as the variation in GC content between orthologous genes is typically most profoundly seen at codon third sites (GC3). Simple analysis of completely sequenced prokaryotic genomes shows that GC3, but not genomic GC, is higher on average in thermophilic species. This demonstrates, if nothing else, that the results from the two measures cannot be presumed to be the same. A proper analysis, however, requires phylogenetic control. Here, therefore, we report the results of a comparative analysis of GC composition and optimal growth temperature for over 100 prokaryotes. Comparative analysis fails to show, in either Archea or Eubacteria, any hint of connection between optimal growth temperature and GC content in the genome as a whole, in protein-coding regions or, more crucially at GC. Conversely, comparable analysis confirms that GC content of structural {RNA} is strongly correlated with optimal temperature. Against the expectations of the thermal adaptation hypothesis, within prokaryotes GC content in protein-coding genies, even at relatively freely evolving sites, cannot be considered an adaptation to the thermal environment.},
  chemicals       = {DNA, Archaeal, DNA, Bacterial},
  citation-subset = {IM},
  completed       = {2001-06-28},
  country         = {England},
  doi             = {10.1098/rspb.2000.1397},
  issn-linking    = {0962-8452},
  issue           = {1466},
  keywords        = {Adaptation, Physiological; Archaea, chemistry, genetics; Bacteria, chemistry, genetics; Base Composition; DNA, Archaeal, chemistry, genetics; DNA, Bacterial, chemistry, genetics; Evolution, Molecular; Genetic Variation; Prokaryotic Cells; Temperature},
  nlm-id          = {101245157},
  owner           = {NLM},
  pmc             = {PMC1088632},
  pmid            = {11296861},
  pubmodel        = {Print},
  pubstatus       = {ppublish},
  revised         = {2018-11-13},
}

@Article{Hildebrand2010,
  author          = {Hildebrand, Falk and Meyer, Axel and Eyre-Walker, Adam},
  title           = {Evidence of selection upon genomic GC-content in bacteria.},
  journal         = {PLoS genetics},
  year            = {2010},
  volume          = {6},
  pages           = {e1001107},
  month           = sep,
  issn            = {1553-7404},
  abstract        = {The genomic GC-content of bacteria varies dramatically, from less than 20% to more than 70%. This variation is generally ascribed to differences in the pattern of mutation between bacteria. Here we test this hypothesis by examining patterns of synonymous polymorphism using datasets from 149 bacterial species. We find a large excess of synonymous GC→AT mutations over AT→GC mutations segregating in all but the most AT-rich bacteria, across a broad range of phylogenetically diverse species. We show that the excess of GC→AT mutations is inconsistent with mutation bias, since it would imply that most GC-rich bacteria are declining in GC-content; such a pattern would be unsustainable. We also show that the patterns are probably not due to translational selection or biased gene conversion, because optimal codons tend to be AT-rich, and the excess of GC→AT SNPs is observed in datasets with no evidence of recombination. We therefore conclude that there is selection to increase synonymous GC-content in many species. Since synonymous GC-content is highly correlated to genomic GC-content, we further conclude that there is selection on genomic base composition in many bacteria.},
  citation-subset = {IM},
  completed       = {2011-01-04},
  country         = {United States},
  doi             = {10.1371/journal.pgen.1001107},
  issn-linking    = {1553-7390},
  issue           = {9},
  keywords        = {Bacteria, classification, genetics; Base Composition, genetics; Bias; Genome, Bacterial, genetics; Models, Genetic; Mutation, genetics; Polymorphism, Single Nucleotide, genetics; Protein Biosynthesis, genetics; Selection, Genetic},
  nlm-id          = {101239074},
  owner           = {NLM},
  pii             = {e1001107},
  pmc             = {PMC2936529},
  pmid            = {20838593},
  pubmodel        = {Electronic},
  pubstatus       = {epublish},
  revised         = {2018-11-13},
}

@Article{Clote2005,
  author          = {Clote, Peter and Ferré, Fabrizio and Kranakis, Evangelos and Krizanc, Danny},
  title           = {Structural {RNA} has lower folding energy than random {RNA} of the same dinucleotide frequency.},
  journal         = {{RNA} (New York, N.Y.)},
  year            = {2005},
  volume          = {11},
  pages           = {578--591},
  month           = may,
  issn            = {1355-8382},
  abstract        = {We present results of computer experiments that indicate that several {RNA}s for which the native state (minimum free energy secondary structure) is functionally important (type III hammerhead ribozymes, signal recognition particle {RNA}s, U2 small nucleolar spliceosomal {RNA}s, certain riboswitches, etc.) all have lower folding energy than random {RNA}s of the same length and dinucleotide frequency. Additionally, we find that whole m{RNA} as well as 5'-UTR, 3'-UTR, and cds regions of m{RNA} have folding energies comparable to that of random {RNA}, although there may be a statistically insignificant trace signal in 3'-UTR and cds regions. Various authors have used nucleotide (approximate) pattern matching and the computation of minimum free energy as filters to detect potential {RNA}s in ESTs and genomes. We introduce a new concept of the asymptotic Z-score and describe a fast, whole-genome scanning algorithm to compute asymptotic minimum free energy Z-scores of moving-window contents. Asymptotic Z-score computations offer another filter, to be used along with nucleotide pattern matching and minimum free energy computations, to detect potential functional {RNA}s in ESTs and genomic regions.},
  chemicals       = {3' Untranslated Regions, 5' Untranslated Regions, Nucleotides, {RNA}},
  citation-subset = {IM},
  completed       = {2005-05-24},
  country         = {United States},
  doi             = {10.1261/rna.7220505},
  issn-linking    = {1355-8382},
  issue           = {5},
  keywords        = {3' Untranslated Regions, chemistry, genetics, metabolism; 5' Untranslated Regions, chemistry, genetics, metabolism; Algorithms; Base Composition; Base Sequence; Computational Biology; Computer Simulation; Expressed Sequence Tags; Markov Chains; Nucleic Acid Conformation; Nucleotides, analysis, chemistry, genetics, metabolism; {RNA}, chemistry, genetics, metabolism; Thermodynamics},
  nlm-id          = {9509184},
  owner           = {NLM},
  pii             = {11/5/578},
  pmc             = {PMC1370746},
  pmid            = {15840812},
  pubmodel        = {Print},
  pubstatus       = {ppublish},
  revised         = {2018-11-13},
}

@Article{Denise1996,
  author  = {Alain Denise},
  title   = {Génération aléatoire et uniforme de mots},
  journal = {Discrete Mathematics},
  year    = {1996},
  volume  = {156},
  pages   = {69--84},
}

