Sensor array for fluorescence diagnostics

Abstract

Presented herein is a sensor platform which can be used for the detection of arbitrary molecules of interest or for clinical diagnosis using test solutions. The sensor may include an array of environmentally sensitive fluorescent reporter probes. Each probe is placed on a separate pixel or several pixels of the sensor array and has a different coating, such that it responds slightly differently to environmental stimuli than every other pixel upon addition of the test solution.

Description

SENSOR ARRAY FOR FLUORESCENCE DIAGNOSTICSCROSS REFERENCES TO RELATED APPLICATIONS[OOOIJ This application claims the benefit of the and priority to U.S. Provisional Application No. 63 / 553,033, titled “Sensor Array for Fluorescence Diagnostics,” filed February 13, 2024, and U.S. Provisional Application No. 63 / 516,047, titled “Sensor Array for Fluorescence Diagnostics,” filed July 27, 2023, each of which is incorporated herein by reference in their entireties.BACKGROUND

[0002] Various types of sensors may be used for imaging and microscopy. A computing device may use a computer vision algorithm to process data acquired via such sensors.SUMMARY

[0003] Other approaches of fluorescent nanotube-based microarrays may be used, but these rely upon specific binding agents such as antibodies, and so can only detect particular molecules for which they have binding affinity, rather than using a generic, machine learning, perception-based approach. For example, Kaleidoscopic fluorescent arrays may be used for perception-based sensing. However, such arrays are limited in scope to a single class of fluorescent molecules (e.g., kaleidolizine derivatives) and were only tested for the detection of volatile organic chemicals (VOCs). It was not attempted to use these arrays for diagnosis of disease, and it was only demonstrated for detecting compounds in the gas phase, and so they would not be suitable for screening serum, saliva, or urine samples. A number of other sensors for VOCs may use carbon nanotubes as reporters. These typically use small molecules as coating agents rather than a deoxyribonucleic acid (DNA), peptides, or other polymers, and are only used for detection of volatile compounds in the gas phase rather than solutions (e.g., serum, saliva, or urine). Polymer wrapping affords higher stability for liquid analytes, as small molecules may be more prone to desorption from the nanotube surface.

[0004] To address these and other technical drawbacks, presented herein is a sensor platform which can be used for the detection of arbitrary molecules of interest or for clinical diagnosis using blood, saliva, or urine samples. The sensor may include an array of environmentally sensitive fluorescent probes. Each probe is placed on a separate pixel or several pixels of the sensor array, and has a different coating, such that it responds slightly differently to environmental stimuli to every other pixel upon addition of a test solution, such as blood or saliva. In this way, the sensor resembles a two-dimensional quick response (QR) code, with each pixel displaying a different value based on the presence of biomolecules, such as proteins, lipids, and salts or change in the environment such as acidity (e.g., pH), temperature, oxygen concentration, etc.

[0005] The sensor uses a machine learning approach and can be trained on analytes with known classification, in order to identify these analytes in unknown samples. For example, by training the sensor with blood from an ovarian cancer patient versus blood from a healthy donor, the ovarian cancer status of unknown blood samples can be predicted. This can also be used for the detection of other molecules of interest, such as drugs, explosives, and environmental pollutants. This assay may involve a microarray, which can be produced via low-cost inkjet printing or microdroplet dispensing. This format allows orders of magnitude higher levels of multiplexing, facilitating a single sensor to detect multiple diseases simultaneously. Given the small size of a microarray, this format also reduces the volume of patient sample needed per test to potentially just a few microliters.

[0006] In the present disclosure, the environmentally sensitive fluorescent probe is single walled carbon nanotubes functionalized with small molecules or coated with polymers. The approach can be generalized for printing other environmentally sensitive fluorophores, such as dye molecules, metal nanoparticles, polymer dots, quantum dots or other articles familiar to specialists in fluorescence and diagnostics. As a result of the nearinfrared fluorescence-based nature of these nanotubes, this sensor is compatible with in vitro diagnostic tools such as microneedle arrays (each needle of which can be printed with a separate nanotube). Furthermore, this printed format may be compatible with lateral flow devices, being able to print directly onto the lateral flow surface. Inkjet printing ofnanotubes can be used to produce fluorescence-based printed nanotube sensors. Machine learning can be used to interpret test results.

[0007] Aspects of the present disclosure are directed to systems for classifying molecules of interest. The system interest may include a sensor array. The sensor array may include a substrate having a side upon which a sample having molecules of interest is configured to be disposed. The sensor array may include a plurality of fluorophore structures arranged along the side of the substrate, each of the plurality of fluorophore structures having a respective fluorescence response profile in reacting to the sample. The system may include a light source. The light source may emit the fluorescent light toward the substrate to illuminate the sample having molecules of interest. The sensor array may include an imaging device. The imaging device may acquire an image of a plurality of light signals corresponding to the plurality of fluorophore structures. The system may include a computing system having one or more processors coupled with memory in communication with the imaging device. The computing system may receive, via the imaging device, the image of the plurality of light signals from the plurality of fluorophore structures. The computing system may generate, using the plurality of light signals of the image, a response code defining a plurality of responses by the corresponding plurality of fluorophore structures to the fluorescent light due to the respective fluorescence response profile in each fluorophore structure of the one or more fluorophore structures. The computing system may determine a classification of the molecules of interest of the sample based on the response code. The computing system may provide an output to identify the classification of the molecules of interest of the sample.

[0008] In some embodiments, at least one of the plurality of fluorophore structures may be configured with an environmental sensitivity with respect to fluorescence in at least one of a spatial or temporal domain. The environmental sensitivity may correspond to a change in at least one of an absorbance intensity or a spectral characteristic. In some embodiments, the one or more fluorophore structures may include a carbon nanotube, a polymer dot, a quantum dot, or a fluorescent dye. In some embodiments, the respective fluorescence response profile of the one or more fluorophore structures may differ from at least one other fluorophore structure of the one or more fluorophore structures.

