scholarly journals iMethyl-Deep: N6 Methyladenosine Identification of Yeast Genome with Automatic Feature Extraction Technique by Using Deep Learning Algorithm

Genes ◽  
2020 ◽  
Vol 11 (5) ◽  
pp. 529 ◽  
Author(s):  
Omid Mahmoudi ◽  
Abdul Wahab ◽  
Kil To Chong
Keyword(s):  
Learning Algorithm ◽  
Feature Representation ◽  
Yeast Genome ◽  
Single Nucleotide ◽  
Automatic Feature Extraction ◽  
Deep Learning Algorithm ◽  
Wide Range ◽  
Benchmark Datasets ◽  
Nucleotide Resolution ◽  
Single Nucleotide Resolution

One of the most common and well studied post-transcription modifications in RNAs is N6-methyladenosine (m6A) which has been involved with a wide range of biological processes. Over the past decades, N6-methyladenosine produced some positive consequences through the high-throughput laboratory techniques but still, these lab processes are time consuming and costly. Diverse computational methods have been proposed to identify m6A sites accurately. In this paper, we proposed a computational model named iMethyl-deep to identify m6A Saccharomyces Cerevisiae on two benchmark datasets M6A2614 and M6A6540 by using single nucleotide resolution to convert RNA sequence into a high quality feature representation. The iMethyl-deep obtained 89.19% and 87.44% of accuracy on M6A2614 and M6A6540 respectively which show that our proposed method outperforms the state-of-the-art predictors, at least 8.44%, 8.96%, 8.69% and 0.173 on M6A2614 and 15.47%, 28.52%, 25.54 and 0.5 on M6A6540 higher in terms of four metrics Sp, Sn, ACC and MCC respectively. Meanwhile, M6A6540 dataset never used to train a model.

Development of coarse-graining DNA models for single-nucleotide resolution analysis

2010 ◽  
Vol 368 (1920) ◽  
pp. 2615-2628 ◽  
Author(s):  
Kentaro Doi ◽  
Tomoaki Haga ◽  
Hirofumi Shintaku ◽  
Satoyuki Kawano
Keyword(s):  
Dna Sequences ◽  
Persistence Length ◽  
Analytical Techniques ◽  
Coarse Graining ◽  
Coarse Grained ◽  
Nucleotide Polymorphisms ◽  
Single Nucleotide ◽  
Wide Range ◽  
Nucleotide Resolution ◽  
Single Nucleotide Resolution

Recently, analytical techniques have been developed for detecting single-nucleotide polymorphisms in DNA sequences. Improvements of the sequence identification techniques has attracted much attention in several fields. However, there are many things that have not been clarified about DNA. In the present study, we have developed a coarse-graining DNA model with single-nucleotide resolution, in which potential functions for hydrogen bonds and the π -stack effect are taken into account. Using Langevin-dynamics simulations, several characteristics of the coarse-grained DNA have been clarified. The validity of the present model has been confirmed, compared with other experimental and computational results. In particular, the melting temperature and persistence length are in good agreement with the experimental results for a wide range of salt concentrations.

scholarly journals NmSEER V2.0: a prediction tool for 2′-O-methylation sites based on random forest and multi-encoding combination

2019 ◽  
Vol 20 (S25) ◽  
Author(s):  
Yiran Zhou ◽  
Qinghua Cui ◽  
Yuan Zhou
Keyword(s):  
Random Forest ◽  
Prediction Model ◽  
Learning Algorithm ◽  
High Sensitivity ◽  
Sequence Information ◽  
Sequence Profile ◽  
Single Nucleotide ◽  
Nucleotide Resolution ◽  
Validation Tests ◽  
Single Nucleotide Resolution

Abstract Background 2′-O-methylation (2′-O-me or Nm) is a post-transcriptional RNA methylation modified at 2′-hydroxy, which is common in mRNAs and various non-coding RNAs. Previous studies revealed the significance of Nm in multiple biological processes. With Nm getting more and more attention, a revolutionary technique termed Nm-seq, was developed to profile Nm sites mainly in mRNA with single nucleotide resolution and high sensitivity. In a recent work, supported by the Nm-seq data, we have reported a method in silico for predicting Nm sites, which relies on nucleotide sequence information, and established an online server named NmSEER. More recently, a more confident dataset produced by refined Nm-seq was available. Therefore, in this work, we redesigned the prediction model to achieve a more robust performance on the new data. Results We redesigned the prediction model from two perspectives, including machine learning algorithm and multi-encoding scheme combination. With optimization by 5-fold cross-validation tests and evaluation by independent test respectively, random forest was selected as the most robust algorithm. Meanwhile, one-hot encoding, together with position-specific dinucleotide sequence profile and K-nucleotide frequency encoding were collectively applied to build the final predictor. Conclusions The predictor of updated version, named NmSEER V2.0, achieves an accurate prediction performance (AUROC = 0.862) and has been settled into a brand-new server, which is available at http://www.rnanut.net/nmseer-v2/ for free.

