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 .
Introductory Remarks
In response to communications filed on 13 October 2025, claims 1, 6-8, 13, 16, and 22-23 are amended per Applicant's request. Claims 5, 14-15, and 19-20 are cancelled. No claims were withdrawn. No new claims were added. Therefore, claims 1-4, 6-13, 16-18, and 21-24 are presently pending in the application, of which claims 1, 16, and 22 are presented in independent form.
The previously raised objection to claims 1, 13, 22, and 24 are withdrawn in view of the amendments to the claims.
The previously raised 101 rejection of the pending claims is maintained.
The previously raised 103 rejection of the pending claims is withdrawn in view of the amendments to the claims. A new ground(s) of rejection has been issued.
Response to Arguments
Applicant’s arguments filed 13 October 2025 with respect to the objection of claims 1, 13, 22, and 24 (see Remarks, first page) have been fully considered and are persuasive. The amendments render the objections moot, and the objections have been accordingly withdrawn.
Applicant’s arguments filed 13 October 2025 with respect to the rejection of the claims under 35 U.S.C. 101 (see Remarks, first and second pages) have been fully considered but are not persuasive.
Applicant argues that the claimed invention utilizes mid-infrared absorption spectral data, as opposed to traditional techniques that employ histological or cytological staining (see Remarks, first page). It is unclear what step of the 101 analysis this argument was meant to be directed towards. Nevertheless, as seen in the claims and Specification, there is nothing that is specific to the mid-infrared absorption spectral data; thus, even claiming such a limitation only provides a context rather than a particular manner of achieving the result, i.e., an insignificant field-of-use limitation.
Applicant argues that “The claimed systems and methods permit for entirely label-free molecular analysis…. Being able to predict an expression pattern of one or more biomarkers in an [sic] label-free, i.e., unstained test biological sample, based on acquired mid-infrared absorbance spectral data is an entirely unconventional practice and certainly one which advances the field of clinical diagnostics” (see Remarks, first page). This is unpersuasive.
Firstly, Applicant appears to misunderstand the technology. “Label-free” does not mean “unstained”, nor is this interpretation supported by the Specification. “Label-free” refers to the machine learning component, not to the treatment/preparation of the biological sample (i.e., the “unstained” aspect). Thus, this logic is erroneous and nonsensical.
Secondly, Applicant’s argument, which rests on the idea that combining these various aspects is unconventional, is unpersuasive. The claims need to represent a concrete embodiment to the purported problem being solved, which the claims do not. Instead, the claims are primarily directed to the resulting goal or effect, rather than a particular manner of achieving the result. In essence, the claims automate mental tasks or processes, simply adding that it is applied using a computer, with token, well-understood, routine, and conventional activities involving the training of that computer.
Thirdly, Applicant’s argument that the use of a specific type of spectral data, the use of unstained test biological samples, etc., amount to significantly more and that “the use of specific types of spectral data and the use of biological samples that are label-free, i.e., unstained” (see Remarks, second page), are unpersuasive, as these only provide context rather than a particular manner of achieving the result, i.e., insignificant field-of-use limitations
Lastly, Applicant’s arguments with respect to preemption (see Remarks, second page), are unpersuasive, as “the absence of complete preemption does not demonstrate patent eligibility” (Ariosa Diagnostics, Inc. v. Sequenom, Inc., 788 F.3d 1371, 1379 (Fed. Cir. 2015)).
For at least the aforementioned reasons and those set forth in the 101 rejection below, the 101 rejection has been maintained.
Applicant’s arguments filed 13 October 2025 with respect to the rejection of the claims under 35 U.S.C. (see Remarks, second through fourth pages) have been fully considered but are not persuasive.
Applicant argues solely that the amendments overcome the prior art of record. The Examiner respectfully disagrees, and the 103 rejection has been modified below to conform to the amended claim language.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-4, 6-13, 17-18 and 23 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Independent Claim 1 recites “wherein the test biological specimen is unstained”, yet when “deriving biomarker expression features from the obtained test spectral data using a trained biomarker expression estimation engine”, the biomarker expression engine is trained using a “training mid-infrared absorption spectral data set” that “comprises a plurality of training mid-infrared absorption spectra derived from a plurality of training tissue samples stained for the presence of one or more biomarkers”.
In a similar vein, dependent Claim 6 recites “wherein the known biomarker expression levels comprise at least one of…known staining intensities for the one or more biomarkers”; dependent claim 8 recites that the training tissue samples are stained (step (iii)), and dependent claim 23 recites “wherein each of the plurality of differentially prepared training biological specimens are stained for the presence of one or more biomarkers”.
The Specification does not provide support for such a limitation, describing, e.g., in Specification, [0150], that it “the biomarker expression estimation engine may learn features from a plurality of acquired and processed training vibrational spectra…and correlate these learned features with class labels associated with the training spectra (e.g., known biomarker expression for one or more biomarkers, known unmasking temperatures, known unmasking duration, tissue quality, etc.)….based on the learned datasets, [the trained biomarker expression engine may] predict an expression of one or more biomarkers within the unstained test biological specimen based on the derived biomarker expression features”. As seen, these class labels in the learned dataset are not from stained tissue samples.
Essentially, what is being claimed instead is that the biomarker expression engine is being trained on stained data, in order to make estimations/predictions on unstained data. In other words, the biomarker expression engine is being trained to solve a problem based on data that is unrelated to the problem being solved. The Specification lacks any detail as to how an engine trained on data of a certain set for solving similar problems of that type of data, is being used to solve a different problem despite being trained on different training data.
Claims 2 and 17 recite “wherein the predicted expression of the one or more biomarkers comprises one of a predicted percent positivity or a predicted staining intensity”. Claims 3 and 18 recite similar, except that it is both. Independent Claims 1 and 16, which claims 2-3 and 17-18 depend upon respectively, state that the “test biological specimen is unstained”. This is rather nonsensical, as a “predicted staining intensity” for an unstained test biological specimen should theoretically be non-existent. The Specification does not describe how the biomarker expression engine itself would evaluate such a condition, and thus such a limitation is not enabled.
