Identification of novel RNA design candidates by clustering the extended RNA-As-Graphs library

Jain, Swati; Zhu, Qiyao; Paz, Amiel S. P.; Schlick, Tamar

doi:10.1016/j.bbagen.2020.129534

Cited by 4 publications

(16 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…31 The 10-fold cross validation accuracy of k-NN classification using the new features increases to 66−73% for tree graphs (from 58−63% using full linear variables) but decreases slightly from 76−81% using full quadratic variables; for dual graphs, we improve the accuracy to 73−78% compared to full linear variables (63− 69%) and it decreased slightly from 76−81% for full quadratic variables. 31 In addition to notable increased classification accuracy compared to linear variables, the new features allow us to incorporate graphs with two vertices and their large associated pool of known RNA structures as fragments in our clustering work. An added advantage of the Fiedler vector scoring model is the introduction of a threshold value for novel motif candidates.…”

Section: ■ Introductionmentioning

confidence: 83%

“…31 By use of our new features, the accuracy of K-means clustering significantly increases from 77.22% to 95% for tree graphs (linear variables) and from 75.42% to 98% for dual graphs; for quadratic variables, notable improvements also result. 31 The 10-fold cross validation accuracy of k-NN classification using the new features increases to 66−73% for tree graphs (from 58−63% using full linear variables) but decreases slightly from 76−81% using full quadratic variables; for dual graphs, we improve the accuracy to 73−78% compared to full linear variables (63− 69%) and it decreased slightly from 76−81% for full quadratic variables. 31 In addition to notable increased classification accuracy compared to linear variables, the new features allow us to incorporate graphs with two vertices and their large associated pool of known RNA structures as fragments in our clustering work.…”

Section: ■ Introductionmentioning

confidence: 91%

“…Using solved RNA structures in PDB, we have found 80 existing tree graphs out of the total 2287 tree graphs that have 2−13 vertices, and 121 existing dual graphs out of the total 110 667 dual graphs that have 2−9 vertices. 31 We have further applied graph theory to select features for the graph topologies to classify hypothetical graphs into "RNAlike" and "non-RNA-like" motifs. 31 Thus, an RNA-like motif resembles existing topologies, so it would be more likely to exist in nature.…”

Section: ■ Introductionmentioning

confidence: 99%

“…31 We have further applied graph theory to select features for the graph topologies to classify hypothetical graphs into "RNAlike" and "non-RNA-like" motifs. 31 Thus, an RNA-like motif resembles existing topologies, so it would be more likely to exist in nature. Such candidates can then be designed by "inverse folding" (produce sequences that fold onto the target motif) by our computational pipeline.…”

Section: ■ Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Fiedler Vector Scoring Approach for Novel RNA Motif Selection

Zhu

Schlick

2021

J. Phys. Chem. B

Self Cite

View full text Add to dashboard Cite

Novel RNA motif design is of great practical importance for technology and medicine. Increasingly, computational design plays an important role in such efforts. Our coarse-grained RAG (RNA-As-Graphs) framework offers strategies for enumerating the universe of RNA 2D folds, selecting “RNA-like” candidates for design, and determining sequences that fold onto these candidates. In RAG, RNA secondary structures are represented as tree or dual graphs. Graphs with known RNA structures are called “existing”, and the others are labeled “hypothetical”. By using simplified features for RNA graphs, we have clustered the hypothetical graphs into “RNA-like” and “non-RNA-like” groups and proposed RNA-like graphs as candidates for design. Here, we propose a new way of designing graph features by using Fiedler vectors. The new features reflect graph shapes better, and they lead to a more clustered organization of existing graphs. We show significant increases in K-means clustering accuracy by using the new features (e.g., up to 95% and 98% accuracy for tree and dual graphs, respectively). In addition, we propose a scoring model for top graph candidate selection. This scoring model allows users to set a threshold for candidates, and it incorporates weighing of existing graphs based on their corresponding number of known RNAs. We include a list of top scored RNA-like candidates, which we hope will stimulate future novel RNA design.

show abstract

Section: ■ Introductionmentioning

confidence: 83%

Section: ■ Introductionmentioning

confidence: 91%

Section: ■ Introductionmentioning

confidence: 99%

Section: ■ Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Fiedler Vector Scoring Approach for Novel RNA Motif Selection

Zhu

Schlick

2021

J. Phys. Chem. B

Self Cite

View full text Add to dashboard Cite

show abstract

“…Numerous coarse-grained RNA models have been proposed over the last few years ( 12 , 13 , 14 , 15 , 16 ), using various degrees of coarse graining. Another class of coarse-grained models uses graph-theory abstractions of motifs encountered in RNA structures ( 17 , 18 , 19 ). One of the most difficult problems in RNA modeling is the handling of ion effects.…”

Section: Main Textmentioning

confidence: 99%