WO2023068823A1 - 시료 내 표적 분석물질에 대한 양음성 판독 장치 및 방법 - Google Patents
시료 내 표적 분석물질에 대한 양음성 판독 장치 및 방법 Download PDFInfo
- Publication number
- WO2023068823A1 WO2023068823A1 PCT/KR2022/015987 KR2022015987W WO2023068823A1 WO 2023068823 A1 WO2023068823 A1 WO 2023068823A1 KR 2022015987 W KR2022015987 W KR 2022015987W WO 2023068823 A1 WO2023068823 A1 WO 2023068823A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- positive
- negative reading
- learning
- signal
- negative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
- G16B40/10—Signal processing, e.g. from mass spectrometry [MS] or from PCR
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
- G01N21/6428—Measuring fluorescence of fluorescent products of reactions or of fluorochrome labelled reactive substances, e.g. measuring quenching effects, using measuring "optrodes"
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
- C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
- C12Q1/6844—Nucleic acid amplification reactions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/0895—Weakly supervised learning, e.g. semi-supervised or self-supervised learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B15/00—ICT specially adapted for analysing two-dimensional [2D] or three-dimensional [3D] molecular structures, e.g. structural or functional relations or structure alignment
- G16B15/30—Drug targeting using structural data; Docking or binding prediction
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/90—Programming languages; Computing architectures; Database systems; Data warehousing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
- G01N2201/1296—Using chemometrical methods using neural networks
Definitions
- the present invention relates to a positive-negative reading device and method for a target analyte in a sample.
- PCR polymerase chain reaction
- Real-time PCR is a PCR-based technology for real-time detection of target nucleic acids in a sample.
- a signal generator is used that emits a detectable fluorescent signal in proportion to the amount of the target nucleic acid during the PCR reaction.
- a fluorescence signal proportional to the amount of the target nucleic acid is detected at each measurement point (cycle) through real-time PCR to obtain a data set including each measurement point and the signal value at the measurement point, and comparing the measurement point from the data set
- An amplification curve or amplification profile curve indicating the intensity of the fluorescence signal to be detected is obtained.
- an amplification curve by real-time PCR is divided into a baseline region, an exponential region, and a plateau region.
- the exponential region is a region in which the emitted fluorescence signal increases in proportion to the increase in the PCR amplification product
- the stagnant region is a region in which the increase in PCR amplification product and the emission of the fluorescence signal reach saturation and the fluorescence signal does not increase any more.
- the baseline region refers to a region in which a fluorescence signal is maintained constant without change at the beginning of the reaction.
- the background signal which is the fluorescence signal of the reaction sample itself and the fluorescence signal of the measurement system itself, rather than the fluorescence signal caused by the amplification of the target analyte ) occupies most of the fluorescence signal in the baseline region.
- the method of using the threshold value predetermines a specific signal threshold value for all reactions to be analyzed (a defined signal threshold is determined for all reactions to be analyzed), and the signal value of the data set reaches the signal threshold value ( It is a method to determine whether it reaches or exceeds.
- Jeffrey Lerner obtains a function fitted to data in U.S. Patent No. 8,560,247, and determines whether the slope of the obtained function exceeds the maximum amplification slope bound.
- a method for determining whether a data set has a jump error is disclosed.
- An object to be solved by the present invention is to provide a technique for more accurately and efficiently reading whether a sample contains the above-described target nucleic acid, that is, whether it is positive or negative.
- a positive/negative reading device includes an input unit for receiving a signal value from a multi-cycle signal generation reaction targeting a target analyte;
- the signal generating reaction generates a signal dependent on the presence of the target analyte in the sample, and pre-learns to estimate the presence or absence of the target analyte in the sample from the signal value in the multiple cycles and the order of the multiple cycles. Includes a positive-negative readout.
- the target analyte may include a target nucleic acid molecule.
- the signal dependent on the presence of the target analyte may include a fluorescence signal.
- the signal generation reaction may include a nucleic acid amplification reaction.
- the positive/negative reading unit may obtain the signal values sequentially from the input unit according to the order of the cycle.
- the positive/negative readout unit may estimate the presence or absence of the target analyte in the sample after completing acquisition of all signal values of the plurality of cycles from the input unit.
- learning data including learning input data and learning correct answer data is used, and the learning input data undergoes a signal generation reaction that generates a signal dependent on the presence of the target analyte. It may include previously obtained signal values for each cycle for learning and information about the order of each cycle, and the correct answer data for learning may include information about whether the target analyte is present or not.
- the plurality of cycle signal values for learning among the input data for learning may be sequentially input to the positive/negative readout unit according to the order of the cycles.
- a backpropagation method may be used in the process of training the positive-negative reading unit to reduce the difference.
- the positive-negative readout unit may include a body unit that is learned based at least in part on the input data for learning; and a fine-tuning unit that is combined with the learned body and is trained to infer whether the learning input data is positive or negative when the learning input data is input to the learned body.
- BERT Bidirectional Encoder Representations from Transformers
- the body part may be learned according to a semi-supervised learning method.
- the process of masking some of the input data for learning and then matching the masked part and the process of matching the order or sequence of signal values having the order included in the input data for learning included can be performed.
- the fine adjustment unit may be learned according to a supervised-learning method.
- the positive/negative reading unit may include an encoder unit generating a context vector from signal values in the plurality of cycles and an order of each of the cycles; and a binary classifier for estimating whether or not the target analyte is present in the sample from the context vector.
- the positive-negative readout unit includes a recurrent neural network model or a short-term long-term memory model
- a weight for a signal value of any one cycle among the plurality of cycles and a cycle temporally preceding any one cycle The weight for the hidden state value calculated for is updated so that the difference between the result output from the output terminal of the positive-negative reading unit and the correct answer data for learning is reduced in response to the input data for learning being input to the input terminal of the positive-negative reading unit.
- the input/output structure of the positive-negative readout unit may be a many-to-one structure that outputs one data when a plurality of data is input.
- the positive-negative reading unit may be provided in the positive-negative reading device for each factor predefined as influencing the signal generation of the signal generation reaction.
- the element may include reaction conditions used in a nucleic acid amplification reaction.
- reaction conditions may be a reaction medium used for the nucleic acid amplification reaction.
- reaction medium may be one or more substances selected from the group consisting of pH-related substances, ionic strength-related substances, enzymes, and enzyme stabilization-related substances.
- the pH-related material may include a buffer
- the ionic strength-related material may include an ionic material
- the enzyme stabilization-related material may include sugar
- the positive-negative reading device further includes a pre-processing unit that performs a predetermined pre-processing operation on the signal values in each of the plurality of cycles, and the positive-negative reading unit further includes a signal value for which the pre-processing operation has been performed by the pre-processing unit. From this, the presence or absence of the target analyte in the sample can be estimated.
- the preprocessing operation may include a correction operation for an abnormal signal among signal values in the plurality of cycles, a smoothing operation for the signal value in the plurality of cycles, or a regression from a signal value in the plurality of cycles.
- a baseline subtraction operation of subtracting the applied baseline signal value from the signal value in the plurality of cycles may be included.
- a positive-negative reading method performed by a positive-negative reading device, includes receiving signal values of the multiple cycles from multiple cycles of signal generation reactions targeting a target analyte;
- the signal generation reaction generates a signal dependent on the presence of the target analyte in the sample, and the model pre-learned the presence or absence of the target analyte in the sample based on the signal value in the multiple cycles and the order of the multiple cycles. It is performed including the step of estimating using
- a computer-readable recording medium storing a computer program according to an embodiment, wherein the computer program includes instructions for causing a processor to perform a positive-negative reading method targeting a target analyte performed by a positive-negative reading device. and receiving signal values of the multiple cycles from multiple cycles of signal generating reactions targeting a target analyte;
- the signal generation reaction generates a signal dependent on the presence of the target analyte in the sample, and the model pre-learned the presence or absence of the target analyte in the sample based on the signal value in the multiple cycles and the order of the multiple cycles. It is performed including the step of estimating using
- whether a sample is positive or negative for a target analyte may be read by a model trained by a deep learning method.
- the speed and accuracy of positive-negative reading results can be improved.
- FIG. 1 is a block diagram of a positive-negative reading system including a positive-negative reading device, a preparation device and a detection device according to an embodiment.
- FIG. 2 is a conceptual diagram of a positive-negative reading device according to an embodiment.
- FIG. 3 is a block diagram showing the configuration of a positive-negative reading device according to an exemplary embodiment.
- FIG. 4 is a conceptual diagram illustrating the concept of a recurrent neural network model.
- FIG. 5 is a conceptual diagram illustrating a case in which a positive-negative readout unit is implemented as a recurrent neural network according to an exemplary embodiment.
- FIG. 6 is a hardware block diagram of a positive-negative reading device according to an exemplary embodiment.
- FIG. 7 is a flow chart of a positive-negative reading method according to an embodiment.
- FIG. 8 is a graph showing signal values for each temperature in a plurality of cycles of a sample when at least one target analyte is included in the sample according to an embodiment.
- target analyte includes a variety of substances (eg, biological and non-biological substances), which can refer to the same subject as the term “target analyte”.
- Such target analytes are specifically biological substances, more specifically at least one of nucleic acid molecules (eg, DNA and RNA), proteins, peptides, carbohydrates, lipids, amino acids, biological compounds, hormones, antibodies, antigens, metabolites, and cells.
- nucleic acid molecules eg, DNA and RNA
- sample includes biological samples (eg, cells, tissues, and body fluids) and non-biological samples (eg, food, water, and soil).
- biological sample is, for example, virus, bacteria, tissue, cell, blood (including whole blood, plasma and serum), lymph, bone marrow, saliva, sputum, swab, aspiration, It may include at least one of milk, urine, feces, eye fluid, semen, brain extract, spinal fluid, joint fluid, thymus fluid, bronchial lavage fluid, ascites fluid, and amniotic fluid.
