Information processing apparatus, method for controlling information processing apparatus, and program
An apparatus includes an acquisition unit configured to acquire quantitative information on a test substance, the quantitative information being estimated by inputting, to a learning model, two or more pieces of spectral information selected from a plurality of pieces of spectral information on a sample containing the test substance and a foreign substance.
1. An apparatus comprising:
a database storing a learning model;
a processor; and
a memory containing instructions that, when executed by the processor, causing the processor to perform operations as:
an analyzing apparatus configured to analyze: (1) a first test substance to produce a plurality of test pieces of test spectral information, and (2) a target sample including a mixture of a second test substance and a foreign substance to produce a plurality of sample pieces of sample spectral information;
a selection unit configured to select two or more test pieces and two or more sample pieces;
an acquisition unit configured to acquire combined test spectral information of the two or more test pieces and combined sample spectral information of the two or more sample pieces;
a generation unit configured to generate a trained learning model using training data from the selected two or more test pieces; and
an estimation unit configured to estimate an amount of the second test substance by applying the trained learning model to the combined sample spectral information,
wherein estimated amount is transformed to a display format of a display unit.
2. The apparatus according to claim 1 , wherein the spectral information is selected based on a wavelength used for measuring a spectrum.
3. The apparatus according to claim 1 , wherein the selected spectral information is more in number than a kind of the test substance.
4. The apparatus according to claim 1 , wherein the spectral information comprises at least one selected from a group consisting of a chromatogram, a photoelectron spectrum, an infrared absorption spectrum, a nuclear magnetic resonance spectrum, a fluorescence spectrum, a fluorescent X-ray spectrum, an ultraviolet-visible absorption spectrum, a Raman spectrum, an atomic absorption spectrum, a frame emission spectrum, an emission spectrum, an X-ray absorption spectrum, an X-ray diffraction spectrum, a paramagnetic resonance absorption spectrum, an electron spin resonance spectrum, and a thermal-analysis spectrum.
5. The apparatus according to claim 1 , further comprising:
an analyzing unit configured to analyze the sample to acquire a plurality of pieces of spectral information on the sample.
6. The apparatus according to claim 5 , wherein the analyzing unit uses at least one selected from a group consisting of chromatography, capillary electrophoresis, photoelectric spectroscopy, infrared absorption spectroscopy, nuclear magnetic resonance spectroscopy, fluorescent spectroscopy, fluorescent X-ray spectroscopy, visible-ultraviolet absorption spectroscopy, Raman spectroscopy, an atomic absorption method, frame emission spectroscopy, emission spectroscopy, X-ray absorption spectroscopy, an X-ray diffraction method, electron spin resonance spectroscopy, and a thermo-analytical method.
7. The apparatus according to claim 1 , wherein the learning model is a learning model learned using, as training data, a plurality of sets of learning spectral information generated based on the selected spectral information and quantitative information on the test substance specified based on the selected spectral information.
8. The apparatus according to claim 7 , wherein the learning spectral information is generated using the selected spectral information and a random noise.
9. The apparatus according to claim 8 , wherein the random noise comprises a waveform obtained by a combination of a plurality of Gaussian functions.
10. The apparatus according to claim 1 , wherein the test substance comprises at least one selected from a group consisting of protein, deoxyribonucleic acid (DNA), virus, fungi, water-soluble vitamins, fat-soluble vitamins, organic acids, fatty acids, amino acids, sugars, agricultural chemicals, and environmental hormones.
11. The apparatus according to claim 10 , wherein the test substance comprises organic acids.
12. The apparatus according to claim 11 , wherein the organic acids comprise a vanillyl mandelic acid and creatinine.
13. The apparatus according to claim 1 , wherein the quantitative information comprises at least one selected from a group consisting of an amount of the test substance in the sample, a concentration of the test substance in the sample, presence or absence of the test substance in the sample, a ratio of the concentration or the amount of the test substance in the sample to a standard amount of the test substance, and a proportion of the concentration or the amount of the test substance in the sample.
14. A method comprising:
analyzing by an analyzing apparatus: (1) a first test substance to produce a plurality of test pieces of test spectral information, and (2) a target sample including a mixture of a second test substance and a foreign substance to produce a plurality of sample pieces of sample spectral information;
selecting two or more test pieces and two or more sample pieces;
acquiring combined test spectral information of the two or more test pieces and combined sample spectral information of the two or more sample pieces;
generating a trained learning model using training data from the selected two or more test pieces; and
estimating an amount of the second test substance by applying the trained learning model to the combined sample spectral information,
wherein estimated amount is transformed to a display format of a display unit.
