DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Applicant’s arguments, see page 7, filed 1/12/26, with respect to the rejection of claims 6 and 20 under 35 U.S.C. 112 have been fully considered and are persuasive. The rejection of claims 6 and 20 has been withdrawn.
Applicant's arguments filed 1/12/26 have been fully considered but they are directed toward new limitations which have not yet been considered. The new limitations are taught by Jones et al. (US20180053644). Jones teaches ionization of gaseous samples (title) including ion mobility spectrometry for sample (analyte) analysis including the use of various analysis techniques including principal component analysis (PCA) to generate PCA data that reduces the dimensionality of complex spectral features ([0115] principal component analysis (PCA); PCA is used to reduce dimensionality [of the data set], [0117-0118, 0525-0529], Fig. 26-29);
orthogonal projections to latent structures discriminant analysis (OPLS-DA) to generate OPLS-DA data ([0115] (xiii) orthogonal (partial least squares) projections to latent structures (OPLS); (xiv) OPLS discriminant analysis (OPLS-DA)) that identifies discriminatory molecular features from the pathogen data (this is a known result of using OPLS-DA, identifying separations (discriminations) among data);
random forests (RF) to generate RF data that classifies the one or more pathogens of the pathogen data ([0115] random forests) and
library matching ([0115-0116, 0119-0120, 0554-0557] library-matching, Fig. 34-35) to generate library matching data that matches each bacterial fingerprint of the pathogen data separately.
Therefore, applicant’s arguments are not persuasive.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 1, 4, 7, 9-10, 15, 17 are rejected under 35 U.S.C. 103 as being unpatentable over Pophristic (US20210343518) in view of Miller et al. (US7576319) further in view of Jones et al. (US20180053644)
Claim 1: Pophristic teaches a device for detecting pathogens ([0025] identifying microbes as occurs in microbial infections, bacterial and viral pathogens) comprising: a chamber (vacuum chamber 120, Fig. 1) configured to receive a sample (samples are held in sample plate device 107) including an analyte and a matrix ([0067] a sample plate device 107 containing samples which are typically made of a matrix and an analyte); a gas inlet (rotary pump 124 is attached at the inlet) extending into the chamber and configured to adjust the pressure within the chamber to ionize the molecules of the sample ([0060] The vacuum chamber 120 may have a rotary pump 124 connected thereto which is required for normal operation); an ion mobility spectrometer (analyzer 130 [0024, 0027] ion mobility spectrometer) configured to obtain the ionized molecules of the sample to obtain pathogen data ([0025]).
Pophristic fails to explicitly teach wherein and a computing device configured to analyze the pathogen data to determine one or more pathogens of the analyte.
However, Miller (Fig. 2B) teaches a differential mobility spectrometer including a computing device 40 in order to correlate drive signals applied to the filter electrodes with detection signals from amplifiers 36, 38, and makes a comparison to stored data in data store 41, and then issues identification data 42 to a readout device, such as for indication of detection of the target molecule (col. 22, lines 23-29).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use a computing device, as taught by Miller, with the device of Pophristic in order to reliably identify analytes (Miller, col. 2, lines 46-48).
Pophristic in view of Miller fails to teach an algorithm including:
principal component analysis (PCA) to generate PCA data that reduces the dimensionality of complex spectral features; orthogonal projections to latent structures discriminant analysis (OPLS-DA) to generate OPLS-DA data that identifies discriminatory molecular features from the pathogen data; random forests (RF) to generate RF data that classifies the one or more pathogens of the pathogen data and library matching to generate library matching data that matches each bacterial fingerprint of the pathogen data separately.
However, Jones teaches ionization of gaseous samples (title) including ion mobility spectrometry for sample (analyte) analysis including the use of various analysis techniques including principal component analysis (PCA) to generate PCA data that reduces the dimensionality of complex spectral features ([0115] principal component analysis (PCA); PCA is used to reduce dimensionality [of the data set], [0117-0118, 0525-0529], Fig. 26-29);
orthogonal projections to latent structures discriminant analysis (OPLS-DA) to generate OPLS-DA data ([0115] (xiii) orthogonal (partial least squares) projections to latent structures (OPLS); (xiv) OPLS discriminant analysis (OPLS-DA)) that identifies discriminatory molecular features from the pathogen data (this is a known result of using OPLS-DA, identifying separations (discriminations) among data);
random forests (RF) to generate RF data that classifies the one or more pathogens of the pathogen data ([0115] random forests) and
library matching ([0115-0116, 0119-0120, 0554-0557] library-matching, Fig. 34-35) to generate library matching data that matches each bacterial fingerprint of the pathogen data separately.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use the teaching of Jones, including various analysis techniques, with the device and computing device of Pophristic in view of Miller in order to classify one or more unknown sample spectra (Jones [0124]).
