Apparatus, method, and non-transitory computer readable medium

Abstract

Provided are a device, a method, and a non-transitory computer-readable medium, the device being provided with: a detection unit that detects the position of a probe hybridized with a nucleic acid contained in a sample, from among a plurality of probes that are respectively provided in a unique position in a biochip and at least some of which have mutually different base sequences; and a learning processing unit that performs learning processing of the model using learning data including a pattern of the position of the probe that hybridizes with the nucleic acid contained in the sample and that is detected by the detection unit, and a species of an organism having the nucleic acid contained in the sample. The model outputs the species of an organism having a nucleic acid contained in a sample according to a new input of a pattern of positions of probes hybridized with the nucleic acid contained in the sample.

Description

Technical Field

[0001] The present invention relates to an apparatus, a method, and a non-transitory computer-readable medium. Background Art

[0002] Patent Document 1 (for example, paragraphs 0215 and 0316) etc. describe "1. Design, synthesize, and purify a fluorescent probe for target RNA. 2. Use Biodot to print the probe (1 nM) and a surfactant (for example, Zwittergent) onto an X plate. 3. Apply 1 drop of blood onto a substrate plate, close the chip and press it, and incubate at room temperature for 1 minute. 4. Insert the chip into the apparatus, take a photo, and analyze the data.", "The printed probe and the surfactant (for example, Zwittergent) dissolve in the blood. The surfactant (for example, Zwittergent) lyses red blood cells, and to promote the probe entering the cells and binding to the target RNA, the white blood cells are permeabilized." Prior Art Documents Patent Document 1: Japanese Patent Application Laid-Open No. 2021-536019 Patent Document 2: Japanese Patent Application Laid-Open No. 2013-510579 Patent Document 3: Japanese Patent Application Laid-Open No. 2018-508228 Patent Document 4: International Publication No. 2019 / 43779 Patent Document 5: Japanese Patent No. 5624487 Patent Document 6: Japanese Patent No. 6439810 Patent Document 7: Japanese Patent No. 5928906 Patent Document 8: Japanese Patent Application Laid-Open No. 2015-42152 Non-Patent Document 1: Takanuma et al., "Development of a Nucleic Acid Detection Method for Rapid Microbial Inspection", Yokogawa Technical Report Vol. 60, 2017, Internet <URL: https: / / web-material3.yokogawa.com / 19 / 13323 / tabs / rd-tr-r06001-002.jp.pdf> Summary of the Invention

[0003] In a first aspect of the present invention, there is provided an apparatus comprising: a detection unit that detects the positions of probes among a plurality of probes that have hybridized with nucleic acids contained in a sample, the plurality of probes being respectively disposed at specific positions in a biochip, and at least a part of the probes having mutually different base sequences; and a learning and processing unit that performs learning processing of a model using learning data, the learning data including the pattern of the positions of the probes that have hybridized with the nucleic acids contained in the sample and have been detected by the detection unit, and the species of the organism having the nucleic acids contained in the sample, the model outputting the species of the organism having the nucleic acids contained in the sample based on a new input of the pattern of the positions of the probes that have hybridized with the nucleic acids contained in the sample.

[0004] In the above apparatus, the learning and processing unit may perform separate and different learning processing of the model for each type of the biochip in which at least one of the base sequence of the probe and the specific position of the probe is different.

[0005] Any of the above apparatuses may further comprise: a supply unit that supplies the model with the pattern of the positions of the probes that have hybridized with the nucleic acids contained in a sample and have been newly detected by the detection unit; and a determination unit that determines the species of the organism having the nucleic acids contained in the sample as the species of the organism output from the model based on the pattern of the positions of the probes supplied by the supply unit.

[0006] In a second aspect of the present invention, there is provided an apparatus comprising: a detection unit that detects the positions of probes among a plurality of probes that have hybridized with nucleic acids contained in a sample, the plurality of probes being respectively disposed at specific positions in a biochip, and at least a part of the probes having mutually different base sequences; a supply unit that supplies the model with the pattern of the positions of the probes detected by the detection unit, the model outputting the species of the organism having the nucleic acids contained in the sample based on an input of the pattern of the positions of the probes that have hybridized with the nucleic acids contained in the sample; and a determination unit that determines the species of the organism having the nucleic acids contained in the sample as the species of the organism output from the model based on the pattern of the positions of the probes supplied by the supply unit.

[0007] In any of the above apparatuses having the determination unit, the supply unit may supply the model corresponding to the biochip in which the positions of the probes detected by the detection unit are located among a plurality of models that are different for each type of the biochip in which at least one of the base sequence of the probe and the specific position of the probe is different, with the pattern of the positions of the probes detected by the detection unit.

[0008] In any of the above apparatuses, at least a part of the plurality of probes may have a base sequence common among a plurality of species of organisms.

[0009] In any of the above-described apparatuses, the plurality of probes may each have a base sequence with 20 or fewer bases.