@InProceedings{Viennot1985,
  author    = {Viennot, G. and Vauchaussade de Chaumont, M.},
  title     = {Enumeration of {RNA} Secondary Structures by Complexity},
  booktitle = {Mathematics in Biology and Medicine},
  year      = {1985},
  editor    = {Capasso, V. and Grosso, E. and Paveri-Fontana, S. L.},
  pages     = {360--365},
  address   = {Berlin, Heidelberg},
  publisher = {Springer Berlin Heidelberg},
  abstract  = {Many investigations in studying primary and secondary structures in Biology require theoretical statistical (that is enumerative) work. We solve one of these problems: enumerate secondary structures of single-stranded nucleic acids ({RNA}, t{RNA}, etc{\ldots}) having a given complexity. This parameter has been introduced for energy computation purpose in order to predict the most stable secondary structure. The method relies on the (non-classical) use of non-commutative variables. Some orthogonal polynomials appear. The final solution shows a relationship between the parameter complexity and another parameter appearing in Hydrography and Botanic.},
  isbn      = {978-3-642-93287-8},
}

@Article{Hofacker1998,
  author    = {Hofacker, Ivo L and Schuster, Peter and Stadler, Peter F},
  title     = {Combinatorics of {RNA} secondary structures},
  journal   = {Discrete Applied Mathematics},
  year      = {1998},
  volume    = {88},
  number    = {1-3},
  pages     = {207--237},
  publisher = {Elsevier},
}

@Article{Zuker1984,
  author    = {Zuker, Michael and Sankoff, David},
  title     = {{{RNA}} secondary structures and their prediction},
  journal   = {Bulletin of mathematical biology},
  year      = {1984},
  volume    = {46},
  number    = {4},
  pages     = {591--621},
  publisher = {Springer},
}

@Article{Nebel2002,
  author   = {Nebel, Markus E.},
  title    = {Combinatorial Properties of {RNA} Secondary Structures},
  journal  = {Journal of Computational Biology},
  year     = {2002},
  volume   = {9},
  number   = {3},
  pages    = {541-573},
  note     = {PMID: 12162892},
  abstract = { The secondary structure of an {RNA} molecule is of great importance and possesses influence, e.g., on the interaction of t{RNA} molecules with proteins or on the stabilization of m{RNA} molecules. The classification of secondary structures by means of their order proved useful with respect to numerous applications. In 1978, Waterman, who gave the first precise formal framework for the topic, suggested to determine the number an,p of secondary structures of size n and given order p. Since then, no satisfactory result has been found. Based on an observation due to Viennot et al., we will derive generating functions for the secondary structures of order p from generating functions for binary tree structures with Horton-Strahler number p. These generating functions enable us to compute a precise asymptotic equivalent for an,p. Furthermore, we will determine the related number of structures when the number of unpaired bases shows up as an additional parameter. Our approach proves to be general enough to compute the average order of a secondary structure together with all the r-th moments and to enumerate substructures such as hairpins or bulges in dependence on the order of the secondary structures considered. },
  doi      = {10.1089/106652702760138628},
  eprint   = {https://doi.org/10.1089/106652702760138628},
  url      = { 
        https://doi.org/10.1089/106652702760138628
    
},
}

@Article{Bundschuh2002,
  author          = {Bundschuh, Ralf and Hwa, Terence},
  title           = {Statistical mechanics of secondary structures formed by random {RNA} sequences.},
  journal         = {Physical review. E, Statistical, nonlinear, and soft matter physics},
  year            = {2002},
  volume          = {65},
  pages           = {031903},
  month           = mar,
  issn            = {1539-3755},
  abstract        = {The formation of secondary structures by a random {RNA} sequence is studied as a model system for the sequence-structure problem omnipresent in biopolymers. Several toy energy models are introduced to allow detailed analytical and numerical studies. First, a two-replica calculation is performed. By mapping the two-replica problem to the denaturation of a single homogeneous {RNA} molecule in six-dimensional embedding space, we show that sequence disorder is perturbatively irrelevant, i.e., an {RNA} molecule with weak sequence disorder is in a molten phase where many secondary structures with comparable total energy coexist. A numerical study of various models at high temperature reproduces behaviors characteristic of the molten phase. On the other hand, a scaling argument based on the external statistics of rare regions can be constructed to show that the low-temperature phase is unstable to sequence disorder. We performed a detailed numerical study of the low-temperature phase using the droplet theory as a guide, and characterized the statistics of large-scale, low-energy excitations of the secondary structures from the ground state structure. We find the excitation energy to grow very slowly (i.e., logarithmically) with the length scale of the excitation, suggesting the existence of a marginal glass phase. The transition between the low-temperature glass phase and the high-temperature molten phase is also characterized numerically. It is revealed by a change in the coefficient of the logarithmic excitation energy, from being disorder dominated to being entropy dominated.},
  chemicals       = {{RNA}},
  citation-subset = {IM},
  completed       = {2002-06-10},
  country         = {United States},
  doi             = {10.1103/PhysRevE.65.031903},
  issn-linking    = {1539-3755},
  issue           = {3 Pt 1},
  keywords        = {Biophysics, methods; Glass; Models, Statistical; Nucleic Acid Conformation; {RNA}, chemistry; Temperature},
  nlm-id          = {101136452},
  owner           = {NLM},
  pmid            = {11909105},
  pubmodel        = {Print-Electronic},
  pubstatus       = {ppublish},
  revised         = {2006-11-15},
}

@Article{Bundschuh2002a,
  author    = {Bundschuh, Ralf and Hwa, Terence},
  title     = {Phases of the secondary structures of {RNA} sequences},
  journal   = {EPL (Europhysics Letters)},
  year      = {2002},
  volume    = {59},
  number    = {6},
  pages     = {903},
  publisher = {IOP Publishing},
}

@Article{Bundschuh2008,
  author    = {Bundschuh, Ralf and Bruinsma, Robijn},
  title     = {Melting of branched {RNA} molecules},
  journal   = {Physical review letters},
  year      = {2008},
  volume    = {100},
  number    = {14},
  pages     = {148101},
  publisher = {APS},
}

@Article{David2007,
  author    = {David, Francois and Wiese, Kay Joerg},
  title     = {Systematic field theory of the {RNA} glass transition},
  journal   = {Physical review letters},
  year      = {2007},
  volume    = {98},
  number    = {12},
  pages     = {128102},
  publisher = {APS},
}

@Article{Bundschuh1999,
  author    = {Bundschuh, Ralf and Hwa, Terence},
  title     = {{RNA} Secondary Structure Formation: A Solvable Model of Heteropolymer Folding},
  journal   = {Phys. Rev. Lett.},
  year      = {1999},
  volume    = {83},
  pages     = {1479--1482},
  month     = {Aug},
  doi       = {10.1103/PhysRevLett.83.1479},
  issue     = {7},
  numpages  = {0},
  publisher = {American Physical Society},
  url       = {https://link.aps.org/doi/10.1103/PhysRevLett.83.1479},
}