scholarly journals Single-Nucleotide-Resolution Computing and Memory in Living Cells

2018 ◽  
Author(s):  
Fahim Farzadfard ◽  
Nava Gharaei ◽  
Yasutomi Higashikuni ◽  
Giyoung Jung ◽  
Jicong Cao ◽  
...  
Keyword(s):  
Living Cells ◽  
Single Nucleotide ◽  
Gene Circuits ◽  
Synthetic Gene Circuits ◽  
Wide Range ◽  
Artificial Learning ◽  
Nucleotide Resolution ◽  
Cellular Phenotypes ◽  
Cellular Circuits ◽  
Single Nucleotide Resolution

AbstractComputing and memory in living cells are central to encoding next-generation therapies and studying in situ biology, but existing strategies have limited encoding capacity and are challenging to scale. To overcome this bottleneck, we developed a highly scalable, robust and compact platform for encoding logic and memory operations in living bacterial and human cells. This platform, named DOMINO for DNA-based Ordered Memory and Iteration Network Operator, converts DNA in living cells into an addressable, readable, and writable computation and storage medium via a single-nucleotide resolution read-write head that enables dynamic and highly efficient DNA manipulation. We demonstrate that the order and combination of DNA writing events can be programmed by biological cues and multiple molecular recorders can be coordinated to encode a wide range of order-independent, sequential, and temporal logic and memory operations. Furthermore, we show that these operators can be used to perform both digital and analog computation, and record signaling dynamics and cellular states in a long-term, autonomous, and minimally disruptive fashion. Finally, we show that the platform can be functionalized with gene regulatory modules and interfaced with cellular circuits to continuously monitor cellular phenotypes and engineer gene circuits with artificial learning capacities. We envision that highly scalable, compact, and modular DOMINO operators will lay the foundation for building robust and sophisticated synthetic gene circuits for numerous biotechnological and biomedical applications.One Sentence SummaryA programmable read-write head with single-nucleotide-resolution for genomic DNA enables robust and scalable computing and memory operations in living cells.

scholarly journals Chromosomal landscape of UV damage formation and repair at single-nucleotide resolution

2016 ◽  
Vol 113 (32) ◽  
pp. 9057-9062 ◽  
Author(s):  
Peng Mao ◽  
Michael J. Smerdon ◽  
Steven A. Roberts ◽  
John J. Wyrick
Keyword(s):  
Transcription Factors ◽  
High Throughput Sequencing ◽  
Dna Lesions ◽  
Yeast Genome ◽  
Uv Damage ◽  
Single Nucleotide ◽  
High Resolution Data ◽  
Pyrimidine Dimers ◽  
Nucleotide Resolution ◽  
Single Nucleotide Resolution

UV-induced DNA lesions are important contributors to mutagenesis and cancer, but it is not fully understood how the chromosomal landscape influences UV lesion formation and repair. Genome-wide profiling of repair activity in UV irradiated cells has revealed significant variations in repair kinetics across the genome, not only among large chromatin domains, but also at individual transcription factor binding sites. Here we report that there is also a striking but predictable variation in initial UV damage levels across a eukaryotic genome. We used a new high-throughput sequencing method, known as CPD-seq, to precisely map UV-induced cyclobutane pyrimidine dimers (CPDs) at single-nucleotide resolution throughout the yeast genome. This analysis revealed that individual nucleosomes significantly alter CPD formation, protecting nucleosomal DNA with an inward rotational setting, even though such DNA is, on average, more intrinsically prone to form CPD lesions. CPD formation is also inhibited by DNA-bound transcription factors, in effect shielding important DNA elements from UV damage. Analysis of CPD repair revealed that initial differences in CPD damage formation often persist, even at later repair time points. Furthermore, our high-resolution data demonstrate, to our knowledge for the first time, that CPD repair is significantly less efficient at translational positions near the dyad of strongly positioned nucleosomes in the yeast genome. These findings define the global roles of nucleosomes and transcription factors in both UV damage formation and repair, and have important implications for our understanding of UV-induced mutagenesis in human cancers.

scholarly journals Chemical probing of the homopurine·homopyrimidine tract in supercoiled DNA at single-nucleotide resolution

FEBS Letters ◽  
1988 ◽  
Vol 234 (2) ◽  
pp. 295-299 ◽  
Author(s):  
M. Vojtíšková ◽  
S. Mirkin ◽  
V. Lyamichev ◽  
O. Voloshin ◽  
M. Frank-Kamenetskii ◽  
...  
Keyword(s):  
Single Nucleotide ◽  
Supercoiled Dna ◽  
Chemical Probing ◽  
Nucleotide Resolution ◽  
Single Nucleotide Resolution
Sign in / Sign up

Export Citation Format

Share Document