The rest of the dependent claims of claim 1 are rejected for at least by virtue of their dependency on claim 1, and for failing to cure the deficiencies of claim 1.
Claims 1-4, 6-13, 17-18 and 23 rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the enablement requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to enable one skilled in the art to which it pertains, or with which it is most nearly connected, to make and/or use the invention.
Independent Claim 1 recites “wherein the test biological specimen is unstained”, yet when “deriving biomarker expression features from the obtained test spectral data using a trained biomarker expression estimation engine”, the biomarker expression engine is trained using a “training mid-infrared absorption spectral data set” that “comprises a plurality of training mid-infrared absorption spectra derived from a plurality of training tissue samples stained for the presence of one or more biomarkers”.
In a similar vein, dependent Claim 6 recites “wherein the known biomarker expression levels comprise at least one of…known staining intensities for the one or more biomarkers”; dependent claim 8 recites that the training tissue samples are stained (step (iii)), and dependent claim 23 recites “wherein each of the plurality of differentially prepared training biological specimens are stained for the presence of one or more biomarkers”.
The Specification does not provide support for such a limitation, describing, e.g., in Specification, [0150], that it “the biomarker expression estimation engine may learn features from a plurality of acquired and processed training vibrational spectra…and correlate these learned features with class labels associated with the training spectra (e.g., known biomarker expression for one or more biomarkers, known unmasking temperatures, known unmasking duration, tissue quality, etc.)….based on the learned datasets, [the trained biomarker expression engine may] predict an expression of one or more biomarkers within the unstained test biological specimen based on the derived biomarker expression features”. As seen, these class labels in the learned dataset are not from stained tissue samples.
Claims 2 and 17 recite “wherein the predicted expression of the one or more biomarkers comprises one of a predicted percent positivity or a predicted staining intensity”. Claims 3 and 18 recite similar, except that it is both. Independent Claims 1 and 16, which claims 2-3 and 17-18 depend upon respectively, state that the “test biological specimen is unstained”. The Specification lacks support for calculating a “predicted staining intensity” for an unstained test biological specimen (which theoretically, should be non-existent).
The rest of the dependent claims of claim 1 are rejected for at least by virtue of their dependency on claim 1, and for failing to cure the deficiencies of claim 1.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-4, 6-13, 17-18 and 23 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Independent Claim 1 recites “wherein the test biological specimen is unstained”, yet when “deriving biomarker expression features from the obtained test spectral data using a trained biomarker expression estimation engine”, the biomarker expression engine is trained using a “training mid-infrared absorption spectral data set” that “comprises a plurality of training mid-infrared absorption spectra derived from a plurality of training tissue samples stained for the presence of one or more biomarkers”.
In a similar vein, dependent Claim 6 recites “wherein the known biomarker expression levels comprise at least one of…known staining intensities for the one or more biomarkers”; dependent claim 8 recites that the training tissue samples are stained (step (iii)), and dependent claim 23 recites “wherein each of the plurality of differentially prepared training biological specimens are stained for the presence of one or more biomarkers”.
Essentially, the biomarker expression engine is being trained on stained data, in order to make estimations/predictions on unstained data. In other words, the biomarker expression engine is being trained to solve a problem based on data that is unrelated to the problem being solved. This is contradictory, and therefore unclear what the metes and bounds of the biomarker expression engine training are with respect to the problem of deriving biomarker expression features for an unstained test biological specimen.
Claims 2 and 17 recite “wherein the predicted expression of the one or more biomarkers comprises one of a predicted percent positivity or a predicted staining intensity”. Claims 3 and 18 recite similar, except that it is both. Independent Claims 1 and 16, which claims 2-3 and 17-18 depend upon respectively, state that the “test biological specimen is unstained”. Therefore, it is unclear how there could be a “predicted staining intensity” for an unstained test biological specimen.
Furthermore, independent claim 1 further recites “wherein the biomarker expression estimation engine is trained using one or more training mid-infrared absorption spectral data sets” and later states “wherein each training vibrational spectrum comprises one or more class labels”. As “vibrational spectrum” is broader than “mid-infrared absorption spectral data”, i.e., they possess different scopes, it is not entirely clear whether the “vibrational spectrum” was referring to the “mid-infrared absorption spectral data” or some other data.
The rest of the dependent claims of claim 1 are rejected for at least by virtue of their dependency on claim 1, and for failing to cure the deficiencies of claim 1.
Claim 7 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
The claim recites “further comprising one or more class labels selected from the group consisting of…”. There is a lack of antecedent basis issue, as independent claim 1, which claim 7 depends upon, recites “wherein each training vibrational spectrum comprises one or more class labels, wherein the one or more class labels comprise known biomarker expression levels for one or more biomarkers”. Furthermore, the relationship between the “one or more class labels” of the “training vibrational spectrum” (in claim 1) and “one or more labels selected from the group consisting of” various elements (in claim 7) cannot be ascertained from the claim.
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 21 is rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. The claim recites “wherein the test biological specimen is unstained”. However, this was already claimed in independent claim 16, which claim 21 depends upon.
Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-4, 6-13, 16-18, and 21-24 are rejected because the claims are directed to a judicial exception (i.e., an abstract idea) without significantly more.
Independent Claims 1, 16, and 22 recite deriving biomarker expression features from obtained test spectral data, and predicting the expression of the one or more biomarkers in the test biological specimen based on the derived biomarker expression features. The independent claims further recite that training is performed using one or more training spectral data sets, wherein each training spectral data set comprises various types of information. These encompass an evaluation, observation, and/or judgment, which falls under the “Mental Processes” grouping of abstract ideas.
Similarly, dependent Claim 6 recites that the training spectral data set is derived by dividing obtained training biological specimen into a plurality of training tissue samples, staining the plurality of training tissue samples for the presence of one or more biomarkers, and quantitatively assessing an expression of the one or more biomarkers in each training tissue sample of the plurality of training tissue samples. These also encompass an evaluation, observation, and/or judgment, which falls under the “Mental Processes” grouping of abstract ideas.