[0009] In some embodiments, at least one fluorophore structure of the plurality of fluorophore structures may include a carbon nanotube. The respective fluorescence response profile of the at least one fluorophore structure is based on at least one of a structural defects, chirality, single-walled, multi-walled, polymer coating, surfactant, peptide, protein, saccharide in the carbon nanotube. In some embodiments, the plurality of fluorophore structures may be grafted to, confined within, adjacent to, or colocalized with a binding agent. The binding agent may include at least one of antibodies, nanobodies, antigens, enzymes, aptamers, or molecularly imprinted polymers. In some embodiments, the plurality of fluorophore structures may be arranged in a one-dimensional line, a two- dimensional area, or three-dimensional volume of the substrate. In some embodiments, the substrate may be formed from at least one of a paper material, plastic material, a metal material, a glass material, a fabric material, a leather material, a semiconductor material, a metal oxide material, a polymer material, epidermis, lateral flow strip, aerogel, or a composite.

[0010] In some embodiments, the imaging device may include at least one of fluorescence microscope, a charge-coupled device (CCD), or a fiber optical device. In some embodiments, the computing system may apply a machine learning model to the plurality of responses of the response code to determine the classification of the molecules of interest in the sample. The computing system may identify the plurality of light signals of the image as corresponding to the one or more fluorophore structures, based on a position of each light signal of the plurality of light signals in the image and a position of each of the plurality of fluorophore structures on the substrate. The computing system may store, using one or more data structures, an association between the sample and the classification of the molecules of interest of the sample.

[0011] In some embodiments, the classification may identify at least one of: presence or extent of disease, presence or type of pathogenic organisms, presence of risk factors or comorbidities, prediction of prognosis, or clinically relevant parameters. In some embodiments, the classification may identify at least one of: presence or concentration of toxic compounds, drugs, explosives, or environmental pollutants. In some embodiments, the classification may identify at least one of: pH level, salt level or salt type, redox species,concentration of oxygen or other gas, temperature, presence of contaminants, or type of cells present.

[0012] In some embodiments, the sample may include at least one of a cell or a cell growth medium. The classification may identify at least one of: a presence or concentration of nutrients, presence or concentration of metabolites, cell confluency; pH, presence, or concentration of toxins, or a biological parameter. In some embodiments, the sample may include at least one of skin, saliva, blood, plasma, serum, urine, feces, sweat, breath, tears, serous fluids, subcutaneous fluid, biopsy samples, bacteria, viruses, fungus, drugs, cultured cells, or cell media. The sample may be obtained from one of a human subject or an animal subject. In some embodiments, the sample may include at least one of a food substance, oil, a perfume, a beverage, a construction material, or a storage container.

[0013] In some embodiments, the sensor array may be administered with a solution to modify the respective fluorescence response profile in each of the plurality of fluorophore structures. In some embodiments, the solution administered to the sensor array may include at least one of a ligand for a recognition agent in at least one of the plurality of fluorophore structures. In some embodiments, at least one of the plurality of fluorophore structures may include a recognition agent.

[0014] Aspects of the present disclosure are directed to systems for validating authenticity. The system may include a sensor array. The sensory array may include a substrate having a side upon which a sample having a pattern is configured to be disposed. The sensory array may include a plurality of fluorophore structures arranged along the side of the substrate. Each of the plurality of fluorophore structures having a respective fluorescence response profile in reacting to the sample. The system may include a light source to emit the fluorescent light toward the substrate to illuminate the sample. The system may include an imaging device to acquire an image of a plurality of light signals corresponding to the plurality of fluorophore structures. The system may include a computing system having one or more processors coupled with memory in communication with the imaging device. The computing system may receive, via the imaging device, the image of the plurality of light signals from the plurality of fluorophore structures, the plurality of light signals capturing the pattern on the sample. The computing system maygenerate, using the plurality of light signals of the image, a response code corresponding to the pattern. The response code may define a plurality of responses by the corresponding plurality of fluorophore structures to the fluorescent light due to the respective fluorescence response profile in each fluorophore structure of the plurality of fluorophore structures. The computing system may determine a validation of the sample as one of authenticated or unauthenticated based on the response code. The computing system may provide an output to identify the validation of the sample as one of authenticated or unauthenticated.

[0015] In some embodiments, the sample may include the pattern configured to at least one of: (i) establish an identity, (ii) validate an authenticity, or (iii) track a chain of ownership of the sample. In some embodiments, the plurality of fluorophore structures arranged in the pattern may respond with a unique fluorescence spectra to the emitted light. In some embodiments, the computing system may store, using one or more data structures, an association between the sample and the response code corresponding to the pattern.

[0016] Aspects of the present disclosure are directed to methods of classifying molecules of interest. The method may include disposing, onto a side of a substrate of a sensor array, a sample having molecules of interest. The sensor array may include a plurality of fluorophore structures arranged along the side of the substrate. Each of the plurality of fluorophore structures having a respective fluorescence response profile in reacting to the sample. The method may include emitting, by a light source, fluorescent light toward a side of a substrate to illuminate a sample having molecules of interest. The method may include acquiring, by an imaging device, an image of the plurality of light signals corresponding to the plurality of fluorophore structures. The method may include receiving, by a computing system, via the imaging device, the image of the plurality of light signals from the plurality of fluorophore structures. The method may include generating, by the computing system, using the plurality of light signals of the image, a response code defining a plurality of responses by the corresponding plurality of fluorophore structures to the fluorescent light due to the respective fluorescence response profile in each fluorophore structure of the plurality of fluorophore structures. The method may include determining, by the computing system, a classification of the molecules of interest of the sample based on the response code. The method may include providing, by the computing system, anoutput to identify the classification of the molecules of interest of the sample. In some embodiments, the method may include administering, on the sensor array, a solution to modify the respective fluorescence response profile in each of the plurality of fluorophore structures.

