Nanopores employ the ionic current from the single molecule blockage to identify the structure,conformation,chemical groups and charges of a single molecule.Despite the tremendous development in designing sensitive po...Nanopores employ the ionic current from the single molecule blockage to identify the structure,conformation,chemical groups and charges of a single molecule.Despite the tremendous development in designing sensitive pore-forming materials,at some extent,the analyte with the single group difference still exhibits similar residual current or duration time.The serious overlap in the statistical results of residual current and duration time brings the difficulties in the nanopore discrimination of each single molecules from the mixture.In this paper,we present the AdaBoost-based machine learning model to identify the multiple analyte with single group difference in the mixed blockages.A set of feature vectors which is obtained from Hidden Markov Model(HMM)is used to train the AdaBoost model.By employing the aerolysin sensing of 5ʹ-AAAA-3ʹ(AA3)and 5ʹ-GAAA-3ʹ(GA3)as the model system,our results show that AdaBoost model increases the identification accu-racy from~0.293 to above 0.991.Furthermore,five sets of mixed blockages of AA3 and GA3 further validate the average accuracy of training and validation,which are 0.997 and 0.989,respectively.The proposed methods improve the capacity of wild-type biological nanopore in efficiently identify the single nucleotide difference without designing of protein and optimizing of the experimental condition.Therefore,the AdaBoost-based machine learning approach could promote the nanopore practical application such as genetic and epigenetic detection.展开更多
Tracking the movement of droplets in digital microfluidics is essential to improve its control stability and obtain dynamic information for its applications such as point-of-care testing,environment monitoring and che...Tracking the movement of droplets in digital microfluidics is essential to improve its control stability and obtain dynamic information for its applications such as point-of-care testing,environment monitoring and chemical synthesis.Herein,an intelligent,accurate and fast droplet tracking method based on machine vision is developed for applications of digital microfluidics.To continuously recognize the transparent droplets in real-time and avoid the interferes from background patterns or inhomogeneous illumination,we introduced the correlation filter tracker,enabling online learning of the multi-features of the droplets in Fourier domain.Results show the proposed droplet tracking method could accurately locate the droplets.We also demonstrated the capacity of the proposed method for estimation of the droplet velocity as faster as 20 mm/s,and its application in online monitoring the Griess reaction for both colorimetric assay of nitrite and study of reaction kinetics.展开更多
基金This research was supported by the National Natural Science Foundation of China(6187118,2183400 and 21711530216)the“Chen Guang”project supported by Shanghai Municipal Education Commission and Shanghai Education Development Foundation(17CG27).
文摘Nanopores employ the ionic current from the single molecule blockage to identify the structure,conformation,chemical groups and charges of a single molecule.Despite the tremendous development in designing sensitive pore-forming materials,at some extent,the analyte with the single group difference still exhibits similar residual current or duration time.The serious overlap in the statistical results of residual current and duration time brings the difficulties in the nanopore discrimination of each single molecules from the mixture.In this paper,we present the AdaBoost-based machine learning model to identify the multiple analyte with single group difference in the mixed blockages.A set of feature vectors which is obtained from Hidden Markov Model(HMM)is used to train the AdaBoost model.By employing the aerolysin sensing of 5ʹ-AAAA-3ʹ(AA3)and 5ʹ-GAAA-3ʹ(GA3)as the model system,our results show that AdaBoost model increases the identification accu-racy from~0.293 to above 0.991.Furthermore,five sets of mixed blockages of AA3 and GA3 further validate the average accuracy of training and validation,which are 0.997 and 0.989,respectively.The proposed methods improve the capacity of wild-type biological nanopore in efficiently identify the single nucleotide difference without designing of protein and optimizing of the experimental condition.Therefore,the AdaBoost-based machine learning approach could promote the nanopore practical application such as genetic and epigenetic detection.
基金the financial support from the National Natural Science Foundation of China(Nos.31701698,81972017)Shanghai Key Laboratory of Forensic Medicine,Academy of Forensic Science(No.KF1910)Shanghai Shenkang Hospital Development Center to promote clinical skills and clinical innovation ability in municipal hospitals of the Three-year Action Plan Project(No.SHDC2020CR3006A).
文摘Tracking the movement of droplets in digital microfluidics is essential to improve its control stability and obtain dynamic information for its applications such as point-of-care testing,environment monitoring and chemical synthesis.Herein,an intelligent,accurate and fast droplet tracking method based on machine vision is developed for applications of digital microfluidics.To continuously recognize the transparent droplets in real-time and avoid the interferes from background patterns or inhomogeneous illumination,we introduced the correlation filter tracker,enabling online learning of the multi-features of the droplets in Fourier domain.Results show the proposed droplet tracking method could accurately locate the droplets.We also demonstrated the capacity of the proposed method for estimation of the droplet velocity as faster as 20 mm/s,and its application in online monitoring the Griess reaction for both colorimetric assay of nitrite and study of reaction kinetics.
