Methods and systems for computational decoding of biological, chemical, and physical entities
The present disclosure provides systems and methods for detecting components of an array of biological, chemical, or physical entities. In an aspect, the present disclosure provides a method for detecting an array of biological, chemical, or physical entities, comprising: (a) using one or more light sensing devices, acquiring pixel information from sites in an array, wherein the sites comprise biological, chemical, or physical entities that produce light; (b) processing the pixel information to identify a set of regions of interest (ROIs) corresponding to the sites in the array that produce the light; (c) classifying the pixel information for the ROIs into a categorical classification from among a plurality of distinct categorical classifications, thereby producing a plurality of pixel classifications; and (d) identifying one or more components of the array of biological, chemical, or physical entities based at least in part on the plurality of pixel classifications.
1. A method for detecting an array of proteins, comprising:
(a) using a set of light sensing devices, (i) acquiring a first set of pixel information from sites in an array, and (ii) acquiring a second set of pixel information from the sites in the array, wherein the sites comprise proteins, wherein the sites further comprise labels that produce light;
(b) processing the pixel information to (i) register the first set of pixel information and the second set of pixel information to a common coordinate system, and (ii) identify a set of regions of interest corresponding to the sites in the array that produce the light in the first set of pixel information and the second set of pixel information;
(c) classifying the pixel information for the set of regions of interest into a categorical classification from among a plurality of distinct categorical classifications, thereby producing a plurality of pixel classifications; and
(d) identifying a protein in the array of proteins based at least in part on the plurality of pixel classifications.
2. The method of claim 1 , wherein the sites comprise affinity agents bound to the proteins, wherein the affinity agents are attached to the labels.
3. The method of claim 1 , wherein the sites comprise structured nucleic acid particles comprising the labels.
4. The method of claim 1 , wherein the labels comprise fluorescent labels.
5. The method of claim 1 , wherein the set of light sensing devices is configured to use four-beam interference to create a two-dimensional sine wave pattern.
6. The method of claim 1 , wherein the set of light sensing devices comprises a material compatible with complementary metal-oxide semiconductor (CMOS) processing, and wherein the set of light sensing devices is configured to be functionalized.
7. The method of claim 1 , wherein each region of interest of the set of regions of interest comprises pixel information corresponding to a single cluster of pixels.
8. The method of claim 7 , wherein (d) further comprises applying a classifier to the set of regions of interest to classify the pixel information corresponding to the single cluster of pixels into the categorical classification.
9. The method of claim 8 , wherein the classifier comprises a trained machine learning classifier.
10. The method of claim 9 , wherein the trained machine learning classifier comprises a supervised machine learning algorithm.
11. The method of claim 9 , wherein the trained machine learning classifier comprises an unsupervised machine learning algorithm.
12. The method of claim 1 , wherein the plurality of distinct categorical classifications comprises a first categorical classification associated with a light signal from a site in the array indicative of a presence of a protein, and a second categorical classification associated with absence of a light signal from the array indicative of an absence of a protein.
13. The method of claim 12 , wherein the first categorical classification is indicative of presence of light produced from an affinity agent bound to a protein.
14. The method of claim 12 , wherein the second categorical classification is indicative of an absence of an affinity agent bound to a protein.
15. The method of claim 1 , wherein the common coordinate system is determined by deconvolving the first set of pixel information with an edge kernel, the edge kernel representing a signal from a set of sites at an edge of the array.
16. The method of claim 15 , wherein the common coordinate system is determined by deconvolving the first set of pixel information with a site kernel, the site kernel representing a signal from a single site in the array.
17. The method of claim 1 , wherein the sites are arranged in a repeating pattern in the array.