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 .
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 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.
Claim Status
Claims 1-18, 24, and 27 are pending.
Claims 19-23 and 25-26 are canceled.
Claims 1 and 24 are objected to.
Claims 1-18, 24, and 27 are rejected.
Priority
Applicant's claim for the benefit of a prior-filed application, PCT/CN2021/121089, filed Sep 27 2021, is acknowledged.
Accordingly, each of claims 1-18, 24, and 27 are afforded the effective filing date of Sep 27 2021.
Information Disclosure Statement
The information disclosure statements (IDS) filed on Sep 28 2022, Mar 22 2023, and Apr 25 2023 are in compliance with the provisions of 37 CFR 1.97 and have therefore been considered. Signed copies of the IDS documents are included with this Office Action.
Drawings
The Drawings submitted Sep 28 2022 are accepted.
Nucleotide and/or Amino Acid Sequence Disclosures
The sequence listing submitted May 23 2024 has been accepted.
Specification
The amendments to the abstract and specification filed Sep 28 2022 and May 23 2024 are accepted.
Claim Objections
The claims are objected to for the following informalities:
In claim 1, limitation 4, a comma should be added after “obtaining respectively” and before “by using…”. Claim 27 is similarly objected to.
Claim Interpretation
In claims 14-16, the terms “traditional machine learning model” and “deep learning model” will be interpreted in light of the specification, which discloses at [0135] as published that “traditional machine learning models refer to processing natural data in an original form” and provides examples of linear regression models, logistic regression models, support vector machine models, decision tree models, K-Nearest Neighbor (KNN) models, random forest models, naive Bayesian models, etc., whereas the “deep learning model has the ability to automatically extract features, and can be composed of multiple processing layers to form a complex computing model, so as to automatically obtain data representation and multiple abstraction levels, which is a learning for feature representation”.
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 1-18, 24, and 27 are rejected under 35 U.S.C. 101 because the claimed invention is directed to one or more judicial exceptions without significantly more.
MPEP 2106 organizes judicial exception analysis into Steps 1, 2A (Prongs One and Two) and 2B as follows below. MPEP 2106 and the following USPTO website provide further explanation and case law citations: uspto.gov/patent/laws-and-regulations/examination-policy/examination-guidance-and-training-materials.
Framework with which to Evaluate Subject Matter Eligibility:
Step 1: Are the claims directed to a process, machine, manufacture, or composition of matter;
Step 2A, Prong One: Do the claims recite a judicially recognized exception, i.e. a law of nature, a natural phenomenon, or an abstract idea;
Step 2A, Prong Two: If the claims recite a judicial exception under Prong One, then is the judicial exception integrated into a practical application (Prong Two); and
Step 2B: If the claims do not integrate the judicial exception, do the claims provide an inventive concept.
Framework Analysis as Pertains to the Instant Claims:
Step 1
With respect to Step 1: yes, the claims are directed to a method and an electronic device, i.e., a process, machine, or manufacture within the above 101 categories [Step 1: YES; See MPEP § 2106.03].
Step 2A, Prong One
With respect to Step 2A, Prong One, the claims recite judicial exceptions in the form of abstract ideas. The MPEP at 2106.04(a)(2) further explains that abstract ideas are defined as:
mathematical concepts (mathematical formulas or equations, mathematical relationships and mathematical calculations);
certain methods of organizing human activity (fundamental economic practices or principles, managing personal behavior or relationships or interactions between people); and/or
mental processes (procedures for observing, evaluating, analyzing/ judging and organizing information).
The claims also recite a law of nature or a natural phenomenon. The MPEP at 2106.04(b) further explains that laws of nature and natural phenomena include naturally occurring principles/relations and nature-based products that are naturally occurring or that do not have markedly different characteristics compared to what occurs in nature.
With respect to the instant claims, under the Step 2A, Prong One evaluation, the claims are found to recite abstract ideas that fall into the grouping of mental processes (in particular procedures for observing, analyzing and organizing information) and mathematical concepts (in particular mathematical relationships and formulas) as well as a law of nature or a natural phenomenon are as follows:
Independent claims 1 and 27: obtaining a sequence feature of the RNA-protein pair to be predicted by performing feature extraction on the RNA-protein pair to be predicted;
obtaining an RNA sequence representation vector and a protein sequence representation vector in the RNA-protein pair to be predicted by vectorizing the RNA-protein pair to be predicted;
obtaining respectively by using multiple interaction prediction models, multiple interaction prediction values of the RNA-protein pair to be predicted, based on the sequence feature of the RNA-protein pair to be predicted, the RNA sequence representation vector and the protein sequence representation vector in the RNA-protein pair to be predicted; and
determining an interaction between the RNA and the protein according to the multiple interaction prediction values.
Dependent claims 2-18 recite further steps that limit the judicial exceptions in independent claim 1 and, as such, also are directed to those abstract ideas. For example, claim 2 further limits obtaining a sequence feature by performing feature extraction in claim 1; claims 3-5 further limit determining a sequence feature in claim 2; claim 6 further limits obtaining an original sequence feature set in claim 2; claims 7-11 further limit performing feature extraction in the original data set in claim 6 to include specific calculations and mathematical formula; claim 12 further limits obtaining an RNA sequence representation vector and a protein sequence representation vector in claim 1; claims 13-16 further limit obtaining multiple interaction prediction values in claim 1 to comprising traditional machine learning and deep learning models; and claims 17-18 further limit determining an interaction to calculations.