- Such a sample may or may not contain the target analyte described above.
- nucleic acid extraction process known in the art may be performed on the sample estimated to contain the target analyte.
- the nucleic acid extraction process may vary depending on the type of sample.
- the extracted nucleic acid is RNA
- a reverse transcription process may be additionally performed to synthesize cDNA (Reference: Sambrook, J. et al., Molecular Cloning. A Laboratory Manual, 3rd ed. Cold Spring Harbor Press (2001).
- data set refers to data obtained from a signal generating reaction to the target analyte using a signal generating means (signal generating means will be discussed later).
- the term "signal generating reaction” refers to a reaction that generates a signal dependent on properties, such as activity, amount, or presence (or absence), specifically presence (or absence), of a target analyte in a sample.
- These signal generating reactions include biological and chemical reactions.
- the biological reaction includes genetic analysis such as PCR, real-time PCR and microarray analysis, immunological analysis, and bacterial growth analysis.
- chemical reactions include the process of analyzing the creation, change or destruction of chemicals.
- the signal generation reaction may be a genetic analysis process, or may be a nucleic acid amplification reaction, an enzymatic reaction, or microbial growth.
- the signal generation reaction described above is accompanied by a signal change. Accordingly, the degree of progress of the signal generation reaction can be evaluated by measuring the change in the signal.
- the term “signal” means a measurable output.
- the measured magnitude or change of this signal serves as an indicator qualitatively or quantitatively indicating the characteristics of the target analyte, specifically the presence or absence of the target analyte in the sample.
- indicators include fluorescence intensity, luminescence intensity, chemiluminescence intensity, bioluminescence intensity, phosphorescence intensity, charge transfer, voltage, current, power, energy, temperature, viscosity, light scatter, radioactivity intensity, and reflectance. , transmittance and absorbance, but are not limited thereto.
- signal generating means means a means for providing a signal indicating the characteristics, specifically the presence or absence, of a target analyte to be analyzed.
- signal generating means can be expressed as “signal generating composition”.
- Such signal generating means include the label itself or an oligonucleotide to which the label is linked.
- the label includes a fluorescent label, a luminescent label, a chemiluminescent label, an electrochemical label, and a metal label.
- the label may be used as a label itself, such as an intercalating dye.
- the label may be used in the form of a single label or an interactive double label comprising a donor molecule and an acceptor molecule, bound to one or more oligonucleotides.
- the signal generating means may additionally include an enzyme having nucleic acid cleavage activity to generate a signal (eg, an enzyme having 5' nucleic acid cleavage activity or an enzyme having 3' nucleic acid cleavage activity).
- an enzyme having nucleic acid cleavage activity to generate a signal (eg, an enzyme having 5' nucleic acid cleavage activity or an enzyme having 3' nucleic acid cleavage activity).
- various methods are known for generating a signal indicating the presence of a target analyte, particularly a target nucleic acid molecule, using the signal generating means.
- Representative examples may include: TaqMan TM probe method (US Pat. No. 5,210,015), molecular beacon method (Tyagi, Nature Biotechnology, v.14 MARCH 1996), Scorpion method (Whitcombe et al., Nature Biotechnology 17: 804-807 (1999)), Sunrise or Amplifluor method (Nazarenko et al., Nucleic Acids Research, 25(12):2516-2521 (1997), and U.S. Patent No. 6,117,635), Lux method ( U.S. Patent No.
- hybridization probe (Bernard PS, et al., Clin Chem 2000, 46, 147-148), PTOCE (PTO cleavage and extension) method (WO 2012/ 096523), PCE-SH (PTO Cleavage and Extension-Dependent Signaling Oligonucleotide Hybridization) method (WO2013/115442), PCE-NH (PTO Cleavage and Extension-Dependent Non-Hybridization) method (PCT/KR2013/012312) and CER method ( WO 2011/037306).
- the aforementioned term “signal generation reaction” may include a signal amplification reaction.
- the term “amplification reaction” means a reaction that increases or decreases the signal generated by the signal generating means.
- the amplification reaction refers to an increase (or amplification) reaction of a signal generated by the signal generating means depending on the presence of a target analyte.
- amplification of the target analyte may or may not be accompanied. More specifically, the amplification reaction may refer to a signal amplification reaction accompanied by amplification of a target analyte.
- the data set obtained through the amplification reaction may include an amplification cycle.
- cycles refers to a unit of change in a condition in a plurality of measurements accompanied by a change in a certain condition.
- the change in the constant condition means, for example, an increase or decrease in temperature, reaction time, number of reactions, concentration, pH, number of copies of a target (for example, nucleic acid) to be measured, and the like.
- cycles can be time or process cycles, unit operation cycles and reproductive cycles.
- cycle means one unit of repetition when a reaction of a certain course is repeated or a reaction is repeated on a regular time interval basis.
- one cycle means a reaction including denaturation of nucleic acids, annealing of primers, and extension of primers.
- the change in constant conditions is an increase in the number of repetitions of the reaction, and the repeating unit of the reaction including the series of steps is set as one cycle.
- an amplification reaction for amplifying a signal representing the presence of a target analyte may be performed in a method in which the target analyte is amplified and the signal is also amplified (eg, real-time PCR method).
- the amplification reaction may be performed in a method in which only a signal indicating the presence of the target analyte is amplified without amplifying the target analyte (eg, the CPT method (Duck P, et al. , Biotechniques, 9:142-148 (1990)), Invader assay (US Pat. Nos. 6,358,691 and 6,194,149)).
- the aforementioned target analyte or target analyte, particularly target nucleic acid molecule can be amplified in various ways: polymerase chain reaction (PCR), ligase chain reaction (LCR) (U.S. Patent Nos. 4,683,195 and 4,683,202; PCR Protocols: A Guide to Methods and Applications (Innis et al., eds, 1990)), strand displacement amplification (SDA) (Walker, et al. Nucleic Acids Res. Clin. Microbiol. (Compton, Nature 350(6313):91-2 (1991)), rolling circle amplification (RCA) (Lisby, Mol. Biotechnol. 12(1):75-99 (1999); Hatchet al., Genet 15(2):35-40 (1999)) and Q-Beta Replicase (Lizardi et al., BiolTechnology 6:1197 (1988)).
- PCR polymerase chain reaction
- LCR ligase chain reaction
- the amplification reaction amplifies a signal while accompanying amplification of a target analyte (specifically, a target nucleic acid molecule).
- a target analyte specifically, a target nucleic acid molecule.
- the amplification reaction is carried out according to PCR, specifically real-time PCR, or isothermal amplification reaction (eg LAMP or RPA).
- a data set obtained by a signal generation reaction includes a plurality of data points including cycles of the signal generation reaction and signal values in the cycles.
- signal value refers to a value obtained by digitizing a signal level (eg, signal intensity) actually measured in a cycle of a signal generation reaction, in particular, an amplification reaction, according to a predetermined scale, or a modified value thereof.
- the modified value may include a mathematically processed signal value of the actually measured signal value.
- Examples of mathematically processed signal values of actually measured signal values may include logarithmic values or derivatives.
- data point means a coordinate value that includes cycle and signal values.
- data refers to all information constituting a data set. For example, each of the cycle and signal value of the amplification reaction may correspond to data.
- Data points obtained by the signal generation reaction, particularly the amplification reaction can be represented by coordinate values that can be represented in a two-dimensional orthogonal coordinate system.
- the X-axis represents the number of cycles
- the Y-axis represents the signal value measured or processed in the cycle.
- data set means a collection of said data points.
- the data set may be a set of data points directly obtained through an amplification reaction performed in the presence of a signal generating means, or may be a modified data set obtained by modifying such a data set.
- the data set may be some or all of a plurality of data points obtained by an amplification reaction or modified data points thereof.
- the data set for the target analyte is 200 or less, 150 or less, 100 or less, 80 or less, 60 or less, 50 or less, 45 or less, 40 or less, and 30 or less. Include data points.
- a data set for a target analyte comprises at least 2, at least 5, at least 10, at least 15 and at least 20 data points.
- the data set may be a data set obtained by processing a plurality of data sets.
- the data sets for the plurality of target analytes are optionally obtained through processing of data sets obtained from reactions performed in the one reaction vessel. It can be.
- data sets for a plurality of target analytes formed in one reaction vessel may be obtained by processing a plurality of data sets obtained from signals measured at different temperatures.
- the aforementioned data set can be plotted and thereby an amplification curve obtained.
- FIG. 1 is a block diagram of a positive-negative reading system 100 comprising a positive-negative reading device 1000, a preparation device 2000 and a detection device 3000 according to an embodiment.
- a positive-negative reading system 100 includes a positive-negative reading device 1000 , a preparation device 2000 and a detection device 3000 . Also, these components may be connected to each other by wired or wireless communication.
- the block diagram shown in FIG. 1 is merely illustrative, and the spirit of the present invention is not limited to that shown in FIG. 1 .
- the positive-negative reading system 100 may further include components not shown in FIG. 1 or may not include at least one of the components shown in FIG. 1 .
- the positive-negative reading system 100 may represent only positive-negative reading devices.
- each component of the positive-negative reading system 100 may be connected differently from that shown in FIG. 1 .
- each configuration will be described in detail.
- the preparation device 2000 is implemented to perform a preparation operation on a sample (or sample or analysis sample).
- the above-described preparation work performed by the preparation device 2000 includes a nucleic acid extraction work and a reaction mixture preparation work for nucleic acid amplification.
- the preparation device 2000 may not perform the nucleic acid extraction operation.
- the nucleic acid extraction operation may be performed by other components not shown in FIG. 1 .
- the detection device 3000 is implemented to perform a nucleic acid amplification reaction and a nucleic acid detection operation on a sample or a sample. Depending on the embodiment, the detection device 3000 may be implemented to perform a nucleic acid detection operation without performing the nucleic acid amplification reaction. However, hereinafter, the detection device 3000 will be described on the premise that the nucleic acid amplification reaction is also implemented. do.
