Abstract | ||
---|---|---|
Rapid sequencing of individual human genome is prerequisite to genomic
medicine, where diseases will be prevented by preemptive cures.
Quantum-mechanical tunneling through single-stranded DNA in a solid-state
nanopore has been proposed for rapid DNA sequencing, but unfortunately the
tunneling current alone cannot distinguish the four nucleotides due to large
fluctuations in molecular conformation and solvent. Here, we propose a
machine-learning approach applied to the tunneling current-voltage (I-V)
characteristic for efficient discrimination between the four nucleotides. We
first combine principal component analysis (PCA) and fuzzy c-means (FCM)
clustering to learn the "fingerprints" of the electronic density-of-states
(DOS) of the four nucleotides, which can be derived from the I-V data. We then
apply the hidden Markov model and the Viterbi algorithm to sequence a time
series of DOS data (i.e., to solve the sequencing problem). Numerical
experiments show that the PCA-FCM approach can classify unlabeled DOS data with
91% accuracy. Furthermore, the classification is found to be robust against
moderate levels of noise, i.e., 70% accuracy is retained with a signal-to-noise
ratio of 26 dB. The PCA-FCM-Viterbi approach provides a 4-fold increase in
accuracy for the sequencing problem compared with PCA alone. In conjunction
with recent developments in nanotechnology, this machine-learning method may
pave the way to the much-awaited rapid, low-cost genome sequencer. |
Year | Venue | Keywords |
---|---|---|
2010 | Clinical Orthopaedics and Related Research | quantitative method,principal component analysis,genome sequence,viterbi algorithm,quantum mechanics,dna sequence,electron density,signal to noise ratio,nucleotides,hidden markov model,human genome,time series,machine learning |
Field | DocType | Volume |
Genome,Computer science,Fuzzy logic,Artificial intelligence,DNA sequencing,Human genome,Cluster analysis,Hidden Markov model,Machine learning,Principal component analysis,Viterbi algorithm | Journal | abs/1012.0 |
ISSN | Citations | PageRank |
International Journal of Computational Science, Vol. 4, No. 4,
2010. pp. 352 - 370 | 0 | 0.34 |
References | Authors | |
3 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Henry Yuen | 1 | 33 | 9.52 |
Fuyuki Shimojo | 2 | 95 | 13.89 |
Kevin J. Zhang | 3 | 1 | 3.52 |
Ken-ichi Nomura | 4 | 132 | 13.36 |
Rajiv K. Kalia | 5 | 239 | 35.66 |
Aiichiro Nakano | 6 | 279 | 47.53 |
Priya Vashishta | 7 | 243 | 37.69 |