The abstract ideas recited in the claims are evaluated under the Broadest Reasonable Interpretation (BRI) and determined to each cover performance either in the mind and/or by mathematical operation because the method only requires a user to manually determine an interaction between an RNA and a protein. Without further detail as to the methodology involved in “obtaining… by performing feature extraction”, “obtaining… by vectorizing”, “obtaining respectively by using multiple interaction prediction models”, and “determining an interaction”, under the BRI, one may simply, for example, use pen and paper to record sequence features of an RNA-protein pair, record a vector of the RNA and protein sequence, input vectors into prediction models to obtain prediction values, and determine whether or not the RNA and protein interact. Further, one may similarly use pen and paper to determine sequence features of an original sequence features set and the RNA-protein pair according to k-mer subsequence conversion, combining, counting, and searching, as recited in the dependent claims.
Some of these steps and those recited in the dependent claims require mathematical techniques as the only supported embodiments. Specifically, vectorizing recites the mathematical technique of turning sequence data into a numbered vector. The prediction models are considered to recite mathematical models because they produce prediction values. Dependent claim 9 further limits the feature extraction to involving a mathematical formula. Further support for mathematical techniques in the claims is disclosed in the specification as published: descriptions of counting k-mers in sequences and equations for examining the k-mer numbers [0078-0090]; descriptions of vectorizing sequences based on k-mers [0128]; “Exemplarily, traditional machine learning models may include linear regression models, logistic regression models, support vector machine models, decision tree models, K-Nearest Neighbor (KNN) models, random forest models, naive Bayesian models, etc.” [0135].
The claims also recite determining the natural relationship of whether an RNA and a protein interact. The ability of the RNA and the protein to interact is the result of their natural, intrinsic properties conveyed in the sequence of the RNA and the protein.
Therefore, claims 1 and 27 and those claims dependent therefrom recite an abstract idea and a law of nature/natural phenomenon [Step 2A, Prong 1: YES; See MPEP § 2106.04].
Step 2A, Prong Two
Because the claims do recite judicial exceptions, direction under Step 2A, Prong Two, provides that the claims must be examined further to determine whether they integrate the judicial exceptions into a practical application (MPEP 2106.04(d)). A claim can be said to integrate a judicial exception into a practical application when it applies, relies on, or uses the judicial exception in a manner that imposes a meaningful limit on the judicial exception. This is performed by analyzing the additional elements of the claim to determine if the judicial exceptions are integrated into a practical application (MPEP 2106.04(d).I.; MPEP 2106.05(a-h)). If the claim contains no additional elements beyond the judicial exceptions, the claim is said to fail to integrate the judicial exceptions into a practical application (MPEP 2106.04(d).III).
Additional elements, Step 2A, Prong Two
With respect to the instant recitations, the claims recite the following additional elements:
Independent claims 1 and 27: acquiring an RNA-protein pair to be predicted.
Dependent claim 16: the deep learning model comprises at least one of a convolutional neural network model and a recurrent neural network model.
Dependent claim 24: outputting a prediction result of the interaction between the RNA and the protein.
The claims also include non-abstract computing elements. For example, independent claim 27 includes an electronic device, comprising a processor and a memory for storing instructions executable by the processor.
Considerations under Step 2A, Prong Two
With respect to Step 2A, Prong Two, the additional elements of the claims do not integrate the judicial exceptions into a practical application for the following reasons. Those steps directed to data gathering, such as “acquiring” an RNA-protein pair as in claims 1 and 27, and to data outputting, such as “outputting” a prediction result as in claim 24, perform functions of collecting and outputting the data needed to carry out the judicial exceptions. Data gathering and outputting do not impose any meaningful limitation on the judicial exceptions, or on how the judicial exceptions are performed. Data gathering and outputting steps are not sufficient to integrate judicial exceptions into a practical application (MPEP 2106.05(g)).
Further steps directed to additional non-abstract computing elements do not describe any specific computational steps by which the “computer parts” perform or carry out the judicial exceptions, nor do they provide any details of how specific structures of the computer, such as the computer-readable recording media, are used to implement these functions. The claims state nothing more than a generic computer which performs the functions that constitute the judicial exceptions. Hence, these are mere instructions to apply the judicial exceptions using a computer, and therefore the claim does not integrate that judicial exceptions into a practical application. The courts have weighed in and consistently maintained that when, for example, a memory, display, processor, machine, etc.… are recited so generically (i.e., no details are provided) that they represent no more than mere instructions to apply the judicial exception on a computer, and these limitations may be viewed as nothing more than generally linking the use of the judicial exception to the technological environment of a computer (MPEP 2106.05(f)).