[0017] Aspects of the present disclosure are directed to methods of validating authenticity of samples. The method may include disposing, onto a side of a substrate of a sensor array, a sample. The sensor array may include a plurality of fluorophore structures arranged along the side of the substrate. Each of the plurality of fluorophore structures may have a respective fluorescence response profile in reacting to the sample. The method may include emitting, by a light source, fluorescent light toward a side of a substrate to illuminate a sample. The method may include acquiring, by an imaging device, an image of a plurality of light signals corresponding to the plurality of fluorophore structures, the plurality of light signals capturing the pattern on the sample. The method may include receiving, by a computing system, via the imaging device, the image of the plurality of light signals from the plurality of fluorophore structures. The method may include generating, by the computing system, using the plurality of light signals of the image, a response code corresponding to the pattern. The response code may define a plurality of responses by the corresponding plurality of fluorophore structures to the fluorescent light due to the respective fluorescence response profile in each fluorophore structure of the plurality of fluorophore structures. The method may include determining, by the computing system, a validation of the sample as one of authenticated or unauthenticated based on the response code. The method may include providing, by the computing system, an output to identify the validation of the sample as one of authenticated or unauthenticated. In some embodiments, the method may include administering, on the sensor array, a solution to modify the respective fluorescence response profile in each of the plurality of fluorophore structures.

[0018] In some embodiments, the method may include using a fluorophore mixture to generate the pattern on the sample using a fluorophore solution. In some embodiments, the method may include modifying the fluorophore mixture using at least one of: an inclusion of additives, a purification of the solution, a size separation, chromatography, or alight treatment. In some embodiments, the purification of the solution further comprises separation of carbon nanotubes with different chirality, surface treatment, and length or chemical modification.

[0019] Aspects of the present disclosure are directed to a sensor array. The sensor array may include a substrate having an area configured to support a sample. The sensory array may include a plurality of fluorophore sensors arranged along the substrate. Each of the plurality of fluorophore nanotubes may have a respective fluorescence response profile in reacting to the sample. Each of the plurality of fluorophore sensors may emit a corresponding light signal of a plurality of light signals. In some embodiments, at least one of the plurality of fluorophore structures may be administered with a solution to modify the respective fluorescence response profile.BRIEF DESCRIPTION OF THE DRAWINGS

[0020] FIG. 1 depicts a block diagram of an example system for classifying samples, in accordance with one or more implementations;[0021 J FIG. 2 depicts a block diagram of a process for illuminating samples in the system for classifying samples, in accordance with one or more implementations;

[0022] FIG. 3 depicts a block diagram of a process for classifying the molecules of interest in the system for classifying samples, in accordance with one or more implementations;

[0023] FIG. 4A depicts a diagram of an example diagnostic response code, in accordance with one or more implementations;

[0024] FIG. 4B depicts a diagram of a nano-sensor array, in accordance with one or more implementations;

[0025] FIG. 5 depicts a flow diagram of a method for classifying molecules of interest, in accordance with one or more implementations;

[0026] FIG. 6 depicts a flow diagram of a method for validating authenticity of samples, in accordance with one or more implementations; and

[0027] FIG. 7 depicts a block diagram of a server system and a client computer system, in accordance with one or more implementations.DETAILED DESCRIPTION

[0028] Following below are more detailed descriptions of various concepts related to, and embodiments of, systems and methods for detecting molecules of interest using fluorophore sensor arrays. It should be appreciated that various concepts introduced above and discussed in greater detail below may be implemented in any of numerous ways, as the disclosed concepts are not limited to any particular manner of implementation. Examples of specific implementations and applications are provided primarily for illustrative purposes.

[0029] Section A describes systems and methods for classifying samples using fluorophore sensor arrays.

[0030] Section B describes a network environment and computing environment which may be useful for practicing various embodiments described herein.A. Systems and Methods for Classifying Samples Using Fluorophore Sensor Arrays

[0031] Presented herein is a two-dimensional array, in which each pixel is covered with ink containing different environmentally sensitive fluorescent carbon nanotubes. The fluorescence spectrum of each pixel can be measured using a fluorescence microscope, a charge-coupled device (CCD) camera, or other fluorimeter. Upon addition of an analyte, even in complex medium, such as serum, saliva, or urine, each pixel responds differently to the analyte and media components, pH, polarity change, oxygen level, etc., due to differences in ink composition (nanotube coating and defects, and presence of surfactants and other additives).

[0032] The unique response of the whole array to a particular analyte or mix of analytes represents that analyte’s spectral ‘fingerprint’, which can be used to identify theanalyte, pattern, or medical condition. In this way, the array resembles a ‘QR code’, with different analytes generating unique fluorescence patterns.

[0033] Analysis of array response can be performed by fluorescent microscopy by using a charge-coupled device (CCD) camera, a fiber optical device, a mobile phone camera, or by other techniques familiar to experts in the field.

[0034] A neural network is trained to recognize array responses to specific analytes or physico-chemical change. For example, by training the array using serum samples from patients with ovarian cancer versus serum from healthy donors and patients with other conditions, the sensor can be made to diagnose ovarian cancer.

[0035] This array can serve as a general sensor. A single array with a sufficiently high number of unique pixels can be trained to recognize multiple different conditions. Following addition of a single patient sample, spectral analysis of the array would then predict the probability of the patient having each condition for which the sensor was trained. This could be used for early-stage screening of multiple conditions, with positive results being followed up with further testing.

[0036] Arrays can be prepared via directly printing pre-made ink, wherein different pixels can be composed of different inks. Arrays can be prepared via printing a generic ink mixture on every pixel and then printing additional reagents on top of the pixels to modify the pixel behavior. Multiple inks can be overlaid onto the pixels to increase complexity for anti-counterfeiting or to alter or tune the fluorescence response upon addition of analyte.

