# US 11,908,548 B2 · Training data generation for artificial intelligence-based sequencing

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

- Number: US 11,908,548 B2
- Document ID: US11908548B2
- Status: Granted
- Kind: B2
- Application number: 17/827,612
- Filed: 2022-05-27
- Published: 2022-09-15
- Granted: 2024-02-20
- Earliest claimed: 2019-03-21
- Assignees: Illumina, Inc.
- Applicants: Illumina, Inc.
- Inventors: Anindita Dutta; Dorna Kashefhaghighi; Amirali Kia
- Web page: https://patentgrep.com/patent/US11908548B2

## 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 relates to generating ground truth training data to train a neural network-based template generator for cluster metadata determination task. In particular, it relates to accessing sequencing images, obtaining, from a base caller, a base call classifying each subpixel in the sequencing images as one of four bases (A, C, T, and G), generating a cluster map that identifies clusters as disjointed regions of contiguous subpixels which share a substantially matching base call sequence, determining cluster metadata based on the disjointed regions in the cluster map, and using the cluster metadata to generate the ground truth training data for training the neural network-based template generator for the cluster metadata determination task.

## Claims

### Claim 1

A computer-implemented method of determining metadata about clusters on a tile of a flow cell, the computer-implemented method comprising:
accessing a set of images of the tile captured during a sequencing run and preliminary center coordinates of the clusters determined by a base caller;
for each image set, obtaining, from the base caller, a base call classifying, as one of four bases, origin subpixels that contain the preliminary center coordinates and
a predetermined neighborhood of contiguous subpixels that are successively contiguous to respective ones of the origin subpixels,
thereby producing a base call sequence for each of the origin subpixels and for each of the predetermined neighborhood of contiguous subpixels;
generating a cluster map that identifies the clusters as disjointed regions of contiguous subpixels that are successively contiguous to at least some of the respective ones of the origin subpixels and share a substantially matching base call sequence of the one of four bases with the at least some of the respective ones of the origin subpixels; and
storing the cluster map in memory for use determining shapes and sizes of the clusters.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further including training a classifier based upon the cluster map, the classifier being a neural network-based template generator for processing input image data to generate a decay map, a ternary map, or a binary map, representing one or more properties of each of a plurality of clusters represented in the input image data for base calling by a neural network-based base caller.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, further including:
determining hyperlocated center coordinates of analytes by calculating centers of mass of the disjointed regions of the cluster map as an average of coordinates of respective contiguous subpixels forming the disjointed regions; and
storing the hyperlocated center coordinates of the clusters in the memory for use as ground truth for training the classifier.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the cluster map identifies boundaries between contiguous subpixels whose base call sequences do not substantially match.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein generating the cluster map comprises identifying as background those subpixels that do not belong to any of the disjointed regions.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the cluster map identifies cluster boundary portions between two contiguous subpixels whose base call sequences do not substantially match.

### Claim 7

A non-transitory computer readable memory including instructions that, when executed by at least one processor, cause a system to implement actions for determining metadata about clusters on a tile of a flow cell, the actions comprising:
accessing a set of images of the tile captured during a sequencing run and preliminary center coordinates of the clusters determined by a base caller;
for each image set, obtaining, from the base caller, a base call classifying, as one of four bases, origin subpixels that contain the preliminary center coordinates and
a predetermined neighborhood of contiguous subpixels that are successively contiguous to respective ones of the origin subpixels,
thereby producing a base call sequence for each of the origin subpixels and for each of the predetermined neighborhood of contiguous subpixels;
generating a cluster map that identifies the clusters as disjointed regions of contiguous subpixels that are successively contiguous to at least some of the respective ones of the origin subpixels and share a substantially matching base call sequence of the one of four bases with the at least some of the respective ones of the origin subpixels; and
storing the cluster map in memory for use determining shapes and sizes of the clusters.

### Claim 8 (depends on 7)

The non-transitory computer readable memory of claim 7, further including instructions that, when executed by the at least one processor, cause the system to implement actions of training a classifier based upon the cluster map, the classifier being a neural network-based template generator for processing input image data to generate a decay map, a ternary map, or a binary map, representing one or more properties of each of a plurality of clusters represented in the input image data for base calling by a neural network-based base caller.