Further, the limitation reciting “the deep learning model comprises at least one of a convolutional neural network model and a recurrent neural network model” in claim 16 provides nothing more than mere instructions to implement the abstract idea of obtaining prediction values on a generic computer. See MPEP 2106.05(f). MPEP 2106.05(f) provides the following considerations for determining whether a claim simply recites a judicial exception with the words “apply it” (or an equivalent), such as mere instructions to implement an abstract idea on a computer: (1) whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished; (2) whether the claim invokes computers or other machinery merely as a tool to perform an existing process; and (3) the particularity or generality of the application of the judicial exception. Therefore, the limitations merely serve to link the judicial exception of “obtaining prediction values” to the technological environment of a neural network model.
The specification as published discloses that “ characteristics of multiple interaction prediction models can be combined effectively, which can further improve the accuracy of predicting the interaction between the RNA and the protein” at [0059], but does not provide a clear explanation for how the additional elements provide these improvements. Therefore, the additional elements do not clearly improve the functioning of a computer, or comprise an improvement to any other technical field. Further, the additional elements do not clearly affect a particular treatment; they do not clearly require or set forth a particular machine; they do not clearly effect a transformation of matter; nor do they clearly provide a nonconventional or unconventional step (MPEP2106.04(d)).
Thus, none of the claims recite additional elements which would integrate a judicial exception into a practical application, and the claims are directed to one or more judicial exceptions [Step 2A, Prong 2: NO; See MPEP § 2106.04(d)].
Step 2B (MPEP 2106.05.A i-vi)
According to analysis so far, the additional elements described above do not provide significantly more than the judicial exception. A determination of whether additional elements provide significantly more also rests on whether the additional elements or a combination of elements represents other than what is well-understood, routine, and conventional. Conventionality is a question of fact and may be evidenced as: a citation to an express statement in the specification or to a statement made by an applicant during prosecution that demonstrates a well-understood, routine or conventional nature of the additional element(s); a citation to one or more of the court decisions as discussed in MPEP 2106(d)(II) as noting the well-understood, routine, conventional nature of the additional element(s); a citation to a publication that demonstrates the well-understood, routine, conventional nature of the additional element(s); and/or a statement that the examiner is taking official notice with respect to the well-understood, routine, conventional nature of the additional element(s).
With respect to the instant claims, the courts have found that receiving and outputting data are well-understood, routine, and conventional functions of a computer when claimed in a merely generic manner or as insignificant extra-solution activity (see Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information), buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network), Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015), and OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93, as discussed in MPEP 2106.05(d)(II)(i)). As such, the claims simply append well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception (MPEP2106.05(d)). The data gathering steps as recited in the instant claims constitute a general link to a technological environment which is insufficient to constitute an inventive concept which would render the claims significantly more than the judicial exception (MPEP2106.05(g)&(h)).
With respect to claims 1 and 27 and those claims dependent therefrom, the computer-related elements or the general purpose computer do not rise to the level of significantly more than the judicial exception. The claims state nothing more than a generic computer which performs the functions that constitute the judicial exceptions. The additional element of the neural networks recited in claim 16 is, at best, a mere instruction to “apply” the abstract ideas, which cannot provide an inventive concept. See MPEP 2106.05(f). Hence, these are mere instructions to apply the judicial exceptions using a computer, which the courts have found to not provide significantly more when recited in a claim with a judicial exception (Alice Corp., 573 U.S. at 225-26, 110 USPQ2d at 1984; see MPEP 2106.05(A)). The specification also notes that computer processors and systems, as example, are commercially available or widely used at FIG. 1, for example. The additional elements are set forth at such a high level of generality that they can be met by a general purpose computer. Therefore, the computer components constitute no more than a general link to a technological environment, which is insufficient to constitute an inventive concept that would render the claims significantly more than the judicial exceptions (see MPEP 2106.05(b)I-III).
Taken alone, the additional elements do not amount to significantly more than the above-identified judicial exception(s). Even when viewed as a combination, the additional elements fail to transform the exception into a patent-eligible application of that exception. Thus, the claims as a whole do not amount to significantly more than the exception itself [Step 2B: NO; See MPEP § 2106.05].
Therefore, the instant claims are not drawn to eligible subject matter as they are directed to one or more judicial exceptions without significantly more. For additional guidance, applicant is directed generally to the MPEP § 2106.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
A. Claims 1-3, 6, 12-15, 17-18, 24, and 27 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Pan et al. (BMC Genomics, 2016, 17(582):1-14; newly cited).
The prior art to Pan discloses a computational method IPMiner (Interaction Pattern Miner) to predict ncRNA-protein interactions from sequences, which makes use of deep learning and further improves its performance using stacked ensembling (abstract). Pan, indicated by the open circles, teaches the instant features, indicated by the closed circles, as follows.
Claim 1 discloses a method for predicting an RNA-protein interaction. Claim 27 discloses an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor. As Pan teaches that IPMiner is a computational method (abstract), it is considered that Pan fairly teaches the electronic device and its components as recited in claim 27.