[0010] In a third aspect of the present invention, there is provided a method including: a detection step of detecting the positions of probes among a plurality of probes that have hybridized with nucleic acids contained in a sample, the plurality of probes being respectively arranged at specific positions in a biochip and at least some of the probes having mutually different base sequences; and a learning process step of performing a learning process of a model using learning data, the learning data including the pattern of the positions of the probes that have hybridized with the nucleic acids contained in the sample and have been detected in the detection step, and the species of the organism having the nucleic acids contained in the sample, the model outputting the species of the organism having the nucleic acids contained in the sample based on a new input of the pattern of the positions of the probes that have hybridized with the nucleic acids contained in the sample.

[0011] In a fourth aspect of the present invention, there is provided a method including: a detection step of detecting the positions of probes among a plurality of probes that have hybridized with nucleic acids contained in a single sample, the plurality of probes being respectively arranged at specific positions in a biochip and at least some of the probes having mutually different base sequences; a supply step of supplying the model with the pattern of the positions of the probes detected in the detection step, the model outputting the species of the organism having the nucleic acids contained in the sample based on an input of the pattern of the positions of the probes that have hybridized with the nucleic acids contained in the sample; and a determination step of determining, as the species of the organism having the nucleic acids contained in the single sample, the species of the organism output from the model based on the pattern of the positions of the probes supplied in the supply step.

[0012] In a fifth aspect of the present invention, there is provided a non-transitory computer-readable medium having recorded thereon a program that causes a computer to function as a detection unit and a learning process unit, the detection unit detecting the positions of probes among a plurality of probes that have hybridized with nucleic acids contained in a sample, the plurality of probes being respectively arranged at specific positions in a biochip and at least some of the probes having mutually different base sequences, the learning process unit performing a learning process of a model using learning data, the learning data including the pattern of the positions of the probes that have hybridized with the nucleic acids contained in the sample and have been detected by the detection unit, and the species of the organism having the nucleic acids contained in the sample, the model outputting the species of the organism having the nucleic acids contained in the sample based on a new input of the pattern of the positions of the probes that have hybridized with the nucleic acids contained in the sample.

[0013] In a sixth aspect of the present invention, a non-transitory computer-readable medium is provided, which records a program that causes a computer to function as a detection unit, a supply unit, and a determination unit. The detection unit detects the positions of probes among a plurality of probes that have hybridized with nucleic acids contained in a sample. The plurality of probes are respectively provided at inherent positions within a biochip, and at least a part of the probes have mutually different base sequences. The supply unit supplies a pattern of the positions of the probes detected by the detection unit to a model. The model outputs the species of a living organism that contains the nucleic acids in the sample based on the input of the pattern of the positions of the probes that have hybridized with the nucleic acids contained in the sample. The determination unit determines the species of the living organism output from the model based on the pattern of the positions of the probes supplied by the supply unit as the species of the living organism that contains the nucleic acids in the one sample.

[0014] In addition, the above summary of the invention does not enumerate all of the essential features of the present invention. In addition, sub-combinations of these feature groups can also form inventions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Device 1 of the embodiment is shown. Figure 2 The probe 101 of the biochip 100 of the embodiment is shown together with the transparent substrate 105 and the nucleic acid 110. Figure 3 The operation of device 1 is shown. Figure 4 Other operations of device 1 are shown. Figure 5 An example of a computer 2200 that can implement the present invention in whole or in part is shown. REFERENCE SIGNS LIST 1 Device 11 Injection unit 12 Detection unit 13 Learning data acquisition unit 14 Storage unit 15 Learning processing unit 16 Supply unit 17 Determination unit 100 Biochip 101 Probe 105 Transparent substrate 110 Nucleic acid 140 Learning data file 141 Model 1011 First probe 1012 Second probe 1013 Fluorescent dye 1014 Quencher 2200 Computer 2201 DVD-ROM 2210 Main Controller 2212 CPU 2214 RAM 2216 Graphics Controller 2218 Display Device 2220 Input / Output Controller 2222 Communication Interface 2224 Hard Disk Drive 2226 DVD-ROM Drive 2230 ROM 2240 Input / Output Chip 2242 Keyboard Detailed Implementation Manner

[0016] The present invention will be described below through embodiments of the invention. However, the following embodiments do not limit the invention claimed in the claims. In addition, all combinations of features described in the embodiments are not necessarily essential in the solution of the invention.

[0017] <1. Device> Figure 1 Figure 1 shows the device 1 of the present embodiment. The device 1 can perform the learning process of the model 141 for determining the types of microorganisms mixed in food or beverages. In addition to or instead of this, the model 141 can be used to determine the types of microorganisms mixed in food or beverages. The device 1 includes an injection unit 11, a detection unit 12, a learning data acquisition unit 13, a storage unit 14, a learning processing unit 15, a supply unit 16, and a determination unit 17.

