DETAILED ACTION
The Applicant’s filing, received 27 April 2023, has been fully considered. The following rejections and/or objections constitute the complete set presently being applied to the instant application.
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 .
Status of the Claims
The preliminary amendment received 27 April 2023 has been accepted.
Claims 1-17, 24, and 25 are pending.
Claims 1-17, 24, and 25 are rejected.
Priority
This application is a 371 of PCT/CN2022/094234, filed 20 May 2022.
Unless otherwise noted, the effective filing date of the claimed invention is 20 May 2022.
Information Disclosure
The information disclosure statements (IDS) received 25 October 2023 and 27 May 2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements have been considered by the examiner.
Drawings
The drawings received 27 April 2023 have been accepted.
Specification
The amendment to the Abstract received 27 April 2023 has been accepted.
The substitute specification received 27 April 2023 has been accepted.
Claim Rejections - 35 USC § 112
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 1-17, 24, and 25 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 claims 1, 24, and 25 are indefinite for reciting the limitation “splicing the first correlation information and the second correlation information to obtain a splicing result” and independent claim 12 is indefinite for reciting the limitation “splicing the first prediction related information and the second prediction related information corresponding to the structural information of a same drug to obtain a plurality of spliced prediction results” because it is not clear as to whether the term ‘splicing’ is intended to be a synonym for ‘concatenate’ (i.e., to link or join together in a chain or series without gaps) and therefore, the splicing result is obtained using the whole of both the first and second sets of information, or alternatively if the limitation ‘splicing’ means that the splicing result is obtained from subsets of the first and second sets of information. One of skill in the art would recognize that ‘data splicing’ could be a misnomer or informal variation of ‘data splitting’ particularly with regard to machine learning (e.g., where there are steps for training, validating, and testing a model).
The limitation ‘splicing’ is interpreted to be synonymous with the term ‘concatenate’.
Claims 2-11 are indefinite for depending from claim 1 and for failing to remedy the indefiniteness of claim 1.
Claims 13-17 are indefinite for depending from claim 12 and for failing to remedy the indefiniteness of claim 12.
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 1-17, 24, and 25 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite: (a) mathematical concepts, (e.g., mathematical relationships, formulas or equations, mathematical calculations); and (b) mental processes, i.e., concepts performed in the human mind, (e.g., observation, evaluation, judgement, opinion).
Claim Interpretations
Independent claims 1, 12, 24, and 25 recite the limitation ‘splicing’. This limitation is interpreted to by synonymous with the term ‘concatenate’ (i.e., to link or join together in a chain or series without gaps).
Subject matter eligibility evaluation in accordance with MPEP 2106.
Eligibility Step 1: Step 1 of the eligibility analysis asks: Is the claim to a process, machine, manufacture or composition of matter?
Claims 1-11 recite a method for predicting drug sensitivity (i.e., a process); claims 12-17 recite a method for training a drug sensitivity prediction model (i.e., a process); and claim 25 recites a device for predicting drug sensitivity, comprising a first memory and a first processor (i.e., a machine or a manufacture).
Therefore, these claims are encompassed by the categories of statutory subject matter, and thus, satisfy the subject matter eligibility requirements under step 1.
[Step 1: YES]
Claim 24 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claim does not fall within at least one of the four categories of patent eligible subject matter because:
Claim 24 is directed to a non-transitory computer-readable storage medium (i.e., a machine or a manufacture); and further directed to an embodiment that comprises a signal and/or software per se, because the broadest reasonable interpretation of the claim limitation reciting “the storage medium being configured to store computer program instructions, wherein when the computer program instructions are run…” (emphasis added) is an intended use of the storage medium, which does not require that the computer program instructions actually be stored on the storage medium.
This rejection at Step 1 may be overcome by amending the claimed subject matter to be limited to being stored on a non-transitory computer-readable storage medium (e.g., see MPEP 2106.03 I.). However, amending the claim to recite being stored on a non-transitory computer-readable storage medium would not overcome a rejection at Step 2A or Step 2B, for the reasons noted below.
[Step 1: NO]
However, in the interest of compact prosecution, claim 24 is examined herein with respect to whether the claim is directed to an abstract idea without significantly more.
