DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . This action is responsive to the Application filed on 05/10/2023. Claims 1-20 are pending in the case. Claims 1, 10, and 18 are independent claims.
Claim Rejections - 35 U.S.C. § 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 for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The 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, 2, 4-7, 9-12, 14, 15, and 17-20 are rejected under 35 U.S.C. § 103 as being unpatentable over Jaganathan et al. (U.S. Pat. App. Pub. No. 2021/0265009, hereinafter Jaganathan) in view of Lee et al. (Lee, Dong-Hyun. "Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks." In Workshop on challenges in representation learning, ICML, vol. 3, no. 2, p. 896. 2013, hereinafter Lee) and Yosinski et al. (Yosinski, Jason, Jeff Clune, Yoshua Bengio, and Hod Lipson. "How transferable are features in deep neural networks?." arXiv preprint arXiv:1411.1792 (2014), hereinafter Yosinski).
As to independent claim 1, Jaganathan teaches
A system comprising (Paragraph 2):
at least one processor (Paragraph 199, "microprocessors"); and
a non-transitory computer readable medium comprising instructions that, when executed by the at least one processor, cause the system to (Paragraph 199, "non-transient storage media"):
configure a field programmable gate array (FPGA) to implement a base-calling-neural network comprising a set of bottom layers and a set of top layers that were initially trained using training images of oligonucleotide clusters (Paragraph 163, "Deep learning processors 3278 can be graphics processing units (GPUs), field-programmable gate arrays (FPGAs)." Paragraph 58, "the neural network-based base calling in which a neural network, i.e., a neural network-based base caller 430, is trained to map sequencing images to base calls 432." Paragraph 68 discusses CNN/RNN which are layered architectures (i.e., bottom layers and top layers). Paragraph 207, "an analyte can be an amplified oligonucleotide." Paragraph 65, "target analyte (e.g., cluster) is to be base called." Paragraph 56, "clusters and their surrounding background." Paragraph 58, "neural network-based base caller 430, is trained to map sequencing images to base calls 432");
provide, to the base-calling-neural network, a set of images of oligonucleotide clusters associated with a target sequencing cycle (Paragraph 56, "clusters and their surrounding background." Paragraph 65, "The input image data comprises a sequence of per-cycle image patches generated for a series of k sequencing cycles of a sequencing run");
generate, utilizing the base-calling-neural network, one or more nucleobase calls for the oligonucleotide clusters and the target sequencing cycle based on the set of images (Paragraph 97, "output layer (e.g., a softmax layer) for generating a base call"); and
… modify, utilizing the FPGA… based on the one or more nucleobase calls (Paragraph 162, “These software modules are generally executed by deep learning processors 3278.” Paragraph 163, "Deep learning processors 3278 can be graphics processing units (GPUs), field-programmable gate arrays (FPGAs)." Paragraph 61, "the neural network-based base caller 430 as ’input image data‘ for base calling").
Jaganathan does not appear to expressly teach modify… one or more network parameters….
Lee teaches modify… one or more network parameters… (Page 1, "Pseudo-Label s, just picking up the class which has the maximum predicted probability every weights update").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having AI-based base calling of index sequences of Jaganathan to include the pseudo-labeling deep neural network techniques of Lee to improve generalization performance and reducing reliance on fully labeled training data (see Lee at page 3 and abstract).
Jaganathan does not appear to expressly teach modify… the set of top layers….
Yosinski teaches modify… the set of top layers… (Page 2, "feature layers can be left frozen, meaning that they do not change during training on the new task. The choice of whether or not to fine-tune the first n layers of the target network").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the AI-based base calling of index sequences of Jaganathan to include the deep neural network techniques of Yosinski to better transfer features and produce a boost to generalization that lingers even after fine-tuning to the target dataset (see Yosinski at abstract).
In short, Lee supports updating network weights using predicted labels/pseudo-labels, and Yosinski supports transfer learning with selective freezing/fine-tuning of layers, especially higher/task-specific layers. In combination with Jaganathan, this creates adapting a pretrained sequencing/base-calling neural network by updating parameters and fine-tuning upper layers.
As to dependent claim 2, Jaganathan further teaches the set of bottom layers comprises a set of spatial layers and the set of top layers comprises a set of temporal layers (Paragraph 68 discusses CNN/RNN which are layered architectures (i.e., bottom layers and top layers)).