[0018] Regarding microorganisms of a specific object, as an example, those selected from the group consisting of the genus Acinetobacter, the genus Actinomyces, the genus Aerococcus, the genus Aeromonas, the genus Alcaligenes, the genus Bacillus, the genus Bacteriodes, the genus Bordetella, the genus Branhamella, the genus Brevibacterium, the genus Campylobacter, the genus Candida, the genus Capnocytophaga, the genus Chromobacterium, the genus Clostridium, the genus Corynebacterium, the genus Cryptococcus, the genus Deinococcus, the genus Enterococcus, the genus Erysipelothrix, the genus Escherichia, the genus Flavobacterium, the genus Gemella, the genus Haemophilus, the genus Klebsiella, the genus Lactobacillus, the genus Lactococcus, the genus Legionella, the genus Leuconostoc, the genus Listeria, the genus Micrococcus, the genus Mycobacterium, the genus Neisseria, the genus Cryptosporidium, the genus Nocardia, the genus Oerskovia, the genus Paracoccus, the genus Pediococcus, the genus Peptostreptococcus, the genus Propionibacterium, the genus Proteus, the genus Pseudomonas, the genus Rahnella, the genus Rhodococcus, the genus Rhodospirillium, the genus Staphylococcus, the genus Streptomyces, the genus Streptococcus, the genus Vibrio, and the genus Yersinia may be used.There are microorganisms that form spores and other such forms under oligotrophic conditions, regardless of the state of the cells caused by such growth conditions.

[0019] <1.1. Injection unit 11> The injection unit 11 injects a sample into the biochip 100. The sample may contain nucleic acids of any microorganism of a specific target (as an example, genomic DNA, ribosomal RNA, plasmid DNA, etc.). The sample can be generated from food or beverage by a conventionally known method. For example, microorganisms contained in a specimen extracted from food or beverage can be recovered by filtration or centrifugation, and the nucleic acids of the microorganisms can be extracted to generate a sample. The recovered microorganisms can be used for nucleic acid extraction after culturing. As a method for extracting nucleic acids from microorganisms, the method described in International Publication No. 2019 / 43779 and Japanese Patent No. 5624487, the so-called dHTP method, can be used. As an example, the microorganisms captured by the filter can be placed together with the filter in a container and exposed to high temperature conditions to destroy the membrane structure of the microorganisms, and the nucleic acids can be extracted. The extracted nucleic acids can be amplified by the PCR (polymerase chain reaction) method.

[0020] The injection unit 11 of the present embodiment can inject a sample into biochips 100 of the same type. The biochip 100 has a plurality of probes inside. Among these plurality of probes, at least some of the probes can have mutually different base sequences. As an example, all the probes of the biochip 100 can each have a base sequence different from that of the other probes, and some of the probes of the biochip 100 can also have the same base sequence as the other probes.

[0021] At least some of the plurality of probes contained in the biochip 100 can have a base sequence common to multiple types of microorganisms. In the case where the biochip 100 has a probe with a base sequence not common to multiple types of microorganisms, the base sequence can be an inherent base sequence of a specific target microorganism or a base sequence not contained in the specific target microorganism. However, at the design stage of the biochip 100, the base sequences of the respective probes can be determined regardless of the base sequences of the nucleic acids of the specific target microorganisms. As an example, as long as the base sequences of the respective probes are the same among biochips 100 of the same type, the base sequences of the respective probes can be randomly determined. Each probe can separately contain a base sequence with 20 or fewer bases. As an example, the number of probes with mutually different base sequences can be 100 or more.

[0022] Each probe can hybridize with a corresponding base sequence. At least a part of the plurality of probes can have a base sequence complementary to at least a part of the nucleic acid of a microorganism of a specific object, and can specifically hybridize with the nucleic acid of the corresponding base sequence.

[0023] The biochip 100 can further include a positive control probe that emits a signal detected by the detection unit 12 independently of the nucleic acid contained in the sample. The positive control probe may not hybridize with the nucleic acid.

[0024] Each probe and the positive control probe can be set at an inherent position within the same type of biochip 100. For example, in the same type of biochip 100, the probes at the same position can have the same base sequence. In the present embodiment, as an example, the biochip 100 can have a plurality of probes and one or more positive control probes on the inner sides of two relatively arranged transparent substrates. The biochip 100 can have an injection port for injecting the sample into the interior and a discharge port for discharging the liquid inside.

[0025] A label can be pre - attached to at least one of the probes of the biochip 100 and the nucleic acid contained in the sample, and the label emits a signal detectable by the detection unit 12 described later in the hybridized state. For example, the label can be attached to the probe, and a signal can be emitted according to the hybridization of the probe with the nucleic acid. Instead, the label can also be attached to the nucleic acid of the sample, and a signal can be emitted regardless of whether the nucleic acid hybridizes with the probe. In this case, after injecting the sample into the biochip 100, the nucleic acid that has not hybridized with the probe can be removed from the biochip 100, and then the signal can be detected. As the label, fluorescent dyes, radioisotopes, paramagnetic isotopes, enzymes, etc. can be used. In the present embodiment, as an example, the label can be a fluorescent dye and can be attached to the probe. In addition, a label can be pre - attached to the positive control probe. The label of the positive control probe can always emit a signal.

[0026] In addition, since at least a part of the probes of the biochip 100 of the present embodiment have a base sequence common to multiple types of microorganisms, it is not possible to determine the microorganism (also referred to as the contaminating microorganism) having the nucleic acid contained in the sample only by confirming the presence or absence of hybridization of individual probes. On the other hand, since at least a part of the probes of the biochip 100 have mutually different base sequences, the position pattern of the hybridized probes may be different depending on the type of the contaminating microorganism. Therefore, the biochip 100 of the present embodiment can determine the type of the contaminating microorganism consistent with the position pattern of the hybridized probes by learning the position pattern of the hybridized probes and the type of the contaminating microorganism.