The method of claim 1 and the actions performed by the processor of claim 27 comprise:
acquiring an RNA-protein pair to be predicted;
Pan teaches downloading RNA-protein complex data (p. 11, col. 1, par. 2).
obtaining a sequence feature of the RNA-protein pair to be predicted by performing feature extraction on the RNA-protein pair to be predicted;
Pan teaches obtaining raw features by extracting simple sequence component composition features for both RNAs and proteins (p. 11, col. 2, par. 3 through p. 12, col. 1, par. 1), which Pan more specifically teaches 1) extracting conjoint triad (3-mer) from protein sequences and 4-mer frequency from RNA sequences (p. 12, col. 1, par. 1).
obtaining an RNA sequence representation vector and a protein sequence representation vector in the RNA-protein pair to be predicted by vectorizing the RNA-protein pair to be predicted;
Pan teaches 2) applying stacked autoencoder to extract high-level features, called SDA, from the extracted sequence features of RNAs and proteins, respectively, such that two sub-networks for protein and RNA are generated (p. 12, col. 1, par. 1). Pan teaches 3) adding another softmax layer to merge the two sub-networks of RNA and protein, and then use label information of training data for fine tuning the above stacked autoencoder, update the weights of networks and extracted features from updated stacked autoencoder, the new feature is called SDA-FT (p. 12, col. 1, par. 1). Pan teaches input data x with d-dimension into the autoencoder to reconstruct z (the high-level features discussed above) of the same shape as x (p. 12, col. 1, par. 3 through col. 2, par. 4), which is considered to read on vectorizing the RNA-protein pair as instantly claimed because a vector may simply be represented by a variable with dimensional data, as is supported by the instant specification as published at least at [0116], which described a 560-dimensional feature value vector of [1, 0, . . . , 0, 1, . . . ].
obtaining respectively by using multiple interaction prediction models, multiple interaction prediction values of the RNA-protein pair to be predicted, based on the sequence feature of the RNA-protein pair to be predicted, the RNA sequence representation vector and the protein sequence representation vector in the RNA-protein pair to be predicted; and
Pan teaches 4) feeding the extracted raw features, SDA and SDA-FT features to random forest classifiers, respectively, and the 3 classifiers are named as RPISeq-RF, SDA-RF and SDA-TF-RF, respectively (p. 12, col. 1, par. 1).
determining an interaction between the RNA and the protein according to the multiple interaction prediction values.
Pan teaches 5) using stacked ensembling to integrate the outputs from the above 3 classifiers, which trains a logistic regression model on the outputs from them (p. 12, col. 1, par. 2), where the outputs are probability of RNA-protein interaction (p. 13, col. 1, par. 1; p. 6, col. 1, par. 2; abstract; see also Fig. 1 for a general overview of IPMiner).
Regarding claim 2, Pan teaches claim 1 as described above. Claim 2 further adds that obtaining a sequence feature of the RNA-protein pair to be predicted by performing feature extraction on the RNA-protein pair to be predicted comprises obtaining an original sequence feature set; and determining a sequence feature of the RNA-protein pair to be predicted according to the original sequence feature set.
Pan teaches downloading RNA-protein complex data (p. 11, col. 1, par. 2) and extracting conjoint triad (3-mer) from protein sequences and 4-mer frequency from RNA sequences (p. 12, col. 1, par. 1) for model training (p. 12, col. 2, par. 3; p. 7, col. 2, par. 2) (i.e., an original sequence feature set).
Regarding claim 3, Pan teaches claims 1-2 as described above. Claim 3 further adds determining a sequence feature of the RNA-protein pair to be predicted according to the original sequence feature set comprises: converting an RNA sequence and a protein sequence in the RNA-protein pair to be predicted into k-mer subsequences, respectively; and searching for each of the k-mer subsequences in the original sequence feature set, and obtaining the sequence feature of the RNA-protein pair to be predicted according to a search result.
Pan teaches extracting conjoint triad (3-mer) from protein sequences and 4-mer frequency from RNA sequences (p. 12, col. 1, par. 1) to obtain raw k-mer features (i.e., converting an RNA sequence and a protein sequence into an RNA and a protein k-mer subsequence, respectively) for model training (p. 11, col. 2, par. 3 through p. 12, col. 2, par. 3; p. 7, col. 2, par. 2). Pan teaches that the protein and RNA features comprise counts for each of the different k-mers for each protein and RNA (i.e., searching for each of the k-mer subsequences in the original sequence feature set).
Regarding claim 6, Pan teaches claims 1-2 as described above. Claim 6 further adds that obtaining an original sequence feature set comprises obtaining an original data set; and performing feature extraction on each RNA-protein pair in the original data set to obtain the original sequence feature set.
Pan teaches downloading RNA-protein complex data (i.e., an original data set) (p. 11, col. 1, par. 2) and extracting conjoint triad (3-mer) from protein sequences and 4-mer frequency from RNA sequences (p. 12, col. 1, par. 1) for model training (p. 12, col. 2, par. 3; p. 7, col. 2, par. 2) (i.e., an original sequence feature set).
Regarding claim 12, Pan teaches claim 1 as described above. Claim 12 further adds that obtaining an RNA sequence representation vector and a protein sequence representation vector in the RNA-protein pair to be predicted by vectorizing the RNA-protein pair to be predicted comprises: converting an RNA sequence and a protein sequence in the RNA-protein pair to be predicted into k-mer subsequences, respectively, wherein the k-mer subsequences comprise M RNA k-mer subsequence and N protein k-mer subsequence; vectorizing each of the M RNA k-mer subsequences to obtain M RNA k-mer vectors; obtaining the RNA sequence representation vector by splicing the M RNA k-mer vectors; vectorizing each of the N protein k-mer subsequences to obtain N protein k-mer vectors; and obtaining the protein sequence representation vector by splicing the N protein k-mer vectors.