[0037] In some applications, pixels can be functionalized with specific recognition agents such as antibodies, aptamers, molecularly imprinted polymers, etc. The agents may be physically wrapped or adsorbed onto the nanotubes, or covalently linked or grafted onto the nanotube surface via, for example, radical chemistry or other coupling chemistry, or via incorporation into gels such as microgel or aerogel.

[0038] A nanotube array may be used as an anti -counterfeiting label. Each pixel or group of pixels may have a different fluorescence spectrum. The different fluorescence spectra may be due to differences in nanotube ink composition. The different fluorescencespectra may prevent forgery. Custom ink may be synthesized using additive compounds, which can affect the fluorescence spectrum of each ink. Custom ink may be synthesized by filtering a generic ink formulation through a custom separation column (e.g., nanotubes with specific dimensions or surface treatment pass through).

[0039] The physical form of the array may approximately be micrometer to millimeter-sized dots of fluorescent ink printed onto paper, glass, polymer sheets, fabric, or another two-dimensional substrate. However, the array could also be printed directly onto the bottom of a microtiter plate well, a cell-culture flask, dish, or other liquid-holding receptacle, depending on application.

[0040] The array can be applied for analysis of liquid or gas samples. The array can be applied for single use or for continuous monitoring of analytical samples. The array could also be used for detection of specific molecules of interest, such as drugs, explosives, and environmental pollutants. This would involve training the neural network using samples of known concentrations of the target molecule in order to recognize the spectral fingerprint of that molecule.

[0041] The array could be printed onto a microneedle surface, with each needle or group of needles representing one pixel. This would facilitate real-time monitoring of biomarkers or drugs within interstitial fluid. The array could be printed onto a wearable sensor in order to monitor changes in the composition of sweat. The array could be printed onto a lateral flow device in order to separate components of the serum, urine, or saliva prior to fluorescence measurement.

[0042] By incorporating this sensor into cell-culture flasks, it is possible to constantly monitor the presence and concentrations of biomolecules, such as metabolites, and to detect contamination such as mycoplasma, bacteria, and fungus. By incorporating the sensor into shipping packaging or freight containers, it is possible to detect the presence of molecules such as drugs or explosives, with applications in border control.

[0043] In addition, the array could be used as an anti-counterfeiting label, due to the difficulty of reproducing a specific array without knowing the exact composition of each pixel. The authenticity of the array could be demonstrated by adding solutions or volatilesof known composition in order to reveal their spectral fingerprints. The composition of the array and of the test solutions or mixture would be predefined information for the entity producing the anti -counterfeiting labels.

[0044] A nanotube array used as an anti -counterfeiting label may lack any environmental sensitivity. Each pixel or group of pixels may have a different fluorescence spectrum (due to differences in nanotube ink composition), providing sufficient complexity to prevent forgery. For the purposes of using the nanotube arrays as anti -counterfeiting labels, custom ink may be synthesized by different organizations using additive compounds which affect the fluorescence spectrum of each ink (the composition of which may be specific for that organization), or by filtering a generic ink formulation through a custom separation column (the composition of which may be specific) such that only nanotubes with specific dimensions or surface treatments pass through.

[0045] Arrays can be any size — micrometer scale for high throughput imaging using, e.g., fluorescence microscopy, or millimeter or centimeter scale for analysis using point-of-care devices such as cameras or mobile phones. Arrays do not need to be two dimensional — they could be a one-dimensional barcode, or another pattern entirely. Arrays can be produced via inkjet printing, micro-pipetting, aerosol printing, screen printing, or other technologies. Inkjet printing may be the most suitable for production of low-cost arrays.

[0046] Carbon nanotubes are not necessary for this array; any environmentally sensitive fluorophore would work in the same way (e.g., fluorescent dyes, quantum dots, polymer dots, carbon dots or combinations of the above). However, the advantage of using carbon nanotubes is the opportunity to perform analysis in the near infrared (NIR) or infrared (IR) optical window, with minimal interference from biological and environmental matrixes.

[0047] If carbon nanotubes are used, they may be either single-walled carbon nanotubes or multi-walled carbon nanotubes. If nanotubes are used as fluorophores, they may be individually wrapped with DNA, polymers, surfactants (both ionic and non-ionic), peptides, saccharides, or other molecules. If nanotubes are used, different pixels mayconsist of different chirality nanotubes, with the same or different coating agents in each pixel.

[0048] Pixels can be individually multiplexed, containing multiple different fluorophores (e.g., different chirality nanotubes, or mixtures of nanotubes and dyes or other fluorophores). These fluorophores could potentially interact with each other differently in the presence of analyte (e.g., increased or decreased non-radiative energy transfer efficiency). The composition of several pixels can be repeated in the same array to increase reproducibility and accuracy of the analysis.

[0049] The sensor may have each pixel providing a unique or semi-unique response to a particular analyte. In some embodiments, each pixel may be created using a unique fhiorophore. In some embodiments, the same fluorophore can be deposited onto multiple spots on a substrate that has varying physical properties at different locations. For example, this could take the form of a polymeric sheet with gradients in pore size and hydrophobicity along each axis. This sheet could be the printing substrate itself or could be placed over the fluorophore such that the analyte has to pass through the sheet in order to reach the fluorophore.

[0050] In some embodiments, the array may be produced by printing an array of identical nanotube pixels, and then printing an array of another substrate, such as DNA, peptides, or proteins on top of the nanotubes. Nanotube microarrays can potentially be prepared via laser-assisted alignment of nanotubes, with different pixels showing different alignments. If the array is printed onto a lateral flow device, every pixel could consist of the same compound. Differences in fluorescence response would then be caused by different components of the serum, saliva, or urine advancing along the lateral flow device at different rates, resulting in different pixels being exposed to different fractions of the analyte.