[0027] <1.2. Detection unit 12> The detection unit 12 detects the positions of the probes among the multiple probes of the biochip 100 that have hybridized with the nucleic acids contained in the sample. The detection unit 12 can use the positions of the positive control probes as a reference to detect the positions of the hybridized probes. The detection unit 12 can detect the hybridized probes and the positive control probes by detecting the labels within the biochip 100. The detection unit 12 can detect the signals emitted from the labels attached to either the hybridized probes or the nucleic acids. The detection unit 12 can also detect the signals emitted from the positive control probes. The detection unit 12 can detect the labels within the biochip 100 while being fixed in position relative to the biochip 100. The detection unit 12 can be disposed opposite to the biochip 100 and detect the labels within the biochip 100 through the transparent substrate of the biochip 100. The detection unit 12 can supply the data of the pattern indicating the positions of the detected labels (also referred to as position pattern data) to the learning data acquisition unit 13 and the supply unit 16. The position pattern data may also include information indicating the intensity of the signals at each detection position. When the detection unit 12 detects fluorescence from the labels as signals, the position pattern data may also include information indicating the wavelengths of the signals at each detection position.

[0028] <1.3. Learning data acquisition unit 13> The learning data acquisition unit 13 acquires learning data, which includes the pattern of the positions of the probes that have hybridized with the nucleic acids contained in the sample and have been detected by the detection unit 12, and the types of microorganisms having the nucleic acids contained in the sample. The learning data can be data used in the learning of the model 141. The microorganisms having the nucleic acids contained in the sample can be the microorganisms that are the extraction sources of the nucleic acids contained in the sample, and can be the microorganisms contained in the food or beverage that is the generation source of the sample.

[0029] The learning data acquisition unit 13 can correspond the position pattern data indicating the position pattern of the probes that have hybridized with the nucleic acids contained in the sample and have been detected with the data indicating the types of microorganisms that are the extraction sources of the nucleic acids (also referred to as class data) to generate learning data. The learning data acquisition unit 13 can acquire the position pattern data from the detection unit 12 and acquire the class data from the operator. As an example, in the learning step of the model 141, a sample containing the nucleic acids of an arbitrary microorganism can be generated by the operator and injected into the biochip 100. The class data of the microorganism can be supplied from the operator to the learning data acquisition unit 13, and the position pattern data of the probes that have hybridized with the nucleic acids of the microorganism can be supplied from the detection unit 12 to the learning data acquisition unit 13. The learning data acquisition unit 13 can acquire the pre-generated learning data in which the position pattern data and the class data are corresponded from the operator or the like. The learning data acquisition unit 13 can supply the acquired learning data to the storage unit 14.

[0030] <1.4. Storage unit 14> The storage unit 14 stores various kinds of information. The storage unit 14 can store the learning data file 140 and the model 141.

[0031] <1.4.1. Learning data file 140> The learning data file 140 stores learning data. In this embodiment, as an example, the learning data file 140 can store each piece of learning data supplied from the learning data acquisition unit 13.

[0032] <1.4.2. Model 141> The model 141 outputs the types of microorganisms mixed in the sample according to the pattern of the positions of the probes newly hybridized with the nucleic acids contained in the sample. In this embodiment, as an example, the model 141 can output the types of microorganisms according to the position pattern data output from the detection unit 12. The model 141 can receive the learning process of the learning processing unit 15. As an example, the model 141 can be an image analysis engine.

[0033] <1.5. Learning processing unit 15> The learning processing unit 15 performs the learning process of the model 141. The learning processing unit 15 reads the learning data from the learning data file 140 of the storage unit 14 and performs the learning process on the model 141 in the storage unit 14. The learning processing unit 15 can perform the learning process of the model 141 through machine learning such as deep learning.

[0034] <1.6. Supply unit 16> The supply unit 16 supplies the pattern of the positions of the probes that hybridize with the nucleic acids contained in one sample and are newly detected by the detection unit 12 to the model 141. The supply unit 16 can supply the position pattern data supplied from the detection unit 12 to the model 141 that has undergone the learning process by the learning processing unit 15. Thus, data representing the types of microorganisms mixed in can be output from the model 141 to the determination unit 17.

[0035] <1.7. Determination unit 17> The determination unit 17 determines the types of microorganisms mixed in the above-mentioned one sample according to the types of microorganisms output from the model 141 when the position pattern data is supplied from the supply unit 16 to the model 141. The determination unit 17 can output information representing the types of microorganisms mixed in to the outside.

[0036] According to the above device 1, learning processing of the model 141 is performed using learning data, where the learning data includes the position pattern of probes detected based on hybridization with nucleic acids contained in a sample and the types of microorganisms having the nucleic acids contained in the sample. Therefore, a model 141 can be generated that outputs the types of microorganisms mixed in according to the input position pattern of hybridized probes. Thus, even without preparing probes with the inherent base sequences of each microorganism, the types of microorganisms mixed in can be determined by inputting the position pattern of hybridized probes into the model 141, and thus the biochip 100 can be made low-cost.

