Information processing device
The information processing device and method leverage mass spectrometry and document expression conversion to accurately match sample compounds with literature, addressing identification challenges and improving compound verification efficiency.
Patent Information
- Application Number
- JP2023078157
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-10
- Publication Date
- 2024-11-21
AI Technical Summary
Existing methods face difficulties in identifying and matching compounds contained in a sample with compounds described in literature due to challenges in obtaining and processing identification information, especially when samples contain multiple compounds and literature descriptions are incomplete.
An information processing device and method that utilizes mass spectrometry to acquire compound masses, converts document expressions into character string representations, and collates similarities between sample and literature data to verify compound matches.
Facilitates easy matching of compounds in samples with literature descriptions, enhancing accuracy and efficiency in identifying compounds contained in samples.
Smart Images

Figure 2024162552000001 
Figure 2024162552000002 
Figure 2024162552000003
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]
[0002] Patent Document 1 discloses a system for searching for documents from a query including a chemical formula, etc., with the aim of providing a document search method and a document search system that can shorten the search time for documents including similar words and improve the search accuracy. Thus, methods for searching for a desired document from among a large number of documents have been widely studied. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] WO2020 / 079751 Summary of the Invention [Problem to be solved by the invention]
[0004] When trying to identify whether a compound contained in a sample matches a compound described in a literature, one can first obtain information for identifying the compound (hereinafter also referred to as "identification information") by measuring various pieces of information obtained from the sample, and then search for compounds having that information in the literature.
[0005] However, it is not easy to obtain identification information of a compound contained in a sample. For example, when a sample contains multiple compounds, the information obtained from the sample is a mixture of identification information of the target compound and identification information of other compounds. Therefore, it is not easy to isolate and obtain identification information of a single compound.
[0006] In addition, even if identification information on a certain compound can be obtained from a sample, it is difficult to search for a compound having that information in a document. For example, when the document is a patent document or a paper, even if the name of a compound contained in a sample is described in the document, the identification information of the compound obtained by analysis is not necessarily described in the document. Therefore, it is difficult to immediately determine whether a certain document describes a target compound based on the identification information of the compound obtained by analysis.
[0007] Furthermore, because just determining whether a compound contained in a single sample matches a compound described in a single document is difficult, it becomes even more difficult to determine whether a compound contained in a single sample matches a compound described in a large number of documents.
[0008] The present invention has been made in consideration of the above problems, and has an object to provide an information processing device, an information processing method, and a program that can easily compare a compound contained in a sample with a compound described in a literature. [Means for solving the problem]
[0009] That is, the present invention is as follows. [1] An acquisition unit that acquires information regarding the masses of compounds contained in a document; and a collation unit that checks whether the sample contains the compound based on a mass spectrometry result of the sample and information on the mass of the compound. Information processing device. [2] the acquiring unit extracts an expression representing the compound from the literature, and acquires information regarding the mass of the compound based on the extracted expression representing the compound; The information processing device described in [1]. [3] the acquiring unit converts an expression representing the compound contained in the literature into character string representation information representing a structure of the compound, and acquires information relating to the mass of the compound based on the character string representation information representing the structure of the compound; An information processing device according to [1] or [2]. [4] The acquisition unit acquires, as the information on the mass of the compound, at least one of information on the monoisotopic mass of the compound, information on the mass of the compound including an adduct ion, and information on the mass of the compound due to a difference in valence. The information processing device according to any one of [1] to [3]. [5] The collation unit determines whether or not the compound is included based on a similarity between a peak included in the mass spectrometry result and information related to the mass of the compound. The information processing device according to any one of [1] to [4]. [6] An information processing device, obtaining information regarding the masses of compounds contained in a document; and determining whether or not the compound is contained in the sample based on the mass spectrometry result of the sample and information on the mass of the compound. Information processing methods. [7] In the information processing device, obtaining information regarding the masses of compounds contained in a document; and determining whether or not the compound is contained in the sample based on the mass spectrometry result of the sample and information on the mass of the compound. program. Effect of the Invention
[0010] An object of the present invention is to provide an information processing device, an information processing method, and a program that can easily compare a compound contained in a sample with a compound described in a literature. [Brief description of the drawings]
[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of a schematic configuration of a system according to an embodiment of the present invention. [Figure 2A] 1 is a diagram illustrating an example of a schematic configuration of an information processing apparatus according to an embodiment of the present invention. [Figure 2B] FIG. 2 is a diagram showing an example of a schematic configuration of matching data; [Figure 2C] FIG. 1 is a schematic diagram showing a flow of obtaining sample compound information. [Figure 2D] FIG. 1 is a schematic diagram showing a flow of obtaining literature compound information. [Figure 2E] FIG. 11 is a schematic diagram showing the flow of a matching process. [Diagram 3] FIG. 4 is a flowchart illustrating an example of an information processing method according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0012] Preferred embodiments of the present invention will be described in detail below with reference to the drawings. Note that the embodiments described below do not unduly limit the contents of the present invention described in the claims. Furthermore, not all of the configurations described below are necessarily essential components of the present invention.