Dependent Claim 12 recites comparing an actual biomarker expression of the test biological specimen with the predicted expression of the one or more biomarkers of the test biological specimen. Dependent Claims 13 and 24 recite compensating the predicted expression of the one or more biomarkers for poor unmasking and/or poor fixation of the test biological specimen. These also encompass an evaluation, observation, and/or judgment, which falls under the “Mental Processes” grouping of abstract ideas.
Because the claims do no more than cover performance of the limitation in the mind but for the recitation of generic computer components, the claims therefore fall within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
The claims are not integrated into a practical application of that idea. In particular, the claims recite various computing hardware components, which are recited at a high level of generality and recited so generically that they represent no more than mere instructions to apply the judicial exception on a computer (see MPEP 2106.05(f)). These limitations can also be viewed as nothing more than an attempt to generally link the use of the judicial exception to the technological environment of a computer (see MPEP 2106.05(h)).
Similarly, the use of a (trained) biomarker expression estimation engine to perform the feature extraction and predictions of biomarker expressions does nothing more than attempt to limit the claims to a particular technological environment—namely, implementation via computers.
The claims variously recite the types of information that are involved in the analysis, which are recited in a contextual manner rather than a particular manner of achieving the intended result. Thus, such limitations amount to nothing more than insignificant field-of-use limitations. Such limitations include that the biological specimen is unstained, the particular data that is being analyzed (e.g., test spectral data comprising vibrational spectral data derived from at least a portion of the biological specimen), the training data/classes comprise certain types of data (see, e.g., independent claims 1, 16, and 22), that the training biological specimen comprises the same/different tissue type as the test biological specimen (independent claims 16 and 22), that the predicted expression comprises one of a predicted percent positivity and/or predicted staining intensity (dependent claims 2-3 and 17-18), that the fixation status of a test biological specimen is unknown (dependent claim 4), the training data/classes including known percent positivities for one or more biomarkers and known staining intensities for one or more biomarkers (dependent claim 6), and that the class labels are selected from a group consisting of various types of data (dependent claim 7), wherein the training tissue sample comprises certain types of data and the quantitative assessment is for percent positivity and/or known staining intensity for the one or more biomarkers (dependent claims 8 and 23), that the trained engine comprises a machine learning algorithm based on dimensionality reduction (dependent claim 9) that comprises one of two different forms of computational algorithms/processes (dependent claim 10), that the trained engine comprises a neural network (dependent claim 11), that biomarker expressions are compared (dependent claim 12), and that the compensation of the predicted expression is for poor unmasking and/or poor fixation (dependent claims 13 and 24).
Furthermore, the training itself is an insignificant extra-solution activity, as are the obtaining of data (see, e.g., claims 1, 8, 16, and 22).
As such, the additional elements do not integrate the abstract idea into a practical application of that idea.
With respect to the well-understood, routine, and conventional elements, as stated previously above, the claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements reciting the use of various computing software and hardware components amount to no more than mere instructions to apply the judicial exception using generic components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept.
Additionally, with regards to the claims’ recitation of obtaining (i.e., receiving) data, this is a well-understood, routine, and conventional computing activities. See MPEP 2106.05(d)(II) (“Receiving or transmitting data over a network, e.g., using the Internet to gather data”).
Lastly, training machine learning algorithms using known labels based on training set is well-understood, routine, and conventional. See, e.g., Kumar et al. (US 2018/0247195 A1) at [0095]; Diem et al. (US 2012/0082362 A1) at [0168-0169] and [0171]; and Chari et al. (US 2013/0097103 A1).
Even as an ordered combination, the claims as a whole do not contain any additional elements that amount to significantly more. The claims broadly state that an assessment is performed on data, and then used to make a prediction about biomarker expression. The rest of the additional limitations provide insignificant field-of-use limitations (describing the context rather than a particular manner of achieving the result).
At this level of generality, such limitations do nothing more than attempt to limit the claims to a particular technological field—namely, implementation via computers. More particularly, the claims attempt to limit the claimed invention to a particular technological field by reciting the use of a trained engine, and add insignificant extra-solution activities such as receiving data and training that engine. As a matter of law, narrowing or reformulating an abstract idea does not add significantly more to it, i.e., by reciting the generic use of a trained engine and generic training steps, and attempt to limit the claims a little more narrowly by reciting the types of information contained, do nothing more than attempt to move the claims to a particular technological environment (i.e., implementation via computers).
In sum, the claims are not limited to any particular manner by which the assessment and prediction of the biomarker expression (levels) occur. Instead, the claims recite the steps at such a high level of generality, and not a specific means for performing the stated functions. Instead, the claimed steps are directed to the resulting goal or effect, rather than a particular manner by which a computer would implement those steps.
In other words, at that level of generality, the claims do no more than describe a desired function or outcome, without providing any limiting detail that confines the claims to a particular solution to an identified problem. The purely functional nature of the claim confirms that it is directed to an abstract idea, not to a concrete embodiment of that idea (see Affinity Labs of Texas LLC v. Amazon.com Inc., 838 F.3d 1253 (Fed. Cir. 2016) at p. 7-8, citing Elec. Power Grp., LLC v. Alstom S.A., 830 F.3d 1350 (Fed. Cir. 2016), slip op. 12 (“[T]he essentially result-focused, functional character of claim language has been a frequent feature of claims held ineligible under § 101”)). As a whole, the claims do not go beyond stating the relevant functions in general terms, without limiting them to a technical means for performing the functions that are arguably an advance over conventional database technologies.
Therefore, for at least the aforementioned reasons, the claims are rejected under 35 U.S.C. 101 for being directed to a judicial exception (i.e., an abstract idea) without significantly more.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-4, 6-7, 11-12, 16-18, and 21-23 are rejected under 35 U.S.C. 103 as being unpatentable over Pirrotte et al. (US 2019/0034586 A1), in view of Barnes et al. (“Barnes”) (US 2017/0270666 A1, incorporating by reference Chukka et al. (“Barnes-IBR-Chukka”) (WO 2014/140085 A1, also published as US 2016/0042511 A1) at [0046]).