[0037] In addition, the types of microorganisms output from the model 141 according to the pattern of the positions of the probes newly detected by the detection unit 12 are determined as the types of microorganisms mixed in. Therefore, by having the detection unit 12 detect the positions of the hybridized probes, the types of microorganisms mixed in can be determined.

[0038] In addition, at least a part of the multiple probes of the biochip 100 has a base sequence common among multiple types of microorganisms. Therefore, compared with the case where each of the multiple probes has an inherent base sequence for each microorganism, the base sequence of the probes can be made shorter. Thus, the biochip 100 can be made low-cost.

[0039] In addition, each of the multiple probes of the biochip 100 has a base sequence with 20 or fewer bases. Therefore, compared with the case of having a base sequence with more than 20 bases, the biochip 100 can be made low-cost.

[0040] <2. Probes of the Biochip 100> Figure 2 The probe 101 of the biochip 100 of the present embodiment is shown together with the transparent substrate 105 and the nucleic acid 110. The blackened arrow marks in the figure represent the probe or the nucleic acid, and the front end side of the arrow represents the 5' end, and the base end side of the arrow represents the 3' end.

[0041] Each probe 101 may include a first probe 1011 and a second probe 1012 having base sequences that are complementary to each other. The first probe 1011 may be a fluorescent probe modified with a fluorescent pigment 1013, and the second probe 1012 may be a quenching probe modified with a quenching substance 1014 that inhibits the luminescence of the fluorescent pigment. As shown on the left side in the figure, when there is no target nucleic acid in the biochip 100, the first probe 1011 and the second probe 1012 hybridize with each other, and the fluorescent pigment 1013 of the first probe 1011 approaches the quenching substance of the second probe 1012, which can inhibit the luminescence of the fluorescent pigment 1013 of the first probe 1011. As shown on the right side in the figure, when there is a target nucleic acid 110 in the biochip 100, at least one of the first probe 1011 and the second probe 1012 hybridizes with the target nucleic acid 110, the fluorescent pigment 1013 of the first probe 1011 is separated from the quenching substance 1014 of the second probe 1012, and the fluorescent pigment 1013 of the first probe 1011 can emit light. In the biochip 100 having such probes, after injecting a sample into the biochip 100, the detection of the label can be performed without removing nucleic acids that have not hybridized with the probe 101 from the biochip 100. As such a biochip 100, for example, a biochip described in Japanese Patent No. 6439810, Japanese Patent No. 5928906, Japanese Patent Laid-Open No. 2015-42152, and the following Literature 1 can be used.

[0042] Literature 1: Takanuma et al., "Development of a Nucleic Acid Detection Method for Rapid Microbial Inspection", Yokogawa Technical Report Vol. 60, 2017, Internet <URL: https: / / web-material3.yokogawa.com / 19 / 13323 / tabs / rd-tr-r06001-002.jp.pdf>

[0043] <3. Operation of Device 1> Figure 3 Represents the operation of Device 1. Device 1 performs the learning process of Model 141 by performing the processes of Steps S11 to S23.

[0044] In Step S11, the injection unit 11 injects a sample into the biochip 100. The injected sample may contain nucleic acids of one or more microorganisms arbitrarily selected by the operator from specific target microorganisms.

[0045] In Step S13, the detection unit 12 detects the positions of the probes among the multiple probes of the biochip 100 that have hybridized with the nucleic acids contained in the sample. Thus, the positions of the probes having mutually different base sequences that have hybridized with the nucleic acids of the microorganisms contained in the sample can be detected.

[0046] In step S15, the learning data acquisition unit 13 acquires learning data including a pattern of positions of probes that hybridize with nucleic acids contained in a sample and are detected by the detection unit 12, and the types of microorganisms having the nucleic acids contained in the sample. The learning data acquisition unit 13 can acquire position pattern data from the detection unit 12 and acquire microorganism category data from the operator. The category data can represent the type of a single microorganism or the types of multiple microorganisms.

[0047] In step S21, the learning data acquisition unit 13 determines whether the number of learning data has reached a reference number. The reference number can be set arbitrarily. When the number of learning data has not reached the reference number (step S21: No), the process can transfer to step S11. When the number of learning data has reached the reference number (step S21: Yes), the process can transfer to step S23.

[0048] In step S23, the learning processing unit 15 performs learning processing of the model 141 using the acquired learning data. Thereby, a model 141 is generated that outputs the types of one or more contaminating microorganisms based on the input pattern of the positions of the hybridized probes.

[0049] In addition, the learning processing unit 15 can perform cross-validation and evaluate the performance of the model 141. For example, after the learning processing unit 15 performs learning processing of the model 141 using a part of the learning data in the storage unit 14, the learning processing unit 15 can evaluate the model 141 based on the degree of consistency between the types of microorganisms output by supplying the position pattern data of another part of the learning data to the model 141 and the types of microorganisms represented by the category data. The learning processing unit 15 can end the learning processing of the model 141 based on the degree of consistency being equal to or higher than a reference value. The learning processing unit 15 can transfer the process to step S11 based on the degree of consistency being less than the reference value, or can output an error signal and end the process. The error signal can prompt the operator to use a different type of biochip to re-perform the operations of steps S11 to S23 for a new model 141.