15. The method according to claim 14 , wherein the spectral information is selected based on a wavelength used for measuring a spectrum.
16. The method according to claim 14 , wherein the selected spectral information is more in number than a kind of the test substance.
17. The method according to claim 14 , wherein the spectral information comprises at least one selected from a group consisting of a chromatogram, a photoelectron spectrum, an infrared absorption spectrum, a nuclear magnetic resonance spectrum, a fluorescence spectrum, a fluorescent X-ray spectrum, an ultraviolet-visible absorption spectrum, a Raman spectrum, an atomic absorption spectrum, a frame emission spectrum, an emission spectrum, an X-ray absorption spectrum, an X-ray diffraction spectrum, a paramagnetic resonance absorption spectrum, an electron spin resonance spectrum, and a thermal-analysis spectrum.
18. The method according to claim 14 , further comprising:
analyzing the sample to acquire a plurality of pieces of spectral information on the sample.
19. The method according to claim 18 , wherein the analyzing is performed using at least one selected from a group consisting of chromatography, capillary electrophoresis, photoelectric spectroscopy, infrared absorption spectroscopy, nuclear magnetic resonance spectroscopy, fluorescent spectroscopy, fluorescent X-ray spectroscopy, visible-ultraviolet absorption spectroscopy, Raman spectroscopy, an atomic absorption method, frame emission spectroscopy, emission spectroscopy, X-ray absorption spectroscopy, an X-ray diffraction method, electron spin resonance spectroscopy, and a thermo-analytical method.
20. The method according to claim 14 , wherein the learning model is a learning model learned using, as training data, a plurality of sets of learning spectral information generated based on the selected spectral information and quantitative information on the test substance specified based on the selected spectral information.
21. The method according to claim 20 , wherein the learning spectral information is generated using the selected spectral information and a random noise.
22. The method according to claim 21 , wherein the random noise is a waveform obtained by a combination of a plurality of Gaussian functions.
23. The method according to claim 14 , wherein the test substance comprises at least one selected from a group consisting of protein, deoxyribonucleic acid (DNA), virus, fungi, water-soluble vitamins, fat-soluble vitamins, organic acids, fatty acids, amino acids, sugars, agricultural chemicals, and environmental hormones.
24. The method according to claim 23 , wherein the test substance comprises organic acids.
25. The method according to claim 24 , wherein the organic acids comprise a vanillyl mandelic acid and creatinine.
26. The method according to claim 14 , wherein the quantitative information comprises at least one selected from a group consisting of an amount of the test substance in the sample, a concentration of the test substance in the sample, presence or absence of the test substance in the sample, a ratio of the concentration or the amount of the test substance in the sample to a standard amount of the test substance, and a proportion of the concentration or the amount of the test substance in the sample.
27. A non-transitory computer-readable recording medium that records a control program for executing a method, the method comprising:
analyzing: (1) a first test substance to produce a plurality of test pieces of test spectral information, and (2) a target sample including a mixture of a second test substance and a foreign substance to produce a plurality of sample pieces of sample spectral information;
selecting two or more test pieces and two or more sample pieces;
acquiring combined test spectral information of the two or more test pieces and combined sample spectral information of the two or more sample pieces;
generating a trained learning model using training data from the selected two or more test pieces; and
estimating an amount of the second test substance by applying the trained learning model to the combined sample spectral information,
wherein estimated amount is transformed to a display format of a display unit.
28. An apparatus comprising:
a database storing a learning model;
a processor; and
a memory containing instructions that, when executed by the processor, causing the processor to perform operations as:
an analyzing apparatus configured to analyze: (1) a first test substance to produce a plurality of test pieces of test spectral information, and (2) a target sample including a mixture of a second test substance and a foreign substance to produce a plurality of sample pieces of sample spectral information;
a selection unit configured to select two or more test pieces and two or more sample pieces;
an acquisition unit configured to acquire combined test spectral information of the two or more test pieces and combined sample spectral information of the two or more sample pieces;
a generation unit configured to generate a trained learning model using training data from the selected two or more test pieces; and
an estimation unit configured to estimate an amount of the second test substance by applying the trained learning model to the combined sample spectral information,
wherein the learning model is learned by associating learning spectral information generated from the plurality of test pieces of test spectral information selected based on the selected two or more sample pieces with quantitative information specified from the selected two or more test pieces, and
wherein estimated amount is transformed to a display format of a display unit.