Eligibility Step 2A: First it is determined in Prong One whether a claim recites a judicial exception, and if so, then it is determined in Prong Two whether the recited judicial exception is integrated into a practical application of that exception.
Eligibility Step 2A Prong One: In determining whether a claim is directed to a judicial exception, examination is performed that analyzes whether the claim recites a judicial exception, i.e., whether a law of nature, natural phenomenon, or abstract idea is set forth or described in the claim.
Independent claim 1 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
calculating first correlation information between the structural information of the drug to be tested and the gene expression information based on a first attention model (i.e., mathematical concepts, e.g., dot-product similarity, scaling, and a softmax normalization function); and
calculating second correlation information between the structural information of the drug to be tested and the gene mutation information based on a second attention model (i.e., mathematical concepts);
splicing (i.e., concatenating) the first correlation information and the second correlation information to obtain a splicing result (i.e., mental processes); and
performing a prediction processing on the splicing result based on a drug sensitivity prediction model to obtain sensitivity information of the cell line to be tested for the drug to be tested (i.e., mathematical concepts, e.g., computing similarity scores, converting them into attention weights, creating a context vector, and calculating a probability distribution).
Independent claim 12 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
obtaining a plurality of pieces of first prediction related information between the structural information of the plurality of drugs and the gene expression information respectively based on a first attention model (i.e., mathematical concepts); and
obtaining a plurality of pieces of second prediction related information between the structural information of the plurality of drugs and the gene mutation information respectively based on a second attention model (i.e., mathematical concepts);
splicing (i.e., concatenating) the first prediction related information and the second prediction related information corresponding to the structural information of a same drug to obtain a plurality of spliced prediction results (i.e., mental processes); and
training a prediction model to be trained by using the plurality of spliced prediction results and the plurality of pieces of reference semi-inhibitory concentration information to obtain a drug sensitivity prediction model (i.e., mathematical concepts, e.g., matrix multiplications, dot products and scaling, softmax normalizations, loss functions, calculus & backpropagation, gradient descent).
Independent claim 24 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
calculating first correlation information between the structural information of the drug to be tested and the gene expression information based on a first attention model (i.e., mathematical concepts); and
calculating second correlation information between the structural information of the drug to be tested and the gene mutation information based on a second attention model (i.e., mathematical concepts);
splicing (i.e., concatenating) the first correlation information and the second correlation information to obtain a splicing result (i.e., mental processes); and
performing a prediction processing on the splicing result based on a drug sensitivity prediction model to obtain sensitivity information of the cell line to be tested for the drug to be tested (i.e., mathematical concepts).
Independent claim 25 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
calculating first correlation information between the structural information of the drug to be tested and the gene expression information based on a first attention model (i.e., mathematical concepts); and
calculating second correlation information between the structural information of the drug to be tested and the gene mutation information based on a second attention model (i.e., mathematical concepts);
splicing (i.e., concatenating) the first correlation information and the second correlation information to obtain a splicing result (i.e., mental processes); and
performing a prediction processing on the splicing result based on a drug sensitivity prediction model to obtain sensitivity information of the cell line to be tested for the drug to be tested (i.e., mathematical concepts).
Dependent claims 2-11 and 13-17 further recite the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas, as noted below.
Dependent claim 2 further recites:
multiplying the gene expression information by a first weight matrix to obtain a first vector, multiplying the structural information of the drug by a second weight matrix to obtain a second vector, and multiplying the structural information of the drug by a third weight matrix to obtain a third vector (i.e., mathematical concepts); and
normalizing the first vector and the second vector to obtain a first processing result, and multiplying the first processing result by the third vector to obtain the first correlation information (i.e., mathematical concepts).
Dependent claim 3 further recites:
transposing the second vector to obtain a transposed vector of the second vector (i.e., mental processes, e.g., flipping the dimensions of a matrix so that its columns match the row dimensions of another matrix), multiplying the first vector by the transposed vector of the second vector to obtain a first product, and dividing the first product by a first constant to obtain a first processing result, the first constant being an arithmetic square root of a dimensionality of the second vector (i.e., mathematical concepts).