- the detection device 3000 may include an optical module and a thermal module.
- the optical module includes a light source module and a detection module.
- the light source module supplies an appropriate optical stimulus to the sample, and the detection module detects an optical signal generated from the sample in response thereto.
- the optical signal may be luminescence, phosphorescence, chemiluminescence, fluorescence, polarized fluorescence or other colored signal.
- the optical signal may be an optical signal generated in response to an optical stimulus applied to the sample.
- the light source module includes a light source configured to irradiate light onto a sample and a filter filtering light emitted from the light source.
- the light sources may be light sources that emit light having the same wavelength characteristics. For example, when the light sources emit light in the same wavelength range, it means that the amount of light emitted for each wavelength range is the same.
- the same means not only completely the same, but also substantially the same.
- substantially the same means that, for example, when light emitted from two light sources is irradiated to the same optical marker through the same filter, the same kind of emitted light is generated from the optical marker with the same level of light.
- the fact that the plurality of light sources have substantially the same wavelength characteristics means that the light quantity or wavelength range of the plurality of light sources has a deviation of 20%, 15%, or 10%.
- a detection module detects the signal.
- the detection module detects fluorescence, which is an optical signal generated from the samples.
- the detection module detects the optical signal by generating an electrical signal according to the strength of the optical signal.
- the detection module includes a detector configured to detect emission light emitted from the sample and a filter configured to filter emission light emitted from the sample.
- the detector is configured to detect emission light emitted from an optical label included in the sample.
- the detector may detect the amount of light for each wavelength by distinguishing the wavelengths of light or detect the total amount of light regardless of the wavelength.
- the detector may use, for example, a photodiode, a photodiode array, a photo multiplier tube (PMT), a CCD image sensor, a CMOS image sensor, an avalanche photodiode (APD), or the like.
- the detector is formed to detect emission light emitted from the optical label included in the sample.
- the detector may be formed toward the sample so that emission light generated from the sample directly reaches the detector, or toward a reflector or optical fiber so that emission light can reach the detector through a reflector or optical fiber.
- the filter of the detection module is a filter for selectively passing emission light emitted from an optical label included in the sample.
- the detection filter of the present disclosure selectively passes emission light emitted from an optical label to accurately detect a target.
- the thermal module is implemented to perform a nucleic acid amplification reaction.
- the thermal module includes a sample holder in which a sample is accommodated.
- the sample holder includes a plurality of holes, and reaction vessels may be located in the holes.
- the reaction vessels may contain samples, from which fluorescence is emitted.
- the sample holder may be a conductive material. When the sample holder is in contact with the reaction vessels, heat can be transferred from the sample holder to the reaction vessels.
- the sample holder may be made of metal such as aluminum, gold, silver, nickel or copper.
- a separate component other than the sample holder may directly supply energy to the reaction vessel to control the temperature of the samples in the reaction vessel.
- the sample holder may be configured to receive the reaction vessels but not to transfer heat to the reaction vessels.
- the thermal block includes a plurality of holes, and reaction vessels may be located in the holes.
- the heating plate is in the form of contacting a thin metal plate to accommodate the sample. It can be operated by passing an electric current through a thin metal to heat the plate.
- sample holder is a receptacle capable of receiving one or more chips or cartridges.
- a cartridge is a fluid cartridge that includes a flow channel.
- the thermal module may additionally include a heat generating element, a heat sink and a heatsink fan for cycling the sample in the sample holder through a series of temperatures.
- the thermal module is used for a PCR-based nucleic acid amplification reaction. More specifically, the thermal module may perform a denaturing step, an annealing step, and an extension (or amplification) step to amplify DNA (deoxyribonucleic acid) having a specific nucleotide sequence. .
- the denaturation step is a step of separating double-stranded DNA into single-stranded DNA by heating a solution containing a sample and a reagent containing double-stranded DNA as template nucleic acid to a specific temperature, for example, about 95°C. .
- a specific temperature for example, about 95°C.
- an oligonucleotide primer having a nucleotide sequence complementary to the nucleotide sequence of the nucleic acid to be amplified is provided, and the separated single-stranded DNA is heated to a specific melting temperature (Tm), for example, 60 ° C.
- Tm specific melting temperature
- This is a step of forming a partial DNA-primer complex by cooling and binding a primer to a specific nucleotide sequence of single-stranded DNA.
- the extension step is a step in which double-stranded DNA is formed based on the primers of the partial DNA-primer complex by a DNA polymerase by maintaining the solution at a specific temperature, for example, 72° C. after the annealing step.
- the thermal module can exponentially amplify DNA having the specific nucleotide sequence by repeating the above three steps, for example, 10 to 50 times.
- the thermal module may perform the annealing step and the extension step simultaneously.
- the thermo module may complete one cycle (circulation) by performing two steps consisting of a denaturation step and an annealing/extension step.
- Such a detection device includes various conventionally known instruments as long as the temperature can be controlled for the amplification reaction. Examples include CFX (Bio-Rad), iCycler (Bio-Rad), LightCycler (Roche), StepOne (ABI), 7500 (ABI), ViiA7 (ABI), QuantStudio (ABI), AriaMx (Agilent), Eco (Illumina ), etc., but are not limited thereto.
- the above-described nucleic acid amplification reaction is performed, if the target analyte is included in the reaction vessel, the amount is amplified, as well as the amount generated by the above-described signal generating means The magnitude of the signal can also be amplified as described above.
- the detection device 3000 is implemented to detect the magnitude of such a signal. Specifically, the detection device 3000 may monitor in real time the magnitude of the above-described signal that changes as the nucleic acid amplification reaction proceeds. The monitored result may be output from the detection device 3000 in the form of a data set mentioned in the definition of the term.
- the nucleic acid amplification reaction when the nucleic acid amplification reaction is performed, since the size of the signal generated by the signal generating means can also be amplified, the nucleic acid amplification reaction will be regarded as causing the signal generating reaction discussed above as a term. let's do it.
- the positive/negative reading device 1000 may receive a detection result of the target analyte of the sample from the detection device 3000 .
- the positive/negative reading device 1000 may receive the previously described data set from the detection device 3000 .
- the positive-negative reading device 1000 may read and output whether the sample is positive-negative for the target analyte. This is conceptually illustrated in FIG. 2 .
- FIG. 2 when the positive-negative reading device 1000 receives a data set as an input as a detection result for a target analyte of a sample, the positive-negative reading device 1000 responds to the data set as an input of the corresponding target analyte of the sample. It reads and outputs whether it is positive or negative.
- FIG. 3 is a block diagram of a positive-negative reading device 1000 according to an embodiment.
- the positive-negative reading device 1000 includes an input unit 1100, a pre-processing unit 1200, and a positive-negative reading unit 1300, but is not limited thereto.
- the positive-negative reading apparatus 1000 may be implemented not to include at least one component shown in FIG. 3 (for example, the pre-processing unit 1200) according to an embodiment, or a component not shown in FIG. 3 may be added. It may be implemented to include as.
- the input unit 1100 is a component that receives data, and for this purpose, the input unit 1100 can be implemented as an input/output port or terminal.
- the positive/negative reading device 1000 may receive the aforementioned data set from the detection device 3000 through the input unit 1100 .
- this data set may include not only the signal value in each cycle detected in the amplification process, but also the order of the cycle of the signal value, but is not limited thereto. no.
- a data set may include data points paired by response number and signal value, and the data points may be ordered from small to large iterations or large to small iterations.
- a data set includes data points paired by response time and signal value, and the data points may be arranged according to short time to long time or long time to short time.
- the unit of the signal value may be, for example, Relative Fluorescence Units (RFU) representing the intensity of a fluorescence signal.
- REU Relative Fluorescence Units
- the range of the order of cycles may be 1 to 45, but is not limited thereto.
- the pre-processing unit 1200 may perform a predetermined pre-processing task on the data set that the positive-negative reading device 1000 receives from the detection device 1300 through the input unit 1100 .
- unwanted, non-analyte related signals that may occur regardless of the presence or absence of the target analyte in the sample can be removed or corrected.
- electrical noise that can be generated in the detection device 3000 regardless of whether the above-described signal generation reaction is executed, noise in the baseline region of the nucleic acid amplification curve, or a rapid increase in fluorescence signal (i.e., A jump, spike, or step signal) or rapid decrease (ie, a dip signal) may be removed or corrected.
- the negative control group is an experimental group in which one or more essential components for the progress of the reaction are not present in the reactants for the signal generating reaction.
- a negative control group in a nucleic acid amplification reaction is an experimental group without a target analyte, an experimental group without primers, an experimental group without a polymerase, or an experimental group with only a buffer.
- the negative control used in one embodiment is an experimental group containing components for nucleic acid amplification excluding the target analyte in the nucleic acid amplification reaction.
- Subtraction of the negative control can be performed by subtracting the signal value of the negative control from the signal value of the data set for the target analyte.
- the signal values of the data set for the target analyte and the signal values of the negative control were obtained in the same reaction and measurement environment, e.g., in the same reaction run on one and the same amplification and analysis device. is a signal value.
- the baseline subtraction can be performed by various methods known in the art (eg, US Patent No. 8,560,247).
- each of these various types of preprocessing operations may be performed in the preprocessor 1200 .
- a preprocessing operation a method disclosed in US Patent No. 8,560,247 or US Application Publication No. 2015/0186598 may be applied.
- signals detected from one assay sample vessel if there is a possibility that they include signals for detecting multiple target analytes using a single type of label, such signals
- An operation for separating or distinguishing signals for each target analyte may be included, which will be described later.
- the above-described preprocessing may include a task for enabling the learning result of the positive/negative reading unit 1300 to reach a desired level.
