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 .
DETAILED ACTION
This Office Action is sent in response to Application’s Communication received on 05/05/2023 for application number 18/312663. The Office hereby acknowledges receipt of the following and placed of record in file: Specification, Drawing, Abstract, Oath/Declaration, and Claims.
Claims (1-20) are presented for examination.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 09/08/2023 were filed prior to current Office Action. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1 and 4 are rejected under AIA 35 U.S.C. 103(a) as being unpatentable over Davey et al. US Patent Application Publication US 20120109598 A1 in view of Homer. US Patent Application Publication US 20120197623 A1 (hereinafter Homer) and further in view of Ozel Duygan Birge. Foreign Application Publication WO 2021260159 A1 (hereinafter Birge) and further in view of Hall, J et al. Foreign Application Publication CN 1890370 A (hereinafter Hall) and further in view of Kostem Emrah. Foreign Patent Application WO 2020232410 A1 (hereinafter Emrah).
Regarding claim 1, Davey teaches A method for correcting signal measurements ([0016], [0068] wherein Davey describes receiving signals and calculating the metric using nucleotide flows and determining values of the signal correction).
Davey teaches calculating a fitting metric that measures the fit between the predicted signals and the signal data from at least some of the plurality of wells. In some cases, the fitting metric measures the fit between the predicted signals and the signal data from less than all of the plurality of wells; wherein the region-wide estimate excludes adjusted signal correction parameters from wells that produce a fitting metric exceeding a predetermined threshold ([0014]).
Davey does not teach providing a plurality of signal measurements to a channel of an input layer.
However, in analogous art of deep artificial neural networks for signal error correction, Homer teaches providing a plurality of signal measurements to a channel of an input layer ([0027-0028], [0279] wherein Homer describes Nucleic acid sequence analysis can be conducted using electronic sensors that generate signals indicative of enzymatic or chemical reactions associated with nucleotide incorporation events to provide an identification of a sample nucleic acid sequence and incorporates analysis of signals relating to consecutive base calls of fragments of a sample nucleic acid sequence of interest).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Davey with Homer by incorporating the method of providing a plurality of signal measurements to a channel of an input layer of Homer into the method of correcting signal measurements providing a plurality of signal measurements to a channel of an input layer of Davey for the purpose of providing new and improved methods and systems for nucleic acid sequence analysis that can address and analyze data reflective of electronically-detected chemical targets and/or reaction by-products associated with nucleotide incorporation events without the need for exogenous labels or dyes to characterize nucleic acid sequences of interest (Homer: page. [0006]).
Davey does not teach an artificial neural network (ANN), wherein the input layer includes one or more channels.
However, in analogous art of deep artificial neural networks for signal error correction, Birge teaches an artificial neural network (ANN), wherein the input layer includes one or more channels (page. 1, paragraph 2, page. 2, page. 42, paragraph 2, pages. 43-44 wherein Birge describes processing signals data as input for ANN that includes channels).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Davey with Birge by incorporating the method of an artificial neural network (ANN), wherein the input layer includes one or more channels of Birge into the method of correcting signal measurements providing a plurality of signal measurements to a channel of an input layer of Davey for the purpose of incorporating ANN with classifiers to analyze nucleotide identity (Birge: page. 42, paragraph 2, pages. 43-44).
Davey does not teach applying the ANN to the plurality of signal measurements to generate a plurality of signal correction values.
However, in analogous art of deep artificial neural networks for signal error correction, Hall teaches applying the ANN to the plurality of signal measurements to generate a plurality of signal correction values (page. 10, paragraph 4, wherein Hall trains the artificial neural network using the dataset by extracting strand and filtering the measure, wherein the training of the network can be applied to any input sequence to give the "will" for evaluation of screening measurements and wherein Hall generates output signal by changing the weights by changing the position).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Davey with Hall by incorporating the method of applying the ANN to the plurality of signal measurements to generate a plurality of signal correction values of Hall into the method of correcting signal measurements providing a plurality of signal measurements to a channel of an input layer of Davey for the purpose of analyzing the difference between the network output signal and the experiment result is used to change all weights to reduce the difference and incorporating a counter-propagating through the network to position so as to have target ' real ' signal unit hidden in the second layer. (Hall: page. 10, paragraph 4).