[0051] In some applications, pixels can be functionalized with specific recognition agents, such as antibodies, aptamers, and molecularly imprinted polymers, among others. Arrays can be printed on paper, plastic, metal, glass, semiconductors, metal oxide, skin (via temporary or permanent tattoos), and other two- or three-dimensional substrates. Arrayscan be produced via inkjet printing, aerosol printing, screen printing, micro-pipetting, stamping, or other technology. In some applications, pixels can be functionalized with specific recognition agents, such as antibodies, aptamers, molecularly imprinted polymers, etc. These agents may be physically wrapped or adsorbed onto the nanotubes, or covalently linked or grafted onto the nanotube surface via, for example, radical chemistry or other coupling chemistry, or via incorporation into gels such as microgel or aerogel.[00521 Additionally, arrays can be prepared either via directly printing pre-made ink wherein different pixels are composed of different inks or by printing a generic ink mixture on every pixel and then printing additional reagents on top of these pixels to further modify their behavior. For all applications of the array, multiple inks can be overlaid onto the same pixels, either to increase complexity for anti -counterfeiting, or to alter or tune the fluorescence response upon addition of analyte.[0053 J Referring now to FIG. 1, depicted is a block diagram of an example system 100 for classifying samples. In overview, the system 100 can include at least one image processing system 105, at least one sensor array 110 (e.g., illustrated in cross-sectional view), at least one light source 115, at least one imaging device 120, and at least one display 125, communicatively coupled with one another via at least one network 130. The image processing system 105 may include at least one image parser 135, at least one code generator 140, at least one sample classifier 145, at least one output handler 150, at least one classification model 155, and at least one database 160, among others. Each of the components in the system 100 as detailed herein may be implemented using hardware (e.g., one or more processors coupled with memory), or a combination of hardware and software as detailed herein in Section B.

[0054] In further detail, the image processing system 105 may (sometimes herein generally referred to as a computing system or a server) be any computing device comprising one or more processors coupled with memory and software and capable of performing the various processes and tasks described herein. The image processing system 105 may be in communication with the sensor array 110, the light source 115, the imaging device 120, the display 125, and other devices, via the network 130. The image processing system 105 may be situated, located, or otherwise associated with at least one server group.The server group may correspond to a data center, a branch office, or a site at which one or more servers corresponding to the image processing system 105 are situated. The image processing system 105 may store, using one or more data structures, an association between the sample and the classification of the molecules of interest of the sample.

[0055] Within the image processing system 105, the image parser 135 may retrieve, identify, or receive images of samples via the sensor array 110 from the imaging device 120 to be processed at the image processing system 105. The code generator 140 may generate codes from the images received by the image parser 135. The sample classifier 145 may determine a classification of molecules in the sample using the codes. The output handler 150 may provide information based on the classification of molecules in the sample. The classification model 155 may be any type of machine learning model or artificial intelligence (Al) algorithm to classify molecules or interest in an image. In general, the classification model 155 may have at least one input and at least one output. The output and the input may be related via a set of weights. The input may be at least one image. The output may include the classification of the molecules from the application of the classification model 155 onto the input image in accordance with the set of weights.

[0056] The set of weights of the classification model 155 may define corresponding parameters to be applied to the input image to generate the output image. In some embodiments, the set of weights may be arranged in one or more transform layers. Each layer may specify a combination or a sequence of applications of the parameters to the input and resultant. The layers may be arranged in accordance with the machine learning algorithm or model for the classification model 155. For example, the classification model 155 such as a clustering algorithm (e.g., A means clustering), a regression algorithm (e.g., linear or logistic regression), a random forest, a decision tree, a support vector machine (SVM), a Naive Bayesian classifier, or an artificial neural network (e.g., convolutional neural network architecture), among others. The classification model 155 may have been initialized, trained, and established to detect the classification using training data (e.g., in accordance with supervised learning techniques).

[0057] The sensor array 110, the light source 115, and the imaging device 120 may be used to conduct fluorescent imaging, spectroscopy, or microscopy in evaluating asample. The sensor array 110 may include a set of fluorophore structures (sometimes herein referred to as pixels). Each of the fluorophore structures may have different fluorescence responses to react differently to a sample placed thereon. The light source 115 may radiate, produce, or otherwise emit fluorescent light to illuminate a sample and the fluorophore structures in the sensor array 110. The fluorophore structures on the sensor array 110 may be used to identify molecules of interest in the sample (e.g., identifying biomarkers for cancer or pollutants in a liquid sample), confirming the composition of a sample (e.g., a drug composition), validating the authenticity of the sample (e.g., as an anti-counterfeit measure), establish an identity (e.g., source, origin, or manufacturer) of the sample, track a chain of ownership of the sample (e.g., establish provenance), and enforcing security policies, among others. The sensor array 110 may be situated in a wide variety of applications, such as diagnostic, anti -counterfeiting, validating compositions, biomarker detection, microfluidic applications, or security applications, among others.

[0058] The imaging device 120 (sometimes herein generally referred to as an image acquirer) may be any device to acquire images of samples illuminated by the light source 115 through the sensor array 110. The imaging device 120 may be, for example, a fluorescence microscope, a charge-coupled device (CCD), or a fiber optical device, among others. The light source 115 and the imaging device 120 may be in communication with the image processing system 105 via the network 130.

[0059] The display 125 may be communicatively coupled with the image processing system 105 or any other computing device comprising one or more processors coupled with memory and software and capable of performing the various processes and tasks described herein. The display 125 may display, render, or otherwise present any information provided by the image processing system 105 or the images of samples acquired via the imaging device 120.