[0050] Figure 4 Represents other operations of the apparatus 1. The apparatus 1 determines contaminating microorganisms by performing the processing of steps S31 to S37 and using the model 141 that has undergone learning processing.

[0051] In step S31, the injection unit 11 injects a sample into the biochip 100. The injected sample can contain nucleic acids of one or more microorganisms among specific target microorganisms.

[0052] In step S33, similarly to step S13, the detection unit 12 detects the positions of the probes among the multiple probes of the biochip 100 that have hybridized with the nucleic acids contained in a sample.

[0053] In step S35, the supply unit 16 supplies the pattern of the positions of the probes detected by the detection unit 12 in step S33 to the model 141. Thereby, data indicating the types of one or more contaminating microorganisms are output from the model 141.

[0054] In step S37, the determination unit 17 determines the types of the microorganisms output from the model 141 as the types of the contaminating microorganisms in a sample. The determination unit 17 can output information indicating the types of the contaminating microorganisms to the outside. After the processing in step S37 is completed, the apparatus 1 can end the operation or can transfer the processing to the above-described step S31.

[0055] <4. Modification Example> In addition, in the above-described embodiment, it has been described that the apparatus 1 includes the injection unit 11, the learning data acquisition unit 13, the storage unit 14, the learning processing unit 15, the supply unit 16, and the determination unit 17, but any of these parts may not be provided. For example, when the apparatus 1 does not include the supply unit 16 and the determination unit 17, the learning processing unit 15 can perform the learning of the model 141 and output the learned model 141. In addition, when the apparatus 1 does not include the learning processing unit 15, the learned model 141 can be used to determine the contaminating microorganisms. In addition, when the apparatus 1 does not include the storage unit 14, the learning processing can be performed on the model 141 in the storage device connected to the outside, or the model 141 in the storage device connected to the outside can be used to determine the contaminating microorganisms.

[0056] In addition, it has been described that the injection unit 11 injects a sample into the same type of biochip 100, but the sample can also be injected into a plurality of types of biochips 100 in which at least one of the base sequences of the probes and the unique positions of the probes is different. In this case, the storage unit 14 can store different models 141 and learning data files 140 for each type of the biochip 100, and the learning data acquisition unit 13 can acquire the type of the biochip 100 used from the operator and store the learning data in the learning data file 140 corresponding to the type of the biochip 100 used.

[0057] In addition, when the sample is injected into a plurality of types of biochips 100, the learning processing unit 15 can perform the learning processing of the model 141 for each type of the biochip 100 respectively. Thereby, different from the case where the same model 141 is learned using different types of biochips 100, a decrease in learning accuracy can be prevented. In addition, the organisms in the sample can be determined using a variety of biochips 100.

[0058] In addition, in the case where a sample is injected into a plurality of types of biochips 100, the supply unit 16 can supply position pattern data to the model 141 corresponding to the biochip 100 that has been used, that is, the biochip 100 at the position where the probe has been detected by the detection unit 12, among the plurality of models 141 that are different for each type of biochip 100. Thereby, it is possible to identify microorganisms in the sample using a variety of biochips 100.

[0059] In addition, it has been described that the model 141 outputs the types of microorganisms containing nucleic acids in the sample, but it may also output the types of one or more organisms other than microorganisms. In this case, the organism of a specific object may be an animal, an insect, a plant, a mycoplasma, a virus, or the like.

[0060] In addition, various embodiments of the present invention can be described with reference to flowcharts and block diagrams. Here, a module can represent (1) a stage of a process of performing an operation or (2) a part of a device having a function of performing an operation. A specific stage and part can be implemented by a dedicated circuit, a programmable circuit supplied together with computer-readable instructions stored on a computer-readable medium, and / or a processor supplied together with computer-readable instructions stored on a computer-readable medium. The dedicated circuit may include digital and / or analog hardware circuits, and may also include an integrated circuit (IC) and / or discrete circuits. The programmable circuit may include a reconfigurable hardware circuit, which includes memory elements such as logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, flip-flops, registers, a field-programmable gate array (FPGA), a programmable logic array (PLA), etc.

[0061] A computer-readable medium may include any tangible device capable of storing instructions executable by an appropriate device. As a result, a computer-readable medium having instructions stored therein includes a product containing instructions capable of being executed in order to manufacture means for performing the operations specified by the flowchart or block diagram. Examples of computer-readable media may include: electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable media may include: floppy (registered trademark) disks, magnetic disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray (RTM) disc, memory stick, integrated circuit card, etc.

[0062] Computer-readable instructions include any one of source code and object code described by any combination of one or more programming languages including assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or object-oriented programming languages such as Smalltalk (registered trademark), JAVA (registered trademark), C++, etc., and existing procedural programming languages such as the "C" programming language or the same programming language.