Davey does not teach subtracting the plurality of signal correction values from the plurality of signal measurements to form a plurality of corrected signal measurements; and applying base calling to the plurality of corrected signal measurements to produce a sequence of base calls.
However, in analogous art of deep artificial neural networks for signal error correction, Emrah teaches subtracting the plurality of signal correction values from the plurality of signal measurements to form a plurality of corrected signal measurements ([0132], [0169] wherein Emrah analyses strands within analyte and reduces purity of signal output from the interrogated position by contamination with signals from adjacent nucleotides and incorporates softmax function takes a class of values and converts them to probabilities that sum to one. the softmax function ensures that the output is a valid, exponentially normalized probability mass function) and applying base calling to the plurality of corrected signal measurements to produce a sequence of base calls (Abstract, [0085], [0112], [0132-0133], [0147-0148], [0167], [0179], [0194-0195], [0296-0297] wherein Emrah incorporates phasing and prephasing channels for the current sequencing cycle from corresponding convolution filters in a plurality of convolution kernels and specifies the sequencing cycle and position of the signal dataset, and produces a binary sequence which are in turn used to infer base calls based on the position-wise pairs).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Davey with Emrah by incorporating the method of subtracting the plurality of signal correction values from the plurality of signal measurements to form a plurality of corrected signal measurements; and applying base calling to the plurality of corrected signal measurements to produce a sequence of base calls of Emrah into the method of correcting signal measurements providing a plurality of signal measurements to a channel of an input layer of Davey for the purpose of using a neural network-based base caller that detects and accounts for stationary, kinetic, and mechanistic properties of the sequencing process, mapping what is observed at each sequence cycle in the assay data to the underlying sequence of nucleotides (Emrah: Abstract).
Regarding claim 4, Davey as modified by Homer, Birge, Hall and Emrah teaches wherein the ANN comprises a convolutional neural network (CNN) ([0001] wherein Emrah teaches an ANN that comprises a convolutional neural network (CNN).
Claim 2 is rejected under AIA 35 U.S.C. 103(a) as being unpatentable over Davey et al. US Patent Application Publication US 20120109598 A1 in view of Homer. US Patent Application Publication US 20120197623 A1 (hereinafter Homer) and further in view of Ozel Duygan Birge. Foreign Application Publication WO 2021260159 A1 (hereinafter Birge) and further in view of Hall, J et al. Foreign Application Publication CN 1890370 A (hereinafter Hall) and further in view of Kostem Emrah. Foreign Patent Application WO 2020232410 A1 (hereinafter Emrah) and further in view of Bai. US Patent Application Publication US 20180336316 A1 (hereinafter Bai).
Regarding claim 2, Davey as modified by Homer, Birge, Hall and Emrah do not teach wherein the input layer further comprises a channel for a plurality of simulated signal measurements, wherein the plurality of simulated signal measurements corresponds to the plurality of signal measurements.
However, in analogous art of deep artificial neural networks for signal error correction, Bai teaches wherein the input layer further comprises a channel for a plurality of simulated signal measurements, wherein the plurality of simulated signal measurements corresponds to the plurality of signal measurements ([0053], [0062] wherein Bai describes modeling signal for space signal measurements).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Davey, Homer, Birge, Hall and Emrah with Bai by incorporating the method of wherein the input layer further comprises a channel for a plurality of simulated signal measurements, wherein the plurality of simulated signal measurements corresponds to the plurality of signal measurements of Bai into the method of correcting signal measurements providing a plurality of signal measurements to a channel of an input layer of Davey, Homer, Birge, Hall and Emrah for the purpose of hypothesizing a candidate allele and determine a log-likelihood of a predicted flow space signal value for the candidate allele, wherein the log-likelihood of the predicted flow space signal value corresponding to a given element of the vector of consensus flow space signal measurements is referred to herein as the family log-likelihood (Bai: [0062]).
Claim 3 is rejected under AIA 35 U.S.C. 103(a) as being unpatentable over Davey et al. US Patent Application Publication US 20120109598 A1 in view of Homer. US Patent Application Publication US 20120197623 A1 (hereinafter Homer) and further in view of Ozel Duygan Birge. Foreign Application Publication WO 2021260159 A1 (hereinafter Birge) and further in view of Hall, J et al. Foreign Application Publication CN 1890370 A (hereinafter Hall) and further in view of Kostem Emrah. Foreign Patent Application WO 2020232410 A1 (hereinafter Emrah) and further in view of Hubbell et al. US Patent Application Publication US 20140296080 A1 (hereinafter Hubbell).