[0060] Referring now to FIG. 2, depicted is a process 200 illuminating samples for detecting molecules of interest therein. The process 200 may include or correspond to operations in the system 100 to illuminate a sample and acquire images through the sensor array. As depicted, the sensor array 110 may have or include at least one substrate 205. The substrate 205 may comprise any material, such as a paper material, plastic material(e.g., polyethylene, polypropylene, polyvinyl chloride, polystyrene, or polyethylene terephthalate), a metallic material (e.g., aluminum, steel, copper, titanium, or nickel), a ceramic material (e.g., alumina, zirconia, silicon carbon, or magnesium oxide), a glass material (e.g., quartz glass, lead crystal, silicate glass, or tempered glass), a semiconductor material (e.g., silicon, germanium, gallium arsenide, indium phosphide, or cadmium telluride), a metal oxide material, a polymer material, epidermal material (e.g., human skin), a gel (e.g., aerogel), or a composite, among others. In some embodiments, the substrate 205 may be part of another device. For example, the substrate 205 may be part of a lateral flow strip that is part of a diagnostic device, including a sample pad, a conjugate pad, a test line, and a control line. A fluid to be evaluated may be placed on the sample pad and flow from the sample pad through the lateral flow strip upon which the substrate 205 is disposed.

[0061] The substrate 205 may have at least one first side 210 and at least one second side 215. The first side 210 may correspond to one lateral surface of the substrate 205. The second side 215 may be opposite of the first side 210 and may correspond to another lateral surface of the substrate 205. The first side 210 may correspond to the surface of the substrate 205 facing the light source 115 and on which fluorescent light (shown in dotted line) is to be illuminated. The second side 215 may correspond to the surface of the substrate 205 away from the light source 115. The substrate 205 may be of any shape, such as circular, regular, triangular, pentagonal, hexagonal, polygonal, or irregular, among others. The substrate 205 may have any dimension, for example, ranging between 10 nm and 10 cm, among others. The first side 210 and the second side 215 may have the same dimension or different dimensions. While described herein as having two sides, the substrate 205 may have any number of form factors. For example, the substrate 205 may correspond to a particular surface or area upon a human skin or tips of a set of microneedles, among others.

[0062] At least one sample 225 may be disposed on at least one of the first side 210 or the second side 215 (e.g., as shown) of the substrate 205. The sample 225 may be any material or object to be analyzed by the image processing system 105 using the sensor array 110 for molecules of interest. The sample 225 may be of an item, object, or material in any phase, such as liquid, solid, or gas, among others, or any combination thereof. In someembodiments, the sample 225 may include a biological sample, such as skin, saliva, blood, plasma, serum, urine, feces, sweat, breath, tears, serous fluids, subcutaneous fluid, biopsy samples, bacteria, viruses, fungus, drugs, cultured cells, or cell media, among others. The biological sample may be acquired or obtained from a human subject or an animal subject. In some embodiments, the sample 225 may include a non-biological sample (e.g., a drug, a forensic sample, environmental pollutant, explosive, consumer good, product of manufacture, or any other item), among others. For example, the sample 225 may be an item of value, such as an identification document (e.g., passport or driver’s license), currency (e.g., coin or paper notes), a weapon, a bag, a computing device (e.g., tablet, smartphone, laptop, or desktop), or a writing utensil, among others. In some embodiments, the sample 225 may include a food substance (e.g., fruit, vegetables, grains, plants, meats, cooking oil or derivatives therefrom), fuel (e.g., motor oil, gasoline, or diesel), a perfume (e.g., fragrant oils, aroma compounds, fixatives, or solvents, or any combination thereof), a beverage (e.g., wine, beer, liquor, soda, or water), a construction material (e.g., wood, concrete, brick, cement, steel, glass, stone, or masonry), or a storage container (e.g., metallic, polymer, or wood material), among others.

[0063] In some embodiments, the sample 225 may be attached, affixed, or otherwise joined to at least one of the first side 210 or the second side 215 of the substrate 205 of the sensor array 110. For example, the sample 225 may be affixed to the first side 210 or the second side 215 of the substrate 205 of the sensor array 110 using an adhesive. In this example, the sensor array 110 affixed to the sample 225 may be used as a barcode to determine an identity, validate an authenticity, or track a chain of ownership of the sample 225, among others. The sample 225 (e.g., cells or cell growth media) may also be placed in contact with the first side 210 or the second side 215 of the substrate 205.

[0064] When the sample is biological material, the sample 225 may be obtained from a subject. The subject may be a human or an animal at risk of cancer or suffering from a disease or cancer. The disease may include, for example, a blood disease (e.g., anemia, leukemia, hemophilia, sickle cell disease), diabetes, kidney disease, a liver disease (e.g., hepatitis or cirrhosis), or a thyroid disorder, among others. The cancer may include, for example, a bone cancer (e.g., osteosarcoma, chondrosarcoma, chordoma, or Ewingsarcoma), a lung cancer (e.g., non-small cell lung cancer (NSCLC) or Small cell lung cancer (SCLC)), a breast cancer (e.g., Ductal carcinoma in situ (DCIS), invasive ductal carcinoma (IDC), Lobular carcinoma in situ (LCIS), and Invasive lobular carcinoma (ILC)), or a colon cancer (e.g., adenocarcinoma, Gastrointestinal carcinoid tumors, lymphomas), among others. The cancer may be present in the sample 225 in the form of tumorous cells. The sample 225 may be taken, collected, or otherwise obtained from at least one anatomical site associated with the disease or cancer within the subject. The sample 225 can include tissue, bone, cartilage, or any other portion of the organ from the anatomical site. The anatomical site may be a primary site or a secondary (e.g., metastasized) site for the cancer. For example, when the subject is at risk of or suffering from thyroid cancer (e.g., papillary, follicular, medullary, or anaplastic), the clinician examining the subject may collect the samples 225 via biopsy from the thyroid of the subject.