Dependent claim 4 further recites:
performing a dimensionality reduction operation on the gene expression information through a first convolution neural network to obtain dimensionality-reduced gene expression information (i.e., mathematical concepts); and performing a dimensionality reduction operation on the structural information of the drug through a second convolution neural network to obtain dimensionality-reduced drug structural information (i.e., mathematical concepts);
multiplying the dimensionality-reduced gene expression information by the first weight matrix to obtain the first vector (i.e., mathematical concepts);
multiplying the dimensionality-reduced drug structural information by the second weight matrix to obtain the second vector (i.e., mathematical concepts); and
multiplying the dimensionality-reduced drug structural information by the third weight matrix to obtain the third vector (i.e., mathematical concepts).
Dependent claim 5 further recites:
multiplying the gene mutation information by a fourth weight matrix to obtain a fourth vector, multiplying the structural information of the drug by a fifth weight matrix to obtain a fifth vector, and multiplying the structural information of the drug by a sixth weight matrix to obtain a sixth vector (i.e., mathematical concepts); and
normalizing the fourth vector and the fifth vector to obtain a second processing result, and multiplying the second processing result by the sixth vector to obtain the second correlation information (i.e., mathematical concepts).
Dependent claim 6 further recites:
transposing the fifth vector to obtain a transposed vector of the fifth vector (i.e., mental processes, e.g., flipping the dimensions of a matrix so that its columns match the row dimensions of another matrix), multiplying the fourth vector by the transposed vector of the fifth vector to obtain a second product, and dividing the second product by a second constant to obtain a second processing result, the second constant being an arithmetic square root of a dimensionality of the fifth vector (i.e., mathematical concepts).
Dependent claim 7 further recites:
performing a dimensionality reduction operation on the gene mutation information through a third convolution neural network to obtain dimensionality-reduced gene mutation information (i.e., mathematical concepts); and performing a dimensionality reduction operation on the structural information of the drug through a second convolution neural network to obtain dimensionality-reduced drug structural information (i.e., mathematical concepts);
multiplying the dimensionality-reduced gene mutation information by the fourth weight matrix to obtain the fourth vector (i.e., mathematical concepts);
multiplying the dimensionality-reduced drug structural information by the fifth weight matrix to obtain the fifth vector (i.e., mathematical concepts); and
multiplying the dimensionality-reduced drug structural information by the sixth weight matrix to obtain the sixth vector (i.e., mathematical concepts).
Dependent claim 8 further recites:
normalizing the average values of the plurality of first gene expression features to obtain a plurality of normalized expression average values (i.e., mathematical concepts), normalizing the standard deviations of the plurality of first gene expression features to obtain a plurality of normalized expression standard deviations (i.e., mathematical concepts), and inputting the plurality of normalized expression standard deviations and the plurality of normalized expression average values into an encoder (i.e., mental processes);
controlling the encoder (i.e., mathematical concepts, e.g., matrix multiplication & vectors, activation function, and optimization & loss functions) to add or subtract the normalized expression standard deviations corresponding to the normalized expression average values to or from a part of the normalized expression average values to obtain a plurality of processed normalized expression average values (i.e., mathematical concepts), and taking another part of unprocessed normalized expression average values and the plurality of processed normalized expression average values as a plurality of encoding input features (i.e., mathematical concepts); and
controlling the encoder (i.e., mathematical concepts, e.g., matrix multiplication & vectors, activation function, and optimization & loss functions) to encode the plurality of encoding input features to obtain a plurality of second gene expression features as the gene expression information, the number of the plurality of second gene expression features being less than the number of the plurality of first gene expression features (i.e., mathematical concepts).
Dependent claim 9 further recites:
the encoder comprises an encoding layer, and the encoding layer comprises an input layer and an output layer (i.e., mathematical concepts, e.g., using linear algebra, calculus, and probability to transform data into numbers);
controlling the encoder (i.e., mathematical concepts) to perform the following operation on the plurality of encoding input features to obtain a plurality of second gene expression features:
y=s(Wx̅+b),
wherein x̅ is the encoding input feature, y is the second gene expression feature, W is a link weight from the input layer to the output layer, b is a deviation of the output layer, and s is a nonlinear function.