- the positive-negative reading unit 1300 is a neural network
- the quality of training data used for learning may affect the performance of the positive-negative reading unit 1300. Therefore, preprocessing processes such as standardization or normalization targeting learning data, preprocessing processes such as correcting or removing outliers after detecting them, and clustering learning data having the same or similar characteristics, and then taking this into account so that learning is performed
- a preprocessing process or a preprocessing process of unifying units of learning data may be performed as the aforementioned preprocessing task.
- a preprocessing process is already known, a detailed description thereof will be omitted.
- the positive/negative reading unit 1300 is implemented to read whether a target analyte is present in a sample. To this end, the positive/negative readout unit 1300 may receive the aforementioned data set from the input unit 1100 or the preprocessor 1200.
- the positive/negative reading unit 1300 can be implemented in various ways.
- the positive/negative reading unit 1300 can be implemented by a neural network.
- the information input to the positive-negative reading unit 1300 that is, the data set
- the information output from the positive-negative reading unit 1300 is the result deduced from the neural network.
- the information output from the positive/negative reading unit 1300 includes a result inferring whether or not the corresponding target analyte is present in the corresponding sample. If the output data is 'positive', it means that the corresponding target analyte is included in the corresponding sample. On the other hand, if the output data is 'negative', it means that the corresponding target analyte is not included in the corresponding sample.
- neural network may be used interchangeably with a classifier, computational model, neural network model, or network function.
- neural networks may be included within the scope of machine learning models.
- a neural network may consist of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of one or more such nodes. In addition, these nodes (or neurons) constituting neural networks may be interconnected by one or more links.
- one or more nodes connected through a link may form a relative relationship of an input node and an output node.
- the concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa.
- an input node to output node relationship may be created around a link. More than one output node can be connected to one input node through a link, and vice versa.
- the value of data of the output node may be determined based on data input to the input node.
- a link interconnecting an input node and an output node may have a weight.
- the weight may be variable, and may be changed by a user or an algorithm in order to perform a function desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes.
- An output node value may be determined based on the weight.
- one or more nodes are interconnected through one or more links to form an input node and output node relationship in the neural network.
- Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having the same number of nodes and links and different weight values of the links, the two neural networks may be recognized as different from each other.
- a neural network may be composed of a set of one or more nodes.
- a subset of nodes constituting a neural network may constitute a layer.
- Some of the nodes constituting the neural network may form one layer based on distances from the first input node.
- a set of nodes having a distance of n from the first input node may constitute n layers.
- the distance from the first input node may be defined by the minimum number of links that must be passed through to reach the corresponding node from the first input node.
- the definition of such a layer is arbitrary for explanation, and the order of a layer in a neural network may be defined in a method different from the above.
- a layer of nodes may be defined by a distance from a final output node.
- An initial input node may refer to one or more nodes to which data is directly input without going through a link in relation to other nodes among nodes in the neural network.
- it may mean nodes that do not have other input nodes connected by a link.
- the final output node may refer to one or more nodes that do not have an output node in relation to other nodes among nodes in the neural network.
- the hidden node may refer to nodes constituting the neural network other than the first input node and the last output node.
- the number of nodes in the input layer may be greater than the number of nodes in the output layer.
- the number of nodes in the input layer may be 45 while the number of nodes in the output layer may be 2.
- the input layer node may be each data point included in the aforementioned data set, and one of the two nodes of the output layer at this time is for 'positive' and the other is for 'negative'.
- the number of nodes in the output layer is two like this, one may correspond to 'positive' indicating the inclusion of the target analyte in the sample, and the other may correspond to 'negative'. it could be
- the number of nodes of the input layer may be less than or equal to the number of nodes of the output layer.
- a 'deep neural network' may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks allow you to uncover latent structures in your data. In other words, it can identify the latent structure of a photo, text, video, sound, or music (e.g., what objects are in the photo, what the content and emotion of the text are, what the content and emotion of the audio are, etc.). .
- Deep neural networks include convolutional neural networks (CNN), recurrent neural networks (RNNs), long short-term memory, auto encoders, generative adversarial networks (GANs), limited Boltzmann Restricted boltzmann machine (RBM), deep belief network (DBN), Q network, U network, Siamese network, Generative Adversarial Network (GAN), Bidirectional Encoder Representations from Transformers (BERT) model, etc.
- CNN convolutional neural networks
- RNNs recurrent neural networks
- GANs generative adversarial networks
- RBM limited Boltzmann Restricted boltzmann machine
- DNN deep belief network
- Q network U network
- Siamese network Generative Adversarial Network
- GAN Generative Adversarial Network
- BERT Bidirectional Encoder Representations from Transformers
- the neural network according to an embodiment may be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning.
- Learning of the neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.
- Contents of learning and learning data of the neural network described below may also be contents of learning or learning data of the positive-negative reading unit 1300 of the present disclosure.
- a neural network can be trained in a way that minimizes errors in output.
- the learning data is repeatedly input into the neural network, the output of the neural network for the learning data and the error of the target are calculated, and the error of the neural network is back-propagated from the output layer of the neural network to the input layer in the direction of reducing the error (Backpropagation is the process of updating the weight of each node in the neural network.
- each learning data is labeled with the correct answer (ie, labeled learning data), and in the case of unsupervised learning, the correct answer may not be labeled in each learning data.
- learning data in the case of supervised learning related to data classification may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network, and an error can be calculated by comparing the output (category) of the neural network and the label of the training data.
- an error may be calculated by comparing input learning data with a neural network output. The calculated error is back-propagated in a reverse direction (ie, from the output layer to the input layer) in the neural network, and the connection weight of each node of each layer of the neural network may be updated according to the back-propagation. The amount of change in the connection weight of each updated node may be determined according to a learning rate.
- the neural network's computation of input data and backpropagation of errors can constitute a learning cycle (epoch).
- the learning rate may be applied differently according to the number of iterations of the learning cycle of the neural network. For example, a high learning rate may be used in the early stages of neural network training to increase efficiency by allowing the neural network to quickly obtain a certain level of performance, and a low learning rate may be used in the late stage to increase accuracy.
- training data may be a subset of real data (ie, data to be processed using the trained neural network), and therefore, the error for the training data decreases but the error for the actual data increases. There may be learning cycles.
- Overfitting is a phenomenon in which errors for actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that has learned a cat by showing a yellow cat does not recognize that it is a cat when it sees a cat other than yellow may be a type of overfitting. Overfitting can act as a cause of increasing the error of machine learning algorithms.
- Various optimization methods can be used to prevent such overfitting. To prevent overfitting, methods such as increasing the training data, regularization, inactivating some nodes in the network during learning, and using a batch normalization layer should be applied. can
- the positive-negative readout unit 1300 is implemented as a neural network, in particular, as a deep neural network, more specifically as a recurrent neural network (RNN), in more detail. Let's take a look.
- a neural network in particular, as a deep neural network, more specifically as a recurrent neural network (RNN), in more detail. Let's take a look.
- RNN recurrent neural network
- a recurrent neural network is one of the neural networks capable of processing time-series data. Therefore, when the positive-negative readout unit 1300 according to an embodiment is implemented as a recurrent neural network, a data set input to the positive-negative readout unit 1300, that is, a multi-cycle signal generation reaction targeting a target analyte. Information on the signal value in each of the plurality of cycles and the order of each of the plurality of cycles, derived from , may be considered by the positive/negative readout unit 1300 as well as information on the order of the signal value.
- the positive/negative reading unit 1300 determines in which cycle the magnitude of the signal value increases, in which cycle it decreases, and from where the cycle does not change.
- the positive/negative reading unit 1300 determines in which cycle the magnitude of the signal value increases, in which cycle it decreases, and from where the cycle does not change.
- the recurrent neural network can be learned by a learning device (not shown in the drawing) according to a supervised-learning method.
- the learning device includes a processor such as a GPU, but is not limited thereto.
- Such a recurrent neural network outputs one data when receiving a plurality of data.
- the input becomes a signal value in a plurality of cycles, and the output becomes whether it is positive or negative. This is shown in FIG. 5 .
- the input data for learning may include a data set obtained in a process of detecting a specific target analyte in a specific sample.
- the correct answer data for learning may include whether or not the corresponding target analyte is included in the corresponding sample, that is, whether it is positive or negative.
- numerous data sets are created and stored in the process of detecting whether various target analytes are included in each of the various samples.
- the detection result is also generated or stored.
- input data for learning used for learning to implement a positive readout unit used to determine whether the target analyte in the sample is positive or negative generates a signal that is substantially the same as a signal generating reaction used for analyzing the target analyte in the sample.
- a data set generated by a reaction generated by a reaction.
- the aforementioned data set for a specific target analyte of a specific sample (eg, signal values in each of the 45 cycles and information on the order of the cycles) is input to the recurrent neural network. And, as correct answer data for learning, whether or not the corresponding target analyte is included in the corresponding sample is input.
- each of N pieces of training data as shown in Table 1 below may be input to the recurrent neural network.
- No Input data for training Answer data for training One ⁇ 100,120,93,... ... ,3000,3100,5000,7000, 7500,8232 ⁇ voice 2 ⁇ 500,720,1030,... ... ,5000,6100,7000,8100, 9500,10232 ⁇ voice ... ... ... N ⁇ 100,123,83,... ,10000,13100,14000,17000, 17500,18232 ⁇ positivity
- 'No' in Table 1 means a number given to each of the N pieces of training data in order to classify the aforementioned N pieces of training data.
- these numbers may not be considered for learning of the aforementioned recurrent neural network.
- the aforementioned N pieces of training data may be input to the recurrent neural network in an order independent of the size of the numbers.
- the input data for learning includes a plurality of signal values separated by commas ',' in braces ' ⁇ '.
- the size of these signal values may be 45, but is not limited thereto.
- a plurality of these signal values separated by commas are sequentially from the left: the first cycle, the second cycle, ... , and the rightmost signal value may be for the last cycle (ex. 45th cycle).