@Article{Jin2008,
  author          = {Jin, Emma Y and Reidys, Christian M},
  title           = {Asymptotic enumeration of {RNA} structures with pseudoknots.},
  journal         = {Bulletin of mathematical biology},
  year            = {2008},
  volume          = {70},
  pages           = {951--970},
  month           = may,
  issn            = {0092-8240},
  abstract        = {In this paper, we present the asymptotic enumeration of {RNA} structures with pseudoknots. We develop a general framework for the computation of exponential growth rate and the asymptotic expansion for the numbers of k-noncrossing {RNA} structures. Our results are based on the generating function for the number of k-noncrossing {RNA} pseudoknot structures, Sk(n), derived in Bull. Math. Biol. (2008), where k-1 denotes the maximal size of sets of mutually intersecting bonds. We prove a functional equation for the generating function Sigman>or=0 Sk(n)zn and obtain for k=2 and k=3, the analytic continuation and singular expansions, respectively. It is implicit in our results that for arbitrary k singular expansions exist and via transfer theorems of analytic combinatorics, we obtain asymptotic expression for the coefficients. We explicitly derive the asymptotic expressions for 2- and 3-noncrossing {RNA} structures. Our main result is the derivation of the formula S3(n) approximately 10.4724.4!/n(n-1)...(n-4)(5+[sqrt]21/2)n.},
  chemicals       = {{RNA}},
  citation-subset = {IM},
  completed       = {2008-06-23},
  country         = {United States},
  doi             = {10.1007/s11538-007-9265-2},
  issn-linking    = {0092-8240},
  issue           = {4},
  keywords        = {Mathematics; Models, Molecular; Nucleic Acid Conformation; {RNA}, chemistry},
  nlm-id          = {0401404},
  owner           = {NLM},
  pmid            = {18340497},
  pubmodel        = {Print-Electronic},
  pubstatus       = {ppublish},
  revised         = {2008-04-04},
}

@Article{Huang2008,
  author          = {Huang, Fenix W D and Reidys, Christian M},
  title           = {Statistics of canonical {RNA} pseudoknot structures.},
  journal         = {Journal of theoretical biology},
  year            = {2008},
  volume          = {253},
  pages           = {570--578},
  month           = aug,
  issn            = {1095-8541},
  abstract        = {In this paper we study canonical {RNA} pseudoknot structures. We prove central limit theorems for the distributions of the arc-numbers of k-noncrossing {RNA} structures with given minimum stack-size tau over n nucleotides. Furthermore we compare the space of all canonical structures with canonical minimum free energy pseudoknot structures. Our results generalize the analysis of Schuster et al. obtained for {RNA} secondary structures [Hofacker, I.L., Schuster, P., Stadler, P.F., 1998. Combinatorics of {RNA} secondary structures. Discrete Appl. Math. 88, 207-237; Jin, E.Y., Reidys, C.M., 2007b. Central and local limit theorems for {RNA} structures. J. Theor. Biol. 250 (2008), 547-559; 2007a. Asymptotic enumeration of {RNA} structures with pseudoknots. Bull. Math. Biol., 70 (4), 951-970] to k-noncrossing {RNA} structures. Here k2 and tau are arbitrary natural numbers. We compare canonical pseudoknot structures to arbitrary structures and show that canonical pseudoknot structures exhibit significantly smaller exponential growth rates. We then compute the asymptotic distribution of their arc-numbers. Finally, we analyze how the minimum stack-size and crossing number factor into the distributions.},
  chemicals       = {{RNA}},
  citation-subset = {IM},
  completed       = {2008-09-04},
  country         = {England},
  doi             = {10.1016/j.jtbi.2008.04.002},
  issn-linking    = {0022-5193},
  issue           = {3},
  keywords        = {Algorithms; Animals; Models, Genetic; Models, Molecular; Nucleic Acid Conformation; {RNA}, genetics},
  nlm-id          = {0376342},
  owner           = {NLM},
  pii             = {S0022-5193(08)00176-8},
  pmid            = {18511081},
  pubmodel        = {Print-Electronic},
  pubstatus       = {ppublish},
  revised         = {2008-07-18},
}

@Article{Clote2006,
  author          = {Clote, Peter},
  title           = {Combinatorics of saturated secondary structures of {RNA}.},
  journal         = {Journal of computational biology : a journal of computational molecular cell biology},
  year            = {2006},
  volume          = {13},
  pages           = {1640--1657},
  month           = nov,
  issn            = {1066-5277},
  abstract        = {Following Zuker (1986), a saturated secondary structure for a given {RNA} sequence is a secondary structure such that no base pair can be added without violating the definition of secondary structure, e.g., without introducing a pseudoknot. In the Nussinov-Jacobson energy model (Nussinov and Jacobson, 1980), where the energy of a secondary structure is -1 times the number of base pairs, saturated secondary structures are local minima in the energy landscape, hence form kinetic traps during the folding process. Here we present recurrence relations and closed form asymptotic limits for combinatorial problems related to the number of saturated secondary structures. In addition, Python source code to compute the number of saturated secondary structures having k base pairs can be found at the web servers link of bioinformatics.bc.edu/clotelab/.},
  chemicals       = {{RNA}},
  citation-subset = {IM},
  completed       = {2007-01-12},
  country         = {United States},
  doi             = {10.1089/cmb.2006.13.1640},
  issn-linking    = {1066-5277},
  issue           = {9},
  keywords        = {Base Pairing; Base Sequence; Biometry; Kinetics; Models, Molecular; Models, Statistical; Nucleic Acid Conformation; {RNA}, chemistry, genetics; Thermodynamics},
  nlm-id          = {9433358},
  owner           = {NLM},
  pmid            = {17147486},
  pubmodel        = {Print},
  pubstatus       = {ppublish},
  revised         = {2006-12-06},
}

@Article{Banderier2015,
  author    = {Banderier, Cyril and Drmota, Michael},
  title     = {Formulae and Asymptotics for Coefficients of Algebraic Functions},
  journal   = {Combinatorics, Probability and Computing},
  year      = {2015},
  volume    = {24},
  number    = {1},
  pages     = {1–53},
  doi       = {10.1017/S0963548314000728},
  publisher = {Cambridge University Press},
}

@Article{Pringsheim1893,
  author  = {A. Pringsheim},
  title   = {Zur Theorie der Taylor'schen Reihe unde der analytischen Funcktionen mit beschränklen Existenzbereich},
  journal = {Mathematische Annalen},
  year    = {1893},
  volume  = {42},
  pages   = {180},
}