As to dependent claim 4, Yosinski further teaches modify one or more network parameters of a first subset of bottom layers from the set of bottom layers based on the one or more nucleobase calls without modifying network parameters of a second subset of bottom layers from the set of bottom layers (Page 2, "feature layers can be left frozen, meaning that they do not change during training on the new task. The choice of whether or not to fine-tune the first n layers of the target network).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the AI-based base calling of index sequences of Jaganathan to include the deep neural network techniques of Yosinski to better transfer features (see Yosinski at abstract).
As to dependent claim 5, Yosinski further teaches configure the FPGA to implement the base-calling-neural network on one or more computing devices of the system differing from one or more additional computing devices of a different system used to initially train the base-calling-neural network using the training images (Page 2, "first train a base network on a base dataset and task, and then we repurpose the learned features, or transfer them, to a second target network to be trained on a target dataset and task").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the AI-based base calling of index sequences of Jaganathan to include the deep neural network techniques of Yosinski to better transfer features (see Yosinski at abstract).
As to dependent claim 6, Jaganathan further teaches modify the one or more network parameters of the set of top layers by: identifying, from the set of top layers, subsets of weights or subsets of scaling values assigned to respective subregions within images of the set of images; and modifying the subsets of weights or the subsets of scaling values based on the one or more nucleobase calls (Paragraph 183, "particular analyte being base called at the current index sequencing cycle, at action 3412, the method includes extracting index image patches from normalized versions of the index images from the current, preceding, succeeding index sequencing cycles, such that, each normalized index image patch depicts intensity emissions of the particular analyte, of some adjacent analytes, and of their surrounding background." Paragraph 177, "multiplying intensity values of the index image with a scaling factor").
As to dependent claim 7, Jaganathan further teaches provide the set of images of oligonucleotide clusters associated with the target sequencing cycle by inputting a prior-cycle image of the oligonucleotide clusters for a prior sequencing cycle before the target sequencing cycle, a target-cycle image of the oligonucleotide clusters for the target sequencing cycle, and a subsequent-cycle image of the oligonucleotide clusters for a subsequent sequencing cycle after the target sequencing cycle; and generate the one or more nucleobase calls for the target sequencing cycle based on the prior-cycle image, the target-cycle image, and the subsequent-cycle image (Paragraph 66, "current (time t) sequencing cycle to be base called is accompanied with (i) data for a left flanking/context/previous/preceding/prior (time t−1) sequencing cycle and (ii) data for a right flanking/context/next/successive/subsequent (time t+1)").
As to dependent claim 9, Jaganathan further teaches generate the one or more nucleobase calls by: determining, utilizing the set of top layers, a set of output values corresponding to the set of images; and determining, utilizing a softmax layer, base-call probabilities for different nucleobase classes based on the set of output values (Paragraph 97, "output layer (e.g., a softmax layer) for generating a base call").
As to independent claim 10, Jaganathan teaches
A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause a system to (Paragraph 199, "non-transient storage media"):
configure a configurable processor to implement a base-calling-neural network comprising a set of bottom layers and a set of top layers that were initially trained using training images of oligonucleotide clusters (Paragraph 163, "Deep learning processors 3278 can be graphics processing units (GPUs), field-programmable gate arrays (FPGAs)." Paragraph 58, "the neural network-based base calling in which a neural network, i.e., a neural network-based base caller 430, is trained to map sequencing images to base calls 432." Paragraph 68 discusses CNN/RNN which are layered architectures (i.e., bottom layers and top layers). Paragraph 207, "an analyte can be an amplified oligonucleotide." Paragraph 65, "target analyte (e.g., cluster) is to be base called." Paragraph 56, "clusters and their surrounding background." Paragraph 58, "neural network-based base caller 430, is trained to map sequencing images to base calls 432");
provide, to the base-calling-neural network, a set of images of oligonucleotide clusters associated with a target sequencing cycle (Paragraph 56, "clusters and their surrounding background." Paragraph 65, "The input image data comprises a sequence of per-cycle image patches generated for a series of k sequencing cycles of a sequencing run");
generate, utilizing the base-calling-neural network, one or more nucleobase calls for the oligonucleotide clusters and the target sequencing cycle based on the set of images (Paragraph 97, "output layer (e.g., a softmax layer) for generating a base call"); and
modify, utilizing the configurable processor… based on the one or more nucleobase calls (Paragraph 163, "Deep learning processors 3278 can be graphics processing units (GPUs), field-programmable gate arrays (FPGAs)." Page 61, "the neural network-based base caller 430 as “input image data” for base calling").