Regarding claim 3, Davey as modified by Homer, Birge, Hall and Emrah do not teach wherein the input layer further comprises a channel for representing a flow order corresponding to nucleotides flowed, wherein the plurality of signal measurements was detected in response to the nucleotides flowed in the flow order.
However, in analogous art of deep artificial neural networks for signal error correction, Hubbell teaches wherein the input layer further comprises a channel for representing a flow order corresponding to nucleotides flowed, wherein the plurality of signal measurements was detected in response to the nucleotides flowed in the flow order (Claim 19 text, [0020], [0085] wherein Hubbell describes a flow order that corresponds nucleotides flowed).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Davey, Homer, Birge, Hall and Emrah with Hubbell by incorporating the method of wherein the input layer further comprises a channel for representing a flow order corresponding to nucleotides flowed, wherein the plurality of signal measurements was detected in response to the nucleotides flowed in the flow order of Hubbell into the method of correcting signal measurements providing a plurality of signal measurements to a channel of an input layer of Davey, Homer, Birge, Hall and Emrah for the purpose of determining a measurement confidence value for each read in the ensemble of sequencing reads, wherein the determining is based on variations between the measured values and model-predicted values for hypothesized sequences obtained using a predictive model of nucleotide incorporations responsive to flows of nucleotide species; and (ii) modifying at least some model-predicted values using a first bias for forward strands and a second bias for reverse strands, wherein the modifying is based on variations between model-predicted values for different hypothesized sequences obtained using the predictive model of nucleotide incorporations responsive to flows of nucleotide species (Hubbell: [0020]).
Claim 5 is rejected under AIA 35 U.S.C. 103(a) as being unpatentable over Davey et al. US Patent Application Publication US 20120109598 A1 in view of Homer. US Patent Application Publication US 20120197623 A1 (hereinafter Homer) and further in view of Ozel Duygan Birge. Foreign Application Publication WO 2021260159 A1 (hereinafter Birge) and further in view of Hall, J et al. Foreign Application Publication CN 1890370 A (hereinafter Hall) and further in view of Kostem Emrah. Foreign Patent Application WO 2020232410 A1 (hereinafter Emrah) and further in view of Cheng et al. US Patent Application Publication US 20210239618 A1 (hereinafter Cheng).
Regarding claim 5, Davey as modified by Homer, Birge, Hall and Emrah do not teach wherein the CNN comprises a U-Net.
However, in analogous art of deep artificial neural networks for signal error correction, Cheng teaches wherein the CNN comprises a U-Net ([0017] Wherein Cheng teaches CNN that comprises U-net).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Davey, Homer, Birge, Hall and Emrah with Cheng by incorporating the method of wherein the CNN comprises a U-Net of Cheng into the method of correcting signal measurements providing a plurality of signal measurements to a channel of an input layer of Davey, Homer, Birge, Hall and Emrah for the purpose of applying the trained CNN to improve signal to noise in raw images wherein the CNN may be a 3D U-net network (e.g., that includes a 3×3×3 convolution filter) (Cheng: [0017]).
Claims 6-12 are rejected under AIA 35 U.S.C. 103(a) as being unpatentable over Davey et al. US Patent Application Publication US 20120109598 A1 in view of Homer. US Patent Application Publication US 20120197623 A1 (hereinafter Homer) and further in view of Ozel Duygan Birge. Foreign Application Publication WO 2021260159 A1 (hereinafter Birge) and further in view of Hall, J et al. Foreign Application Publication CN 1890370 A (hereinafter Hall) and further in view of Kostem Emrah. Foreign Patent Application WO 2020232410 A1 (hereinafter Emrah) and further in view of Cheng et al. US Patent Application Publication US 20210239618 A1 (hereinafter Cheng) and further in view of Chang, Hong-jie et al. Foreign Patent Application Publication CN 113989271 A (hereinafter Chang).
Regarding claim 6, Davey as modified by Homer, Birge, Hall, Emrah and Cheng do not teach wherein the U-Net comprises an encoder configured to receive the channels of the input layer and to generate feature maps at a plurality of scales.