[0065] The sensor array 110 may include a set of fluorophore structures 220 A-N (hereinafter generally referred to as fluorophore structures 220) disposed, situated, or arranged along the substrate 205. Each of the fluorophore structures 220 (sometimes herein referred to as pixels) may span or extend at least partially (e.g., as depicted) or fully between the first side 210 and the second side 215 of the substrate 205. The set of fluorophore structures 220 may be disposed, arrayed, or otherwise arranged in a onedimensional line (e.g., a line or a curve along the substrate 205), a two-dimensional (e.g., across a region of a surface of the substrate 205), or a three-dimensional volume (e.g., with some fluorophore structures 220 deposited on top of one another within the substrate 205). In some embodiments, the set of fluorophore structures 220 may be disposed, arrayed, or otherwise arranged along the substrate 205 in a pattern. The pattern may be used to establish an identity of the sample 225 (e.g., to which the sensor array 110 is affixed), validate an authenticity of the sample 225, or track a chain of ownership of the sample 225, among others. For example, the fluorophore structures 220 in the sensor array 110 may be used as a barcode affixed to a product or item corresponding to the sample 225 to establish the identity, validate the authenticate, or track the chain of ownership of the product or item.

[0066] Each of the fluorophore structures 220 may include, for example, a carbon nanotube, a polymer dot, a quantum dot, a fluorescent dye, or any fluorophores, amongothers. The carbon nanotube may include rolled-up sheets of graphene, single-walled nanotubes (SWNTs), or multi -walled nanotubes (MWNTs). The size of the quantum dots or polymer dots can be adjusted to change the color of the light emitted or to emit light at different wavelengths. The fluorescent dye may re-emit light upon light excitation. In some embodiments, the fluorophore structures 220 may be grafted to, confined within, adjacent to, or otherwise colocalized with one or more binding agents. The binding agents may include, for example, antibodies, proteins, peptides, nanobodies, antigens, enzymes, aptamers, or molecularly imprinted polymers, among others.

[0067] The set of fluorophore structures 220 may be arranged in any pattern, such as a linear formation, grid formation, staggered formation, a cross formation, or irregular pattern. Each fluorophore structure 220 may correspond to a respective portion along the first side 210 (or the second sides 215) off the substrate 205. The portion may be of any shape, such as circular, regular, triangular, pentagonal, hexagonal, polygonal, or irregular, among others. The diameter of the fluorophore structures 220 may be of any dimension ranging between nanometers and millimeters. For example, the diameter of the fluorophore structures 220 may range between 0.5-3 nm for SWNTs, between 3-100 nm for MWNTs, between 1-10 nm for quantum dots, between 10-100 nm for polymer dots, and between 1- 10 pm, among others. Each fluorophore structure 220 may be separated from at least one other fluorophore structure 220 at a distance. For instance, one fluorophore structure 220 may have a distance of between 1 nm and 1 cm, relative to the adjacent fluorophore structure 220.

[0068] Each of the fluorophore structures 220 may have or be characterized by a unique fluorescence response profile to the fluorescent light. In the sensor array 110, at least one fluorophore structure 220 may have a fluorescence response profile different from another fluorophore structure 220. In some embodiments, at least one of the fluorophore structures 220 may be configured with an environmental sensitivity with respect to fluorescence in at least one of a spatial or temporal domain. The environmental sensitivity may correspond to, may be correlated with, or otherwise may include a change in at least one of an absorbance intensity or a spectral characteristic of the fluorophore structure 220. For example, when the sensor array 110 is used as a barcode affixed to a productcorresponding to the sample 225, each of the fluorophore structures 220 may have a different fluorescence response profile. Due to the different response profile or environmental sensitivity (or both), each fluorophore structure 220 may generate fhiorophores with unique fluorescence spectra when affixed to the sample 225.

[0069] Upon placement, disposal, or addition of the sample 225 onto the first side 210 of the substrate 205, the fluorophore structures 220 can undergo a reaction to the sample 225, changing the fluorescent properties of the fluorophore structures 220. The fluorescence response profile may identify, define, or characterize a change in fluorescence properties of the fluorophore structure 220 in response to undergoing a reaction (e.g., a physicochemical reaction) with the sample 225. Each fluorophore structure 220 may absorb the fluorescent light emitted upon the first side 210 at a particular wavelength and emit another light signal in accordance with the fluorescence properties of the fluorophore structure 220. The reaction may be a change in the intensity, color, or pattern of the transmitted light. The sample 225 itself may be used to treat the set of fluorophore structures 220 to alter, set, or otherwise change the fluorescent properties of the fluorophore structures 220.

[0070] The reaction of the individual fluorophore structures 220 with the sample 225 may include, for example, an electrostatic interaction, a hydrophobic interaction, a specific interaction, an oxidation reaction, a reduction reaction, or an ionic reaction, among others. Electrostatic interactions may correspond to the attraction or repulsion between charged particles between the fluorophore structure 220 and the sample 225. Hydrophobic interactions may correspond to interactions between nonpolar molecules of the fluorophore structure 220 in the presence of water in the sample 225. Specific interactions refer to certain types of interactions between specific molecules or functional groups in the sample 225 with the fluorophore structure 220 (e.g., binding agents in the nanotube to specific antibodies in a biological sample). Oxidation may correspond to a reaction in which fluorophore structure 220 loses electrons or changes its oxidation state. Reduction may correspond to the gain of electrons by the fluorophore structure 220. An ionic interaction may correspond to the electrostatic interactions to form positive or negatively charged ions between the fluorophore structure 220 and the sample 225.