Jaganathan does not appear to expressly teach modify… one or more network parameters….
Lee teaches modify… one or more network parameters… (Page 1, "Pseudo-Label s, just picking up the class which has the maximum predicted probability every weights update").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having AI-based base calling of index sequences of Jaganathan to include the pseudo-labeling deep neural network techniques of Lee to improve accuracy and speed (see Lee at abstract).
Jaganathan does not appear to expressly teach modify… the set of top layers.
Yosinski teaches modify… the set of top layers (Page 2, "feature layers can be left frozen, meaning that they do not change during training on the new task. The choice of whether or not to fine-tune the first n layers of the target network").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the AI-based base calling of index sequences of Jaganathan to include the deep neural network techniques of Yosinski to better transfer features (see Yosinski at abstract).
As to dependent claim 11, Jaganathan further teaches the configurable processor comprises an application-specific integrated circuit (ASIC), an application-specific standard product (ASSP), a coarse-grained reconfigurable array (CGRA), or a field programmable gate array (FPGA) (Paragraph 163, "Deep learning processors 3278 can be graphics processing units (GPUs), field-programmable gate arrays (FPGAs).").
As to dependent claim 12, Jaganathan further teaches the set of bottom layers comprises a set of spatial layers and the set of top layers comprises a set of temporal layers (Paragraph 68 discusses CNN/RNN which are layered architectures (i.e., bottom layers and top layers)).
As to dependent claim 14, Jaganathan further teaches modify the one or more network parameters of the set of top layers by: identifying, from the set of top layers, subsets of weights or subsets of scaling values assigned to respective subregions within images of the set of images; and modifying the subsets of weights or the subsets of scaling values based on the one or more nucleobase calls (Paragraph 183, "particular analyte being base called at the current index sequencing cycle, at action 3412, the method includes extracting index image patches from normalized versions of the index images from the current, preceding, succeeding index sequencing cycles, such that, each normalized index image patch depicts intensity emissions of the particular analyte, of some adjacent analytes, and of their surrounding background." Paragraph 177, "multiplying intensity values of the index image with a scaling factor").
As to dependent claim 15, Jaganathan further teaches provide the set of images of oligonucleotide clusters associated with the target sequencing cycle by inputting a prior-cycle image of the oligonucleotide clusters for a prior sequencing cycle before the target sequencing cycle, a target-cycle image of the oligonucleotide clusters for the target sequencing cycle, and a subsequent-cycle image of the oligonucleotide clusters for a subsequent sequencing cycle after the target sequencing cycle; and generate the one or more nucleobase calls for the target sequencing cycle based on the prior-cycle image, the target-cycle image, and the subsequent-cycle image (Paragraph 66, "current (time t) sequencing cycle to be base called is accompanied with (i) data for a left flanking/context/previous/preceding/prior (time t−1) sequencing cycle and (ii) data for a right flanking/context/next/successive/subsequent (time t+1)").
As to dependent claim 17, Yosinski further teaches configure the configurable processor to implement the base-calling-neural network on one or more computing devices of the system differing from one or more additional computing devices of a different system used to initially train the base-calling-neural network using the training images (Page 2, "transfer learning, we first train a base network on a base dataset and task, and then we repurpose the learned features, or transfer them, to a second target network").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the AI-based base calling of index sequences of Jaganathan to include the deep neural network techniques of Yosinski to better transfer features (see Yosinski at abstract).