Pan teaches obtaining raw features by extracting simple sequence component composition features for both RNAs and proteins, by extracting conjoint triad (3-mer) from protein sequences and 4-mer frequency from RNA sequences to form 343 dimensional features for each protein sequence (i.e., spliced N protein k-mer vectors) and 256 dimensional features for each RNA sequence (i.e., spliced M RNA k-mer vectors) (p. 11, col. 2, par. 3 through p. 12, col. 1, par. 2).
Regarding claim 13, Pan teaches claim 1 as described above. Claim 13 further adds that obtaining respectively by using multiple interaction prediction models, multiple interaction prediction values of the RNA-protein pair to be predicted, based on the sequence feature of the RNA-protein pair to be predicted, the RNA sequence representation vector and the protein sequence representation vector in the RNA-protein pair to be predicted comprises: inputting the sequence feature of the RNA-protein pair to be predicted into at least one first interaction prediction model to obtain at least one first interaction prediction value; and inputting the RNA sequence representation vector and the protein sequence representation vector in the RNA-protein pair to be predicted into at least one second interaction prediction model to obtain at least one second interaction prediction value.
Pan teaches 4) feeding the extracted raw features (i.e., sequence feature of the RNA-protein pair), SDA and SDA-FT features (i.e., the RNA sequence representation vector and the protein sequence representation vector) to random forest classifiers, respectively, and the 3 classifiers are named as RPISeq-RF, SDA-RF and SDA-TF-RF (i.e., at least first and second interaction predication models), respectively (p. 12, col. 1, par. 1; Fig. 1).
Regarding claim 14, Pan teaches claim 1 as described above. Claim 14 further adds that obtaining respectively by using multiple interaction prediction models, multiple interaction prediction values of the RNA-protein pair to be predicted, based on the sequence feature of the RNA-protein pair to be predicted, the RNA sequence representation vector and the protein sequence representation vector in the RNA-protein pair to be predicted comprises: inputting the sequence feature of the RNA-protein pair to be predicted into at least one traditional machine learning model to obtain at least one first interaction prediction value; and inputting the RNA sequence representation vector and the protein sequence representation vector in the RNA-protein pair to be predicted into at least one deep learning model to obtain at least one second interaction prediction value.
Pan teaches 4) feeding the extracted raw features (i.e., sequence feature of the RNA-protein pair), SDA and SDA-FT features (i.e., the RNA sequence representation vector and the protein sequence representation vector) to random forest classifiers, respectively, and the 3 classifiers are named as RPISeq-RF, SDA-RF and SDA-TF-RF (i.e., at least first and second interaction predication models), respectively (p. 12, col. 1, par. 1; Fig. 1). The random forest model acting on the extracted raw features reads on a traditional machine learning model, as is supported by the instant specification as published at [0135], which sets forth that traditional machine learning models refer to processing natural data in an original form and provides random forest models as one example. As Pan teaches applying stacked autoencoder to automatically extract high-level features, called SDA and SDA-FT, from the extracted sequence features of RNAs and proteins (p. 12, col. 1, par. 1; Fig. 1), which Pan describes as a deep learning network (p. 2, col. 2, par. 4; p. 9-10, Discussion; p. 12, col. 1, par. 7 through col. 2, par. 6), the combination of the autoencoder and random forest taught by Pan to predict protein interactions from these features reads on inputting the RNA sequence representation vector and the protein sequence representation vector in the RNA-protein pair to be predicted into at least one deep learning model to obtain at least one second interaction prediction value as instantly claimed. Such an interpretation is supported by the instant specification as published at [0135], which sets forth that deep learning model has the ability to automatically extract features, and can be composed of multiple processing layers to form a complex computing model, so as to automatically obtain data representation and multiple abstraction levels, which is a learning for feature representation.
Regarding claim 15, Pan teaches claims 1 and 14 as described above. Claim 15 further adds that each of the at least one deep learning model comprises at least two sub-deep learning models; and said inputting the RNA sequence representation vector and the protein sequence representation vector in the RNA-protein pair to be predicted into at least one deep learning model to obtain at least one second interaction prediction value comprises: inputting the RNA sequence representation vector in the RNA-protein pair to be predicted into a first sub-deep learning model to obtain a first sequence feature; inputting the protein sequence representation vector in the RNA-protein pair to be predicted into a second sub-deep learning model to obtain a second sequence feature; and fusing the first sequence feature and the second sequence feature, and obtaining the second interaction prediction value according to a fused feature.
Pan teaches that the raw RNA and protein features are separately input into their own stacked autoencoder (i.e., two sub-deep learning models) to obtain features, followed by the autoencoder merging (i.e., fusing) the RNA and protein networks to produce the final features which are input into the random forest classifier (p. 3, col. 2, par. 3; Fig. 1).
Regarding claim 17, Pan teaches claim 1 as described above. Claim 17 further adds that determining an interaction between the RNA and the protein according to the multiple interaction prediction values comprises: calculating a weighted sum of the multiple interaction prediction values; and determining the interaction between the RNA and the protein according to a calculation result.