Dependent claim 10 further recites:
the encoding layer further comprises an intermediate hidden layer between the input layer and the output layer (i.e., mathematical concepts), and the input layer, the intermediate hidden layer and the output layer constitute a three-layer neural network with a gradually decreased number of neurons (i.e., mathematical concepts).
Dependent claim 11 further recites:
the sensitivity prediction model comprises a four-layer neural network with a gradually decreased number of neurons (i.e., mathematical concepts).
Dependent claim 13 further recites:
training the prediction model to be trained in a multi-iteration manner for multiple times according to the plurality of spliced (i.e., concatenated) prediction results and the plurality of pieces of reference semi-inhibitory concentration information to obtain the drug sensitivity prediction model (i.e., mathematical concepts, e.g., matrix multiplications, dot products and scaling, softmax normalizations, loss functions, calculus & backpropagation, gradient descent);
wherein
during each iteration, the plurality of spliced prediction results are input into the drug sensitivity model to be trained to obtain a plurality of pieces of predicted semi-inhibitory concentration information, sensitivity loss information is obtained according to the plurality of pieces of predicted semi-inhibitory concentration information and the plurality of pieces of reference semi-inhibitory concentration information, the prediction model to be trained is optimized according to the sensitivity loss information, and the optimized model is used as a prediction model to be trained in a next iteration; or
during each iteration, the plurality of spliced prediction results are input into the prediction model to be trained in batches to obtain a plurality of pieces of predicted semi-inhibitory concentration information of a current batch, sensitivity loss information of the current batch is obtained according to the plurality of pieces of predicted semi-inhibitory concentration information of the current batch and a plurality of pieces of reference semi-inhibitory concentration information corresponding to the current batch, the prediction model to be obtained is optimized according to the sensitivity loss information of the current batch, and the optimized model is used as a prediction model to be trained for a next batch or a next iteration.
Dependent claim 14 further recites:
multiplying the gene expression information by a first weight matrix to obtain a first vector, multiplying the structural information of the plurality of drugs by a corresponding second weight matrix respectively to obtain a plurality of second vectors, and multiplying the structural information of the plurality of drugs by a corresponding third weight matrix respectively to obtain a plurality of third vectors (i.e., mathematical concepts);
normalizing the first vector and the second vector corresponding to the structural information of a same drug to obtain a plurality of first processing results (i.e., mathematical concepts); and
multiplying the first processing result by the third vector corresponding to the structural information of a same drug to obtain the plurality of pieces of first correlation information (i.e., mathematical concepts).
Dependent claim 15 further recites:
training the first attention model using the structural information of the plurality of drugs and the gene expression information to obtain a first weight matrix, a second weight matrix and a third weight matrix (i.e., mathematical concepts, e.g., random initialization followed by iterative optimization via backpropagation and gradient descent).
Dependent claim 16 further recites:
multiplying the gene mutation information by a fourth weight matrix to obtain a fourth vector, multiplying the structural information of the plurality of drugs by a corresponding fifth weight matrix respectively to obtain a plurality of fifth vectors, and multiplying the structural information of the plurality of drugs by a corresponding sixth weight matrix respectively to obtain a plurality of sixth vectors (i.e., mathematical concepts);
normalizing the fourth vector and the fifth vector corresponding to the structural information of a same drug to obtain a plurality of second processing results (i.e., mathematical concepts); and
multiplying the second processing result by the sixth vector corresponding to the structural information of a same drug to obtain the plurality of pieces of second correlation information (i.e., mathematical concepts).
Dependent claim 17 further recites:
training the second attention model using the structural information of the plurality of drugs and the gene expression information to obtain a fourth weight matrix, a fifth weight matrix and a sixth weight matrix (i.e., mathematical concepts, e.g., random initialization followed by iterative optimization via backpropagation and gradient descent).