As to independent claim 18, Jaganathan teaches
A computer-implemented method comprising (Paragraph 2. Paragraph 199, "microprocessors"):
configuring a configurable processor to implement a base-calling-neural network comprising a set of bottom layers and a set of top layers that were initially trained using training images of oligonucleotide clusters (Paragraph 163, "Deep learning processors 3278 can be graphics processing units (GPUs), field-programmable gate arrays (FPGAs)." Paragraph 58, "the neural network-based base calling in which a neural network, i.e., a neural network-based base caller 430, is trained to map sequencing images to base calls 432." Paragraph 68 discusses CNN/RNN which are layered architectures (i.e., bottom layers and top layers). Paragraph 207, "an analyte can be an amplified oligonucleotide." Paragraph 65, "target analyte (e.g., cluster) is to be base called." Paragraph 56, "clusters and their surrounding background." Paragraph 58, "neural network-based base caller 430, is trained to map sequencing images to base calls 432");
providing, to the base-calling-neural network, a set of images of oligonucleotide clusters associated with a target sequencing cycle (Paragraph 56, "clusters and their surrounding background." Paragraph 65, "The input image data comprises a sequence of per-cycle image patches generated for a series of k sequencing cycles of a sequencing run");
generating, utilizing the base-calling-neural network, one or more nucleobase calls for the oligonucleotide clusters and the target sequencing cycle based on the set of images (Paragraph 97, "output layer (e.g., a softmax layer) for generating a base call"); and
modifying, utilizing the configurable processor… based on the one or more nucleobase calls (Paragraph 163, "Deep learning processors 3278 can be graphics processing units (GPUs), field-programmable gate arrays (FPGAs)." Page 61, "the neural network-based base caller 430 as “input image data” for base calling").
Jaganathan does not appear to expressly teach modifying… one or more network parameters….
Lee teaches modifying… one or more network parameters… (Page 1, "Pseudo-Label s, just picking up the class which has the maximum predicted probability every weights update").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having AI-based base calling of index sequences of Jaganathan to include the pseudo-labeling deep neural network techniques of Lee to improve accuracy and speed (see Lee at abstract).
Jaganathan does not appear to expressly teach modifying… the set of top layers….
Yosinski teaches modifying… the set of top layers… (Page 2, "feature layers can be left frozen, meaning that they do not change during training on the new task. The choice of whether or not to fine-tune the first n layers of the target network").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the AI-based base calling of index sequences of Jaganathan to include the deep neural network techniques of Yosinski to better transfer features (see Yosinski at abstract).
As to dependent claim 19, Jaganathan further teaches generating, utilizing an additional instance of the base-calling-neural network implemented by an additional configurable processor, one or more additional nucleobase calls for additional oligonucleotide clusters and a sequencing cycle based on an additional set of images (Paragraph 69, "model parallelism, data parallelism, and synchronous/asynchronous SG").
Lee further teaches modifying, utilizing the configurable processor, a subset of network parameters of the set of top layers from the base-calling-neural network based on the one or more additional nucleobase calls (Page 1, "Pseudo-Label s, just picking up the class which has the maximum predicted probability every weights update").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having AI-based base calling of index sequences of Jaganathan to include the pseudo-labeling deep neural network techniques of Lee to improve accuracy and speed (see Lee at abstract).
As to dependent claim 20, Yosinski further teaches modifying the one or more network parameters comprises modifying one or more network parameters of a first subset of bottom layers from the set of bottom layers based on the one or more nucleobase calls without modifying network parameters of a second subset of bottom layers from the set of bottom layers (Page 2, "feature layers can be left frozen, meaning that they do not change during training on the new task. The choice of whether or not to fine-tune the first n layers of the target network).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the AI-based base calling of index sequences of Jaganathan to include the deep neural network techniques of Yosinski to better transfer features (see Yosinski at abstract).
Claims 3 and 13 are rejected under 35 U.S.C. § 103 as being unpatentable over Jaganathan in view of Lee, Yosinski, and Gupta et al. (Gupta, Suyog, Ankur Agrawal, Kailash Gopalakrishnan, and Pritish Narayanan. "Deep Learning with Limited Numerical Precision." arXiv e-prints (2015): arXiv-1502, hereinafter Gupta).
As to dependent claim 3, the rejection of claim 1 is incorporated.
Jaganathan does not appear to expressly teach modify the one or more network parameters of the set of top layers by: determining a gradient with a fixed-point range based on an error signal derived from the one or more nucleobase calls; and adjusting one or more weights for one or more top layers of the set of top layers according to the determined gradient.
Gupta teaches modify the one or more network parameters of the set of top layers by: determining a gradient with a fixed-point range based on an error signal derived from the one or more nucleobase calls; and adjusting one or more weights for one or more top layers of the set of top layers according to the determined gradient (Page 3, "fixed-point format limits the precision to FL bits, sets the range").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having AI-based base calling of index sequences of Jaganathan to include the deep learning techniques of Gupta to increase energy efficiency (see Gupta at abstract).