- the correct answer data for learning may have a value of either 'positive' or 'negative'.
- 'positive' indicates that the sample for the corresponding No contains the target analyte
- 'negative' indicates that the sample for the corresponding No does not contain the target analyte.
- learning is performed using an error backpropagation method so that an error between an output result according to an input and the above-described correct answer data for learning is minimized.
- the weight (W xh in FIG. 4) for the signal value (x in FIG. 4) of any one cycle among the plurality of cycles, and the The weight (W hh of eh 4) for the hidden state value calculated in the cycle is updated so that the difference between the estimated result and the correct answer data for learning is reduced in response to the input data for learning being input to the input terminal of the positive-negative reading unit. do.
- This learning process is performed until the performance of the recurrent neural network satisfies a predetermined criterion.
- the predetermined criterion may be established in a variety of ways. For example, a predetermined criterion may be determined by a known cross-validation.
- the positive-negative readout unit 1300 may be implemented in a long short-term memory model method.
- the short-term memory model it is known as a model that compensates for the loss of the influence of past data, which is a disadvantage of recurrent neural networks.
- the learning method for the long and short term memory model and the utilization method after completion of learning are the same as those of the recurrent neural network, description thereof will be omitted.
- the positive/negative readout unit 1300 may be implemented in a BERT (Bidirectional Encoder Representations from Transformers) model method.
- BERT is composed of a body part learned through a pre-training method and a fine-tuning part learned through a fine-tuning method.
- a plurality of data sets obtained when each of the various samples contains various target analytes are semi-supervised learning methods known as MLM (Mask Language Model) and NSP (Next Sentence Prediction). used for learning).
- MLM Manufacturing Language Model
- NSP Next Sentence Prediction
- each data set includes signal values having an order for each cycle, and learning according to the aforementioned NSP can be applied to the body part through a process of matching the order or precedence relationship of these signal values.
- supervised learning is performed in which the feature vector derived from the body unit is used as an input and whether or not the target analyte is included in the sample is the correct answer, and the fine adjustment unit is learned accordingly.
- the BERT model itself is a known technology, except for estimating the target analyte in the sample using the BERT model or whether the data used for its learning is a data set and whether it is positive or negative, the BERT model itself Further description of itself will be omitted.
- the positive-negative readout unit 1300 is all information included in the data set, that is, signals for all cycles. It can be seen conceptually as including an encoder unit that extracts a context vector from the input value and a binary classification unit that reads positive/negative values based on the extracted context vector.
- the positive/negative readout unit 1300 may be implemented to include an encoder unit and a binary classification unit.
- the above-described positive/negative reading unit 1300 may be provided in the positive/negative reading device for each factor predefined as influencing the signal generation of the signal generation reaction.
- the element includes reaction conditions used in a nucleic acid amplification reaction.
- the reaction conditions are characterized in that the reaction medium used for the nucleic acid amplification reaction.
- the reaction medium is one or more substances selected from the group consisting of pH related substances, ionic strength related substances, enzymes and enzyme stabilization related substances.
- the pH related material includes a buffer
- the ionic strength related material includes an ionic material
- the enzyme stabilization related material includes sugar
- one positive-negative reading unit 1300 may be provided in the positive-negative reading device 1000 for each target analyte such as sars-cov-2 or Zika virus.
- which positive-negative reading unit 1300 among the plurality of positive-negative reading units 1300 to be used may be determined by a user using a separate algorithm or the positive-negative reading apparatus 1000 .
- separate positive and negative readouts may be provided depending on the signal generation reaction used to detect the target analyte.
- a positive or negative readout may be provided for each factor predefined as influencing signal generation of the signal generation response.
- factors predefined as influencing the signal generation of the signal generation reaction include concentrations of oligonucleotides, enzymes, labels, and reaction composition components for detecting a target analyte.
- Reactive composition components include buffer, salts, metal ions and dNTPs.
- the factor predefined as influencing the signal generation of the signal generation reaction includes a signal generation reaction condition.
- Oligonucleotides include primers or probes.
- whether a sample is positive or negative for a target analyte can be read by a model trained by a deep learning method.
- the speed and accuracy of positive-negative reading results can be improved.
- the above-described positive-negative reading device 1000 can be implemented according to a hardware block configuration diagram as shown in FIG. 6 . Let's look more specifically.
- the positive/negative reading device 1000 includes a storage device 1610 that stores at least one command, a processor 1620 that executes at least one command of the storage device 1610, and a transceiver 1630. ), an input interface device 1640 and an output interface device 1650.
- Each of the components 1610 , 1620 , 1630 , 1640 , and 1650 included in the positive-negative reading device 1000 are connected by a data bus 1660 to communicate with each other.
- the storage device 1610 may perform the function of the storage unit 1400 . Also, the storage device 1610 may include at least one of a memory or a volatile storage medium and a non-volatile storage medium. For example, the storage device 1610 may include at least one of a read only memory (ROM) and a random access memory (RAM).
- ROM read only memory
- RAM random access memory
- the storage device 1610 may further include at least one command to be executed by the processor 1620 to be described later, and store signal values of each of a plurality of cycles input from a user in the input interface device 1640, data for learning, and the like.
- the processor 1620 may refer to a central processing unit (CPU), a graphics processing unit (GPU), a micro controller unit (MCU), or a dedicated processor on which methods according to embodiments are performed.
- CPU central processing unit
- GPU graphics processing unit
- MCU micro controller unit
- the processor 1620 may perform the functions of the pre-processing unit 1200 and the positive/negative reading unit 1300 by at least one program command stored in the storage device 1610. Each of these may be stored in a memory in the form of at least one module and executed by a processor.
- the transmitting/receiving device 1630 may receive or transmit data from an internal device or an external device connected through communication, and may perform the function of the input unit 1100 .
- the transceiver 1630 may receive data about a data set of samples, analysis samples, and amplified samples from the preparation device 2000 or the detection device 3000 .
- the input interface device 1640 may receive at least one control signal or set value from a user.
- the input interface device 1640 may receive a user input such as a preprocessing method to be performed by the preprocessor 1200 and a jumping correction criterion.
- the output interface device 1650 may output and visualize at least one piece of information including whether or not the target analyte of the sample read by the positive/negative reader 1300 is positive or negative by the operation of the processor 1620 .
- FIG. 7 is a flow chart of a positive-negative reading method according to an embodiment.
- the positive-negative reading method according to this flowchart may be performed by the positive-negative reading device 1000 described above.
- the positive-negative reading method shown in FIG. 7 is only exemplary, and the spirit of the present invention is not limited to that shown in FIG. 7 .
- the positive-negative reading device 1000 obtains a signal value at each of the plurality of cycles from a multi-cycle signal generation reaction targeting a target analyte in a sample to be read as positive-negative through the input unit 1100.
- Input can be received (S100).
- Such a signal value may be received from the detection device 3000 as described above, but is not limited thereto.
- the positive-negative reading device 1000 uses a pre-learned model to determine the presence or absence of a target analyte in a sample from signal values in a plurality of cycles and the sequence of the plurality of cycles through the positive-negative readout unit 1300. and read (S200).
- the positive/negative reading unit 1300 may receive the above-described data set from the input unit 1100 or the pre-processing unit 1200 as described above.
- a target analyte to be detected in a sample included in one reaction container may be one.
- a signal dependent on the presence of the target analyte may be detected during signal generation using a signal generating composition including a label.
- the positive/negative reading device 1000 also receives this signal from the detecting device 3000 and reads whether the signal is positive/negative.
- the reaction container includes signal generating compositions that provide signals depending on the presence of the target analytes, and signals indicating the presence of the target analytes may be provided through the signal generating reaction.
- the signal generation means it is possible to generate signals having different characteristics (eg, signals of different wavelengths) for each target analyte, and a distinct data set for each target analyte can be obtained.
- a separate positive-negative readout for each target analyte is provided, and the corresponding data set can be analyzed at the corresponding positive-negative readout to confirm the presence of the target analyte.
- signals having substantially the same characteristics may be generated for a plurality of target analytes, depending on the signal generating means used.
- a distinct data set for each target analyte may be obtained through a series of processes.
- a separate positive-negative readout for each target analyte is provided, and the corresponding data set can be analyzed at the corresponding positive-negative readout to confirm the presence of the target analyte.
- the input unit 1100 of the positive-negative reading device 1000 receives a detected signal from one assay sample container (reaction tube) from the detection device.
- the signal is a signal provided by a method of detecting a plurality of target analytes using a single type of label. Let's assume that these signals are received as input.
- the pre-processing unit 1200 of the positive-negative reading device 1000 divides the above-described signals received by the input unit 1100 from the detection device 3000 into signals for each of a plurality of target analytes. Perform pre-processing to separate. This division or separation operation is described in known methods (eg, WO2015147370, WO2015147377, WO2015147382, WO2015147412). This classification or separation process will be described in more detail with reference to the above-described known methods.
- a first signal generating composition when a first target analyte and a second target analyte are to be detected in one reaction vessel, when a first signal generating composition is used to detect the first target analyte, the first signal is generated.
- the composition is capable of generating a signal indicative of the presence of a first target analyte at a first temperature in a signal generating reaction.
- a signal indicative of the presence of the first target analyte can be generated even at the second temperature.
- the second signal generating composition when the second signal generating composition is used to detect the second target analyte, the second signal generating composition may prevent a signal from being generated even if the second target analyte exists at the first temperature in the signal generating reaction. there is.
- the second signal generating composition may generate a signal indicating the presence of the second target analyte at the second temperature.
- the signal generating reaction includes a reaction performed by the first signal generating composition generating a signal at each of the first temperature and the second temperature when the target analyte is present in the sample.
- the signal generating reaction is performed by a second signal generating composition that does not generate a signal at the first temperature and generates a signal at the second temperature when a target analyte different from the target analyte is present in the sample. reaction may be further included.