The abstract ideas recited in the claims are evaluated under the broadest reasonable interpretation (BRI) of the claim limitations when read in light of and consistent with the specification. As noted in the foregoing section, the claims are determined to contain limitations that can practically be performed in the human mind with the aid of a pen and paper (e.g., splicing the first correlation information and the second correlation information to obtain a splicing result), and therefore recite judicial exceptions from the mental process grouping of abstract ideas. Additionally, the recited limitations that are identified as judicial exceptions from the mathematical concepts grouping of abstract ideas (e.g., calculating first correlation information between the structural information of the drug to be tested and the gene expression information based on a first attention model) are abstract ideas irrespective of whether or not the limitations are practical to perform in the human mind.
Therefore, claims 1-17, 24, and 25 recite an abstract idea.
[Step 2A Prong One: YES]
Eligibility Step 2A Prong Two: In determining whether a claim is directed to a judicial exception, further examination is performed that analyzes if the claim recites additional elements that when examined as a whole integrates the judicial exception(s) into a practical application (MPEP 2106.04(d)). A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception. The claimed additional elements are analyzed to determine if the abstract idea is integrated into a practical application (MPEP 2106.04(d)(I); MPEP 2106.05(a-h)). If the claim contains no additional elements beyond the abstract idea, the claim fails to integrate the abstract idea into a practical application (MPEP 2106.04(d)(III)).
The judicial exceptions identified in Eligibility Step 2A Prong One are not integrated into a practical application because of the reasons noted below.
Dependent claims 2-7, 9-11 and 13-17 do not recite any elements in addition to the judicial exception, and thus are part of the judicial exception.
The additional elements in independent claim 1 include:
acquiring gene expression information of a cell line to be tested, gene mutation information of the cell line to be tested, and structural information of a drug to be tested (i.e., gathering data);
The additional elements in independent claim 12 include:
acquiring a training sample set, the training sample set comprising gene expression information of a cell line, gene mutation information of the cell line, structural information of a plurality of drugs and a plurality of pieces of reference semi-inhibitory concentration information, wherein each piece of reference semi-inhibitory concentration information corresponds to the structural information of one drug (i.e., gathering data).
The additional elements in independent claim 24 include:
a non-transitory computer-readable storage medium; and
acquiring gene expression information of a cell line to be tested, gene mutation information of the cell line to be tested, and structural information of a drug to be tested (i.e., gathering data).
The additional elements in independent claim 25 include:
a device comprising a first memory, a first processor, and a computer program stored on the first memory; and
acquiring gene expression information of a cell line to be tested, gene mutation information of the cell line to be tested, and structural information of a drug to be tested (i.e., gathering data).
The additional element in dependent claim 8 includes:
acquiring raw data of the gene expression information, the raw data of the gene expression information comprising average values of a plurality of first gene expression features and standard deviations of the plurality of first gene expression features (i.e., gathering data).
The additional elements of a device comprising a first memory, a first processor, and a computer program stored on the first memory (claim 25); and a non-transitory computer-readable storage medium (claim 24); invoke a computer and/or computer-related components merely as tools for use in the claimed process, such that they amount to no more than mere instructions to apply the exceptions using a generic computer (MPEP 2106.05(f)), and therefore are not an improvement to computer functionality itself, or an improvement to any other technology or technical field, and thus, do not integrate the judicial exceptions into a practical application (MPEP 2106.04(d)(1)).
The additional elements of acquiring gene expression information of a cell line to be tested, gene mutation information of the cell line to be tested, and structural information of a drug to be tested (i.e., gathering data) (claims 1, 24, and 25); acquiring a training sample set, the training sample set comprising gene expression information of a cell line, gene mutation information of the cell line, structural information of a plurality of drugs and a plurality of pieces of reference semi-inhibitory concentration information, wherein each piece of reference semi-inhibitory concentration information corresponds to the structural information of one drug (i.e., gathering data) (claim 12); and acquiring raw data of the gene expression information, the raw data of the gene expression information comprising average values of a plurality of first gene expression features and standard deviations of the plurality of first gene expression features (i.e., gathering data) (claim 8); are merely a pre-solution activity of gathering data for use in the claimed process – a nominal or tangential addition to the claims that does not meaningfully limit the claims, and therefore does not add more than insignificant extra-solution activity to the judicial exceptions (MPEP 2106.05(g)).