@Article{Flajolet1990,
  author    = {Philippe Flajolet and Andrew M. Odlyzko},
  title     = {Singularity Analysis of Generating Functions},
  journal   = {{SIAM} J. Discrete Math.},
  year      = {1990},
  volume    = {3},
  number    = {2},
  pages     = {216--240},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  biburl    = {https://dblp.org/rec/bib/journals/siamdm/FlajoletO90},
  doi       = {10.1137/0403019},
  timestamp = {Fri, 26 May 2017 22:54:48 +0200},
  url       = {https://doi.org/10.1137/0403019},
}

@Article{Lalley1993,
  author    = {Lalley, Steven P},
  title     = {Finite range random walk on free groups and homogeneous trees},
  journal   = {The Annals of Probability},
  year      = {1993},
  pages     = {2087--2130},
  publisher = {JSTOR},
}

@Article{Woods1997,
  author    = {Woods, Alan R},
  title     = {Coloring rules for finite trees, and probabilities of monadic second order sentences},
  journal   = {Random Structures \& Algorithms},
  year      = {1997},
  volume    = {10},
  number    = {4},
  pages     = {453--485},
  publisher = {Wiley Online Library},
}

@Article{Akutsu2000,
  author   = {Tatsuya Akutsu},
  title    = {Dynamic programming algorithms for {RNA} secondary structure prediction with pseudoknots},
  journal  = {Discrete Applied Mathematics},
  year     = {2000},
  volume   = {104},
  number   = {1},
  pages    = {45 - 62},
  issn     = {0166-218X},
  abstract = {This paper shows simple dynamic programming algorithms for {RNA} secondary structure prediction with pseudoknots. For a basic version of the problem (i.e., maximizing the number of base pairs), this paper presents an O(n4) time exact algorithm and an O(n4−δ) time approximation algorithm. The latter one outputs, for most {RNA} sequences, a secondary structure in which the number of base pairs is at least 1−ε of the optimal, where ε,δ are any constants satisfying 0<ε,δ<1. Several related results are shown too.},
  doi      = {https://doi.org/10.1016/S0166-218X(00)00186-4},
  keywords = {{RNA} secondary structure, Pseudoknot, Approximation algorithms, Computational biology, Dynamic programming},
  url      = {http://www.sciencedirect.com/science/article/pii/S0166218X00001864},
}

@Article{Leontis2001,
  author    = {Leontis, Neocles B and Westhof, Eric},
  title     = {Geometric nomenclature and classification of {{RNA}} base pairs},
  journal   = {{{RNA}}},
  year      = {2001},
  volume    = {7},
  number    = {4},
  pages     = {499--512},
  publisher = {Cambridge University Press},
}

@Article{Yoffe2011,
  author          = {Yoffe, Aron M and Prinsen, Peter and Gelbart, William M and Ben-Shaul, Avinoam},
  title           = {The ends of a large {RNA} molecule are necessarily close.},
  journal         = {Nucleic acids research},
  year            = {2011},
  volume          = {39},
  pages           = {292--299},
  month           = jan,
  issn            = {1362-4962},
  abstract        = {We show on general theoretical grounds that the two ends of single-stranded (ss) {RNA} molecules (consisting of roughly equal proportions of A, C, G and U) are necessarily close together, largely independent of their length and sequence. This is demonstrated to be a direct consequence of two generic properties of the equilibrium secondary structures, namely that the average proportion of bases in pairs is ∼60% and that the average duplex length is ∼4. Based on mfold and Vienna computations on large numbers of ss{RNA}s of various lengths (1000-10 000 nt) and sequences (both random and biological), we find that the 5'-3' distance-defined as the sum of H-bond and covalent (ss) links separating the ends of the {RNA} chain-is small, averaging 15-20 for each set of viral sequences tested. For random sequences this distance is ∼12, consistent with the theory. We discuss the relevance of these results to evolved sequence complementarity and specific protein binding effects that are known to be important for keeping the two ends of viral and messenger {RNA}s in close proximity. Finally we speculate on how our conclusions imply indistinguishability in size and shape of equilibrated forms of linear and covalently circularized ss{RNA} molecules.},
  chemicals       = {{RNA}, Circular, {RNA}, Viral, {RNA}},
  citation-subset = {IM},
  completed       = {2011-02-09},
  country         = {England},
  doi             = {10.1093/nar/gkq642},
  issn-linking    = {0305-1048},
  issue           = {1},
  keywords        = {Models, Molecular; Nucleic Acid Conformation; {RNA}, chemistry; {RNA}, Circular; {RNA}, Viral, chemistry},
  nlm-id          = {0411011},
  owner           = {NLM},
  pii             = {gkq642},
  pmc             = {PMC3017586},
  pmid            = {20810537},
  pubmodel        = {Print-Electronic},
  pubstatus       = {ppublish},
  revised         = {2019-12-10},
}

@Article{Wells1998,
  author          = {Wells, S E and Hillner, P E and Vale, R D and Sachs, A B},
  title           = {Circularization of m{RNA} by eukaryotic translation initiation factors.},
  journal         = {Molecular cell},
  year            = {1998},
  volume          = {2},
  pages           = {135--140},
  month           = jul,
  issn            = {1097-2765},
  abstract        = {Communication between the 5' cap structure and 3' poly(A) tail of eukaryotic m{RNA} results in the synergistic enhancement of translation. The cap and poly(A) tail binding proteins, eIF4E and Pab1p, mediate this effect in the yeast S. cerevisiae through their interactions with different parts of the translation factor eIF4G. Here, we demonstrate the reconstitution of an eIF4E/eIF4G/Pab1p complex with recombinant proteins, and show by atomic force microscopy that the complex can circularize capped, polyadenylated {RNA}. Our results suggest that formation of circular m{RNA} by translation factors could contribute to the control of m{RNA} expression in the eukaryotic cell.},
  chemicals       = {EIF4G1 protein, human, Eukaryotic Initiation Factor-4E, Eukaryotic Initiation Factor-4G, Fungal Proteins, Macromolecular Substances, Peptide Fragments, Peptide Initiation Factors, Poly(A)-Binding Proteins, {RNA}, Circular, {RNA}, Fungal, {RNA}, Messenger, {RNA}-Binding Proteins, Recombinant Fusion Proteins, Saccharomyces cerevisiae Proteins, TIF4631 protein, S cerevisiae, {RNA}, Glutathione Transferase},
  citation-subset = {IM},
  completed       = {1998-08-31},
  country         = {United States},
  doi             = {10.1016/s1097-2765(00)80122-7},
  issn-linking    = {1097-2765},
  issue           = {1},
  keywords        = {Eukaryotic Initiation Factor-4E; Eukaryotic Initiation Factor-4G; Fungal Proteins, metabolism; Glutathione Transferase, genetics, metabolism; Macromolecular Substances; Microscopy, Atomic Force; Nucleic Acid Conformation; Peptide Fragments, genetics, metabolism; Peptide Initiation Factors, genetics, metabolism, ultrastructure; Poly(A)-Binding Proteins; Protein Biosynthesis; {RNA}, biosynthesis, ultrastructure; {RNA}, Circular; {RNA}, Fungal, chemistry, metabolism, ultrastructure; {RNA}, Messenger, chemistry, metabolism, ultrastructure; {RNA}-Binding Proteins, metabolism, ultrastructure; Recombinant Fusion Proteins, metabolism; Saccharomyces cerevisiae, genetics; Saccharomyces cerevisiae Proteins},
  nlm-id          = {9802571},
  owner           = {NLM},
  pii             = {S1097-2765(00)80122-7},
  pmid            = {9702200},
  pubmodel        = {Print},
  pubstatus       = {ppublish},
  revised         = {2019-12-10},
}