As to dependent claim 13, the rejection of claim 10 is incorporated.
Jaganathan does not appear to expressly teach modify the one or more network parameters of the set of top layers by: determining a gradient with a fixed-point range based on an error signal derived from the one or more nucleobase calls; and adjusting one or more weights for one or more top layers of the set of top layers according to the determined gradient.
Gupta teaches modify the one or more network parameters of the set of top layers by: determining a gradient with a fixed-point range based on an error signal derived from the one or more nucleobase calls; and adjusting one or more weights for one or more top layers of the set of top layers according to the determined gradient (Page 3, "fixed-point format limits the precision to FL bits, sets the range").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having AI-based base calling of index sequences of Jaganathan to include the deep learning techniques of Gupta to increase energy efficiency (see Gupta at abstract).
Claims 8 and 16 are rejected under 35 U.S.C. § 103 as being unpatentable over Jaganathan in view of Lee, Yosinski, and Langlois et al. (Int’l. Pat. App. Pub. WO-2018129314-A1, hereinafter Langlois).
As to dependent claim 8, the rejection of claim 7 is incorporated.
Jaganathan does not appear to expressly teach generate the one or more nucleobase calls for the oligonucleotide clusters and the target sequencing cycle in part by determining, using the set of bottom layers, intermediate values for the subsequent-cycle image; and generate one or more additional nucleobase call for the oligonucleotide clusters and the subsequent sequencing cycle in part by reusing the intermediate values for the subsequent-cycle image.
Langlois teaches generate the one or more nucleobase calls for the oligonucleotide clusters and the target sequencing cycle in part by determining, using the set of bottom layers, intermediate values for the subsequent-cycle image; and generate one or more additional nucleobase call for the oligonucleotide clusters and the subsequent sequencing cycle in part by reusing the intermediate values for the subsequent-cycle image (Paragraph 9, "producing the partially phase-corrected color values for the immediately succeeding base calling cycle additionally includes summing (i) the phasing corrected color values of the plurality of sites, and (ii) the color values of the plurality of sites from the image of the substrate measured in (b). In some implementations, storing the partially phase-corrected color values for the immediately succeeding base calling cycle").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the AI-based base calling of index sequences of Jaganathan to include the sequencing techniques of Langlois to reduce background signal and crosstalk between cycles (see Langlois at paragraph 116).
As to dependent claim 16, the rejection of claim 15 is incorporated.
Jaganathan does not appear to expressly teach generate the one or more nucleobase calls for the oligonucleotide clusters and the target sequencing cycle in part by determining, using the set of bottom layers, intermediate values for the subsequent-cycle image; and generate one or more additional nucleobase call for the oligonucleotide clusters and the subsequent sequencing cycle in part by reusing the intermediate values for the subsequent-cycle image.
Langlois teaches generate the one or more nucleobase calls for the oligonucleotide clusters and the target sequencing cycle in part by determining, using the set of bottom layers, intermediate values for the subsequent-cycle image; and generate one or more additional nucleobase call for the oligonucleotide clusters and the subsequent sequencing cycle in part by reusing the intermediate values for the subsequent-cycle image (Paragraph 9, "producing the partially phase-corrected color values for the immediately succeeding base calling cycle additionally includes summing (i) the phasing corrected color values of the plurality of sites, and (ii) the color values of the plurality of sites from the image of the substrate measured in (b). In some implementations, storing the partially phase-corrected color values for the immediately succeeding base calling cycle").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the AI-based base calling of index sequences of Jaganathan to include the sequencing techniques of Langlois to reduce background signal and crosstalk between cycles (see Langlois at paragraph 116).
Conclusion
It is noted that any citation to specific pages, columns, lines, or figures in the prior art references and any interpretation of the references should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. In re Heck, 699 F.2d 1331, 1332-33, 216 U.S.P.Q. 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1009, 158 U.S.P.Q. 275, 277 (C.C.P.A. 1968)).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Casey R. Garner whose telephone number is 571-272-2467. The examiner can normally be reached Monday to Friday, 8am to 5pm, Eastern Time.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Alexey Shmatov can be reached on 571-270-3428. 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 Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center and Private PAIR to authorized users only. Should you have questions about access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/Casey R. Garner/Primary Examiner, Art Unit 2123