Thus, the additionally recited elements merely invoke a computer and/or computer related components as tools; and/or amount to insignificant extra-solution activity; and as such, when all limitations in claims 1-17, 24, and 25 have been considered as a whole (i.e., the analysis takes into consideration all the claim limitations and how those limitations interact and impact each other when evaluating whether the exception is integrated into a practical application), the claims are deemed to not recite any additional elements that would integrate a judicial exception into a practical application, and therefore claims 1-17, 24, and 25 are directed to an abstract idea (MPEP 2106.04(d)).
[Step 2A Prong Two: NO]
Eligibility Step 2B: Because the claims recite an abstract idea, and do not integrate that abstract idea into a practical application, the claims are probed for a specific inventive concept. The judicial exception alone cannot provide that inventive concept or practical application (MPEP 2106.05). Identifying whether the additional elements beyond the abstract idea amount to such an inventive concept requires considering the additional elements individually and in combination to determine if they amount to significantly more than the judicial exception (MPEP 2106.05A i-vi).
The claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception(s) because of the reasons noted below.
Dependent claims 2-7, 9-11 and 13-17 do not recite any elements in addition to the judicial exception(s).
The additional elements recited in independent claims 1, 12, 24 and 25 and dependent claim 8 are identified above, and carried over from Step 2A Prong Two along with their conclusions for analysis at Step 2B. Any additional element or combination of elements that was considered to be insignificant extra-solution activity at Step 2A Prong Two was re-evaluated at Step 2B, because if such re-evaluation finds that the element is unconventional or otherwise more than what is well-understood, routine, conventional activity in the field, this finding may indicate that the additional element is no longer considered to be insignificant; and all additional elements and combination of elements were evaluated to determine whether any additional elements or combination of elements are other than what is well-understood, routine, conventional activity in the field, or simply append well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, per MPEP 2106.05(d).
The additional elements of a device comprising a first memory, a first processor, and a computer program stored on the first memory (claim 25); a non-transitory computer-readable storage medium (claim 24); and gathering data (claims 1, 8, 12, 24, and 25); are conventional computer components and/or functions (see MPEP at 2106.05(b) and 2106.05(d)(II) regarding conventionality of computer components and computer processes).
Therefore, when taken alone (i.e., individually), all additional elements in claims 1-17, 24, and 25 do not amount to significantly more than the above-identified judicial exception(s). Even when evaluated as an ordered combination, the additional elements fail to transform the exception(s) into a patent-eligible application of that exception. Thus, claims 1-17, 24, and 25 are deemed to not contribute an inventive concept, i.e., amount to significantly more than the judicial exception(s) (MPEP 2106.05(II)).
[Step 2B: NO]
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claims 1, 12, 24, and 25 are rejected under 35 U.S.C. 103 as being unpatentable over Nguyen et al. (“Integrating Molecular Graph Data of Drugs and Multiple -Omic Data of Cell Lines for Drug Response Prediction.” IEEE/ACM Transactions on Computational Biology and Bioinformatics, March/April 2022, vol. 19, no. 2, pp. 710-717) and Zuo et al. (“SWnet: a deep learning model for drug response prediction from cancer genomic signatures and compound chemical structures.” BMC Bioinformatics, 2021, vol. 22:434, pp. 1-16).
Independent claims 1, 24, and 25 broadly encompass a method for predicting drug sensitivity, comprising steps of acquiring gene expression information of a cell line to be tested, gene mutation information of the cell line to be tested, and structural information of a drug to be tested; calculating first correlation information between the structural information of the drug to be tested and the gene expression information based on a first attention model, and calculating second correlation information between the structural information of the drug to be tested and the gene mutation information based on a second attention model; splicing the first correlation information and the second correlation information to obtain a splicing result; and performing a prediction processing on the splicing result based on a drug sensitivity prediction model to obtain sensitivity information of the cell line to be tested for the drug to be tested.