Claim 4: Pophristic in view of Miller further in view of Jones teaches the device of claim 1. Pophristic teaches a heat source (elements 122 which may be heater elements [0061]) within the chamber (see Fig. 1) configured to adjust the temperature within the chamber.
Claim 7: Pophristic in view of Miller further in view of Jones teaches the device of claim 1. Pophristic teaches an airlock door (valve plate 105) configured to selectively permit access to the chamber ([0061] An optional valve plate 105 resides between the flange device 101 surface and the sample plate device 107 which slides to one of two positions. In the open position, a channel in the valve plate 105 of equal diameter to the inner diameter of channel 102 is aligned with channel 102 so that the lower pressure in chamber 120 is in fluid communication with the sample in the sample plate device 107.)
Claim 9: Pophristic teaches a system for detecting pathogens ([0025] identifying microbes as occurs in microbial infections, bacterial and viral pathogens) comprising: a pathogen detection device comprising: a chamber (vacuum chamber 120, Fig. 1) configured to receive a sample including an analyte and a matrix ([0067] a sample plate device 107 containing samples which are typically made of a matrix and an analyte); a gas inlet (rotary pump 124 is attached at the inlet) extending into the chamber and configured to adjust the pressure within the chamber to ionize the molecules of the sample ([0060] The vacuum chamber 120 may have a rotary pump 124 connected thereto which is required for normal operation where an inlet aperture); an ion mobility spectrometer (analyzer 130 [0024, 0027] ion mobility spectrometer) configured to obtain the ionized molecules of the sample to obtain pathogen data ([0025]).
Pophristic fails to teach an external computing device in communication with the pathogen detection, the external computing device configured to analyze the pathogen data to determine one or more pathogens of the analyte.
However, Miller (Fig. 2B) teaches a differential mobility spectrometer including a computing device 40 in order to correlate drive signals applied to the filter electrodes with detection signals from amplifiers 36, 38, and makes a comparison to stored data in data store 41, and then issues identification data 42 to a readout device, such as for indication of detection of the target molecule (col. 22, lines 23-29).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use a computing device, as taught by Miller, with the device of Pophristic in order to reliably identify analytes (Miller, col. 2, lines 46-48).
Pophristic in view of Miller fails to teach an algorithm including:
principal component analysis (PCA) to generate PCA data that reduces the dimensionality of complex spectral features; orthogonal projections to latent structures discriminant analysis (OPLS-DA) to generate OPLS-DA data that identifies discriminatory molecular features from the pathogen data; random forests (RF) to generate RF data that classifies the one or more pathogens of the pathogen data and library matching to generate library matching data that matches each bacterial fingerprint of the pathogen data separately.
However, Jones teaches ionization of gaseous samples (title) including ion mobility spectrometry for sample (analyte) analysis including the use of various analysis techniques including principal component analysis (PCA) to generate PCA data that reduces the dimensionality of complex spectral features ([0115] principal component analysis (PCA); PCA is used to reduce dimensionality [of the data set], [0117-0118, 0525-0529], Fig. 26-29);
orthogonal projections to latent structures discriminant analysis (OPLS-DA) to generate OPLS-DA data ([0115] (xiii) orthogonal (partial least squares) projections to latent structures (OPLS); (xiv) OPLS discriminant analysis (OPLS-DA)) that identifies discriminatory molecular features from the pathogen data (this is a known result of using OPLS-DA, identifying separations (discriminations) among data);
random forests (RF) to generate RF data that classifies the one or more pathogens of the pathogen data ([0115] random forests) and
library matching ([0115-0116, 0119-0120, 0554-0557] library-matching, Fig. 34-35) to generate library matching data that matches each bacterial fingerprint of the pathogen data separately.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use the teaching of Jones, including various analysis techniques, with the device and computing device of Pophristic in view of Miller in order to classify one or more unknown sample spectra (Jones [0124]).