[0013] 1. System Fig. 1 is a schematic diagram showing a smart verification system of the present embodiment. As shown in Fig. 1, in one example of the smart verification system of the present embodiment, a server 100 that performs a verification process, a terminal 200 used by a user, a device 300 that analyzes sample information, and a server 400 that accumulates literature information are connected via a network N.
[0014] The server 100 performing the matching process may execute a process of matching the information on the sample acquired from the device 300 with the information on the document acquired from the server 400, based on a request for the matching process from the terminal 200. The matching process will be described later.
[0015] The terminal 200 is a terminal scanned by a user, and transmits a request for a matching process to the server 100. The request for the matching process may include information specifying information about the sample to be used in the matching process, such as using a portion of the information about the sample acquired by the device 300 for the matching process. The request for the matching process may also include information specifying the range of documents to be targeted in the matching process, such as targeting documents from the 2020s or documents from a specific publisher. The terminal 200 may then receive information about the results of the matching process from the server 100, and control the display of the results on an output device.
[0016] The device 300 may be a computer included in a known analytical device, or may be an independent computer connected to such an analytical device. The device 300 may obtain the analysis results of the sample from the analytical device and transmit them to the server 100 or the terminal 200 upon request.
[0017] In this embodiment, the sample may be a compound, an agent, or a composition. As an example, the sample may be a chemical product available on the market.
[0018] Examples of the analytical device include, but are not limited to, elemental analysis devices such as fully automatic elemental analyzers (EA), energy dispersive X-ray fluorescence analyzers (EDX-XRF), and inductively coupled plasma mass analyzers (ICP-MS); morphological observation analysis devices such as transmission electron microscopes (TEM), scanning transmission electron microscopes (STEM (EDX, EELS)), and fluorescent X-ray analysis microscopes; chemical structure analysis devices such as ultraviolet-visible-near infrared spectrometers (UV-VIS), ultraviolet-visible-near infrared spectrometers (UV-VIS), nuclear magnetic resonance analyzers (NMR), X-ray diffraction devices (XRD), and matrix-assisted laser desorption / ionization-time of flight mass spectrometers (MALDI-TOFMS); chromatographic analysis devices such as gas chromatograph mass spectrometers (GC / MS) and liquid chromatograph mass spectrometers (LC-MS); and thermal analysis devices such as thermogravimetric differential thermal analyzers (TG-DTA).
[0019] In the following, the present embodiment will be described using a mass spectrometer as an example, however, the system of the present embodiment is not limited to those using a mass spectrometer, and can also be applied to conventionally known analytical devices such as those exemplified above, so long as the physical parameters obtained from the literature and the sample in the comparison process match.
[0020] The server 400 may be a server that accumulates information on patent documents, technical papers, etc. Specifically, the server 400 may be a document server of a patent office of a country, a server of a company that provides a patent document search service, or a server of a paper search service operated by a domestic or international academic society. The server 400 may transmit information on patent documents, technical papers, etc. to the server 100 or the terminal 200 in response to a request.
[0021] Hereinafter, each component will be described in detail assuming that the information processing device of this embodiment is the server 100. However, without being limited to this, the terminal 200 scanned by the user may execute the matching process executed by the server 100.