Independent claim 12 broadly encompasses a method for training a drug sensitivity prediction model, comprising steps of acquiring a training sample set, the training sample set comprising gene expression information of a cell line, gene mutation information of the cell line, structural information of a plurality of drugs and a plurality of pieces of reference semi-inhibitory concentration information, wherein each piece of reference semi-inhibitory concentration information corresponds to the structural information of one drug; obtaining a plurality of pieces of first prediction related information between the structural information of the plurality of drugs and the gene expression information respectively based on a first attention model; and obtaining a plurality of pieces of second prediction related information between the structural information of the plurality of drugs and the gene mutation information respectively based on a second attention model; splicing the first prediction related information and the second prediction related information corresponding to the structural information of a same drug to obtain a plurality of spliced prediction results; and training a prediction model to be trained by using the plurality of spliced prediction results and the plurality of pieces of reference semi-inhibitory concentration information to obtain a drug sensitivity prediction model.
Nguyen et al. is directed to a deep learning model that integrates molecular graph data of drugs (i.e., structural features) and multi-omics data of cell lines (i.e., gene expression, genetic mutations, methylation) for drug response prediction.
Zuo et al. is directed to a deep learning model with attention mechanisms for drug response prediction from cancer genomic signatures (i.e., gene expression and genetic mutations) and compound chemical structures.
Regarding independent claims 1, 12, 24, and 25, Nguyen et al. shows a deep learning-based method to integrate molecular graph representation of drugs (i.e., structure) and multi-omic data of cell lines (i.e., genomic mutation data; epigenetic methylation data; and transcriptomic gene expression data) for drug response prediction, and further shows vectors are concatenated (i.e., spliced) and put through two fully connected (FC) layers to predict the response values, and can comprise a classifier for predicting binary form of the response values (i.e., sensitive, and resistant) (Fig. 1). Nguyen et al. further shows evaluating the prediction performance of the model using different combinations of the multi-omic data, i.e., gene expression data combined with mutation data (page 713, Section 2.4; page 714, Table 2 & Fig. 2). Nguyen et al. further shows steps of training the model including validation and testing (page 713, Section 2.4) and using drug response values in terms of IC50 (i.e., inhibitory concentration information) (page 712, col. 1, para. 1).
Regarding independent claims 1, 12, 24, and 25, Nguyen et al. does not show calculating first correlation information between the structural information of the drug to be tested and the gene expression information based on a first attention model; and calculating second correlation information between the structural information of the drug to be tested and the gene mutation information based on a second attention model; and splicing the first correlation information and the second correlation information to obtain a splicing result.
However, 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 have modified the method shown by Nguyen et al. to correlate drug structure data with gene expression data and separately correlate drug structure data with gene mutation data, and then concatenate the two sets of data. One of ordinary skill in the art would have been motivated to modify the methods of Nguyen et al. in this manner because Nguyen et al. shows a deep learning-based method to integrate molecular graph representation of drugs (i.e., structure) and multi-omic data of cell lines (i.e., genomic mutation data; epigenetic methylation data; and transcriptomic gene expression data) for drug response prediction, and further shows vectors are concatenated (i.e., spliced), and further evaluating the prediction performance of the model using different combinations of the multi-omic data, i.e., gene expression data combined with mutation data. This modification would have had a reasonable expectation of success given that Nguyen et al. explicitly shows using a deep learning model with structural data of drugs integrated with multi-omics data of cell lines.
Regarding independent claims 1, 12, 24, and 25, Zuo et al. shows a deep learning model for drug response prediction that integrates gene expression, genetic mutation, and chemical structure of compounds in a multi-task convolutional architecture (Abstract); and further shows that the deep learning model comprises a self-attention gene weight layer network to combine the information of gene mutation and gene expression and also includes a self-attention mechanism to incorporate the structural similarity between compounds (page 2, para. 3).
Therefore, it would have been further prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method shown by Nguyen et al. by incorporating attention mechanisms in the deep learning model, as shown by Zuo et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the methods of Nguyen et al. with the methods of Zuo et al., because Zuo et al. shows that that in a multi-task model, each drug has its own gene weight parameters, which are supposed to be relevant to the drug itself, however similar drugs may have similar gene weight parameters, thus, in order to take into consideration the similarity between drugs’ chemical structures, a self-attention method can be applied which uses a drug similarity matrix to update the parameters of the gene weight layer. This modification would have had a reasonable expectation of success given that both Nguyen et al. and Zuo et al. disclose methods for modelling anticancer drug sensitivity.