- the first temperature is a higher temperature than the second temperature. In one embodiment, the first temperature is lower than the second temperature.
- the signal generating composition there may be a first temperature range that generates a signal for a first target analyte but not a signal for a second target analyte.
- detection temperatures for each of the two target analytes may be determined in consideration of the above two temperature ranges (the first temperature range and the second temperature range).
- a relatively high temperature detected among the detected temperatures may be selected from the first temperature range.
- a relatively high detection temperature only a signal corresponding to the first target analyte is generated even if both the first target analyte and the second target analyte are present in one sample.
- a relatively low temperature detected temperature among the detected temperatures may be selected from the second temperature range.
- a signal corresponding to the first target analyte as well as a signal corresponding to the second target analyte are generated.
- one of the two target analytes has a relatively high temperature detection temperature determined by a corresponding signal generating composition (first signal generating composition), and the other has a corresponding another signal generating composition (second signal generating composition). It has a relatively low temperature detection temperature determined by
- the preprocessing unit 1200 may separate signals indicating the presence of two target analytes through a predetermined operation, and transmit the result of the separation to the positive/negative reading unit 1300.
- a 'predetermined operation' will be described with reference to FIG. 8 .
- CT Chlamydia Trachomatis
- NG Neisseria Gonorrhoeae
- the first temperature is 72°C
- the second temperature is 60°C.
- CT is an example for a target analyte having a relatively high detection temperature
- NG is an example for a target analyte having a relatively low detection temperature.
- Signals for both CT and NG may exist in signals detected at a relatively low detection temperature.
- a signal for CT may be removed from signals obtained at a relatively low detection temperature by using a signal obtained at a relatively high detection temperature.
- a signal representing the presence or absence of NG that is, a data set can be obtained.
- the data set is input to the positive/negative reading unit 1300, whether or not NG in the sample is positive/negative can be read.
- whether a sample is positive or negative for a target analyte can be read by a model trained by a deep learning method.
- the speed and accuracy of positive-negative reading results can be improved.
- the positive-negative reading method described above may be implemented in the form of a computer program programmed to perform each step included in the method.
- the corresponding computer program may be included in a computer readable recording medium. That is, according to various implementations of the present invention, it can be implemented in the form of a computer readable recording medium for storing the above-described computer program or a computer program stored in the above-described computer readable recording medium.
- Combinations of each block of the block diagram and each step of the flowchart accompanying the present invention may be performed by computer program instructions. Since these computer program instructions may be loaded into an encoding processor of a general-purpose computer, special-purpose computer, or other programmable data processing equipment, the instructions executed by the encoding processor of the computer or other programmable data processing equipment are each block or block diagram of the block diagram. Each step in the flow chart creates means for performing the functions described.
- These computer program instructions may also be stored in a computer usable or computer readable memory that can be directed to a computer or other programmable data processing equipment to implement functionality in a particular way, such that the computer usable or computer readable memory
- the instructions stored in may also produce an article of manufacture containing instruction means for performing the functions described in each block of the block diagram or each step of the flow chart.
- the computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to generate computer or other programmable data processing equipment. It is also possible that the instructions performing the processing equipment provide steps for executing the functions described in each block of the block diagram and each step of the flowchart.
- each block or each step may represent a module, segment or portion of code that includes one or more executable instructions for executing specified logical function(s). It should also be noted that in some alternative embodiments, it is possible for the functions mentioned in the blocks or steps to occur out of order. For example, two blocks or steps shown in succession may in fact be performed substantially concurrently, or the blocks or steps may sometimes be performed in reverse order depending on their function.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Medical Informatics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Organic Chemistry (AREA)
- Immunology (AREA)
- Databases & Information Systems (AREA)
- Biotechnology (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Biochemistry (AREA)
- Zoology (AREA)
- Wood Science & Technology (AREA)
- Analytical Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pathology (AREA)
- Genetics & Genomics (AREA)
- Microbiology (AREA)
- Optics & Photonics (AREA)
Abstract
Description
| No | 학습용 입력 데이터 | 학습용 정답 데이터 |
| 1 | {100,120,93,……,3000,3100,5000,7000, 7500,8232} | 음성 |
| 2 | {500,720,1030,……,5000,6100,7000,8100, 9500,10232} | 음성 |
| ... | ... | ... |
| N | {100,123,83,…,10000,13100,14000,17000, 17500,18232} | 양성 |
Claims (26)
- 표적 분석물질을 타겟으로 하는 복수 사이클의 신호 발생 반응으로부터 신호값을 입력받는 입력부; 상기 신호 발생 반응은 시료 내에 상기 표적 분석물질의 존재에 의존적인 신호를 발생시키고,상기 복수 사이클에서의 신호값 및 상기 복수 사이클의 순서로부터, 상기 시료 내에 상기 표적 분석물질의 존부를 추정하도록 기 학습된 양음성 판독부를 포함하는양음성 판독 장치.
- 제 1 항에 있어서,상기 표적 분석물질은 표적 핵산 분자를 포함하는양음성 판독 장치.
- 제 1 항에 있어서,상기 표적 분석물질의 존재에 의존적인 신호는,형광 신호를 포함하는양음성 판독 장치.
- 제 1 항에 있어서,상기 신호 발생 반응은 핵산증폭 반응을 포함하는양음성 판독 장치.
- 제 1 항에 있어서,상기 양음성 판독부는,상기 신호값을 그 사이클의 순서에 따라 순차적으로 상기 입력부로부터 획득하는양음성 판독 장치.
- 제 1 항에 있어서,상기 양음성 판독부는,상기 복수 사이클의 신호값 모두에 대해 상기 입력부로부터 획득을 완료한 이후에 상기 시료 내 상기 표적 분석물질의 존부를 추정하는양음성 판독 장치.
- 제 1 항에 있어서,상기 양음성 판독부의 학습 과정에서는 학습용 입력 데이터와 학습용 정답 데이터를 포함하는 학습용 데이터가 이용되되,상기 학습용 입력 데이터는, 상기 표적 분석물질의 존재에 의존적인 신호를 발생시키는 신호 발생 반응이 이루어져서 기 획득된 복수의 학습용 사이클 별 신호값 및 각 사이클의 순서에 대한 정보를 포함하고,상기 학습용 정답 데이터는, 상기 표적 분석물질의 존부에 대한 정보를 포함하는양음성 판독 장치.
- 제 7 항에 있어서,상기 양음성 판독부의 학습 과정에서는,상기 학습용 입력 데이터 중 상기 복수의 학습용 사이클 신호값이 상기 사이클의 순서에 따라 상기 양음성 판독부에 순차적으로 입력되는양음성 판독 장치.
- 제 8 항에 있어서,상기 양음성 판독부의 학습 과정에서는,상기 학습용 입력 데이터가 상기 양음성 판독부에 입력된 것에 대응해서 추정된 결과와 상기 학습용 정답 데이터를 비교하는 과정; 및상기 비교를 통해 도출된 차이가 줄어들도록 상기 양음성 판독부를 학습시키는 과정이 포함되어서 수행되는양음성 판독 장치.
- 제 9 항에 있어서,상기 차이가 줄어들도록 상기 양음성 판독부를 학습시키는 과정에는,역전파(backpropagation) 방식이 이용되는양음성 판독 장치.
- 제 7 항에 있어서,상기 양음성 판독부가 BERT(Bidirectional Encoder Representations from Transformers) 모델을 포함할 때,상기 양음성 판독부는,상기 학습용 입력 데이터에 적어도 부분적으로 기초해서 학습되는 바디(body)부; 및상기 학습이 완료된 바디부와 결합되어서, 상기 학습용 입력 데이터가 상기 학습이 완료된 바디부에 입력되면 양음성 여부를 추론하도록 학습되는 미세 조정(fine-tuning)부를 포함하는양음성 판독 장치.
- 제 11 항에 있어서,상기 바디부는 반지도 학습(semi-supervised learning) 방식에 따라 학습되는양음성 판독 장치.
- 제 12 항에 있어서,상기 반지도 학습 방식에서는,상기 학습용 입력 데이터 중 일부를 마스킹(masking)한 뒤 상기 마스킹된 일부를 맞추는 과정 및 상기 학습용 입력 데이터에 포함되는 순서를 갖는 신호값의 순서 내지 선후 관계를 맞추는 과정이 포함되어서 수행되는양음성 판독 장치.
- 제 11 항에 있어서,상기 미세 조정부는,지도 학습(supervised-learning) 방식에 따라 학습되는양음성 판독 장치.
- 제 11 항에 있어서,상기 양음성 판독부는,상기 복수 사이클에서의 신호값 및 상기 사이클 각각의 순서로부터 컨텍스트 벡터를 생성하는 인코더부; 및상기 컨텍스트 벡터로부터 상기 시료 내 상기 표적 분석물질의 존부를 추정하는 이진 분류부를 포함하는양음성 판독 장치.
- 제 1 항에 있어서,상기 양음성 판독부가 순환 신경망 모델 또는 장단기 메모리 모델을 포함할 때의 학습 과정에서는,상기 복수의 사이클 중에서 어느 하나의 사이클의 신호값에 대한 가중치 및 상기 어느 하나의 사이클보다 시간적으로 선행하는 사이클에 대해 연산된 은닉 상태값에 대한 가중치가, 학습용 입력 데이터가 상기 양음성 판독부의 입력단에 입력된 것에 대응해서 상기 양음성 판독부의 출력단에서 출력된 결과와 학습용 정답 데이터 간의 차이가 줄어들도록 갱신됨으로써 학습되는양음성 판독 장치.
- 제 1 항에 있어서,상기 양음성 판독부가 순환 신경망 모델 또는 장단기 메모리 모델을 포함할 때의 상기 양음성 판독부의 입출력 구조는,복수 개의 데이터를 입력받으면 1개의 데이터를 출력하는 many-to-one 구조인양음성 판독 장치.