Regarding claim 1: Pirrotte teaches A system for predicting an expression of one or more biomarkers in a test biological specimen the system comprising:
(i) one or more processors, and (ii) one or more memories coupled to the one or more processors, the one or more memories to store computer-executable instructions that, when executed by the one or more processors, cause the system to perform operations comprising (Pirrotte, [0030-0031], where the disclosed system may include one or more processors/controllers and one or more tangible, non-transitory memories, where system program or processing instructions may be loaded onto the non-transitory, tangible computer-readable medium having instructions stored thereon, that in response to execution by a controller, cause the controller to perform the disclosed operations):
a. obtaining test mid-infrared absorption spectral data from at least a portion of the test biological specimen … (Pirrotte, [0028], where a convolutional neural network (CNN) is used to predict the amino acid sequence of a sample based on mass spectrum data input into the CNN (implying “obtaining test spectral data”), the sample being, e.g., a bodily sample, tissue sample, etc., obtained from a subject, e.g., person (Pirrotte, [0028]));
b. deriving biomarker expression features from the obtained test spectral data using a trained biomarker expression estimation engine (Pirrotte, [0023] and [0035-0038], where the system identifies the presence or absence of peaks in the spectral data by discretizing the mass spectral data into one-dimensional vectors, segments or buckets, and utilizing convolutional and pooling layers to divide the discretized one-dimensional vector into smaller “images”, where pooling methods combine multiple images into one image to look for a feature, e.g., using the convolutional neural network (CNN) which was trained in Pirrotte, [0039]), wherein the biomarker expression estimation engine is trained using one or more training mid-infrared absorption spectral data sets, wherein each training mid-infrared absorption spectral data set comprises a plurality of training mid-infrared absorption spectra derived from a plurality of training tissue samples …, and wherein each training vibrational spectrum comprises one or more class labels, wherein the one or more class labels comprise known biomarker [features] for one or more biomarkers (Pirrotte, [0039], where to train the CNN, protein samples with known spectra (i.e., spectra already matched to a protein (i.e., “class labels compris[ing] known biomarker [features] for one or more biomarkers”)) were used to train the CNN to recognize, based on the sequence output, what the input spectra should look like. See Pirrotte, [0040], where the training of the CNN uses spectra matched to a protein or peptide sequence (i.e., “wherein the one or more class labels comprise known biomarker [features] for one or more biomarkers”)); and
c. predicting the expression of the one or more biomarkers in the test biological specimen based on the derived biomarker expression features (Pirrotte, [0038], where the CNN uses feature learning and classification to identify amino acids in the sample, where based on the features found in the convolution and pooling steps (i.e., “based on the derived biomarker expression features”), the CNN classifies (or identifies) the presence or absence of each amino acid (i.e., “biomarker”)).
Although Pirrotte does not appear to explicitly state that the spectral data relates to mid-infrared absorption spectral data as claimed (which is a type of vibrational spectral data, as disclosed by Pirrotte), one of ordinary skill in the art would have found it obvious to have modified Pirrotte to have explicitly utilized mid-infrared absorption spectral data as claimed, as one of ordinary skill in the art would have recognized that many chemical components of interest have molecular vibrations that are excited in the mid-infrared region of the optical spectrum (spanning wavelengths between 5 to 25 microns).1 Therefore, one of ordinary skill in the art would have been motivated to modify Pirrotte to utilize mid-infrared absorption with the motivation of utilizing a mid-infrared light source that can provide useful information about the chemistry of the sample as a function of position on the sample.2
Furthermore, although Pirrotte does not appear to explicitly teach wherein the test biological specimen is unstained, the claimed invention does not distinguish over the prior art because the differences in the claim limitations and the prior art’s disclosure are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The prediction/application of the biomarker expression estimation engine to the test biological specimen would have been performed the same regardless of the specific data involved (i.e., unstained test biological specimen as claimed, or some other data). Thus, this descriptive material will not distinguish the claimed invention from the prior art in terms of patentability. See In re Gulack, 703 F.2d 1381, 1385, 217 USPQ2d 401, 404 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Therefore, it would have been obvious to a person of ordinary skill in the art to have referred to Pirrotte as modified’s teachings in making the claimed invention, because such data does not functionally relate to the steps in the method claimed and because the subjective interpretation of the data does not patentably distinguish the claimed invention over the prior art.
Pirrotte does not appear to explicitly teach [wherein the mid-infrared absorption spectral training data set is derived from a plurality of training tissue samples] stained for the presence of one or more biomarkers, [and that the class label biomarker features relate to] biomarker expression levels.
Barnes teaches [wherein the mid-infrared absorption spectral training data set is derived from a plurality of training tissue samples] stained for the presence of one or more biomarkers (Barnes, [0008], where the system may be trained using a training cohort that includes histopathological tissue slides from several patients, which were processed according to a specific staining protocol and analyzed using automated image analysis algorithms to quantify stains or biomarker expressions in the tissue slides), [and]
[that the class label biomarker features relate to] biomarker expression levels (Barnes, [0038], where as part of the image analysis, regions in each of the tumor marker IHC tissue slide are automatically analyzed and scored using relevant marker-specific image analysis algorithms to calculate scores for each marker, representing percent positivity, H-score, etc. See also, e.g., Barnes-IBR-Chukka, [0004], [0020] and [0022], where the system, using a trained classifier, can automatically count and classify positively-stained nuclear objects, negatively-stained nuclear objects, tissue, or other features, in order to, e.g., assign a score to (regions of) an image associated with the sample (i.e., “biomarker expression levels”). The facility initially trains an object classifier using a plurality of “ground truth” sample slides or training images, where the ground truth slides are annotated).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Pirrotte and Barnes (hereinafter “Pirrotte as modified”) with the motivation of taking into account any factors that may influence the outcome of the analysis, thereby leading to greater accuracy in making assessments.