[0022] 1.1.Server 100 The information processing device (server 100) of this embodiment includes an acquisition unit that acquires information regarding the mass of a compound contained in a literature (hereinafter also referred to as "literature compound information"), and a comparison unit that checks whether the sample contains the compound based on the mass analysis result of a sample (hereinafter also referred to as "sample compound information") and the information regarding the mass of the compound.
[0023] Fig. 2A shows a schematic configuration diagram of the server 100. As shown in Fig. 2A, the information processing device (server 100) includes, for example, a processor 110, a communication interface 120, an input / output interface 130, a memory 140, a storage 150, and one or more buses 160 for interconnecting these components.
[0024] Processor 110 may include, by way of example and not limitation, one or more central processing units (CPUs); Microprocessor (MPU, Graphics Processing Unit (GPU), Processor Core, Multiprocessor processors, application specific integrated circuits (ASICs), application specific integrated circuits (FPGAs), etc. The present invention includes the above-described embodiments, which are disclosed in the accompanying drawings, and which are incorporated herein by reference in their entirety. Each of the above may implement a process, function, or method.
[0025] The communication interface 120 transmits and receives various data to and from other devices via a network. The communication may be performed either wired or wirelessly, and any communication protocol may be used as long as the devices can communicate with each other. For example, the communication interface 120 is implemented as hardware such as a network adapter, various communication software, or a combination of these.
[0026] The input / output interface 130 includes an input device for inputting various operations and an output device for outputting processing results, etc. For example, the input / output interface 130 may include information input devices such as a keyboard, a mouse, and a touch panel, and an information output device such as a display device 131. Note that the server 100 may receive a predetermined input and execute a predetermined output by connecting an external input / output interface 130.
[0027] The memory 140 temporarily stores the program loaded from the storage 150. The memory 140 provides a working area for the processor 110. Various data generated during program execution is also temporarily stored. 40 may be, for example, a DRAM, SRAM, DDR RAM or other random access solid state memory. A high-speed random access memory such as a memory device, or a combination of these. Good too.
[0028] The storage 150 stores programs, each functional unit, and various data. The storage 150 may store, for example, matching data 151. As shown in Fig. 2B, the matching data 151 may include a matching ID assigned to each matching process, sample compound information and literature compound information used for matching, and a matching result.
[0029] Storage 150 may also be, for example, one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or non-volatile memory such as other non-volatile solid-state storage devices, or a combination thereof. Another example of storage 150 may include one or more storage devices located remotely from processor 110.
[0030] The processor 110 executes processes, functions, or methods realized by codes or instructions included in a program stored in the storage 150. As shown in Fig. 2A, the processor 110 of this embodiment may function as a transmitting / receiving unit 111, an acquiring unit 112, a matching unit 113, and an output unit 114. Each functional unit will be described below.
[0031] The transmission / reception unit 111 may function, for example, as a transmission unit that transmits various information to other devices such as the terminal 200, the device 300, and the server 400 via the communication interface 120 and the network N, or as a reception unit that receives various information from other devices such as the terminal 200, the device 300, and the server 400.
[0032] For example, the transmitting / receiving unit 111 may receive a request for operation processing from the terminal 200, may receive sample compound information from the device 300, or may receive literature compound information from the server 400. In addition, the transmitting / receiving unit 111 may transmit a result of the matching processing to the terminal 200.
[0033] The acquiring unit 112 may acquire sample compound information from an apparatus 300 that analyzes sample information. FIG. 2C shows a flow of acquiring mass spectrometry results by analyzing a sample and recording the results in the matching data 151. The example shown in FIG. 2C shows that a sample containing multiple compounds (Unknown Chem1, 2, 3, ...) is subjected to mass spectrometry to obtain peaks corresponding to the masses of each compound contained in the sample as the mass spectrometry results. FIG. 2C shows an example of mass spectrum data obtained by the apparatus 300 having multiple peaks of m / z: ..., 120.09, 136.15, ..., 184.07, .... Here, each peak corresponds to each compound contained in the sample.