- 제 1 항에 있어서,상기 양음성 판독부는,상기 신호 발생 반응의 신호 발생에 영향을 미치는 것으로 기 정의된 요소(factor)마다 상기 양음성 판독 장치에 마련되는양음성 판독 장치.
- 제 18항에 있어서,상기 기 정의된 요소는,핵산 증폭 반응에 이용되는 반응 조건들을 포함하는양음성 판독 장치.
- 제 19 항에 있어서,상기 반응 조건은, 상기 핵산 증폭 반응에 이용되는 반응 미디엄인 것을 특징으로 하는양음성 판독 장치.
- 제 20 항에 있어서,상기 반응 미디엄은,pH 관련 물질, 이온 세기 관련 물질, 효소 및 효소 안정화 관련 물질로부터 구성된 군으로부터 선택되는 하나 이상의 물질인 것을 특징으로 하는,양음성 판독 장치.
- 제 21 항에 있어서,상기 pH 관련 물질은 버퍼를 포함하고,상기 이온 세기 관련 물질은 이온성 물질을 포함하고,상기 효소 안정화 관련 물질은 당을 포함하는 것을 특징으로 하는양음성 판독 장치.
- 제 1 항에 있어서,상기 양음성 판독 장치는,상기 복수 사이클 각각에서의 신호값을 대상으로 소정의 전처리 작업을 수행하는 전처리부를 더 포함하며,상기 양음성 판독부는,상기 전처리부에 의해 상기 전처리 작업이 수행된 신호값으로부터, 상기 시료 내 상기 표적 분석물질의 존부를 추정하는양음성 판독 장치.
- 제 23 항에 있어서,상기 전처리 작업은,상기 복수 사이클에서의 신호값 중 비정상 신호(abnormal signal)에 대한 보정 작업, 상기 복수 사이클에서의 신호값에 대한 스무딩(smoothing) 작업 또는 상기 복수 사이클에서의 신호값으로부터 regression된 베이스라인 signal value를 상기 복수 사이클에서의 신호값으로부터 차감하는 베이스라인 차감(baseline subtraciton) 작업을 포함하는양음성 판독 장치.
- 양음성 판독 장치에 의해 수행되는 양음성 판독 방법에 있어서,표적 분석물질을 타겟으로 하는 복수 사이클의 신호 발생 반응으로부터, 상기 복수 사이클에서의 신호값을 입력받는 단계; 상기 신호 발생 반응은 시료 내에 상기 표적 분석물질의 존재에 의존적인 신호를 발생시키고,상기 복수 사이클에서의 신호값 및 상기 복수 사이클의 순서로부터, 상기 시료 내에 상기 표적 분석물질의 존부를 기 학습된 모델을 이용하여 추정하는 단계를 포함하는양음성 판독 방법.
- 컴퓨터 프로그램을 저장하는 컴퓨터 판독 가능한 기록 매체로서,상기 컴퓨터 프로그램은,양음성 판독 장치에 의해 수행되는 표적 분석물질을 타겟으로 하는 양음성 판독 방법을 프로세서가 수행하도록 하기 위한 명령어를 포함하고,상기 방법은,표적 분석물질을 타겟으로 하는 복수 사이클의 신호 발생 반응으로부터, 상기 복수 사이클에서의 신호값을 입력받는 단계; 상기 신호 발생 반응은 시료 내에 상기 표적 분석물질의 존재에 의존적인 신호를 발생시키고,상기 복수 사이클에서의 신호값 및 상기 복수 사이클의 순서로부터, 상기 시료 내에 상기 표적 분석물질의 존부를 기 학습된 모델을 이용하여 추정하는 단계를 포함하는컴퓨터 판독 가능한 기록 매체.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020247016153A KR20240093623A (ko) | 2021-10-21 | 2022-10-20 | 시료 내 표적 분석물질에 대한 양음성 판독 장치 및 방법 |
| US18/701,453 US20240418649A1 (en) | 2021-10-21 | 2022-10-20 | Device and method for reading positive/negative with respect to target assay substance in sample |
| EP22884045.0A EP4421814A4 (en) | 2021-10-21 | 2022-10-20 | APPROVAL AND METHOD FOR READING A POSITIVE/NEGATIVE RESULT WITH RESPECT TO A TARGET TEST SUBSTANCE IN A SAMPLE |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR10-2021-0141223 | 2021-10-21 | ||
| KR20210141223 | 2021-10-21 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023068823A1 true WO2023068823A1 (ko) | 2023-04-27 |
Family
ID=86059491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2022/015987 Ceased WO2023068823A1 (ko) | 2021-10-21 | 2022-10-20 | 시료 내 표적 분석물질에 대한 양음성 판독 장치 및 방법 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20240418649A1 (ko) |
| EP (1) | EP4421814A4 (ko) |
| KR (1) | KR20240093623A (ko) |
| WO (1) | WO2023068823A1 (ko) |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4683195A (en) | 1986-01-30 | 1987-07-28 | Cetus Corporation | Process for amplifying, detecting, and/or-cloning nucleic acid sequences |
| US4683202A (en) | 1985-03-28 | 1987-07-28 | Cetus Corporation | Process for amplifying nucleic acid sequences |
| US4800159A (en) | 1986-02-07 | 1989-01-24 | Cetus Corporation | Process for amplifying, detecting, and/or cloning nucleic acid sequences |
| US5210015A (en) | 1990-08-06 | 1993-05-11 | Hoffman-La Roche Inc. | Homogeneous assay system using the nuclease activity of a nucleic acid polymerase |
| US5876930A (en) | 1994-11-16 | 1999-03-02 | Perkin-Elmer Corporation | Hybridization assay using self-quenching fluorescence probe |
| US6117635A (en) | 1996-07-16 | 2000-09-12 | Intergen Company | Nucleic acid amplification oligonucleotides with molecular energy transfer labels and methods based thereon |
| US6194149B1 (en) | 1998-03-03 | 2001-02-27 | Third Wave Technologies, Inc. | Target-dependent reactions using structure-bridging oligonucleotides |
| WO2001032922A2 (en) * | 1999-10-29 | 2001-05-10 | Stratagene | Methods for detection of a target nucleic acid sequence |
| US6977295B2 (en) | 1999-04-21 | 2005-12-20 | Invitrogen Corporation | Locked nucleic acid hybrids and methods of use |
| US20070111249A1 (en) * | 2001-08-21 | 2007-05-17 | Applera Corporation | Automatic threshold setting for quantitative polymerase chain reaction |
| US7348141B2 (en) | 2000-03-29 | 2008-03-25 | Lgc Limited | Hybridization beacon and method of rapid sequence detection and discrimination |
| US7363168B2 (en) * | 2001-10-02 | 2008-04-22 | Stratagene California | Adaptive baseline algorithm for quantitative PCR |
| US20090119020A1 (en) | 2007-09-25 | 2009-05-07 | Roche Molecular Systems, Inc. | Pcr elbow determination using quadratic test for curvature analysis of a double sigmoid |
| US7537886B1 (en) | 1999-06-22 | 2009-05-26 | Life Technologies Corporation | Primers and methods for the detection and discrimination of nucleic acids |
| WO2011037306A1 (en) | 2009-09-24 | 2011-03-31 | Seegene, Inc. | Detection of target nucleic acid sequences by cyclic exonucleolytic reactions |
| KR20110052681A (ko) * | 2008-08-08 | 2011-05-18 | 스미스 디텍션 인크. | Pcr 검정을 위한 검출 알고리즘 |
| WO2012096523A2 (en) | 2011-01-11 | 2012-07-19 | Seegene, Inc. | Detection of target nucleic acid sequences by pto cleavage and extension assay |
| WO2013115442A1 (en) | 2012-02-02 | 2013-08-08 | Seegene, Inc. | Detection of target nucleic acid sequence by pto cleavage and extension-dependent signaling oligonucleotide hybridization assay |
| US8560247B2 (en) | 2008-09-09 | 2013-10-15 | Bio-Rad Laboratories, Inc. | Multi-stage, regression-based PCR analysis system |
| US20150186598A1 (en) | 2013-12-30 | 2015-07-02 | Roche Molecular Systems, Inc. | Detection and correction of jumps in real-time pcr signals |
| WO2015147382A1 (en) | 2014-03-28 | 2015-10-01 | Seegene, Inc. | Detection of target nucleic acid sequences using different detection temperatures |
| KR20170051539A (ko) * | 2014-10-01 | 2017-05-11 | 주식회사 씨젠 | 시료의 분석 방법 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3130679B1 (de) * | 2015-08-13 | 2018-02-28 | Cladiac GmbH | Verfahren und testsystem zum nachweis und/oder quantifizieren einer ziel-nukleinsäure in einer probe |
| WO2017052300A1 (en) * | 2015-09-24 | 2017-03-30 | Seegene, Inc. . | Multiple dataset analysis for determining the presence or absence of target analyte |
| JP7470095B2 (ja) * | 2018-07-10 | 2024-04-17 | ジェン-プローブ・インコーポレーテッド | 核酸を検出および定量するための方法およびシステム |
| DE102020202360B4 (de) * | 2020-02-25 | 2024-03-21 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren und Vorrichtung zur Durchführung eines qPCR-Verfahrens |
-
2022
- 2022-10-20 US US18/701,453 patent/US20240418649A1/en active Pending
- 2022-10-20 EP EP22884045.0A patent/EP4421814A4/en active Pending
- 2022-10-20 KR KR1020247016153A patent/KR20240093623A/ko active Pending
- 2022-10-20 WO PCT/KR2022/015987 patent/WO2023068823A1/ko not_active Ceased
Patent Citations (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4683202A (en) | 1985-03-28 | 1987-07-28 | Cetus Corporation | Process for amplifying nucleic acid sequences |
| US4683202B1 (ko) | 1985-03-28 | 1990-11-27 | Cetus Corp | |
| US4683195A (en) | 1986-01-30 | 1987-07-28 | Cetus Corporation | Process for amplifying, detecting, and/or-cloning nucleic acid sequences |
| US4683195B1 (ko) | 1986-01-30 | 1990-11-27 | Cetus Corp | |
| US4800159A (en) | 1986-02-07 | 1989-01-24 | Cetus Corporation | Process for amplifying, detecting, and/or cloning nucleic acid sequences |
| US5210015A (en) | 1990-08-06 | 1993-05-11 | Hoffman-La Roche Inc. | Homogeneous assay system using the nuclease activity of a nucleic acid polymerase |
| US5876930A (en) | 1994-11-16 | 1999-03-02 | Perkin-Elmer Corporation | Hybridization assay using self-quenching fluorescence probe |
| US6117635A (en) | 1996-07-16 | 2000-09-12 | Intergen Company | Nucleic acid amplification oligonucleotides with molecular energy transfer labels and methods based thereon |
