# US 12,217,831 B2 · Artificial intelligence-based quality scoring

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,217,831 B2
- Document ID: US12217831B2
- Status: Granted
- Kind: B2
- Application number: 18/296,125
- Filed: 2023-04-05
- Published: 2024-02-29
- Granted: 2025-02-04
- Earliest claimed: 2019-03-21
- Assignees: Illumina, Inc.
- Applicants: Illumina, Inc.
- Inventors: Kishore Jaganathan; John Randall Gobbel; Amirali Kia
- Web page: https://patentgrep.com/patent/US12217831B2

## CPC

- G16B 40/20: Supervised data analysis
- G06F 16/58: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F 16/907: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06F 18/23: Clustering techniques
- G06F 18/23211: with adaptive number of clusters
- G06F 18/24: Classification techniques
- G06F 18/2415: based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F 18/2431: Multiple classes
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/09: Supervised learning
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06V 10/267: {by performing operations on regions, e.g. growing, shrinking or watersheds}
- G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]}
- G06V 10/751: {Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching}
- G06V 10/763: {Non-hierarchical techniques, e.g. based on statistics of modelling distributions}
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/7715: {Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods}
- G06V 10/7784: {based on feedback from supervisors}
- G06V 10/82: using neural networks
- G06V 10/993: {Evaluation of the quality of the acquired pattern}
- G06V 20/69: Microscopic objects, e.g. biological cells or cellular parts
- G16B 30/20: Sequence assembly
- G16B 40/00: ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
- G16B 40/10: Signal processing, e.g. from mass spectrometry [MS] or from PCR
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/048: Activation functions
- G06N 5/046: Forward inferencing; Production systems
- G06V 20/47: {Detecting features for summarising video content}
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The technology disclosed assigns quality scores to bases called by a neural network-based base caller by (i) quantizing classification scores of predicted base calls produced by the neural network-based base caller in response to processing training data during training, (ii) selecting a set of quantized classification scores, (iii) for each quantized classification score in the set, determining a base calling error rate by comparing its predicted base calls to corresponding ground truth base calls, (iv) determining a fit between the quantized classification scores and their base calling error rates, and (v) correlating the quality scores to the quantized classification scores based on the fit.

## Claims

### Claim 1

A system comprising:
at least one processor; and
a non-transitory computer readable medium storing instructions that, when executed by the at least one processor, cause the system to:
identify one or more base calls for one or more analytes based on sequencing images captured at one or more sequencing cycles;
feed, to an input layer of a neural network, input data representing the sequencing images;
generate, based on the input data and utilizing an output layer of the neural network, one or more predicted quality indications for the one or more base calls; and
determine, based on the one or more predicted quality indications, one or more quality predictions for the one or more base calls.

### Claim 2 (depends on 1)

The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to feed the input data representing the sequencing images by feeding, to the input layer of the neural network:
a first subset of per-cycle image patches depicting intensity emissions from a target cluster and one or more adjacent clusters at a preceding sequencing cycle occurring before a target sequencing cycle;
a second subset of per-cycle image patches depicting intensity emissions from the target cluster and the one or more adjacent clusters at the target sequencing cycle; and
a third subset of per-cycle image patches depicting intensity emissions from the target cluster and the one or more adjacent clusters at a subsequent sequencing cycle occurring after the target sequencing cycle.

### Claim 3 (depends on 1)

The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to feed the input data representing the sequencing images by feeding, to the input layer of the neural network:
supplemental distance information that identifies distances between pixels within the sequencing images; or
image channel information identifying one or more image channels corresponding to the sequencing images.

### Claim 4 (depends on 1)

The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to determine the one or more quality predictions for the one or more base calls by determining one or more quality scores for the one or more base calls.

### Claim 5 (depends on 1)

The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to:
generate the one or more predicted quality indications by generating a first likelihood of a base call of the one or more base calls being a high quality, a second likelihood of the base call being a medium quality, and a third likelihood of the base call being a low quality; and
based on the first likelihood, the second likelihood, and the second likelihood, determine the one or more quality predictions for the one or more base calls by classifying a quality of the base call as a high quality, a medium quality, or a low quality.

### Claim 6 (depends on 1)

The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to:
generate the one or more predicted quality indications by generating quality-score likelihoods of a base call of the one or more base calls being assigned individual quality scores; and
based on the quality-score likelihoods, determine the one or more quality predictions for the one or more base calls by assigning the base call a quality score from one of the individual quality scores.

### Claim 7 (depends on 1)

The system of claim 1, wherein the neural network is a convolutional neural network.