Claim 10: Pophristic in view of Miller further in view of Jones teaches the system of claim 9. Pophristic fails to teach wherein the external computing device is one of a smartphone, a laptop computer, a desktop computer, or a tablet computer.
However, Miller teaches wherein the external computing device is one of a smartphone, a laptop computer, a desktop computer, or a tablet computer (computer or microprocessor 40 see Fig. 2B; col. 22, lines 23-25).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use a computing device, as taught by Miller, with the device of Pophristic in order to reliably identify analytes (Miller, col. 2, lines 46-48).
Claim 15: Pophristic teaches a method for detecting pathogens comprising: introducing a sample ([0067] a sample plate device 107 containing samples which are typically made of a matrix and an analyte) into a pathogen detection device (apparatus 100 and analyzer 130, Fig. 1; [0025] identifying microbes as occurs in microbial infections, bacterial and viral pathogens); adjusting the pressure within the pathogen detection device to ionize the molecules of the sample (as-phase ions generated by vacuum matrix-assisted ionization (vMAI) [0060] The vacuum chamber 120 may have a rotary pump 124 connected thereto which is required for normal operation where an inlet aperture); introducing the ionized molecules of the sample into an ion mobility spectrometer ([0061] gas-phase ions and charged particles produced from a sample traverse into the analyzer 130, which may be a mass or ion mobility analyzer.); operating the ionized mobility spectrometer; obtaining pathogen data from the ionized mobility spectrometer related to the ionized molecules of the sample ([0060] Gas-phase ions generated by vacuum matrix-assisted ionization (vMAI) are transmitted into the analyzer 130 through restriction 126), but fails to teach analyzing the pathogen data; and determining at least one pathogen of the sample based on the analysis of the pathogen data.
However, Miller (Fig. 2B) teaches a differential mobility spectrometer including a computing device 40 in order to correlate drive signals applied to the filter electrodes with detection signals from amplifiers 36, 38, and makes a comparison to stored data in data store 41, and then issues identification data 42 to a readout device, such as for indication of detection of the target molecule (col. 22, lines 23-29).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use a computing device, as taught by Miller, with the device of Pophristic in order to reliably identify analytes (Miller, col. 2, lines 46-48).
Pophristic in view of Miller fails to teach an algorithm including:
principal component analysis (PCA) to generate PCA data that reduces the dimensionality of complex spectral features; orthogonal projections to latent structures discriminant analysis (OPLS-DA) to generate OPLS-DA data that identifies discriminatory molecular features from the pathogen data; random forests (RF) to generate RF data that classifies the one or more pathogens of the pathogen data and library matching to generate library matching data that matches each bacterial fingerprint of the pathogen data separately.
However, Jones teaches ionization of gaseous samples (title) including ion mobility spectrometry for sample (analyte) analysis including the use of various analysis techniques including principal component analysis (PCA) to generate PCA data that reduces the dimensionality of complex spectral features ([0115] principal component analysis (PCA); PCA is used to reduce dimensionality [of the data set], [0117-0118, 0525-0529], Fig. 26-29);
orthogonal projections to latent structures discriminant analysis (OPLS-DA) to generate OPLS-DA data ([0115] (xiii) orthogonal (partial least squares) projections to latent structures (OPLS); (xiv) OPLS discriminant analysis (OPLS-DA)) that identifies discriminatory molecular features from the pathogen data (this is a known result of using OPLS-DA, identifying separations (discriminations) among data);
random forests (RF) to generate RF data that classifies the one or more pathogens of the pathogen data ([0115] random forests) and
library matching ([0115-0116, 0119-0120, 0554-0557] library-matching, Fig. 34-35) to generate library matching data that matches each bacterial fingerprint of the pathogen data separately.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use the teaching of Jones, including various analysis techniques, with the device and computing device of Pophristic in view of Miller in order to classify one or more unknown sample spectra (Jones [0124]).