[0063] The computer-readable instructions can be provided to a processor or programmable circuit of a general-purpose computer, a special-purpose computer, or other programmable data processing device via a local or local area network (LAN), a wide area network (WAN) such as the Internet, and the computer-readable instructions are executed to fabricate means for performing the operations specified by the flowchart or block diagram. Examples of the processor include: a computer processor, a processing unit, a microprocessor, a digital signal processor, a controller, a microcontroller, etc.

[0064] Figure 5 Examples of the computer 2200 that can implement various aspects of the present invention as a whole or in part. Through the program installed in the computer 2200, the computer 2200 can function as an operation associated with the device of the embodiment of the present invention or one or more parts of the device, or execute the operation or the one or more parts, and / or the computer 2200 can execute the process of the embodiment of the present invention or a stage of the process. In order to cause the computer 2200 to execute specific operations associated with several or all of the modules of the flowcharts and block diagrams described in this specification, such a program can be executed by the CPU 2212.

[0065] The computer 2200 of this embodiment includes a CPU 2212, a RAM 2214, a graphics controller 2216, and a display device 2218, which are interconnected through a main controller 2210. The computer 2200 also includes input / output units such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive, which are connected to the main controller 2210 via an input / output controller 2220. The computer also includes conventional input / output units such as a ROM 2230 and a keyboard 2242, which are connected to the input / output controller 2220 via an input / output chip 2240.

[0066] The CPU 2212 operates in accordance with programs stored in the ROM 2230 and the RAM 2214, thereby controlling each unit. The graphics controller 2216 acquires image data generated by the CPU 2212 in a frame buffer or the like provided in the RAM 2214 or itself, and displays the image data on the display device 2218.

[0067] The communication interface 2222 can communicate with other electronic devices via a network. The hard disk drive 2224 stores programs and data used by the CPU 2212 within the computer 2200. The DVD-ROM drive 2226 reads programs or data from the DVD-ROM 2201 and provides the programs or data to the hard disk drive 2224 via the RAM 2214. The IC card drive reads programs and data from the IC card and / or writes programs and data to the IC card.

[0068] The ROM 2230 stores therein a boot program and the like executed by the computer 2200 when activated and / or programs dependent on the hardware of the computer 2200. The input / output chip 2240 can also connect various input / output units to the input / output controller 2220 via a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0069] Programs are provided by a computer-readable medium such as the DVD-ROM 2201 or the IC card. The programs are read from the computer-readable medium and installed in the hard disk drive 2224, the RAM 2214, or the ROM 2230, which are also examples of computer-readable media, and are executed by the CPU 2212. The information processing described within these programs is read into the computer 2200, thereby bringing about cooperation between the programs and the above various types of hardware resources. The device or method can be configured to implement the operation or processing of information by accompanying the use of the computer 2200.

[0070] For example, in the case of performing communication between the computer 2200 and an external device, the CPU 2212 can execute a communication program loaded in the RAM 2214 and instruct the communication interface 2222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 2212, the communication interface 2222 reads the transmission data stored in the transmission buffer processing area provided in a recording medium such as the RAM 2214, the hard disk drive 2224, the DVD-ROM 2201, or the IC card, transmits the read transmission data to the network, or writes the received data received from the network to the reception buffer processing area provided on the recording medium, etc.

[0071] In addition, the CPU 2212 can read all or a necessary part of a file or database stored in an external recording medium such as the hard disk drive 2224, the DVD-ROM drive 2226 (DVD-ROM 2201), the IC card, etc. into the RAM 2214 and perform various types of processing on the data on the RAM 2214. Then, the CPU 2212 writes the processed data back to the external recording medium.

[0072] All kinds of information such as various types of programs, data, tables, and databases can be stored in a recording medium and undergo information processing. The CPU 2212 performs various types of processing described throughout this disclosure on the data read from the RAM 2214 and writes the results back to the RAM 2214. The various types of processing include various types of operations, information processing, conditional judgment, conditional branch, unconditional branch, information retrieval / replacement, etc. specified by the instruction sequence of the program. In addition, the CPU 2212 can retrieve information in files, databases, etc. within the recording medium. For example, in the case where a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 2212 can retrieve an entry that matches the condition specifying the attribute value of the first attribute from the plurality of entries, and read the attribute value of the second attribute stored in the entry, thereby obtaining the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0073] The programs or software modules described above can be stored in a computer-readable medium on or near the computer 2200. In addition, a recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable medium, whereby the program is provided to the computer 2200 via the network.

[0074] As described above, the present invention has been described using embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments. It is obvious that various changes or improvements can be made to the above embodiments by those skilled in the art. According to the description in the claims, the embodiments with such changes or improvements can also be included in the technical scope of the present invention.

[0075] In the claims, the description, and the drawings, the execution order of each process such as actions, processes, steps, and stages in the apparatus, system, program, and method is not specifically indicated as "earlier", "before", etc. In addition, it should be noted that as long as the output of the previous process is not used in the subsequent process, it can be implemented in any order. Regarding the action flow in the claims, the description, and the drawings, even if it is described using "first," "next," etc. for the sake of convenience, it does not mean that it must be implemented in that order.