### Claim 8 (depends on 1)

The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to generate the one or more predicted quality indications for the one or more base calls by generating, utilizing a regression layer from the output layer, continuous values that identify a quality of the one or more base calls.

### Claim 9 (depends on 1)

The system of claim 1, further comprising instructions that, when executed by the at least one processor, cause the system to:
feed, to a supplemental input module, one or more quality predictor values for the one or more base calls; and
generate, utilizing the output layer of the neural network, the one or more predicted quality indications further based on the one or more quality predictor values.

### Claim 10 (depends on 9)

The system of claim 9, wherein the one or more quality predictor values comprise one or more of online overlap, purity, phasing, start5, hexamer score, motif accumulation, endiness, approximate homopolymer, intensity decay, penultimate chastity, signal overlap with background (SOWB), shifted purity G adjustment, peak height, peak width, peak location, relative peak locations, peak height ration, peak spacing ration, or peak correspondence.

### Claim 11

A non-transitory computer readable medium storing instructions that, when executed by at least one processor, cause a system to:
identify one or more base calls for one or more analytes based on sequencing images captured at one or more sequencing cycles;
feed, to an input layer of a neural network, input data representing the sequencing images;
generate, based on the input data and utilizing an output layer of the neural network, one or more predicted quality indications for the one or more base calls; and
determine, based on the one or more predicted quality indications, one or more quality predictions for the one or more base calls.

### Claim 12 (depends on 11)

The non-transitory computer readable medium of claim 11, further storing instructions that, when executed by the at least one processor, cause the system to feed the input data representing the sequencing images by feeding, to the input layer of the neural network:
a first subset of per-cycle image patches depicting intensity emissions from a target cluster and one or more adjacent clusters at a preceding sequencing cycle occurring before a target sequencing cycle;
a second subset of per-cycle image patches depicting intensity emissions from the target cluster and the one or more adjacent clusters at the target sequencing cycle; and
a third subset of per-cycle image patches depicting intensity emissions from the target cluster and the one or more adjacent clusters at a subsequent sequencing cycle occurring after the target sequencing cycle.

### Claim 13 (depends on 11)

The non-transitory computer readable medium of claim 11, further storing instructions that, when executed by the at least one processor, cause the system to determine the one or more quality predictions for the one or more base calls by determining one or more quality scores for the one or more base calls.

### Claim 14 (depends on 13)

The non-transitory computer readable medium of claim 13, further storing instructions that, when executed by the at least one processor, cause the system to:
generate the one or more predicted quality indications by generating a first likelihood of a base call of the one or more base calls being a high quality, a second likelihood of the base call being a medium quality, and a third likelihood of the base call being a low quality; and
based on the first likelihood, the second likelihood, and the second likelihood, determine the one or more quality predictions for the one or more base calls by classifying a quality of the base call as a high quality, a medium quality, or a low quality.

### Claim 15 (depends on 11)

The non-transitory computer readable medium of claim 11, further storing instructions that, when executed by the at least one processor, cause the system to:
generate the one or more predicted quality indications by generating quality-score likelihoods of a base call of the one or more base calls being assigned individual quality scores; and
based on the quality-score likelihoods, determine the one or more quality predictions for the one or more base calls by assigning the base call a quality score from one of the individual quality scores.

### Claim 16

A computer-implemented method comprising:
identifying one or more base calls for one or more analytes based on sequencing images captured at one or more sequencing cycles;
feeding, to an input layer of a neural network, input data representing the sequencing images;
generating, based on the input data and utilizing an output layer of the neural network, one or more predicted quality indications for the one or more base calls; and
determining, based on the one or more predicted quality indications, one or more quality predictions for the one or more base calls.

### Claim 17 (depends on 16)

The computer-implemented method of claim 16, wherein the neural network is a convolutional neural network.

### Claim 18 (depends on 16)

The computer-implemented method of claim 16, wherein generating the one or more predicted quality indications for the one or more base calls comprises generating, utilizing a regression layer from the output layer, continuous values that identify a quality of the one or more base calls.

### Claim 19 (depends on 16)

The computer-implemented method of claim 16, further comprising:
feeding, to a supplemental input module, one or more quality predictor values for the one or more base calls; and
generating, utilizing the output layer of the neural network, the one or more predicted quality indications further based on the one or more quality predictor values.

### Claim 20 (depends on 19)

The computer-implemented method of claim 19, wherein the one or more quality predictor values comprise one or more of online overlap, purity, phasing, start5, hexamer score, motif accumulation, endiness, approximate homopolymer, intensity decay, penultimate chastity, signal overlap with background (SOWB), shifted purity G adjustment, peak height, peak width, peak location, relative peak locations, peak height ration, peak spacing ration, or peak correspondence.