Claim 17: Pophristic in view of Miller further in view of Jones teaches the method of claim 15. Pophristic teaches wherein the pressure within the pathogen detection device is adjusted via a gas inlet into the pathogen detection device (rotary pump 124 is attached at the inlet; [0060] The vacuum chamber 120 may have a rotary pump 124 connected thereto which is required for normal operation…).
Claims 2, 3, 16 are rejected under 35 U.S.C. 103 as being unpatentable over Pophristic in view of Miller further in view of Jones further in view of Miller et al. (US6495823, herein after Miller2).
Claim 2: Pophristic in view of Miller further in view of Jones teaches the device of claim 1, but fails to teach a housing configured to house the chamber, the ion mobility spectrometer, and the computing device.
Miller2 teaches a housing, Fig. 5 (col. 7, lines 1-15) which houses a spectrometer 10, a controller 30 including microprocessor 36, and a flow path 26.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use a housing, as taught by Miller2 for the obvious benefit of maintaining the positional relationship between the components and protecting the components from external damage.
Claim 3: Pophristic in view of Miller further in view of Jones further in view of Miller2 teaches the device of claim 2. Pophristic fails to teach wherein the housing is configured to be handheld.
However, Miller teaches a hand-held device (field-portable) col. 2, lines 30-32; col. 50, lines 4-11. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to make the housing hand-held in order to provide a compact and portable device (col. 2, lines 30-32). Additionally, Miller2 teaches, Fig. 5, that the miniaturized is realized, where it is one inch by one inch (col. 7, lines 1-2) thus sized to be hand-held.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to make the device of Pophristic in view of Miller further in view of Miller2 to be a handheld size for the obvious benefit of compactness and portability.
Claim 16: Pophristic in view of Miller further in view of Jones teaches the method of claim 15, but fails to teach wherein the pathogen detection device and the ion mobility spectrometer are contained within the same housing.
Miller2 teaches a housing, Fig. 5 (col. 7, lines 1-15) which houses a spectrometer 10, a controller 30 including microprocessor 36, and a flow path 26.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use a housing, as taught by Miller2 for the obvious benefit of maintaining the positional relationship between the components and protecting the components from external damage.
Claims 5 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Pophristic in view of Miller further in view of Jones further in view of Mamerow et al. (US20200309753).
Claim 5: Pophristic in view of Miller further in view of Jones teaches the device of claim 1, but fails to teach wherein the algorithm uses deep learning artificial intelligence algorithms to identify pathogen fingerprint profiles of the pathogen data.
However, Mamerow teaches a system and method for detecting microbiome/molecules using ion mobility spectrometry (claim 3) including the use of artificial intelligence to analyze the data [0031, 0086].
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use artificial intelligence, as taught by Mamerow, with the device, data, and library based analysis as taught by Pophristic in view of Miller further in view of Jones, in order to identify patterns from the data in real-time (Mamerow [0031]).
Claim 19: Pophristic in view of Miller further in view of Jones teaches the method of claim 15, but fails to teach wherein the algorithm uses deep learning artificial intelligence algorithms to identify pathogen fingerprint profiles of the pathogen data.
However, Mamerow teaches a system and method for detecting microbiome/molecules using ion mobility spectrometry (claim 3) including the use of artificial intelligence to analyze the data [0031, 0086].
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use artificial intelligence, as taught by Mamerow, with the device, data, and library based analysis as taught by Pophristic in view of Miller further in view of Jones, in order to identify patterns from the data in real-time (Mamerow [0031]).
Claims 6 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Pophristic in view of Miller further in view of Jones further in view of Mamerow further in view of Tenzer (US2022004840) further in view of Cho et al. (US20220415447)
Claim 6: Pophristic in view of Miller further in view of Jones further in view of Mamerow teaches the device of claim 5, but fails to teach wherein the computing device trains the deep learning artificial intelligence algorithms by: splitting the pathogen data into training data and a testing data; fitting the OPLS-DA data and the RF data to the training data; selecting variables of the training data that cause classification; predicting the identity of unknown microorganisms of the training data; and evaluating the performance of the prediction using accuracy, precision, recall, and F1-score.
However, Tenzer teaches an ion mobility spectrometer (title) which uses deep learning algorithms which can be training on real data or simulated data in order to match “fingerprints”. ([0032, 0115] This matching (intensity distribution) can even be carried out using machine learning algorithms such as deep learning algorithms).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use the teaching of Tenzer, including training an algorithm using deep learning with the system and data of Pophristic in view of Miller further in view of Jones further in view of Mamerow in order to allow for an improved association of detected fragments with corresponding precursor ions (Tenzer [0005]).