[0034] The acquiring unit 112 acquires mass analysis results for a plurality of compounds from the device 300 and records them in the matching data 151 (step S01). At this time, the acquiring unit 112 may exclude peaks having a predetermined mass or less using a low-pass filter or the like and record them in the matching data 151 as sample compound information, or may exclude peaks having a predetermined mass or more using a high-pass filter or the like and record them in the matching data 151. Alternatively, the acquiring unit 112 may exclude peaks having an intensity of a predetermined value or less using a low-pass filter or the like and record them in the matching data 151 as sample compound information.
[0035] In addition, the mass analysis results of a peak in a mass range specified by the user using the terminal 200, or a specific peak or peaks specified by the user using the terminal 200, may be recorded in the matching data 151 as sample compound information.
[0036] The mass analysis results recorded in the matching data 151 are used in the matching process described below. Therefore, by removing peaks that are likely to be noise using the above-mentioned filtering process or by specifying them through a user operation, it is possible to eliminate unnecessary matching processes.
[0037] The acquisition unit 112 may acquire at least one of the following information on the mass of a compound: information on the monoisotopic mass of a compound, information on the mass of a compound including an adduct ion, and information on the mass of a compound due to differences in valence. This allows the process of matching the sample compound information with the literature compound information to be performed taking these pieces of information into consideration.
[0038] The acquiring unit 112 may acquire information on the masses of compounds contained in documents from the server 400 that accumulates document information. Fig. 2D shows a flow of identifying compounds contained in documents from documents accumulated in the server 400 and acquiring information on their masses. In the example shown in Fig. 2D, the server 400 stores data on a plurality of documents (D1, D2, ... Dn, ...), and each document data discloses a plurality of compounds (Chem 1, Chem 2, ... Chem m, ...) contained in the document.
[0039] The acquiring unit 112 acquires one or more document data from the server 400, and extracts expressions representing compounds contained in the documents by processing such as text mining (step S02). As a result, expressions representing compounds described in the documents can be extracted and listed. When extracting expressions representing compounds, the acquiring unit 112 may use a publicly known library such as a python library that extracts expressions representing compounds from text data. Such a conventionally known library is not particularly limited, but an example of such a library is the python library ChemDataExtractor. In addition, as long as it is possible to extract expressions representing compounds from text data, other publicly known libraries may be used without being limited to ChemDataExtractor.
[0040] For non-English literature data, the literature data may be converted to English text data using a python library such as ChemDataExtractor. The conversion to English text data may be performed by known machine translation.
[0041] Next, the acquisition unit 112 may convert the expression representing the compound described in the document acquired as described above into character string expression information showing the structure of the compound (step S03). Such character string expression information is not particularly limited, but may be, for example, SMILES (simplified molecular input line entry system). Note that, as long as it is possible to show the structure of the compound, the notation method is not limited to SMILES, and other notation methods may be used.
[0042] The acquiring unit 112 may then convert the character string representation information acquired as described above into information related to the mass of the compound (step S04). At this time, the acquiring unit 112 may acquire information related to the mass corresponding to the character string representation information from an external server (not shown) having a database of compounds.
[0043] In this way, by converting the expression representing the compound into character string expression information showing the structure of the compound in step S03, it becomes possible to convert the expression representing the compound into other information based on the structure in the following step S04. In this embodiment, information related to mass is exemplified as "other information based on the structure", but by converting the expression representing the compound into information related to mass, it becomes possible to compare it with the mass analysis result obtained from the device 300.
[0044] Note that, since one compound may be referred to by expressions representing multiple compounds, an example of converting the compound into character string expression information that can uniquely define the compound has been described above. However, as a modified example, if information regarding the mass of a compound can be obtained from the expression representing the compound using a table that associates the expression representing the compound with mass, it is not necessary to convert the expression representing the compound into character string expression information showing the structure of the compound in step S03.
[0045] In this manner, the acquisition unit 112 can extract expressions representing compounds contained in the literature from the literature data recorded in the server 400, and record information regarding the mass of the compound in the matching data 151 (steps S02 to S04).
