Результаты исследований: Научные публикации в периодических изданиях › статья в журнале по материалам конференции › Рецензирование
Unsupervised Machine Learning Methods for Determining Special Points of the Polymerase Chain Reaction Fluorescence Accumulation Curve. / Орехов, Андрей Владимирович; Потехина, М. А.
в: Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika), Том 78, № Suppl 1, 2023, стр. 169–179.Результаты исследований: Научные публикации в периодических изданиях › статья в журнале по материалам конференции › Рецензирование
}
TY - JOUR
T1 - Unsupervised Machine Learning Methods for Determining Special Points of the Polymerase Chain Reaction Fluorescence Accumulation Curve
AU - Орехов, Андрей Владимирович
AU - Потехина, М. А.
N1 - Conference code: 7
PY - 2023
Y1 - 2023
N2 - The polymerase chain reaction (PCR) method is a cyclic process based on the repeated copying of a certain fragment of DNA using enzymes in vitro. The main molecular mechanism of PCR is amplification - accumulation of copies of the selected nucleotide sequence. Real-time polymerase chain reaction - one of the varieties of the PCR method, it allows you to determine not only the presence of the target nucleotide sequence in the sample, but also measure the number of its copies. The efficiency of the real-time polymerase chain reaction is characterized by the exponential section of the fluorescence accumulation curve (PCR kinetic curve). This curve consists of a baseline, an exponential phase and a plateau phase. Of theoretical and practical interest is the analytical determination of the moments of transition of the PCR kinetic curve from linear to exponential growth, and then reaching a plateau. Unsupervised machine learning methods can be used to solve this problem. If we consider amplification as a quasi-deterministic discrete random process, for which the fluorescence accumulation curves are monotonically increasing trajectories, then the moments of transition from the baseline to the exponential phase and from the exponential phase to the plateau phase are trajectory anomalies. Their detection is possible with the help of quadratic forms of approximation-estimation tests.
AB - The polymerase chain reaction (PCR) method is a cyclic process based on the repeated copying of a certain fragment of DNA using enzymes in vitro. The main molecular mechanism of PCR is amplification - accumulation of copies of the selected nucleotide sequence. Real-time polymerase chain reaction - one of the varieties of the PCR method, it allows you to determine not only the presence of the target nucleotide sequence in the sample, but also measure the number of its copies. The efficiency of the real-time polymerase chain reaction is characterized by the exponential section of the fluorescence accumulation curve (PCR kinetic curve). This curve consists of a baseline, an exponential phase and a plateau phase. Of theoretical and practical interest is the analytical determination of the moments of transition of the PCR kinetic curve from linear to exponential growth, and then reaching a plateau. Unsupervised machine learning methods can be used to solve this problem. If we consider amplification as a quasi-deterministic discrete random process, for which the fluorescence accumulation curves are monotonically increasing trajectories, then the moments of transition from the baseline to the exponential phase and from the exponential phase to the plateau phase are trajectory anomalies. Their detection is possible with the help of quadratic forms of approximation-estimation tests.
KW - polymerase chain reaction
KW - unsupervised machine learning
KW - least squares method
KW - approximation-estimation tests
KW - Markov moment
U2 - 10.3103/S0027134923070238
DO - 10.3103/S0027134923070238
M3 - Conference article
VL - 78
SP - 169
EP - 179
JO - Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika)
JF - Moscow University Physics Bulletin (English Translation of Vestnik Moskovskogo Universiteta, Fizika)
SN - 0027-1349
IS - Suppl 1
T2 - The 7th International Conference on Deep Learning in Computational Physics
Y2 - 21 June 2023 through 23 June 2023
ER -
ID: 114526492