Pan teaches that when the weights of logistic regression for all individual classifiers is the same, then the averaging strategy is used (p. 12, col. 2, par. 5 through p. 13, col. 1, par. 1; p. 6, col. 1, par. 2), which reads on a weighted sum as instantly claimed.
Regarding claim 18, Pan teaches claims 1 and 17 as described above. Claim 18 further adds that determining the interaction between the RNA and the protein according to a calculation result comprises: determining the interaction between the RNA and the protein occurs in response to the calculation result being greater than a preset interaction prediction threshold; and determining the interaction between the RNA and the protein does not occur in response to the calculation result being less than or equal to the preset interaction prediction threshold.
Pan teaches determining the probability that a protein and RNA pair interact (p. 12, col. 2, par. 6) and determining the true and false positives of these predictions (p. 13, col. 1, par. 2). It is therefore considered that Pan inherently teaches using the probability (i.e, a prediction threshold) to determine whether or not the protein and RNA pairs interact, as instantly claimed.
Regarding claim 24, Pan teaches claim 1 as described above. Claim 24 further adds outputting a prediction result of the interaction between the RNA and the protein.
Pan at least teaches constructing RNA-protein networks using the predicted scores from IPMiner (p. 9, col. 1, par. 2 through col. 2, par. 1; Fig. 4), which reads on outputting a prediction result as instantly claimed.
B. Claims 7-8 and 10 under 35 U.S.C. 102(a)(1) as being anticipated by Pan, as applied to claims 1-2 and 6 in the above, and as evidenced by Muppirala et al. (BMC Bioinformatics, 2011, 12(1):489, p. 1-11; newly cited) and Shen et al. (PNAS, 2007, 104(11):4337-4341; newly cited).
Regarding claims 7-8, Pan teaches claims 1-2 and 6 as described above. Claim 7 further adds that performing feature extraction on each RNA-protein pair in the original data set to obtain the original sequence feature set comprises obtaining k-mer subsequences by performing permutation with repetition on basic units of the RNA and the protein, respectively; counting frequency of occurrence of each of the k-mer subsequences in the original data set, and calculating variance of each of the k-mer subsequences according to the frequency of occurrence; and determining the original sequence feature set according to the variance of each of the k-mer subsequences. Claim 8 further adds that counting frequency of occurrence of each of the k-mer subsequences in the original data set, and calculating variance of each of the k-mer subsequences according to the frequency of occurrence comprises: counting number of occurrence of each of the k-mer subsequences in the original data set; calculating the frequency of occurrence of each of the k-mer subsequences in the original data set according to the number of occurrence; marking whether each of the k-mer subsequences occurs in each RNA-protein pair by traversing the original data set; and calculating the variance of each of the k-mer subsequences according to the frequency of occurrence of each of the k-mer subsequences in the original data set and a marking value of each of the k-mer subsequences in each RNA-protein pair.
Pan teaches extracting conjoint k-mers of RNA and protein sequences, obtaining the frequency of the k-mers, and normalizing the frequency of the k-mers to obtain the feature values 4-mer nucleotides in RNA sequences, which is AAAA, AAAC. . .TTTT (p. 11, col. 2, par. 3 through p. 12, col. 1, par. 1). While Pan does not explicitly teach calculating variance of the k-mers, Pan teaches following the method of Muppirala to determine these features (p. 12, col. 1, par. 1). Muppirala discloses the framework for RPISeq (abstract), which is employed in the method of Pan as described above. Muppirala teaches representations of protein and RNA sequences as vectors composed of conjoint k-mers (p. 8, col. 2, par. 4 through p. 9, col. 1, par. 1), according to the method of Shen. Shen discloses a method for protein-protein interaction prediction using only the information of protein sequences (abstract), where they developed a conjoint triad method for describing protein-protein sequences (p. 4338, col. 1, par. 5 through col. 2, par. 2). Shen discloses an equation to normalize the frequencies of the k-mers according to the frequency of a given k-mer in the protein (i.e., marking as in claim 8) in accordance with the frequency of all the k-mers found (i.e., by traversing the original data set as in claim 8), which reads on calculating variance of each of the k-mer subsequences according to the frequency of occurrence as instantly claimed. As Pan teaches using the method of Muppirala, who teaches using the method of Shen, it is considered that Pan as evidenced by Muppirala and Shen teaches the instant limitation.
Regarding claim 10, Pan teaches claims 1-2 and 6, and as evidenced by Muppirala and Shen, claims 7 as described above. Claim 10 further adds determining the original sequence feature set according to the variance of each of the k-mer subsequences comprises: determining a k-mer subsequence that meets a preset condition according to the variance of each of the k-mer subsequences, and forming the original sequence feature set by using the k-mer subsequence that meets the preset condition.
Pan as evidenced by Muppirala and Shen teaches determining the variance of the k-mers as described above. Shen teaches that the frequencies of the k-mers are normalized to produce numerical values of each protein in a certain range of 0 to 1, which are then used to make the feature vectors (i.e., determining a k-mer subsequence that meets a preset condition according to the variance of each of the k-mer subsequences) (p. 4338, col. 2, par. 2). Therefore, Pan as evidenced by Muppirala and Shen teaches the instant claim.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
A. Claims 4-5 are rejected under 35 U.S.C. 103 as being unpatentable over Pan, as applied to claims 1-2 in the above 35 USC 102 rejection, and in further view of the features of Pan.