Regarding claim 2: Pirrotte as modified teaches The system of claim 1, wherein the predicted expression of the one or more biomarkers comprises one of a predicted percent positivity or a predicted staining intensity (Barnes, [0038], where as part of the image analysis, regions in each of the tumor marker IHC tissue slide are automatically analyzed and scored using relevant marker-specific image analysis algorithms to calculate scores for each marker, representing percent positivity, H-score, etc.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Pirrotte and Barnes with the motivation of diminishing bias by taking into account any factors that may influence the outcome of the analysis, thereby leading to greater accuracy in making assessments.
Regarding claim 3: Pirrotte as modified teaches The system of claim 1, wherein the predicted expression of the one or more biomarkers comprises both a predicted percent positivity and a predicted staining intensity ((Barnes, [0046], where image analysis algorithms may be used to determine a presence of one or more of a nucleus, a cell wall, a tumor cell, or other structures within the field of view, where stain intensity values and counts of specific nuclei for each field of view may be used to determine a percent positivity, H-Score, or a regional heterogeneity).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Pirrotte and Barnes with the motivation of being able to classify different sections of tissue, e.g., it is necessary to combine intensity staining measurement and object counting to precisely quantitative the percentage of positivity stained nuclei in an epithelial part of the tissue section, since in many areas of histopathology, just a broad category does not give enough information for the referring clinician to make decisions about patient prognosis and treatment.3
Regarding claim 4: Pirrotte as modified teaches The system of claim 1, wherein a fixation status of the test biological specimen is unknown (Pirrotte, [0028], where a sample can include a variety of sample types, where the sample may have been processed and processing of the biological sample includes fixation, etc.).
Although Pirrotte does not appear to explicitly state that the type of information relates to knowing that a fixation status of the test biological specimen is unknown, as claimed, the claimed invention does not distinguish over the prior art because the differences in the claim limitations and the prior art’s disclosure are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The deriving of biomarker expression features and predicting expression of one or more biomarkers based on the derived biomarker expression features would have been performed the same regardless of the specific data involved (i.e., knowing or not knowing the fixation status of the test biological specimen, or some other relevant feature data). Thus, this descriptive material will not distinguish the claimed invention from the prior art in terms of patentability. See In re Gulack, 703 F.2d 1381, 1385, 217 USPQ2d 401, 404 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994.
Therefore, it would have been obvious to a person of ordinary skill in the art to have referred to Pirrotte’s teachings in making the claimed invention, because such data does not functionally relate to the steps in the method claimed and because the subjective interpretation of the data does not patentably distinguish the claimed invention over the prior art.
Regarding claim 6: Pirrotte as modified teaches The system of claim 1, wherein the known biomarker expression levels comprise at least one of known percent positivities for the one or more biomarkers and known staining intensities for the one or more biomarkers (Barnes-IBR-Chukka, [0004], [0020] and [0022], where the system, using a trained classifier, can automatically count and classify positively-stained nuclear objects, negatively-stained nuclear objects, tissue, or other features, in order to, e.g., assign a score to (regions of) an image associated with the sample (i.e., “quantitatively assessing an expression of the one or more biomarkers”). The facility initially trains an object classifier using a plurality of “ground truth” sample slides or training images, where the ground truth slides are annotated).
Regarding claim 7: Pirrotte as modified teaches The system of claim 1, further comprising one or more class labels selected from the group consisting of a known unmasking duration, a known unmasking temperature, a qualitative assessment of an unmasking state, a known fixation duration, and a qualitative assessment of a fixation state (Pirrotte, [0039], where to train the CNN, protein samples with known spectra (i.e., spectra already matched to a protein) were used to train the CNN to recognize, based on the sequence output, what the input spectra should look like. See Pirrotte, [0040], where the training of the CNN uses spectra matched to a protein or peptide sequence).
Although Pirrotte does not appear to explicitly teach that the class labels relate to a known unmasking duration, a known unmasking temperature, a qualitative assessment of an unmasking state, a known fixation duration, and a qualitative assessment of a fixation state data, the claimed invention does not distinguish over the prior art because the differences in the claim limitations and the prior art’s disclosure are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The training of the biomarker expression estimation engine would have been performed the same regardless of the specific data involved (i.e., the claimed labels, or some other data). Thus, this descriptive material will not distinguish the claimed invention from the prior art in terms of patentability. See In re Gulack, 703 F.2d 1381, 1385, 217 USPQ2d 401, 404 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Therefore, it would have been obvious to a person of ordinary skill in the art to have referred to Pirrotte’s teachings in making the claimed invention, because such data does not functionally relate to the steps in the method claimed and because the subjective interpretation of the data does not patentably distinguish the claimed invention over the prior art.
Regarding claim 11: Pirrotte as modified teaches The system of claim 1, wherein the trained biomarker expression estimation engine comprises a neural network (Pirrotte, [0023] and [0035-0038], where the system identifies the presence or absence of peaks in the spectral data by discretizing the mass spectral data into one-dimensional vectors, segments or buckets, and utilizing convolutional and pooling layers to divide the discretized one-dimensional vector into smaller “images”, where pooling methods combine multiple images into one image to look for a feature, e.g., using the convolutional neural network (CNN) which was trained in Pirrotte, [0039]).
Regarding claim 12: Pirrotte as modified teaches The system of claim 1, further comprising operations for comparing an actual biomarker expression of the test biological specimen with the predicted expression of the one or more biomarkers of the test biological specimen (Pirrotte, [0039], where the CNN-predicted amnio acid sequence was compared to the database-matched amino acid sequence for the particular spectra data.
Note that it would have been obvious to one of ordinary skill in the art to have the system automatically perform such a comparison step (instead of using it for, e.g., purposes of validating by testers) with the motivation of automatically determining the accuracy of the CNN, e.g., to determine whether further training is needed, without requiring the use of manual testers, thereby improving learning response time (i.e., avoiding delays from requiring people to review it manually)).