@Article{Albert2002,
  author  = {Albert, R. AND Barab{\'a}si, A.-L.},
  title   = {Statistical mechanics of complex networks},
  journal = {Reviews of modern {P}hysics},
  year    = {2002},
  volume  = {74},
  pages   = {47--97},
}

@Article{Bowman2010,
  author  = {Bowman, G. R. AND Pande, V. S.},
  title   = {Protein folded states are kinetic hubs.},
  journal = {Proc. Natl. Acad. Sci. U.S.A.},
  year    = {2010},
  volume  = {107},
  number  = {24},
  pages   = {10890--10895},
  month   = {June},
}

@Article{Scala2001,
  author  = {Scala, A. AND Nunes~Amaral, L.A. AND Barth{\'e}l{\'e}my, M.},
  title   = {Small-world networks and the conformation space of a short lattice polymer chain},
  journal = {Europhys. Lett.},
  year    = {2001},
  volume  = {55},
  number  = {4},
  pages   = {594--600},
}

@Article{VanNoort2004,
  author  = {Van Noort, V. AND Snel, B. AND Huynen, M. A.},
  title   = {The yeast coexpression network has a small-world, scale-free architecture and can be explained by a simple model.},
  journal = {EMBO Rep.},
  year    = {2004},
  volume  = {5},
  number  = {3},
  pages   = {280--284},
  month   = {March},
}

@Article{Watts1998,
  author  = {Watts, D. J. AND Strogatz, S. H.},
  title   = {Collective dynamics of 'small-world' networks.},
  journal = {Nature},
  year    = {1998},
  volume  = {393},
  number  = {6684},
  pages   = {440--442},
  month   = {June},
}

@Article{Wuchty2003,
  author  = {Wuchty, S.},
  title   = {Small worlds in {{RNA}} structures.},
  journal = {Nucleic. Acids. Res.},
  year    = {2003},
  volume  = {31},
  number  = {3},
  pages   = {1108--1117},
  month   = {February},
}

@Article{Newman2001,
  author  = {Newman, M. E. AND Strogatz, S. H. AND Watts, D. J.},
  title   = {Random graphs with arbitrary degree distributions and their applications.},
  journal = {Phys. Rev. E},
  year    = {2001},
  volume  = {64},
  number  = {2},
  pages   = {026118},
  month   = {August},
}

@Article{Flamm2000,
  author  = {C. Flamm and W. Fontana and I.L. Hofacker and P. Schuster},
  title   = {{{RNA}} folding at elementary step resolution},
  journal = {{RNA}},
  year    = {2000},
  volume  = {6},
  pages   = {325--338},
}

@Article{Cont2008,
  author  = {Cont, R. AND Tanimura, E.},
  title   = {Small-world graphs: characterization and alternative constructions},
  journal = {Adv. in Appl. Probab.},
  year    = {2008},
  volume  = {40},
  number  = {4},
  pages   = {939--965},
}

@Article{Clote2015,
  author          = {Clote, Peter},
  title           = {Expected degree for {RNA} secondary structure networks.},
  journal         = {Journal of computational chemistry},
  year            = {2015},
  volume          = {36},
  pages           = {103--117},
  month           = jan,
  issn            = {1096-987X},
  abstract        = {Consider the network of all secondary structures of a given {RNA} sequence, where nodes are connected when the corresponding structures have base pair distance one. The expected degree of the network is the average number of neighbors, where average may be computed with respect to the either the uniform or Boltzmann probability. Here, we describe the first algorithm, {RNA}expNumNbors, that can compute the expected number of neighbors, or expected network degree, of an input sequence. For {RNA} sequences from the Rfam database, the expected degree is significantly less than the constrained minimum free energy structure, defined to have minimum free energy (MFE) over all structures consistent with the Rfam consensus structure. The expected degree of structural {RNA}s, such as purine riboswitches, paradoxically appears to be smaller than that of random {RNA}, yet the difference between the degree of the MFE structure and the expected degree is larger than that of random {RNA}. Expected degree does not seem to correlate with standard structural diversity measures of {RNA}, such as positional entropy and ensemble defect. The program {RNA}expNumNbors is written in C, runs in cubic time and quadratic space, and is publicly available at http://bioinformatics.bc.edu/clotelab/{RNA}expNumNbors.},
  chemicals       = {{RNA}},
  citation-subset = {IM},
  completed       = {2015-10-28},
  country         = {United States},
  doi             = {10.1002/jcc.23776},
  issn-linking    = {0192-8651},
  issue           = {2},
  keywords        = {Algorithms; Base Sequence; Databases, Factual; Nucleic Acid Conformation; {RNA}, chemistry; Software; Thermodynamics; {RNA} secondary structure; macromolecular network; network degree; small-world},
  nlm-id          = {9878362},
  owner           = {NLM},
  pmid            = {25382310},
  pubmodel        = {Print-Electronic},
  pubstatus       = {ppublish},
  revised         = {2014-12-16},
}