Pophristic in view of Miller further in view of Jones further in view of Mamerow further in view of Tenzer fails to teach evaluating the performance of the prediction using accuracy, precision, recall, and F1-score.
However, Cho teaches the accuracy, precision, recall, and F1-score used to evaluate algorithm classifiers: see tables 2-5.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use accuracy, precision, recall, and F1-score, as taught by Cho, to evaluate the algorithm of claim 5 in order to effectively reduce the time required for conventional microbial culture, identification and antibiotic susceptibility testing (Cho [0024]).
Claim 20: Pophristic in view of Miller further in view of Jones further in view of Mamerow teaches the method of claim 19, but fails to teach training the deep learning artificial intelligence algorithms by: splitting the pathogen data into training data and a testing data; fitting the OPLS-DA data and the RF data to the training data; selecting variables of the training data that cause classification; predicting the identity of unknown microorganisms of the training data; and evaluating the performance of the prediction using accuracy, precision, recall, and F1-score.
However, Tenzer teaches an ion mobility spectrometer (title) which uses deep learning algorithms which can be training on real data or simulated data in order to match “fingerprints”. ([0032, 0115] This matching (intensity distribution) can even be carried out using machine learning algorithms such as deep learning algorithms).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use the teaching of Tenzer with the method of Pophristic in view of Miller further in view of Jones further in view of Mamerow in order to allow for an improved association of detected fragments with corresponding precursor ions (Tenzer [0005]).
Pophristic in view of Miller further in view of Jones further in view of Mamerow further in view of Tenzer fails to teach evaluating the performance of the prediction using accuracy, precision, recall, and F1-score.
However, Cho teaches the accuracy, precision, recall, and F1-score used to evaluate algorithm classifiers: see tables 2-5.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use accuracy, precision, recall, and F1-score, as taught by Cho, to evaluate the algorithm of claim 5 in order to effectively reduce the time required for conventional microbial culture, identification and antibiotic susceptibility testing (Cho [0024]).
Claims 8 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Pophristic in view of Miller further in view of Jones further in view of Trimpin et al. (US10679838).
Claim 8: Pophristic in view of Miller further in view of Jones teaches the device of claim 1, but fails to teach a sampling rod configured to selectively transmit the sample into the chamber.
However, Trimpin teaches a method for ionizing samples for ion mobility spectrometry (Title) including a sample rod (substrate holder 22) for introducing the sample 29 to the low-pressure region 10.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use a sample rod (holder) as taught by Trimpin with the device of Pophristic in view of Miller further in view of Jones in order to introduce the sample into the lower pressure region 10 without detrimentally raising the pressure in region (Trimpin, col. 21, lines 12-18).
Claim 18: Pophristic in view of Miller further in view of Jones teaches the method of claim 15, but fails to teach adjusting the temperature within the pathogen detection device via one of an ultraviolet lamp or an infrared lamp.
However, Trimpin teaches a method for ionizing samples for ion mobility spectrometry (Title) including a sample rod (substrate holder 22) for introducing the sample 29 to the low-pressure region 10. Trimpin uses heat in the form of radiative (IR), visible, ultraviolet (UV), or conductive heat (col. 7, lines 30-37).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to include an ultraviolet or infrared lamp with the device of Pophristic in view of Miller further in view of Jones in order to enhance the dissolvation process and enhance ionization process (Trimpin, col. 16, lines 16-19).
Claims 11-12 are rejected under 35 U.S.C. 103 as being unpatentable over Pophristic in view of Miller further in view of Jones further in view of Chen et al. (US20230343574).
Claim 11: Pophristic in view of Miller further in view of Jones teaches the system of claim 9, but fails to teach wherein the pathogen detection device is in communication with the external computing device via a wireless telecommunication network.
Chen teaches a mass spectrometer (MS) system 400 ([0057,0084]) including a system controller 500 (or controller or computing device) in communication with one or more of the components of the MS system 400 either wired or wirelessly [0057].