Regarding claims 4-5, Pan teaches claims 1-2 as described above. Claims 4-5 further add converting an RNA sequence and a protein sequence in the RNA-protein pair to be predicted into k-mer subsequences, respectively, wherein the k-mer subsequences comprise an RNA k-mer subsequence and a protein k-mer subsequence; combining the RNA k-mer subsequence and the protein k-mer subsequence to obtain multiple RNA-protein k-mer subsequence pairs; and searching for each of the RNA-protein k-mer subsequence pairs in the original sequence feature set, and obtaining the sequence feature of the RNA-protein pair to be predicted according to a search result (claim 4); and converting an RNA sequence and a protein sequence in the RNA-protein pair to be predicted into k-mer subsequences, respectively, wherein the k-mer subsequences comprise an RNA k-mer subsequence and a protein k-mer subsequence; searching for each of the k-mer subsequences in the original sequence feature set to obtain a first sequence feature; combining the RNA k-mer subsequence and the protein k-mer subsequence to obtain multiple RNA-protein k-mer subsequence pairs; searching for each of the RNA-protein k-mer subsequence pairs in the original sequence feature set to obtain a second sequence feature; and forming the sequence feature of the RNA-protein pair to be predicted by using the first sequence feature and the second sequence feature (claim 5).
Pan teaches extracting conjoint triad (3-mer) from protein sequences and 4-mer frequency from RNA sequences (p. 12, col. 1, par. 1) to obtain raw k-mer features (i.e., converting an RNA sequence and a protein sequence into an RNA and a protein k-mer subsequence, respectively, as in claims 4-5) for model training (p. 11, col. 2, par. 3 through p. 12, col. 2, par. 3; p. 7, col. 2, par. 2). Pan teaches that the protein and RNA features comprise counts for each of the different k-mers for each protein and RNA (i.e., searching for each of the k-mer subsequences in the original sequence feature set, as in claims 4-5).
Pan does not teach combining the RNA k-mer subsequence and the protein k-mer subsequence to obtain multiple RNA-protein k-mer subsequence pairs and searching for each of the RNA-protein k-mer subsequence pairs in the original sequence feature set to obtain features as in claims 4 and 5.
However, Pan teaches for the learned k-mer features of the RNA and protein sequences both examining the separate and merged features of the RNA and protein sequences (p. 12, col. 1, par. 2 and col. 2, par. 3; Fig. 1).
Regarding claims 4-5, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, in the course of routine experimentation and with a reasonable expectation of success, the features of Pan to examine the raw k-mer features of the proteins and RNA sequences separately, as explicitly taught by Pan (described above) and in combinations of pairs because Pan already teaches such a feature for the other examined feature vectors of the RNA and protein sequences, as discussed above. As Pan teaches the act of merging combining k-mer sequences in a different context, it would have been obvious to one of ordinary skill in the art to apply this action to the raw features.
B. Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Pan, as applied to claims 1-2 and 6 in the above 35 USC 102 rejection, and as evidenced by Muppirala and Shen, as applied to claims 7-8, in the above 35 USC 102 rejection, and in view of the features of Shen.
Regarding claim 9, Pan teaches claims 1-2 and 6, and as evidenced by Muppirala and Shen, claims 7-8 as described above. Claim 9 further adds an equation for calculating the variance of each of the k-mer subsequences.
Shen teaches Eq. 1 of
PNG
media_image1.png
18
424
media_image1.png
Greyscale
(p. 4338, col. 2, par. 2), where fi reads on Appearin, min{f1…f343} reads on Freqi, and 343 reads on N as instantly claimed. Shen teaches determining a vector space consisting of di (p. 4338, col. 2, par. 2), which reads on summing all of the determined numbers as instantly claimed. While Shen does not explicitly teach squaring the equation as instantly claimed, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, in the course of routine experimentation and with a reasonable expectation of success, the equation of Shen to only produce a positive number for each k-mer. Therefore, it is considered that Pan as evidenced by Muppirala and the features of Shen teach the limitations of claim 9.
C. Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Pan, as applied to claims 1 and 14 as applied in the above 35 USC 102 rejection, as evidenced by Hu et al. (RNA Biology, 2018, 15(6):797-806; IDS reference) and in further view of Pan et al. (Bioinformatics, 2018, 34(10):3427-3436; newly cited).
Regarding claim 16, Pan teaches claims 1 and 14 as described above. Claim 16 further adds that the traditional machine learning model comprises at least one of a logistic regression model, a support vector machine model and a decision tree model, and the deep learning model comprises at least one of a convolutional neural network model and a recurrent neural network model.
Pan teaches using a random forest model to analyze the raw features extracted from the RNA and protein sequences as described above (p. 3, col. 2, par. 3; Fig. 1). Hu discloses that random forest is a classifier that uses multiple decision trees to train and predict samples (p. 804, col. 1, par. 2). Therefore, Pan as evidenced by Hu teaches a traditional machine learning model which is a decision tree model as instantly claimed. Pan teaches that in future work, better network architectures to learn high-level features will be achieved by introducing convolutional neural networks (p. 10, col. 2, par. 3), but does not explicitly teach using a convolutional neural network.