@Article{Andronescu2008,
  author          = {Andronescu, Mirela and Bereg, Vera and Hoos, Holger H and Condon, Anne},
  title           = {{RNA} STRAND: the {RNA} secondary structure and statistical analysis database.},
  journal         = {BMC bioinformatics},
  year            = {2008},
  volume          = {9},
  pages           = {340},
  month           = aug,
  issn            = {1471-2105},
  abstract        = {The ability to access, search and analyse secondary structures of a large set of known {RNA} molecules is very important for deriving improved {RNA} energy models, for evaluating computational predictions of {RNA} secondary structures and for a better understanding of {RNA} folding. Currently there is no database that can easily provide these capabilities for almost all {RNA} molecules with known secondary structures. In this paper we describe {RNA} STRAND - the {RNA} secondary STRucture and statistical ANalysis Database, a curated database containing known secondary structures of any type and organism. Our new database provides a wide collection of known {RNA} secondary structures drawn from public databases, searchable and downloadable in a common format. Comprehensive statistical information on the secondary structures in our database is provided using the {RNA} Secondary Structure Analyser, a new tool we have developed to analyse {RNA} secondary structures. The information thus obtained is valuable for understanding to which extent and with which probability certain structural motifs can appear. We outline several ways in which the data provided in {RNA} STRAND can facilitate research on {RNA} structure, including the improvement of {RNA} energy models and evaluation of secondary structure prediction programs. In order to keep up-to-date with new {RNA} secondary structure experiments, we offer the necessary tools to add solved {RNA} secondary structures to our database and invite researchers to contribute to {RNA} STRAND. {RNA} STRAND is a carefully assembled database of trusted {RNA} secondary structures, with easy on-line tools for searching, analyzing and downloading user selected entries, and is publicly available at http://www.rnasoft.ca/strand.},
  chemicals       = {{RNA}},
  citation-subset = {IM},
  completed       = {2008-10-17},
  country         = {England},
  doi             = {10.1186/1471-2105-9-340},
  issn-linking    = {1471-2105},
  keywords        = {Computer Graphics; Computer Simulation; Database Management Systems; Databases, Genetic; Information Storage and Retrieval, methods; Models, Chemical; Models, Molecular; Nucleic Acid Conformation; {RNA}, chemistry, ultrastructure; User-Computer Interface},
  nlm-id          = {100965194},
  owner           = {NLM},
  pii             = {1471-2105-9-340},
  pmc             = {PMC2536673},
  pmid            = {18700982},
  pubmodel        = {Electronic},
  pubstatus       = {epublish},
  revised         = {2018-11-13},
}

@Article{Giegerich2004,
  author          = {Giegerich, Robert and Voss, Björn and Rehmsmeier, Marc},
  title           = {Abstract shapes of {RNA}.},
  journal         = {Nucleic acids research},
  year            = {2004},
  volume          = {32},
  pages           = {4843--4851},
  issn            = {1362-4962},
  abstract        = {The function of a non-protein-coding {RNA} is often determined by its structure. Since experimental determination of {RNA} structure is time-consuming and expensive, its computational prediction is of great interest, and efficient solutions based on thermodynamic parameters are known. Frequently, however, the predicted minimum free energy structures are not the native ones, leading to the necessity of generating suboptimal solutions. While this can be accomplished by a number of programs, the user is often confronted with large outputs of similar structures, although he or she is interested in structures with more fundamental differences, or, in other words, with different abstract shapes. Here, we formalize the concept of abstract shapes and introduce their efficient computation. Each shape of an {RNA} molecule comprises a class of similar structures and has a representative structure of minimal free energy within the class. Shape analysis is implemented in the program {RNA}shapes. We applied {RNA}shapes to the prediction of optimal and suboptimal abstract shapes of several {RNA}s. For a given energy range, the number of shapes is considerably smaller than the number of structures, and in all cases, the native structures were among the top shape representatives. This demonstrates that the researcher can quickly focus on the structures of interest, without processing up to thousands of near-optimal solutions. We complement this study with a large-scale analysis of the growth behaviour of structure and shape spaces. {RNA}shapes is available for download and as an online version on the Bielefeld Bioinformatics Server.},
  chemicals       = {5' Untranslated Regions, {RNA}, Small Nuclear, {RNA}, Untranslated, {RNA}, Viral, U2 small nuclear {RNA}, {RNA}, Transfer},
  citation-subset = {IM},
  completed       = {2004-09-24},
  country         = {England},
  doi             = {10.1093/nar/gkh779},
  issn-linking    = {0305-1048},
  issue           = {16},
  keywords        = {5' Untranslated Regions, chemistry; Base Sequence; Computational Biology, methods; HIV-1, genetics; Humans; Internet; Molecular Sequence Data; Nucleic Acid Conformation; {RNA}, Small Nuclear, chemistry; {RNA}, Transfer, chemistry; {RNA}, Untranslated, chemistry; {RNA}, Viral, chemistry; Software; Terminology as Topic},
  nlm-id          = {0411011},
  owner           = {NLM},
  pii             = {32/16/4843},
  pmc             = {PMC519098},
  pmid            = {15371549},
  pubmodel        = {Electronic-Print},
  pubstatus       = {epublish},
  revised         = {2019-12-10},
}

@Article{Reeder2005,
  author          = {Reeder, Jens and Giegerich, Robert},
  title           = {Consensus shapes: an alternative to the Sankoff algorithm for {RNA} consensus structure prediction.},
  journal         = {Bioinformatics (Oxford, England)},
  year            = {2005},
  volume          = {21},
  pages           = {3516--3523},
  month           = sep,
  issn            = {1367-4803},
  abstract        = {The well-known Sankoff algorithm for simultaneous {RNA} sequence alignment and folding is currently considered an ideal, but computationally over-expensive method. Available tools implement this algorithm under various pragmatic restrictions. They are still expensive to use, and it is difficult to judge if the moderate quality of results is because of the underlying model or to its imperfect implementation. We propose to redefine the consensus structure prediction problem in a way that does not imply a multiple sequence alignment step. For a family of {RNA} sequences, our method explicitly and independently enumerates the near-optimal abstract shape space, and predicts as the consensus an abstract shape common to all sequences. For each sequence, it delivers the thermodynamically best structure which has this common shape. Since the shape space is much smaller than the structure space, and identification of common shapes can be done in linear time (in the number of shapes considered), the method is essentially linear in the number of sequences. Our evaluation shows that the new method compares favorably with available alternatives. The new method has been implemented in the program {RNA}cast and is available on the Bielefeld Bioinformatics Server. jreeder@TechFak.Uni-Bielefeld.DE, robert@TechFak.Uni-Bielefeld.DE SUPPLEMENTARY INFORMATION: Available at http://bibiserv.techfak.uni-bielefeld.de/rnacast/supplementary.html},
  chemicals       = {{RNA}},
  citation-subset = {IM},
  completed       = {2005-12-07},
  country         = {England},
  doi             = {10.1093/bioinformatics/bti577},
  issn-linking    = {1367-4803},
  issue           = {17},
  keywords        = {Algorithms; Base Sequence; Computer Simulation; Consensus Sequence; Models, Chemical; Models, Molecular; Molecular Sequence Data; Nucleic Acid Conformation; {RNA}, analysis, chemistry; Sequence Alignment, methods; Sequence Analysis, {RNA}, methods; Sequence Homology, Nucleic Acid; Software},
  nlm-id          = {9808944},
  owner           = {NLM},
  pii             = {bti577},
  pmid            = {16020472},
  pubmodel        = {Print-Electronic},
  pubstatus       = {ppublish},
  revised         = {2019-12-10},
}