However, in analogous art of deep artificial neural networks for signal error correction, Chang teaches wherein the U-Net comprises an encoder configured to receive the channels of the input layer and to generate feature maps at a plurality of scales (Claims 3-4 text, page. 8, wherein Chang describes-net with an encoder for performing operations that pertain to generating feature maps).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Davey, Homer, Birge, Hall, Emrah and Cheng with Chang by incorporating the method of wherein the U-Net comprises an encoder configured to receive the channels of the input layer and to generate feature maps at a plurality of scales of Chang into the method of correcting signal measurements providing a plurality of signal measurements to a channel of an input layer of Davey, Homer, Birge, Hall, Emrah and Cheng for the purpose of adding a space attention module in the feature fusion link, for improving the weight of the improved U-net network to the paint surface area, at the same time, reducing the weight of the non-paint surface area (Chang: page. 8).
Regarding claim 7, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Chang teach wherein the encoder further comprises a plurality of layer groups, wherein each layer group comprises one or more convolutional layers, wherein the convolutional layer applies a plurality of convolutions to input channels provided to the convolutional layer to produce a plurality of feature maps (pages. 7-9 wherein Chang generates feature maps using layers that comprises convolutional layers).
Regarding claim 8, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Chang teach wherein the convolutional layer further includes a batch normalization applied to the plurality of feature maps to produce normalized feature maps (pages. 7-9 wherein Chang incorporates batch normalization layer to produced feature maps).
Regarding claim 9, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Chang teach wherein the convolutional layer further includes applying an activation function to the normalized feature maps to produce output feature maps for output channels of the convolutional layer maps (pages. 7-9 wherein Chang incorporates batch normalization layer to produced feature maps based on calculation of the channel attention module with values that represents activation function).
Regarding claim 10, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Chang teach wherein each layer group further comprises a pooling layer, wherein the pooling layer receives output channels from a last convolutional layer in the one or more convolutional layers, wherein the pooling layer applies a MaxPool operation (Claims 3 and 7 text, wherein Chang describes the activation function in the channel attention module for performing an average pool operation and a maximum pool operation on the feature map).
Regarding claim 11, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Chang teach wherein the U-Net further comprises a decoder, wherein the decoder receives the feature maps having the plurality of scales from the encoder ([0049], [0061], [0064] wherein Cheng incorporates encoder-decoder architectures for receiving feature maps).
Regarding claim 12, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Chang wherein the U-Net further comprises a Convolutional Block Attention Module (CBAM), wherein the CBAM is applied to outputs of a last pooling layer of the encoder and provides refined feature maps to a first layer of the decoder (Abstract, wherein Chang describes a method for embedding serial double-channel CBAM module in feature fusion stage to improve the U-net network).
Claims 13-20 are rejected under AIA 35 U.S.C. 103(a) as being unpatentable over Davey et al. US Patent Application Publication US 20120109598 A1 in view of Homer. US Patent Application Publication US 20120197623 A1 (hereinafter Homer) and further in view of Ozel Duygan Birge. Foreign Application Publication WO 2021260159 A1 (hereinafter Birge) and further in view of Hall, J et al. Foreign Application Publication CN 1890370 A (hereinafter Hall) and further in view of Kostem Emrah. Foreign Patent Application WO 2020232410 A1 (hereinafter Emrah) and further in view of Cheng et al. US Patent Application Publication US 20210239618 A1 (hereinafter Cheng) and further in view of Chang, Hong-jie et al. Foreign Patent Application Publication CN 113989271 A (hereinafter Chang) and further in view of Dutta Anindita et al. Foreign Application Publication WO 2020191391 A2 (hereinafter Dutta).
Regarding claim 13, Davey as modified by Homer, Birge, Hall, Emrah and Cheng do not wherein the decoder further comprises a second plurality of layer groups, wherein each layer group comprises a convolution transpose layer.
However, in analogous art of deep artificial neural networks for signal error correction, Dutta teaches wherein the decoder further comprises a second plurality of layer groups, wherein each layer group comprises a convolution transpose layer ([00399], [00610], [00791] wherein Dutta teaches layers with convolution transpose layer).
It would have been obvious to a person in the ordinary skill in the art before the effective filing date of the claimed invention to combine Davey, Homer, Birge, Hall, Emrah, Cheng and Chang with Dutta by incorporating the method of wherein the decoder further comprises a second plurality of layer groups, wherein each layer group comprises a convolution transpose layer of scales of Dutta into the method of correcting signal measurements providing a plurality of signal measurements to a channel of an input layer of Davey, Homer, Birge, Hall, Emrah, Cheng and Chang for the purpose of adding pointwise and depthwise separable convolutions (Dutta: [00399]).