Regarding claim 16: Pirrotte teaches A non-transitory computer-readable medium storing instructions for predicting an expression of one or more biomarkers in a test biological specimen treated (Pirrotte, [0030-0031], where the disclosed system may include one or more processors/controllers and one or more tangible, non-transitory memories, where system program or processing instructions may be loaded onto the non-transitory, tangible computer-readable medium having instructions stored thereon, that in response to execution by a controller, cause the controller to perform the disclosed operations. See Pirrotte, [0028], where a sample can include a variety of sample types, where the sample may have been processed and processing of the biological sample includes filtration, distillation, extraction, concentration, fixation, inactivation of interfering components, addition of reagents, etc. (i.e., “test biological specimen treated”), etc.), comprising:
(a) obtaining test mid-infrared absorption spectral data from at least a portion of the test biological specimen (Pirrotte, [0028], where a convolutional neural network (CNN) is used to predict the amino acid sequence of a sample based on mass spectrum data input into the CNN (implying “obtaining test spectral data”), the sample being, e.g., a bodily sample, tissue sample, etc., obtained from a subject, e.g., person (Pirrotte, [0028])) … ;
(b) deriving biomarker expression features from the obtained test mid-infrared absorption spectral data using a trained biomarker expression estimation engine (Pirrotte, [0023] and [0035-0038], where the system identifies the presence or absence of peaks in the spectral data by discretizing the mass spectral data into one-dimensional vectors, segments or buckets, and utilizing convolutional and pooling layers to divide the discretized one-dimensional vector into smaller “images”, where pooling methods combine multiple images into one image to look for a feature, e.g., using the convolutional neural network (CNN) which was trained in Pirrotte, [0039]), wherein the biomarker expression estimation engine is trained using training mid-infrared absorption spectral data sets acquired from a plurality of … training biological specimens and wherein the training mid-infrared absorption spectral data sets comprise class labels of known biomarker [features] for one or more biomarkers (Pirrotte, [0039], where to train the CNN, protein samples with known spectra (i.e., spectra already matched to a protein (i.e., “class labels compris[ing] known biomarker [features] for one or more biomarkers”)) were used to train the CNN to recognize, based on the sequence output, what the input spectra should look like. See Pirrotte, [0040], where the training of the CNN uses spectra matched to a protein or peptide sequence (i.e., “wherein the one or more class labels comprise known biomarker [features] for one or more biomarkers”)) …; and
(c) predicting the expression of the one more biomarkers in the test biological specimen based on the derived biomarker expression features (Pirrotte, [0038], where the CNN uses feature learning and classification to identify amino acids in the sample, where based on the features found in the convolution and pooling steps (i.e., “based on the derived biomarker expression features”), the CNN classifies (or identifies) the presence or absence of each amino acid (i.e., “biomarker”)).
Although Pirrotte does not appear to explicitly state that the spectral data relates to mid-infrared absorption spectral data as claimed (which is a type of vibrational spectral data, as disclosed by Pirrotte), one of ordinary skill in the art would have found it obvious to have modified Pirrotte to have explicitly utilized mid-infrared absorption spectral data as claimed, as one of ordinary skill in the art would have recognized that many chemical components of interest have molecular vibrations that are excited in the mid-infrared region of the optical spectrum (spanning wavelengths between 5 to 25 microns).4 Therefore, one of ordinary skill in the art would have been motivated to modify Pirrotte to utilize mid-infrared absorption with the motivation of utilizing a mid-infrared light source that can provide useful information about the chemistry of the sample as a function of position on the sample.5
Although Pirrotte does not appear to explicitly state wherein the test biological specimen has an unknown fixation status and/or unknown unmasking status, and wherein the test biological specimen is unstained as claimed, the claimed invention does not distinguish over the prior art because the differences in the claim limitations and the prior art’s disclosure are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The claimed steps would have been performed the same regardless of the specific data involved (i.e., unstained test biological specimen and poor unmasking and/or poor fixation of the test biological specimen as claimed, or some other data). Thus, this descriptive material will not distinguish the claimed invention from the prior art in terms of patentability. See In re Gulack, 703 F.2d 1381, 1385, 217 USPQ2d 401, 404 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Therefore, it would have been obvious to a person of ordinary skill in the art to have referred to Pirrotte’s teachings in making the claimed invention, because such data does not functionally relate to the steps in the method claimed and because the subjective interpretation of the data does not patentably distinguish the claimed invention over the prior art.
Pirrotte does not appear to explicitly teach that the training data is acquired from a plurality of differentially prepared training biological specimens, and wherein the training biological specimen comprises a different tissue type than the test biological specimen; [and that the class label biomarker features relate to] biomarker expression.
Barnes teaches the training data is acquired from a plurality of differentially prepared training biological specimens (Barnes, [0058], where additional information within the training data for training the system include tissue and biomarker data, as well as a concentration of chemicals used in staining, a reaction times for chemicals applied to the tissue in staining, and/or pre-analytic conditions of the tissue including a fixation method, a duration, how the section was embedded, etc.), and wherein the training biological specimen comprises a different tissue type than the test biological specimen (Barnes, [0075], where for each of the extracted tissue objects, characteristics of the extracted object are identified, and a trained classifier can be used to classify the extracted object. Furthermore, different trained classifiers can be used to analyze different types of tissues and markers (meaning that some of the training data is for one type of tissues, with the test biological specimen possibly being a different type of tissue, thereby utilizing another, different trained classifier));
[that the class label biomarker features relate to] biomarker expression (Barnes, [0038], where as part of the image analysis, regions in each of the tumor marker IHC tissue slide are automatically analyzed and scored using relevant marker-specific image analysis algorithms to calculate scores for each marker, representing percent positivity, H-score, etc. See also, e.g., Barnes-IBR-Chukka, [0004], [0020] and [0022], where the system, using a trained classifier, can automatically count and classify positively-stained nuclear objects, negatively-stained nuclear objects, tissue, or other features, in order to, e.g., assign a score to (regions of) an image associated with the sample (i.e., “biomarker expression”). The facility initially trains an object classifier using a plurality of “ground truth” sample slides or training images, where the ground truth slides are annotated).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Pirrotte and Barnes with the motivation of (1) providing a quantitative value indicative of one or more of, e.g., the likelihood of a particular cancer, disease, or condition, e.g., tissue type or cancer subtype6, thereby improving accuracy by using algorithms trained with specific types of samples (and samples that were prepared in certain manners); and (2) taking into account any factors that may influence the outcome of the analysis, thereby leading to greater accuracy in making assessments.