### Claim 9 (depends on 6)

The non-transitory computer readable memory of claim 6, further including instructions that, when executed by the at least one processor, cause the system to implement actions of:
determining hyperlocated center coordinates of the analytes by calculating centers of mass of the disjointed regions of the cluster map as an average of coordinates of respective contiguous subpixels forming the disjointed regions; and
storing the hyperlocated center coordinates of the clusters in the memory for use as ground truth for training the classifier.

### Claim 10 (depends on 5)

The non-transitory computer readable memory of claim 5, wherein the cluster map identifies boundaries between contiguous subpixels whose base call sequences do not substantially match.

### Claim 11 (depends on 7)

The non-transitory computer readable memory of claim 7, further including instructions that, when executed by the at least one processor, cause the system to implement actions comprising generating the cluster map by identifying as background those subpixels that do not belong to any of the disjointed regions.

### Claim 12 (depends on 7)

The non-transitory computer readable memory of claim 7, wherein the cluster map identifies cluster boundary portions between two contiguous subpixels whose base call sequences do not substantially match.

### Claim 13 (depends on 7)

The non-transitory computer readable memory of claim 7, further including instructions that, when executed by the at least one processor, cause the system to implement actions comprising generating the cluster map based on:
identifying origin subpixels at preliminary center coordinates of the clusters determined by the base caller; and
breadth-first searching for substantially matching base call sequences by beginning with the origin subpixels and continuing with successively contiguous non-origin subpixels.

### Claim 14

A computer-implemented system including:
at least one processor;
a non-transitory computer readable memory including instructions that, when executed by at least a processor, cause the computer-implemented system to implement actions for determining metadata about clusters on a tile of a flow cell, the actions comprising:
accessing a set of images of the tile captured during a sequencing run and preliminary center coordinates of the clusters determined by a base caller;
for each image set, obtaining from the base caller, a base call classifying, as one of four bases, origin subpixels that contain the preliminary center coordinates and a predetermined neighborhood of contiguous subpixels that are successively contiguous to respective ones of the origin subpixels, thereby producing a base call sequence for each of the origin subpixels and for each of the predetermined neighborhood of contiguous subpixels;
generating a cluster map that identifies the clusters as disiointed regions of contiguous subpixels that are successively contiguous to at least some of the respective ones of the origin subpixels and share a substantially matching base call sequence of the one of four bases with the at least some of the respective ones of the origin subpixels; and
storing the cluster map in memory for use determining shapes and sizes of the clusters.

### Claim 15 (depends on 14)

The computer-implemented system of claim 14, further including instructions that, when executed by the at least one processor, cause the computer-implemented system to implement actions of training a classifier based upon the cluster map, the classifier being a neural network-based template generator for processing input image data to generate a decay map, a ternary map, or a binary map, representing one or more properties of each of a plurality of clusters represented in the input image data for base calling by a neural network-based base caller.

### Claim 16 (depends on 15)

The computer-implemented system of claim 15, further including instructions that, when executed by the at least one processor, cause the computer-implemented system to implement actions comprising:
determining hyperlocated center coordinates of analytes by calculating centers of mass of the disjointed regions of the cluster map as an average of coordinates of respective contiguous subpixels forming the disjointed regions; and
storing the hyperlocated center coordinates of the clusters in the memory for use as ground truth for training the classifier.

### Claim 17 (depends on 14)

The computer-implemented system of claim 14, wherein the cluster map identifies boundaries between contiguous subpixels whose base call sequences do not substantially match.

### Claim 18 (depends on 14)

The computer-implemented system of claim 14, further including instructions that, when executed by the at least one processor, cause the computer-implemented system to implement actions comprising generating the cluster map by identifying as background those subpixels that do not belong to any of the disjointed regions.

### Claim 19 (depends on 14)

The computer-implemented system of claim 14, wherein the cluster map identifies cluster boundary portions between two contiguous subpixels whose base call sequences do not substantially match.

### Claim 20 (depends on 14)

The computer-implemented system of claim 14, further including instructions that, when executed by the at least one processor, cause the computer-implemented system to implement actions comprising generating the cluster map based on:
identifying origin subpixels at preliminary center coordinates of the clusters determined by the base caller; and
breadth-first searching for substantially matching base call sequences by beginning with the origin subpixels and continuing with successively contiguous non-origin subpixels.