[0046] Note that if this process is performed on all documents recorded in the server 400, the matching process will take a long time, so the user may select the documents to be processed in steps S02 to S04. For example, in a request for matching from the terminal 200, the documents to be processed may be specified as documents from the 2020s, patent documents of a specific patent applicant, or documents specified by a specific document number. In this case, the acquisition unit 112 of the server 100 may acquire document data within the range specified by the user from the server 400 and execute steps S02 to S04.
[0047] The collation unit 113 verifies whether or not the sample contains a compound described in the literature based on the sample compound information and the literature compound information. At this time, the collation unit 113 may verify whether or not the sample contains the compound based on the similarity between a peak included in the mass spectrometry result and information on the mass of the compound. The similarity may be predetermined or may be specified by a user. The similarity is not particularly limited, and may be, for example, an error tolerance δ expressed by a range of values such as ±α with respect to a certain value. By considering such similarity, it is possible to appropriately classify the peaks into groups even when the measurement accuracy of the exact mass of the peaks varies depending on the mass spectrometer.
[0048] FIG. 2E shows a flow of executing the matching process and recording the matching result in the matching data 151. The matching process is not particularly limited, but for example, the information on the mass of each compound included in the sample compound information recorded in the matching data 151 (m / z: ..., 120.09, 136.15, ..., 184.07, ...) is matched with the information on the mass of each compound included in the literature compound information (D1: Chem 1: 118.05, Chem 2: 136.15, ... Chem m, ...; Dn: Chem 1: 136.15, Chem 2: ..., ... Chem m: 184.07, ...; ...) to confirm whether there is a matching mass. Note that the significant digits of m / z are an example for ease of explanation, and are not limited to two decimal places.
[0049] According to the method of this embodiment, the identity of the compounds can be judged with a difference of less than m / z 0.002. In the example shown in FIG. 2E, the collation unit 113 may record in the collation data 151 the collation result that compound A (m / z 136.15) contained in the sample is identical to that disclosed as chem 2 of D1 and chem 1 of Dn, and compound B (m / z 184.07) is identical to that disclosed as chem m of Dn.
[0050] Conventionally, even if m / z 136.15 was obtained as mass spectrometry data of a compound contained in a sample, it was difficult to estimate a specific compound that satisfies this m / z value only from the value of m / z 136.15. However, as in the present embodiment, by correlating the compound contained in the sample with a specific compound disclosed in a literature, it becomes possible to identify the compound contained in the sample.
[0051] In addition, the identification in this embodiment may include a judgment of whether the composition formula matches, and may include a judgment of whether isomers such as structural isomers and stereoisomers match. According to this embodiment, for example, the composition formula represented by the value of m / z 136.15 is clarified, so that the isomers contained in the composition formula can be more easily identified by corresponding them to specific compounds disclosed in the literature. In addition, when the structure of the compound (isomer) contained in the sample is to be further analyzed on the premise that the composition formula has been identified, the compound contained in the sample may be analyzed by combining, for example, nuclear magnetic resonance analysis (NMR), circular dichroism spectrometer (CD), and other spectrometers, without any particular limitation.
[0052] The output unit 114 can output the collation result thus obtained in various modes. For example, the output unit 114 may output the probability that the sample contains a specific compound. In the example shown in FIG. 2E, the probability that compound A is contained is output as 90% or more. The method of calculating the probability is not particularly limited, but as an example, when a compound with m / z 136.15 is disclosed in multiple documents, such as chem 2 of D1 and chem 1 of Dn, and the expressions representing the compounds represented by chem 2 of D1 and chem 1 of Dn are substantially the same even if there is a fluctuation in the expression, the probability may be output as high.
[0053] The output unit 114 may also output a document disclosing a compound contained in the sample. In addition to identifying the compound contained in the sample, the output unit 114 may also output the relevance between the sample and the document. In this case, the output unit 114 may output information about the document, assuming that the higher the match between the compounds contained in the sample and the compounds disclosed in one document, the higher the relevance with the sample. For example, if a patent document X that discloses all of the compounds contained in the sample is found, it can be said that the sample is highly likely to be an embodiment of the invention disclosed in that patent document X. Also, if a document that discloses many, if not all, of the compounds contained in the sample is found in one document, it can be said that the relevance between the document and the sample is high. In addition to identifying the compounds contained in the sample, the relevance between the sample and the document is also useful information.