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention connect an external computing device wirelessly, as taught by Chen, with the device of claim 9 for the obvious benefit of mobility of the computer and remote data monitoring.
Claim 12: Pophristic in view of Miller further in view of Jones teaches the system of claim 9, but fails to teach wherein the external computing device includes data processing hardware and memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations to analyze the pathogen data to determine one or more pathogens of the analyte.
However, Chen teaches a mass spectrometer (MS) system 400 ([0057,0084]) including a system controller 500 (or controller or computing device) [0057] The system controller 500 may also be configured to receive and process the ion measurement signals produced by and outputted from the ion detector 462 during operation, as needed to produce user-interpretable data relating to the sample (or calibrant solution) under analysis... For all such purposes, the system controller 500 may include any suitable combination of hardware, firmware, software, etc., including one or more electronics-based processors and memories, as appreciated by persons skilled in the art. For example, the system controller 500 may include a non-transitory computer-readable medium that includes non-transitory instructions for performing any of the methods disclosed herein.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use the teaching of Chen including hardware, software, and instructions to analyze the results of the mass spectrometer with the device of Pophristic in view of Miller in order to process output signals from the ion detector as needed to produce a user-interpretable mass spectrum (Chen [0002]).
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Pophristic in view of Miller further in view of Jones further in view of Chen further in view of Mamerow.
Claim 13: Pophristic in view of Miller further in view of Jones further in view of Chen teaches the system of claim 12, but fails to teach wherein the algorithm uses deep learning artificial intelligence algorithms to identify pathogen fingerprint profiles of the pathogen data.
However, Mamerow teaches a system and method for detecting microbiome/molecules using ion mobility spectrometry (claim 3) including the use of artificial intelligence to analyze the data [0031, 0086].
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use artificial intelligence, as taught by Mamerow, with the device and data as taught by Pophristic in view of Miller further in view of Jones further in view of Chen, in order to identify patterns from the data in real-time (Mamerow [0031]).
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Pophristic in view of Miller further in view of Jones further in view of Chen further in view of Mamerow further in view of Tenzer.
Claim 14: Pophristic in view of Miller further in view of Jones further in view of Chen further in view of Mamerow teaches the system of claim 13, but fails to teach wherein the external computing device trains the deep learning artificial intelligence algorithms by: splitting the pathogen data into training data and a testing data; fitting the OPLS-DA data and the RF data to the training data; selecting variables of the training data that cause classification; predicting the identity of unknown microorganisms of the training data; and evaluating the performance of the prediction using accuracy, precision, recall, and F1-score.
However, Tenzer teaches an ion mobility spectrometer (title) which uses deep learning algorithms which can be training on real data or simulated data in order to match “fingerprints”. ([0115] This matching (intensity distribution) can even be carried out using machine learning algorithms such as deep learning algorithms).
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use the teaching of Tenzer with the system of Pophristic in view of Miller further in view of Jones further in view of Mamerow in order to allow for an improved association of detected fragments with corresponding precursor ions (Tenzer [0005]).
Pophristic in view of Miller further in view of Jones further in view of Mamerow further in view of Tenzer fails to teach evaluating the performance of the prediction using accuracy, precision, recall, and F1-score.
However, Cho teaches the accuracy, precision, recall, and F1-score used to evaluate algorithm classifiers: see tables 2-5.
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the invention to use accuracy, precision, recall, and F1-score, as taught by Cho, to evaluate the algorithm of claim 5 in order to effectively reduce the time required for conventional microbial culture, identification and antibiotic susceptibility testing (Cho [0024]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. (Worley et al. “PCA as a practical indicator of OPLS-DA model reliability”. Curr Metabolomics. 2016;4(2):97-103.) Worley, pg. 1, Background: Orthogonal Projections to Latent Structures Discriminant Analysis (OPLS-DA) are powerful statistical modeling tools that provide insights into separations between experimental groups based on high-dimensional spectral measurements from NMR, MS or other analytical instrumentation.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JEAN MORELLO whose telephone number is (313)446-6583. The examiner can normally be reached M-F 9-4.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kristina Deherrera can be reached at 303-297-4237. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JEAN F MORELLO/Examiner, Art Unit 2855 2/19/26
/KRISTINA M DEHERRERA/Supervisory Patent Examiner, Art Unit 2855