| US6194149B1 (en) | 1998-03-03 | 2001-02-27 | Third Wave Technologies, Inc. | Target-dependent reactions using structure-bridging oligonucleotides |
| US6358691B1 (en) | 1998-03-03 | 2002-03-19 | Third Wave Technologies, Inc. | Target-dependent reactions using structure-bridging oligonucleotides |
| US6977295B2 (en) | 1999-04-21 | 2005-12-20 | Invitrogen Corporation | Locked nucleic acid hybrids and methods of use |
| US7537886B1 (en) | 1999-06-22 | 2009-05-26 | Life Technologies Corporation | Primers and methods for the detection and discrimination of nucleic acids |
| WO2001032922A2 (en) * | 1999-10-29 | 2001-05-10 | Stratagene | Methods for detection of a target nucleic acid sequence |
| US7348141B2 (en) | 2000-03-29 | 2008-03-25 | Lgc Limited | Hybridization beacon and method of rapid sequence detection and discrimination |
| US20070111249A1 (en) * | 2001-08-21 | 2007-05-17 | Applera Corporation | Automatic threshold setting for quantitative polymerase chain reaction |
| US7363168B2 (en) * | 2001-10-02 | 2008-04-22 | Stratagene California | Adaptive baseline algorithm for quantitative PCR |
| US20090119020A1 (en) | 2007-09-25 | 2009-05-07 | Roche Molecular Systems, Inc. | Pcr elbow determination using quadratic test for curvature analysis of a double sigmoid |
| KR20110052681A (ko) * | 2008-08-08 | 2011-05-18 | 스미스 디텍션 인크. | Pcr 검정을 위한 검출 알고리즘 |
| US8560247B2 (en) | 2008-09-09 | 2013-10-15 | Bio-Rad Laboratories, Inc. | Multi-stage, regression-based PCR analysis system |
| WO2011037306A1 (en) | 2009-09-24 | 2011-03-31 | Seegene, Inc. | Detection of target nucleic acid sequences by cyclic exonucleolytic reactions |
| WO2012096523A2 (en) | 2011-01-11 | 2012-07-19 | Seegene, Inc. | Detection of target nucleic acid sequences by pto cleavage and extension assay |
| WO2013115442A1 (en) | 2012-02-02 | 2013-08-08 | Seegene, Inc. | Detection of target nucleic acid sequence by pto cleavage and extension-dependent signaling oligonucleotide hybridization assay |
| US20150186598A1 (en) | 2013-12-30 | 2015-07-02 | Roche Molecular Systems, Inc. | Detection and correction of jumps in real-time pcr signals |
| WO2015147382A1 (en) | 2014-03-28 | 2015-10-01 | Seegene, Inc. | Detection of target nucleic acid sequences using different detection temperatures |
| WO2015147377A1 (en) | 2014-03-28 | 2015-10-01 | Seegene, Inc. | Detection of a target nucleic acid sequence using two different detection temperatures |
| WO2015147370A1 (en) | 2014-03-28 | 2015-10-01 | Seegene, Inc. | Detection of target nucleic acid sequences using different detection temperatures |
| WO2015147412A1 (en) | 2014-03-28 | 2015-10-01 | Seegene, Inc. | Detection of target nucleic acid sequences using different detection temperatures |
| KR20170051539A (ko) * | 2014-10-01 | 2017-05-11 | 주식회사 씨젠 | 시료의 분석 방법 |
Non-Patent Citations (18)
| Title |
|---|
| "PCR Protocols: A Guide to Methods and Applications", 1990 |
| BERNARD PS ET AL., CLIN CHEM, vol. 46, 2000, pages 147 - 148 |
| COMPTON, NATURE, vol. 350, no. 6313, 1991, pages 91 - 2 |
| D.J. FRENCH ET AL., MOLECULAR AND CELLULAR PROBES, vol. 13, 2001, pages 363 - 374 |
| DUCK P ET AL., BIOTECHNIQUES, vol. 9, 1990, pages 142 - 148 |
| HATCHET ET AL., GENET ANAL., vol. 15, no. 2, 1999, pages 35 - 40 |
| LISBY, MOL. BIOTECHNOL., vol. 12, no. 1, 1999, pages 75 - 99 |
| LIZARDI ET AL., BIOLTECHNOLOGY, vol. 6, 1988, pages 1197 |
| NAZARENKO ET AL., NUCLEIC ACIDS RESEARCH, vol. 25, no. 12, 1997, pages 2516 - 2521 |
| PHYFFER ET AL., J. CLIN. MICROBIOL., vol. 34, 1996, pages 834 - 841 |
| SAIKI ET AL., SCIENCE, vol. 230, 1985, pages 1350 - 1354 |
| See also references of EP4421814A4 |
| SHERRILL CB ET AL., JOURNAL OF THE AMERICAN CHEMICAL SOCIETY, vol. 126, 2004, pages 4550 - 4556 |
| TYAGI, NATURE BIOTECHNOLOGY, 14 March 1996 (1996-03-14) |
| VUORINEN ET AL., J. CLIN. MICROBIOL., vol. 33, 1995, pages 1856 - 1859 |
| WALKER ET AL., NUCLEIC ACIDS RES., vol. 20, no. 7, 1992, pages 1691 - 6 |
| WALKER PCR METHODS APPL, vol. 3, no. 1, 1993, pages 1 - 6 |
| WHITCOMBE ET AL., NATURE BIOTECHNOLOGY, vol. 17, 1999, pages 804 - 807 |
Also Published As
| Publication number | Publication date |
|---|---|
| KR20240093623A (ko) | 2024-06-24 |
| US20240418649A1 (en) | 2024-12-19 |
| EP4421814A1 (en) | 2024-08-28 |
| EP4421814A4 (en) | 2025-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Malpartida-Cardenas et al. | Quantitative and rapid Plasmodium falciparum malaria diagnosis and artemisinin-resistance detection using a CMOS Lab-on-Chip platform | |
| Ali et al. | Analysis of pork adulteration in commercial burgers targeting porcine-specific mitochondrial cytochrome B gene by TaqMan probe real-time polymerase chain reaction | |
| Tsai et al. | Development of TaqMan probe-based insulated isothermal PCR (iiPCR) for sensitive and specific on-site pathogen detection | |
| Chen et al. | Rapid Sanger sequencing of the 16S rRNA gene for identification of some common pathogens | |
| Duan et al. | Development and evaluation of a novel and rapid detection assay for Botrytis cinerea based on loop-mediated isothermal amplification | |
| AU2022202180B2 (en) | Method and device for analyzing target analyte in sample | |
| Dhami et al. | A HRM real-time PCR assay for rapid and specific identification of the emerging pest spotted-wing drosophila (Drosophila suzukii) | |
| CN106995841B (zh) | 一种转基因大豆检测用多重pcr试剂盒及检测方法 | |
| JP2012530243A (ja) | 核酸検出方法 | |
| Li et al. | Morphology and molecular identification of the Eimeria spp. in domestic rabbits | |
| Hu et al. | Visual identification for species and sex derived from bloodstain based on phosphate-mediated isothermal amplification colorimetric system | |
| WO2023068823A1 (ko) | 시료 내 표적 분석물질에 대한 양음성 판독 장치 및 방법 | |
| Guan et al. | A simple method to extract DNA from hair shafts using enzymatic laundry powder | |
| Sumon et al. | Droplet digital PCR for fish pathogen detection and quantification: A systematic review and meta‐analysis | |
| WO2024147568A1 (ko) | 분자진단 분석 결과의 획득 방법, 분자진단 분석 결과를 추정하는 모델의 획득 방법 및 이를 수행하는 컴퓨터 장치 | |
| Kanchanaphum | Time course of detection of human male DNA from stained blood sample on various surfaces by loop mediated isothermal amplification and polymerase chain reaction | |
| WO2022146052A1 (en) | Optical spectrometry-based method and device for detecting target analyte in sample | |
| WO2024128468A1 (ko) | Assay용 컴포넌트 생성 방법 및 이를 수행하는 assay용 컴포넌트 생성 장치 | |
| Kakumanu et al. | Detection, quantification, and elimination of Wolbachia in bed bugs | |
| RU2722758C1 (ru) | Набор синтетических олигонуклеотидов для выявления ДНК представителей семейства Оленевые | |
| WO2023121167A1 (ko) | 검출 장치의 성능을 예측하기 위한 방법 | |
| WO2026005528A1 (ko) | 시료 내 타겟 분석물에 대한 데이터 세트의 보정 방법 및 장치 | |
| Tupik et al. | Microchip device with dry-stored reagents for Loop mediated isothermal amplification | |
| Gaddam et al. | Quantitative and qualitative assessment of sex sorted semen of Bos indicus and Bos taurus breeds | |
| WO2023177221A1 (en) | Device for determining presence/absence of target nucleic acid, method for determining presence/absence of target by the device, server for distributing update information, and method for distributing update information by the server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22884045 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 18701453 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2022884045 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2022884045 Country of ref document: EP Effective date: 20240521 |