Regarding claim 17: Claim 17 recites substantially the same claim limitations as claim 2, and is rejected for the same reasons.
Regarding claim 18: Claim 18 recites substantially the same claim limitations as claim 3, and is rejected for the same reasons.
Regarding claim 21: Pirrotte as modified teaches The non-transitory computer-readable medium of claim 16, wherein the test biological specimen is unstained (Pirrotte, [0028], where a convolutional neural network (CNN) is used to predict the amino acid sequence of a sample based on mass spectrum data input into the CNN (implying “obtaining test spectral data”), the sample being, e.g., a bodily sample, tissue sample, etc., obtained from a subject, e.g., person (Pirrotte, [0028])).
Although Pirrotte does not appear to explicitly teach wherein the test biological specimen is unstained, the claimed invention does not distinguish over the prior art because the differences in the claim limitations and the prior art’s disclosure are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The prediction/application of the biomarker expression estimation engine to the test biological specimen would have been performed the same regardless of the specific data involved (i.e., unstained test biological specimen, or some other data). Thus, this descriptive material will not distinguish the claimed invention from the prior art in terms of patentability. See In re Gulack, 703 F.2d 1381, 1385, 217 USPQ2d 401, 404 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Therefore, it would have been obvious to a person of ordinary skill in the art to have referred to Pirrotte as modified’s teachings in making the claimed invention, because such data does not functionally relate to the steps in the method claimed and because the subjective interpretation of the data does not patentably distinguish the claimed invention over the prior art.
Regarding claim 22: Claim 22 recites substantially the same claim limitations as claim 16, and is rejected for the same reasons.
Regarding claim 23: Pirrotte as modified teaches The method of claim 22, wherein each of the plurality of differentially prepared training biological specimens are stained for the presence of one or more biomarkers (Barnes, [0058], where additional information within the training data for training the system include tissue and biomarker data, as well as a concentration of chemicals used in staining, a reaction times for chemicals applied to the tissue in staining, and/or pre-analytic conditions of the tissue including a fixation method, a duration, how the section was embedded, etc. See also Barnes, [0008], where the system may be trained using a training cohort that includes histopathological tissue slides from several patients, which were processed according to a specific staining protocol and analyzed using automated image analysis algorithms to quantify stains or biomarker expressions in the tissue slides).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Pirrotte et al. (US 2019/0034586 A1), in view of Barnes et al. (“Barnes”) (US 2017/0270666 A1, incorporating by reference Chukka et al. (“Barnes-IBR-Chukka”) (WO 2014/140085 A1, also published as US 2016/0042511 A1) at [0046]), in further view of Thagaard et al. (“Thagaard”) (US 2021/0150701 A1).
Regarding claim 8: Pirrotte as modified teaches The system of claim 1, but does not appear to explicitly teach wherein each training spectral data set is derived by: (i) obtaining a training biological specimen; (ii) dividing the obtained training biological specimen into a plurality of training tissue samples; (iii) staining the plurality of training tissue samples for the presence of one or more biomarkers; and (iv) quantitatively assessing an expression of the one or more biomarkers in each training tissue sample of the plurality of training tissue samples, wherein each training tissue sample of the plurality of training tissue samples is differentially unmasked, differentially fixed, or both differentially unmasked and differentially fixed.
Thagaard teaches (i) obtaining a training biological specimen (Thagaard, [0074], where in a first step, a tissue sample is acquired);
(ii) dividing the obtained training biological specimen into a plurality of training tissue samples; (iii) staining the plurality of training tissue samples for the presence of one or more biomarkers (Thagaard, [0074], where in steps 2-3, serial tissue sections are sectioned and transferred to microscopic glass slides. In steps 4-5, the tissue on each glass slide is processed with different staining protocols, where in step 4, the first staining protocol could be a specific biomarker. In step 5, the second staining protocol is different from the first staining); and
(iv) quantitatively assessing an expression of the one or more biomarkers in each training tissue sample of the plurality of training tissue samples … (Thagaard, [0074], where in step 11, deep learning algorithms can be trained on training annotations from the second image and the corresponding output value of the image results of the first image. See Thagaard, [0062], where a deep learning model may be trained to recognize expressions in certain stained tissue samples, e.g., the staining being specific for a marker in a particular specimen, such as a marker for protein expression (Thagaard, [0046]).
See also, e.g., Barnes-IBR-Chukka, [0004], [0020] and [0022], where the system, using a trained classifier, can automatically count and classify positively-stained nuclear objects, negatively-stained nuclear objects, tissue, or other features, in order to, e.g., assign a score to (regions of) an image associated with the sample (i.e., “quantitatively assessing an expression of the one or more biomarkers”). The facility initially trains an object classifier using a plurality of “ground truth” sample slides or training images, where the ground truth slides are annotated).
Although Thagaard does not appear to explicitly state that the information relates to wherein each training tissue sample of the plurality of training tissue samples is differentially unmasked, differentially fixed, or both differentially unmasked and differentially fixed, the claimed invention does not distinguish over the prior art because the differences in the claim limitations and the prior art’s disclosure are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The deriving of biomarker expression features and predicting expression of one or more biomarkers based on the derived biomarker expression features would have been performed the same regardless of the specific data involved (i.e., vibrational spectral data as claimed, or some other data). Thus, this descriptive material will not distinguish the claimed invention from the prior art in terms of patentability. See In re Gulack, 703 F.2d 1381, 1385, 217 USPQ2d 401, 404 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Therefore, it would have been obvious to a person of ordinary skill in the art to have referred to Thagaard’s teachings in making the claimed invention, because such data does not functionally relate to the steps in the method claimed and because the subjective interpretation of the data does not patentably distinguish the claimed invention over the prior art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Pirrotte as modified and Thagaard with the motivation of overcoming challenges related to variation and subjectivity in ground truth labelling, thereby ensuring proper ground truth annotations in order to improve the accuracy of deep learning techniques (see, e.g., Thagaard, [0004-0005]).