[0054] 1.2. Operation Processing Next, the operation process of the system 1 of this embodiment will be described with reference to Fig. 3. Fig. 3 shows an example of a flowchart showing a matching process performed using the server 100. Note that the process procedure described below is merely an example, and each process may be changed as much as possible within the scope of the technical idea of the present disclosure, and steps may be omitted, replaced, or added as appropriate.
[0055] In step S01, the acquisition unit 112 of the server 100 acquires a mass spectrometry result of a sample. The mass spectrometry result acquired at this time may be a result after filtering, or may be information on the monoisotopic mass of a compound, information on the mass of a compound including an adduct ion, information on the mass of a compound due to differences in valence, etc.
[0056] In steps S02 to S04, the acquisition unit 112 of the server 100 extracts an expression representing a compound from the literature, and acquires information regarding the mass of the compound based on the extracted expression representing the compound. More specifically, the acquisition unit 112 of the server 100 converts the expression representing the compound contained in the literature into character string expression information representing the structure of the compound, and acquires information regarding the mass of the compound based on the character string expression information representing the structure of the compound.
[0057] In step S05, the collation unit 113 of the server 100 verifies whether the sample contains the compound based on the mass spectrometry result of the sample and the information on the mass of the compound. After that, the output unit 114 of the server 100 may output the collation result and transmit it to the terminal 200.
[0058] 2. Information processing method The information processing method of this embodiment executes the steps of: an information processing device acquiring information regarding the mass of a compound contained in a literature; and a step of verifying whether or not the sample contains the compound based on the mass analysis results of the sample and the information regarding the mass of the compound.
[0059] Note that since the specific aspects of the method of this embodiment have been described above in the operational processing, detailed description thereof will be omitted here.
[0060] 3. Program The program of this embodiment causes an information processing device to execute the steps of acquiring information regarding the mass of a compound contained in a literature, and comparing whether or not the sample contains the compound based on the mass analysis results of the sample and the information regarding the mass of the compound.
[0061] The program may be recorded on a readable recording medium. Since the specific aspects of the processing executed by the program of the present embodiment have been described above in the operation processing, detailed description thereof will be omitted here. [Industrial Applicability]
[0062] The present invention has industrial applicability in the analysis of chemical products. [Explanation of symbols]
[0063] 1...system, 100...server, 110...processor, 111...transmitter / receiver, 112...acquisition unit, 113...matching unit, 114...output unit, 120...communication interface, 130...input / output interface, 131...display device, 140...memory, 150...storage, 151...matching data, 160...bus, 200...terminal, 300...device, 400...server.
Claims
1. An acquisition unit that acquires information regarding the masses of compounds contained in a document; and a collation unit that checks whether the sample contains the compound based on a mass spectrometry result of the sample and information on the mass of the compound. Information processing device.
2. the acquiring unit extracts an expression representing the compound from the literature, and acquires information regarding the mass of the compound based on the extracted expression representing the compound; The information processing device according to claim 1 .
3. the acquiring unit converts an expression representing the compound contained in the literature into character string representation information representing a structure of the compound, and acquires information relating to the mass of the compound based on the character string representation information representing the structure of the compound; The information processing device according to claim 1 .
4. The acquisition unit acquires, as the information on the mass of the compound, at least one of information on the monoisotopic mass of the compound, information on the mass of the compound including an adduct ion, and information on the mass of the compound due to a difference in valence. The information processing device according to claim 1 .
5. The collation unit determines whether or not the compound is included based on a similarity between a peak included in the mass spectrometry result and information related to the mass of the compound. The information processing device according to claim 1 .
6. An information processing device, obtaining information regarding the masses of compounds contained in a document; and determining whether or not the compound is contained in the sample based on the mass spectrometry result of the sample and information on the mass of the compound. Information processing methods.
7. In the information processing device, obtaining information regarding the masses of compounds contained in a document; and determining whether or not the compound is contained in the sample based on the mass spectrometry result of the sample and information on the mass of the compound. program.
Citation Information
Patent Citations
Document search method and document search system
WO2020079751A1