Regarding claim 14, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Dutta teach wherein the convolution transpose layer applies a plurality of transposed convolutions to input channels provided to the convolution transpose layer to produce a plurality of upsampled feature maps ([00113], [00115], [00267], [00353], [00356-0357] wherein Dutta disclosed technology that can use upsampled images produced by interpolating sensor pixels into subpixels and then producing templates that resolve positional uncertainty, and wherein Dutta uses the cluster map that is upsampled).
Regarding claim 15, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Dutta teach wherein each layer group of the decoder further comprises one or more convolutional layers, wherein the convolutional layer applies a plurality of convolutions to input channels provided to the convolutional layer to produce a plurality of feature maps ([00401], [001275], [001281], [001285], [001291], [001296] wherein Dutta describes convolutional layers to produce feature maps).
Regarding claim 16, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Dutta teach wherein the convolutional layer further includes a batch normalization applied to the plurality of feature maps to produce normalized feature maps ([00791] wherein Dutta applies a batch normalization to the feature maps).
Regarding claim 17, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Dutta teach wherein the convolutional layer further includes applying an activation function to the normalized feature maps to produce output feature maps for output channels of the convolutional layer ([00791] wherein Duta applies an activation function to normalized feature maps).
Regarding claim 18, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Dutta teach wherein a first convolutional layer of the layer group of the decoder receives output channels from the convolution transpose layer of the layer group, further comprising: concatenating feature maps from a layer group of the encoder with feature maps from the convolution transpose layer to form concatenated feature maps, wherein the feature maps from the layer group of the encoder and the feature maps from the convolution transpose layer have a same scale; and applying the first convolutional layer of the layer group to the concatenated feature maps ([00424], [00426], [001438] wherein Dutta combines intensities of the identified subpixels and normalizes the combined intensities to produce a per-image cluster intensity for the given cluster in each of the upsampled images. The normalization is performed by a normalizer and is based on a normalization factor. Wherein the normalization factor is a number of the identified subpixels. This is done to normalize/account for different cluster sizes and uneven illuminations that clusters receive depending on their location on the flow cell), ([0058] wherein Cheng describes up-sampling the feature map and a concatenation layer for concatenation the up-sampled feature map with the corresponding feature map from the encoder phase).
Regarding claim 19, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Dutta teach wherein a second convolutional layer of the layer group of the decoder receives output channels from a first convolutional layer of the layer group ([00657], [00668], [00908], [001285], [001302], [001372], [001400] wherein Dutta describes convolving image patches extracted from the upsampled images through a convolutional neural network to generate a convolved representation of the image patches, processing the convolved representation through an output layer to produce, for each subpixel in the array, likelihoods of a base incorporated at the current one of the plurality of sequencing cycles being A, C, T, and G, classifying the base as A, C, T, or G based on the likelihoods, and base calling each one of the plurality of the analytes based on a base classification assigned to a respective subpixel containing a center of a corresponding analyte).
Regarding claim 20, Davey as modified by Homer, Birge, Hall, Emrah, Cheng and Dutta teach applying a plurality convolution to a plurality of outputs of a last layer group of the second plurality of layer groups to produce the plurality of signal correction values ([00317], [00867] wherein Dutta’s process relies on growing nascent DNA strands complementary to template DNA strands with modified nucleotides, while tracking the emitted signal of each newly added nucleotide. The modified nucleotides have a 3’ removable block that anchors a fluorophore signal of the nucleotide type, wherein Dutta describes Calibration that is a process in which a statistical quality table is derived from empirical data that includes various well -characterized human and non-human samples sequenced on a number of instruments. Using a modified version of the Phred algorithm, a quality table is developed and refined using characteristics of the raw signals and error rates determined by aligning reads to the appropriate references), ([0016], [0068] wherein Davey describes receiving signals and calculating the metric using nucleotide flows and determining values of the signal correction).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HASSAN MRABI whose telephone number is (571)272-8875. The examiner can normally be reached on Monday-Friday, 7:30am-5pm. Alt, Friday, EST.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Viker Lamardo can be reached on 571-270-5871. 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 http://pair-direct.uspto.gov. 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.
/HASSAN MRABI/Examiner, Art Unit 2144