Claims 2-11 and 13-17 are rejected under 35 U.S.C. 103 as being unpatentable over Nguyen et al. and Zuo et al. as applied to claims 1, 12, 24, and 25 above, and further in view of Manica et al. (“Toward Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-Based Convolutional Encoders,” Molecular Pharmaceutics, 2019, vol. 16, pp. 4797-4806).
Dependent claims 2-11 and 13-17 further define the computational characteristics of the deep learning model with respect to using the model for predicting drug sensitivity (claims 2-11) and training the model (claims 13-17).
Manica et al. is directed to an architecture for interpretable prediction of anticancer compound sensitivity using a multimodal attention-based convolutional encoder, which is based on three key pillars of drug sensitivity: compounds’ structure in the form of a SMILES sequence, gene expression profiles of tumors, and prior knowledge on intracellular interactions from protein-protein interaction networks.
Regarding dependent claims 2-11 and 13-17, Nguyen et al. and Zuo et al. as applied to claims 1, 12, 24, and 25 above, do not explicitly show detailed characteristics of attention-based deep learning models as recited by claims 2-11 and 13-17, e.g., dynamic weighting, encoders, context-vector generation, hidden layers, and a gradually decreased number of neurons.
Regarding dependent claims 2-11, Manica et al. shows an embedding layer transforms raw SMILES strings into a sequence of vectors in an embedding space (Figure 2), and further shows an attention-based gene expression encoder that generates attention weights that are in turn applied to the input gene subset via a dot product (Figure 2) (in machine learning, vectors are treated as columns by default, meaning that transposition becomes a necessary formatting step to make the linear algebra and dimensions fit properly when performing matrix multiplication); normalizing a weighted adjacency matrix (page 4799, col. 2, equation 2); employing network propagation to reduce high-dimensional raw data to a subset of data (page 4799, col. 2, para. 2); a single dense softmax layer with the same dimensionality as the input produces an attention weight distribution over the genes and filters them in a dot product, ensuring that the most informative genes are given a higher weight for further processing (page 4800, col. 1, para. 3); and several neural network SMILES encoder architectures (Section 2.3). and a baseline deep neural network model that is a six-layered DNN with [512], 256, 128, 64, 32, 16] units and a sigmoid activation (page 4800, col. 1, para. 2).
Regarding dependent claims 13-17, Manica et al. shows a training procedure implemented in TensorFlow 1.10 with a MSE loss function that was optimized with Adam and a decreasing learning rate, batch normalization, a sigmoid activation, and all models were trained with a batch size of 2048 for a maximum of 500k steps (page 4801, Section 2.5.).
Therefore, 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 have modified the method shown by Nguyen et al. and Zuo et al. as applied to claims 1, 12, 24, and 25 above, by incorporating methods for using attention-based convolutional encoders, as shown by Manica et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the methods of Nguyen et al. and Zuo et al. as applied to claims 1, 12, 24, and 25 above, with the methods of Manica et al., because Manica et al. shows methods for using a convolutional attention-based encoder that significantly outperforms a baseline model as well as a previously reported state-of-the-art model for multimodal drug sensitivity prediction (Abstract). This modification would have had a reasonable expectation of success given that both Nguyen et al. and Zuo et al. as applied to claims 1, 12, 24, and 25 above, and Manica et al. disclose methods for modelling anticancer drug sensitivity.
Thus, the instant claimed invention would have been prima facie obvious.
Conclusion
No claims are allowed,
This Office action is a Non-Final action. A shortened statutory period for reply to this action is set to expire THREE MONTHS from the mailing date of this application.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to STEVEN W. BAILEY whose telephone number is (571)272-8170. The examiner can normally be reached Mon - Fri. 1000 - 1800.
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, KARLHEINZ SKOWRONEK can be reached at (571) 272-9047. 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.
/STEVEN W. BAILEY/Examiner, Art Unit 1687
Prosecution Insights