@Article{Janssen2008,
  author          = {Janssen, Stefan and Reeder, Jens and Giegerich, Robert},
  title           = {Shape based indexing for faster search of {RNA} family databases.},
  journal         = {BMC bioinformatics},
  year            = {2008},
  volume          = {9},
  pages           = {131},
  month           = feb,
  issn            = {1471-2105},
  abstract        = {Most non-coding {RNA} families exert their function by means of a conserved, common secondary structure. The Rfam data base contains more than five hundred structurally annotated {RNA} families. Unfortunately, searching for new family members using covariance models (CMs) is very time consuming. Filtering approaches that use the sequence conservation to reduce the number of CM searches, are fast, but it is unknown to which sacrifice. We present a new filtering approach, which exploits the family specific secondary structure and significantly reduces the number of CM searches. The filter eliminates approximately 85% of the queries and discards only 2.6% true positives when evaluating Rfam against itself. First results also capture previously undetected non-coding {RNA}s in a recent human {RNA}z screen. The {RNA} shape index filter ({RNA}sifter) is based on the following rationale: An {RNA} family is characterised by structure, much more succinctly than by sequence content. Structures of individual family members, which naturally have different length and sequence composition, may exhibit structural variation in detail, but overall, they have a common shape in a more abstract sense. Given a fixed release of the Rfam data base, we can compute these abstract shapes for all families. This is called a shape index. If a query sequence belongs to a certain family, it must be able to fold into the family shape with reasonable free energy. Therefore, rather than matching the query against all families in the data base, we can first (and quickly) compute its feasible shape(s), and use the shape index to access only those families where a good match is possible due to a common shape with the query.},
  chemicals       = {{RNA}},
  citation-subset = {IM},
  completed       = {2008-04-23},
  country         = {England},
  doi             = {10.1186/1471-2105-9-131},
  issn-linking    = {1471-2105},
  keywords        = {Algorithms; Base Sequence; Database Management Systems; Databases, Genetic; Information Storage and Retrieval, methods; Molecular Sequence Data; {RNA}, genetics; Sequence Alignment, methods; Sequence Analysis, {RNA}, methods},
  nlm-id          = {100965194},
  owner           = {NLM},
  pii             = {1471-2105-9-131},
  pmc             = {PMC2277397},
  pmid            = {18312625},
  pubmodel        = {Electronic},
  pubstatus       = {epublish},
  revised         = {2018-11-13},
}

@Article{Burbano2007,
  author          = {Burbano, Hernán A and Andrade, Eugenio},
  title           = {Analysis of t{RNA} abstract shapes of precursor/derivative amino acids in Archaea.},
  journal         = {Gene},
  year            = {2007},
  volume          = {396},
  pages           = {75--83},
  month           = jul,
  issn            = {0378-1119},
  abstract        = {Wong's theory of the genetic code's origin states that because of historical constraints, codon assignment depends on the relation between precursor and derivative amino acids, a result of the coevolutionary process between amino acids' biosynthetic pathways and t{RNA}s. Based on arguments supporting the assumption that natural selection favors more stable and thus functionally constrained structures, we tested whether precursor and derivative t{RNA}s are equally evolved by measuring their structural parameters, thermostability and molecular plasticity. We also estimated the extent to which precursor and derivative t{RNA}s differ within Archaea. We used Archaea sequences of both precursor and derivative t{RNA}s in order to examine the plastic repertoires or sets of suboptimal structures at a defined free energy interval. We grouped secondary structures according to their helix nesting and adjacency using abstract shapes analysis. This clustering enabled us to infer a consensus sequence for all shapes that fit the clover leaf secondary structure [Giegerich, R., et al., Nucleic Acids Res 2004; 32 (16): 4843-51.]. This consensus sequence was then folded in order to retrieve a set of suboptimal structures. For each pair of precursor and derivative t{RNA}s, we compared these plastic repertoires based on the number of secondary structures, the thermostability of the minimum free energy structure and two structural parameters (base pair propensity (P) and mean length of helical stem structures (S)), which were measured for every representative secondary structure [Schultes, E.A., et al., J Mol Evol 1999; 49 (1): 76-83.]. We found that derivative t{RNA}s have fewer numbers of shapes, higher thermostability and more stable parameters than precursor t{RNA}s, a fact in full agreement with Wong's coevolution theory of the genetic code.},
  chemicals       = {Amino Acids, {RNA}, Transfer},
  citation-subset = {IM},
  completed       = {2007-08-01},
  country         = {Netherlands},
  doi             = {10.1016/j.gene.2007.02.024},
  issn-linking    = {0378-1119},
  issue           = {1},
  keywords        = {Amino Acids, genetics; Archaea, genetics; Base Composition, genetics; Base Pairing; Base Sequence; Evolution, Molecular; Genetic Code; Molecular Sequence Data; {RNA}, Transfer, chemistry, genetics; Thermodynamics},
  nlm-id          = {7706761},
  owner           = {NLM},
  pii             = {S0378-1119(07)00113-8},
  pmid            = {17433860},
  pubmodel        = {Print-Electronic},
  pubstatus       = {ppublish},
  revised         = {2007-06-04},
}

@Article{Voss2006,
  author          = {Voss, Björn and Giegerich, Robert and Rehmsmeier, Marc},
  title           = {Complete probabilistic analysis of {RNA} shapes.},
  journal         = {BMC biology},
  year            = {2006},
  volume          = {4},
  pages           = {5},
  month           = feb,
  issn            = {1741-7007},
  abstract        = {Soon after the first algorithms for {RNA} folding became available, it was recognised that the prediction of only one energetically optimal structure is insufficient to achieve reliable results. An in-depth analysis of the folding space as a whole appeared necessary to deduce the structural properties of a given {RNA} molecule reliably. Folding space analysis comprises various methods such as suboptimal folding, computation of base pair probabilities, sampling procedures and abstract shape analysis. Common to many approaches is the idea of partitioning the folding space into classes of structures, for which certain properties can be derived. In this paper we extend the approach of abstract shape analysis. We show how to compute the accumulated probabilities of all structures that share the same shape. While this implies a complete (non-heuristic) analysis of the folding space, the computational effort depends only on the size of the shape space, which is much smaller. This approach has been integrated into the tool {RNA} shapes, and we apply it to various {RNA}s. Analyses of conformational switches show the existence of two shapes with probabilities approximately 2/3 vs. 1/3, whereas the analysis of a micro{RNA} precursor reveals one shape with a probability near to 1.0. Furthermore, it is shown that a shape can outperform an energetically more favourable one by achieving a higher probability. From these results, and the fact that we use a complete and exact analysis of the folding space, we conclude that this approach opens up new and promising routes for investigating and understanding {RNA} secondary structure.},
  chemicals       = {{RNA}},
  citation-subset = {IM},
  completed       = {2006-07-17},
  country         = {England},
  doi             = {10.1186/1741-7007-4-5},
  issn-linking    = {1741-7007},
  keywords        = {Algorithms; Computational Biology, methods; Models, Statistical; Models, Theoretical; Nucleic Acid Conformation; Probability; Programming Languages; {RNA}, chemistry},
  nlm-id          = {101190720},
  owner           = {NLM},
  pii             = {1741-7007-4-5},
  pmc             = {PMC1479382},
  pmid            = {16480488},
  pubmodel        = {Electronic},
  pubstatus       = {epublish},
  revised         = {2018-11-13},
}