However, the prior art to Pan 2018 discloses a computational method iDeepE to predict RNA–protein binding sites from RNA sequences by combining global and local convolutional neural networks to learn high-level features (abstract; entire document is relevant).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine, in the course of routine experimentation and with a reasonable expectation of success, Pan as evidenced by Hu and Pan 2018 because each reference discloses machine learning methods for predicting RNA-protein interaction. Pan specifically motivates incorporating a convolutional neural network into IPMiner to improve high-level feature learning (Pan 2016, p. 10, col. 2, par. 3), and Pan 2018 specifically motivates incorporating IPMiner to improve iDeepE’s performance (p. 3434, col. 2, par. 2). Therefore, it would have been obvious to one of ordinary skill in the art to combine Pan and Pan 2018 to include a convolutional neural network in the architecture of IPMiner.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-17, 24, and 27 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-5, 10-18, 21, and 24 of copending Application No. 17/916,540 (reference application). Although the claims at issue are not identical, they are not patentably distinct from each other for the following reasons.
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
Claim 18 is provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-5, 10-18, 21, and 24 of copending Application No. 17/916,540, as applied to claims 1 and 17, and in view of Pan et al. (BMC Genomics, 2016, 17(582):1-14; newly cited).
This is a provisional nonstatutory double patenting rejection.
Regarding instant claims 1 and 27, reference claims 1 and 24 disclose the limitations of claims 1 and 27.
Regarding instant claim 2, reference claim 2 discloses the limitations of claim 2.
Regarding instant claim 3, reference claim 3 discloses the limitations of claim 3.
Regarding instant claim 4, reference claim 4 discloses the limitations of claim 4.
Regarding instant claim 5, reference claim 5 discloses the limitations of claim 5.
Regarding instant claim 6, reference claim 13 discloses the limitations of claim 6.
Regarding instant claim 7, reference claims 14-15 discloses the limitations of claim 7.
Regarding instant claim 8, reference claim 15 and 18 discloses the limitations of claim 8.
Regarding instant claim 9, reference claim 16 discloses the limitations of claim 9.
Regarding instant claim 10, reference claim 17 discloses the limitations of claim 10.
Regarding instant claim 11, reference claim 18 discloses the limitations of claim 11.
Regarding instant claim 12, reference claim 4 discloses the limitations of claim 12.
Regarding instant claim 13, reference claim 10 discloses the limitations of claim 13.
Regarding instant claim 14, reference claim 10 discloses the limitations of claim 14.
Regarding instant claim 15, reference claim 10 discloses the limitations of claim 15.
Regarding instant claim 16, reference claim 11 discloses the limitations of claim 16.
Regarding instant claim 17, reference claim 12 discloses the limitations of claim 17.
Regarding instant claim 18, the reference claims do not disclose the limitations of claim 18.
However, the prior art to Pan discloses a computational method IPMiner (Interaction Pattern Miner) to predict ncRNA-protein interactions from sequences, which makes use of deep learning and further improves its performance using stacked ensembling (abstract). Pan teaches 4) feeding the extracted raw features and learned features to 3 random forest classifiers. Pan teaches determining the probability that a protein and RNA pair interact (p. 12, col. 2, par. 6) and determining the true and false positives of these predictions (p. 13, col. 1, par. 2). It is therefore considered that Pan inherently teaches using the probability (i.e, a prediction threshold) to determine whether or not the protein and RNA pairs interact, as instantly claimed.
Regarding claim 18, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine, in the course of routine experimentation and with a reasonable expectation of success, the reference application and Pan because each reference discloses machine learning methods for predicting RNA-protein interaction. The motivation to determine interactions based on a probability/threshold as taught by Pan would have been to be able to perform model evaluation, as taught by Pan (p. 13, col. 1, par. 2).
Regarding instant claim 24, reference claim 21 discloses the limitations of claim 24.
Conclusion
No claims are allowed.
Claim 11 appears to be free of the prior art. Neither the closest prior art to Pan et al. (BMC Genomics, 2016, 17(582):1-14) or any art identified in IDS or through the indicated searches teach the limitations “counting frequency of occurrence of each of the k-mer subsequences contained in the first candidate itemset in the original data set, and forming a frequent itemset by using a k-mer subsequence that meets a preset occurrence frequency threshold”, “cross-combining the RNA k-mer subsequence and the protein k-mer subsequence contained in the frequent itemset, and forming a second candidate itemset by using a k-mer subsequence pair obtained through cross-combination”, “counting frequency of occurrence of each k-mer subsequence pair contained in the second candidate itemset in the original data set, to obtain a support degree of each k-mer subsequence pair”, and “forming the original sequence feature set by using a k-mer subsequence pair whose support degree meets a preset condition”.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JANNA NICOLE SCHULTZHAUS whose telephone number is (571)272-0812. The examiner can normally be reached on Monday - Friday 8-4.
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, Olivia Wise can be reached on (571)272-2249. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/JANNA NICOLE SCHULTZHAUS/Examiner, Art Unit 1685
Prosecution Insights