Claims 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Pirrotte et al. (US 2019/0034586 A1), in view of Barnes et al. (“Barnes”) (US 2017/0270666 A1, incorporating by reference Chukka et al. (“Barnes-IBR-Chukka”) (WO 2014/140085 A1, also published as US 2016/0042511 A1) at [0046]), in further view of Kumar et al. (“Kumar”) (US 2018/0247195 A1).
Regarding claim 9: Pirrotte as modified teaches The system of claim 1, but does not appear to explicitly teach wherein the trained biomarker expression estimation engine comprises a machine learning algorithm based on dimensionality reduction.
Kumar teaches wherein the trained biomarker expression estimation engine comprises a machine learning algorithm based on dimensionality reduction (Kumar, [0017], where the system applies a dimensionality reduction algorithm to the feature coordinate space as part of training an artificial neural network).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Pirrotte as modified and Kumar (hereinafter “Pirrotte as modified and by Kumar”) with the motivation of allowing a machine learning algorithm to directly compare the relationship of two populations in a single data space that would be intractably large if the dimensions of the two data spaces were simply concatenated (Kumar, [0123]).
Regarding claim 10: Pirrotte as modified and by Kumar teaches The system of claim 9, wherein the dimensionality reduction comprises one of (i) a projection onto latent structure regression model, or (ii) a principal component analysis plus discriminant analysis (Kumar, [0109], where both linear discriminant analysis (LDA) and principal component analysis (PCA) are commonly used for dimensionality reduction, where it is common to use both LDA and PCA in combination, where PCA is first computed on the overall dataset for dimensionality reduction followed by LDA).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Pirrotte as modified and Kumar with the motivation of minimizing redundant information, providing the neural network with a clearer signal and thereby improving neural network performance through the use of PCA (Kumar, [0144]), while also maintaining class-discriminatory information by maximizing the separation between multiple classes through the use of LDA (Kumar, [0108]).
Claims 13 and 24 are rejected under 35 U.S.C. 103 as being unpatentable over Pirrotte et al. (US 2019/0034586 A1), in view of Barnes et al. (“Barnes”) (US 2017/0270666 A1, incorporating by reference Chukka et al. (“Barnes-IBR-Chukka”) (WO 2014/140085 A1, also published as US 2016/0042511 A1) at [0046]), in further view of Garsha et al. (“Garsha”) (US 2018/0121709 A1, incorporating by reference Bredno et al. (“Garsha-IBR-Bredno”) (WO 2014/195193, also published as US 2016/0098590 A1), at [0115]).
Regarding claim 13: Pirrotte as modified teaches The system of claim 1, but does not appear to explicitly teach further comprising operations for compensating the predicted expression of the one or more biomarkers for poor unmasking and/or poor fixation of the test biological specimen.
Garsha teaches further comprising operations for compensating the predicted expression of the one or more biomarkers for poor unmasking and/or poor fixation of the test biological specimen (Garsha, [0115], where in the case of low quality images or poor correlations against ideal results, one or more reference column vectors in matrix R are adjusted, and the unmixing is repeated iteratively using adjusted reference vectors. The reference vectors are adjusted to within a search space. See also Garsha-IBR-Bredno, [0036], where when a quality of the image is compromised, this triggers an adjustment to a reference vector used to unmix the image, or influences a quality metric in addition to all the results of the correlation steps. If the quality metric is unacceptable or below a threshold, the reference vectors may be adjusted within a search space for each reference vector that defines how much and in which direction the reference vector can be changed).
Although Garsha does not appear to explicitly state that the quality pertains to poor unmasking and/or poor fixation of the test biological specimen, as claimed, the claimed invention does not distinguish over the prior art because the differences in the claim limitations and the prior art’s disclosure are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. The compensation of the predicted expression would have been performed the same regardless of the specific data involved (i.e., poor unmasking and/or poor fixation of the test biological specimen as claimed, or some other data). Thus, this descriptive material will not distinguish the claimed invention from the prior art in terms of patentability. See In re Gulack, 703 F.2d 1381, 1385, 217 USPQ2d 401, 404 (Fed. Cir. 1983); In re Lowry, 32 F.3d 1579, 32 USPQ2d 1031 (Fed. Cir. 1994).
Therefore, it would have been obvious to a person of ordinary skill in the art to have referred to Garsha’s teachings in making the claimed invention, because such data does not functionally relate to the steps in the method claimed and because the subjective interpretation of the data does not patentably distinguish the claimed invention over the prior art.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Pirrotte as modified and Garsha with the motivation of taking into account any factors that may influence the outcome of the analysis and making corresponding adjustments to the analysis, thereby leading to greater accuracy in making assessments.
Regarding claim 24: Claim 24 recites substantially the same claim limitations as claim 13, and is rejected for the same reasons.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. See the enclosed 892 form. Ghetler (US 2016/0373663 A1) is cited to show why one of ordinary skill in the art would have utilized mid-infrared absorption spectral data; see Ghetler at [0001].
The prior art should be considered to define the claims over the art of record.
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 IRENE BAKER whose telephone number is (408)918-7601. The examiner can normally be reached M-F 8-5PM PT.
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, NEVEEN ABEL-JALIL can be reached at (571)270-0474. 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.
/IRENE BAKER/Primary Examiner, Art Unit 2152
7 January 2026
1 Ghetler. US 2016/0373663 A1 at [0001].
2 See immediately preceding footnote.
3 Gholap et al. US 2011/0311123 A1 at [0086].
4 Ghetler. US 2016/0373663 A1 at [0001].
5 See immediately preceding footnote.
6 Wilde et al. US 2018/0122508 A1 at [0185].