Claims

1. A device, characterized in that: have: A detection unit that detects the position of a probe hybridized with a nucleic acid contained in a sample among a plurality of probes, wherein the plurality of probes are respectively arranged at specific positions in the biochip, and at least a part of the probes have base sequences different from each other; as well as A learning processing unit performs learning processing on a model using learning data, wherein the learning data includes a pattern of positions of probes hybridized with nucleic acids contained in a sample and detected by the detection unit, and a type of organism having the nucleic acids contained in the sample, wherein the model outputs the type of organism having the nucleic acids contained in the sample based on a new input of the pattern of positions of probes hybridized with nucleic acids contained in the sample.

2. The device according to claim 1, characterized in that The learning processing unit performs learning processing of the model that is different for each type of the biochip having different at least one of the base sequence of the probe and the unique position of the probe.

3. The device according to claim 1, characterized in that Also available: a supply unit that supplies the model with a pattern of positions of probes that hybridize with nucleic acids contained in one sample and are newly detected by the detection unit; as well as The identification unit identifies the type of organism output from the model based on the pattern of positions where the probes are supplied by the supply unit as the type of organism having the nucleic acid contained in the one sample.

4. The device according to claim 3, characterized in that The supply unit supplies a pattern of the positions of the probes detected by the detection unit to the model corresponding to the biochip in which the positions of the probes are detected by the detection unit, among the plurality of models that are different for each type of the biochips that are different in at least one of the base sequence of the probes and the inherent positions of the probes.

5. The device according to claim 1, characterized in that At least a part of the plurality of probes has a base sequence common to a plurality of species of organisms.

6. The device according to claim 1, characterized in that Each of the plurality of probes has a base sequence having 20 or less bases.

7. A device, characterized in that: have: A detection unit that detects the position of a probe hybridized with a nucleic acid contained in a sample among a plurality of probes, wherein the plurality of probes are respectively arranged at specific positions in the biochip, and at least a part of the probes have base sequences different from each other; a supply unit that supplies the pattern of the positions of the probes detected by the detection unit to the model, wherein the model outputs the type of organism having the nucleic acid contained in the sample based on the input of the pattern of the positions of the probes hybridized with the nucleic acid contained in the sample; as well as The identification unit identifies the type of organism output from the model based on the pattern of positions where the probes are supplied by the supply unit as the type of organism having the nucleic acid contained in the one sample.

8. A method, characterized in that have: A detection step of detecting the position of a probe hybridized with a nucleic acid contained in a sample among a plurality of probes, wherein the plurality of probes are respectively arranged at specific positions in the biochip, and at least a part of the probes have base sequences different from each other; as well as A learning processing step, using learning data to perform learning processing on the model, wherein the learning data includes a pattern of the positions of probes hybridized with the nucleic acid contained in the sample and detected by the detection step, and a type of organism having the nucleic acid contained in the sample, wherein the model outputs the type of organism having the nucleic acid contained in the sample based on a new input of the pattern of the positions of the probes hybridized with the nucleic acid contained in the sample.

9. A method, characterized in that have: A detection step of detecting the position of a probe hybridized with a nucleic acid contained in a sample among a plurality of probes, wherein the plurality of probes are respectively arranged at specific positions in the biochip, and at least a part of the probes have base sequences different from each other; a supplying step of supplying the pattern of the positions of the probes detected by the detecting step to the model, wherein the model outputs the type of organism having the nucleic acid contained in the sample based on the input of the pattern of the positions of the probes hybridized with the nucleic acid contained in the sample; as well as The step of determining the type of organism output from the model based on the pattern of positions to which the probes are supplied in the supplying step is a step of determining the type of organism having the nucleic acid contained in the one sample.

10. A non-transitory computer-readable medium, characterized in that The program that enables the computer to function as a detection unit and a learning processing unit is recorded therein. The detection unit detects the position of a probe hybridized with a nucleic acid contained in a sample among a plurality of probes, wherein the plurality of probes are respectively arranged at specific positions in the biochip, and at least a part of the probes have base sequences different from each other. The learning processing unit performs learning processing on the model using learning data, wherein the learning data includes a pattern of positions of probes hybridized with nucleic acids contained in a sample and detected by the detection unit, and a type of organism having the nucleic acids contained in the sample, and the model outputs the type of organism having the nucleic acids contained in the sample based on new input of the pattern of positions of probes hybridized with nucleic acids contained in the sample.

11. A non-transitory computer-readable medium, characterized in that The program that causes the computer to function as a detection unit, a supply unit, and a determination unit is recorded therein. The detection unit detects the position of a probe hybridized with a nucleic acid contained in a sample among a plurality of probes, wherein the plurality of probes are respectively arranged at specific positions in the biochip, and at least a part of the probes have base sequences different from each other. The supply unit supplies the pattern of the positions of the probes detected by the detection unit to the model, and the model outputs the type of organism having the nucleic acid contained in the sample based on the input of the pattern of the positions of the probes hybridized with the nucleic acid contained in the sample. The identification unit identifies the type of organism output from the model based on the pattern of positions where the probes are supplied by the supply unit as the type of organism having the nucleic acid contained in the one sample.

Images