@Article{Findeiss2017,
  author          = {Findei{\ss}, Sven and Etzel, Maja and Will, Sebastian and M{\"o}rl, Mario and Stadler, Peter F},
  title           = {Design of Artificial Riboswitches as Biosensors.},
  journal         = {Sensors (Basel, Switzerland)},
  year            = {2017},
  volume          = {17},
  number          = {9},
  pages           = {E1990},
  month           = aug,
  issn            = {1424-8220},
  abstract        = {{RNA} aptamers readily recognize small organic molecules, polypeptides, as well as other nucleic acids in a highly specific manner. Many such aptamers have evolved as parts of regulatory systems in nature. Experimental selection techniques such as SELEX have been very successful in finding artificial aptamers for a wide variety of natural and synthetic ligands. Changes in structure and/or stability of aptamers upon ligand binding can propagate through larger {RNA} constructs and cause specific structural changes at distal positions. In turn, these may affect transcription, translation, splicing, or binding events. The {RNA} secondary structure model realistically describes both thermodynamic and kinetic aspects of {RNA} structure formation and refolding at a single, consistent level of modelling. Thus, this framework allows studying the function of natural riboswitches in silico. Moreover, it enables rationally designing artificial switches, combining essentially arbitrary sensors with a broad choice of read-out systems. Eventually, this approach sets the stage for constructing versatile biosensors.},
  chemicals       = {Aptamers, Nucleotide, Ligands, Riboswitch},
  citation-subset = {IM},
  completed       = {2018-05-31},
  country         = {Switzerland},
  doi             = {10.3390/s17091990},
  issn-linking    = {1424-8220},
  issue           = {9},
  keywords        = {Aptamers, Nucleotide; Biosensing Techniques; Kinetics; Ligands; Riboswitch; {RNA} structure; aptamer; folding kinetics; ligand binding; rational design; refolding; thermodynamics},
  nlm-id          = {101204366},
  owner           = {NLM},
  pii             = {E1990},
  pmc             = {PMC5621056},
  pmid            = {28867802},
  pubmodel        = {Electronic},
  pubstatus       = {epublish},
  revised         = {2019-01-16},
}

@Article{Grabbe2016,
  author          = {Grabbe, Stephan and Haas, Heinrich and Diken, Mustafa and Kranz, Lena M and Langguth, Peter and Sahin, Ugur},
  title           = {Translating nanoparticulate-personalized cancer vaccines into clinical applications: case study with {RNA}-lipoplexes for the treatment of melanoma.},
  journal         = {Nanomedicine (London, England)},
  year            = {2016},
  volume          = {11},
  pages           = {2723--2734},
  month           = oct,
  issn            = {1748-6963},
  abstract        = {The development of nucleic acid based vaccines against cancer has gained considerable momentum through the advancement of modern sequencing technologies and on novel {RNA}-based synthetic drug formats, which can be readily adapted following identification of every patient's tumor-specific mutations. Furthermore, affordable and individual 'on demand' production of molecularly optimized vaccines should allow their application in large groups of patients. This has resulted in the therapeutic concept of an active personalized cancer vaccine, which has been brought into clinical testing. Successful trials have been performed by intranodal administration of sterile isotonic solutions of synthetic {RNA} vaccines. The second generation of {RNA} vaccines which is currently being developed encompasses intravenously injectable {RNA} nanoparticle formulations (lipoplexes), made up from lipid excipients, denoted {RNA} . A first product that has made its way from bench to bedside is a therapeutic vaccine for intravenous administration based on a fixed set of four {RNA} lipoplex drug products, each encoding for one shared tumor antigen (Lipoplex Melanoma {RNA} Immunotherapy, 'Lipo-MERIT'). This article describes the steps for translating these novel {RNA} nanomedicines into clinical trials.},
  chemicals       = {Antigens, Neoplasm, Cancer Vaccines, Excipients, Liposomes, {RNA}, Messenger, {RNA}},
  citation-subset = {IM},
  completed       = {2018-03-22},
  country         = {England},
  doi             = {10.2217/nnm-2016-0275},
  issn-linking    = {1743-5889},
  issue           = {20},
  keywords        = {Animals; Antigens, Neoplasm, genetics, immunology; Cancer Vaccines, immunology; Clinical Trials as Topic; Excipients; Humans; Immunotherapy, methods; Liposomes, chemistry; Melanoma, immunology, therapy; Nanomedicine; Nanoparticles, chemistry, therapeutic use; Precision Medicine; {RNA}, administration & dosage, chemistry, immunology; {RNA}, Messenger, administration & dosage, chemistry, pharmacology, therapeutic use; cancer; drug delivery; lipoplex; liposomes; m{RNA}; tumor immunotherapy},
  nlm-id          = {101278111},
  owner           = {NLM},
  pmid            = {27700619},
  pubmodel        = {Print},
  pubstatus       = {ppublish},
  revised         = {2018-03-22},
}

@Article{Takahashi2013,
  author  = {Takahashi, Melissa K. and Lucks, Julius B.},
  title   = {A modular strategy for engineering orthogonal chimeric {{RNA}} transcription regulators},
  journal = {Nucleic Acids Research},
  year    = {2013},
  volume  = {41},
  number  = {15},
  pages   = {7577-7588},
  doi     = {10.1093/nar/gkt452},
}

@Article{Wu2014,
  author  = {Wu, Sherry Y. and Lopez-Berestein, Gabriel and Calin, George A. and Sood, Anil K.},
  title   = {{{RNA}}i Therapies: Drugging the Undruggable},
  journal = {Science Translational Medicine},
  year    = {2014},
  volume  = {6},
  number  = {240},
  pages   = {240ps7},
  doi     = {10.1126/scitranslmed.3008362},
}

@InProceedings{Bonnet2018,
  author    = {{\'{E}}douard Bonnet and Pawe{\l} Rz{{a}}{\.{z}}ewski and Florian Sikora},
  title     = {Designing {{RNA}} Secondary Structures Is Hard},
  booktitle = {Research in Computational Molecular Biology - 22nd Annual International Conference, {RECOMB} 2018},
  year      = {2018},
  editor    = {Benjamin J. Raphael},