[0071] The fluorescence response profile may, for example, include an excitation wavelength, an emission wavelength, a quantum yield, a Stokes’ shift, or dark fraction, among others. The excitation wavelength may define a range of wavelengths of the incoming fluorescent light the materials in the fluorophore structure 220 can absorb. The emission wavelength may define a range of wavelengths at which the fluorophore structure 220 can emit the light signals. The quantum yield may identify a ratio of fluorescent light photons that are emitted through fluorescence through the fluorophore structure 220. The Stokes’ shift may define a difference between the excitation and emission wavelengths. The dark fraction may identify a proportion of molecules active in the fluorophore structure 220 for fluorescence emission.

[0072] The fluorescence response profile may be dependent on specific properties of the fluorophore structure 220 and the molecular interactions occurring within or around the fluorophore structure 220. In some embodiments, when the fluorophore structures 220 are carbon nanotubes, the differences in the fluorescence response profile may be due to differences in: structural defects, chirality, single-walled, multi-walled nanotubes, polymer coating, surfactant, peptide, protein, saccharide, or other modification to carbon nanotubes, among others. The fluorophore structures 220 can be structured to be sensitive to a particular molecule. For example, when anti-counterfeit inks or chemical makers are applied to a sample, the fluorescent light can create a specific pattern or color change that is difficult to replicate. The sensor array 110 may be exposed to additional solutions or gases to instigate, initiate, or otherwise initiate a change in the fluorescent profiles of the fluorophore structure 220. With the change to pre-identified fluorescent profiles, the fluorophore structures 220 on the sensor array 110 may be used for various purposes, including validation. The fluorescence response profile of each of the fluorophore structures 220 may be dependent on the structure of the fluorophore structure 220 itself, such as the presence of a coating agent, a defect, a chirality, single-walled, multi-walled, polymer surfactant, peptide, or saccharide.

[0073] For the structures affecting fluorescence response profile, the coating agent may correspond to a substance used to modify or encapsulate fluorophore structure 220 to modify the fluorescence response profile. The defect may correspond to inserted ormanufactured abnormalities or imperfections (e.g., impurities, clustering, photobleaching, or inhomogeneity) within the fluorophore structure 220. The chirality may correspond to an arrangement of molecules in the structure of the fluorophore structure 220, such as dichroism, asymmetry, or mirroring, among others. The single-walled or multi-walled may correspond to a structure of walls of molecules in the fluorophore structure 220, such as single-walled carbon nanotubes (SWCNT) and multi-walled carbon nanotubes (MWCNT). The presence of polymers may correspond to inclusion of polymer molecules within the molecules of the fluorophore structure 220. The presence of surfactant (also referred to herein as surface-active agent) may correspond to inclusion of compounds to modify solubility, stability, or dispersion of molecules within the fluorophore structure 220. The presence of peptide may be to introduce chain of amino acids into the fluorophore molecules in each fluorophore structure 220.

[0074] The arrangement of the fluorophore structure 220 along the first side 210 of the substrate 205 and the fluorescence response profile of each fluorophore structure 220 can be set or configured based on an application. For example, for the purposes of anticounterfeit labeling, the substrate 205 may correspond to a surface of an item (e.g., as a label), and the set of fluorophore structures 220 may be arranged in a matrix barcode pattern (e.g., a bar code, a quick-response (QR) code, or a universal product code (UPC)) along the surface. The distinct fluorescence patterns can form a QR code or fingerprint. The QR code or fingerprint can be used to identify molecules, specific analytes, patterns, or medical conditions, among others. Each fluorophore structure 220 may have a different fluorescence response profile, with various additives and structural elements to set the fluorescence properties of the fluorophore structure 220 in reacting with the molecules of the underlying items. The arrangement and setting of the response profiles may make it difficult for another party to replicate the substrate 205 forming the label, or the item itself. In some embodiments, the arrangement of the plurality of fluorophore structures 220 in accordance with the pattern may be used to produce a unique fluorescence spectra in response to light.

[0075] The sensor array 110 itself may be assembled, created, or otherwise manufactured in accordance with any number of techniques. For example, the sensor array110 may be manufactured by printing ink (e.g., carbon nanotube-based ink) to place, deposit, or otherwise arrange onto a material forming the substrate 205. The ink may correspond to the set of fluorophore structures 220 along the first side 210 of the substrate 205. In some embodiments, the ink may initially be generic across the set of fluorophore structures 220, and then subsequently agents may be added to individually modify the fluorescence response profiles. In some embodiments, the ink may be particular to each respective fluorophore structure 220, synthesized using additive compounds that affect the fluorescence spectrum of each ink (e.g., allowing for a tailored response profile for each ink). In some embodiments, the set of fluorophore structures 220 may be produced, created, or otherwise formed using one or more a fluorophore mixture (e.g., in the form of a solution), particularly an entity. The fluorophore mixture may be modified using at least one an inclusion of additives, a purification of the solution, a size separation, chromatography, or a light treatment, among others. The purification of the solution further comprises separation of carbon nanotubes with different chirality, surface treatment, and length or chemical modification.[0076J The fluorophore mixture used to form the fluorophore structures 220 may result in each fluorophore structure 220 having a unique fluorescence response profile. By configuring the fluorophore structures 220 in this manner, the set of fluorophore structures 220 of the sensor array 110 may form a unique bar code to generate fluorophores with unique fluorescence spectra when affixed to the sample 225. As each mixture may vary from one another and may also differ, the fluorophore structures 220 may be unique to the particular sensor array 110, making it difficult to reproduce the barcode (e.g., as represented by the set of fluorophore structures 220). The use of different form factors (e.g., two- dimensional or three-dimensional) for the fluorophore structures 220 may also increase the difficulty of reproducing the barcode corresponding to the set of fluorophore structures 220.

[0077] In some embodiments, a test solution 230 (sometimes herein referred to as a solution or additive) may be applied, provided, or otherwise administered to the sensor array 110. The test solution 230 may alter, change, or otherwise modify the fluorescence response profile of one or more of the fluorophore structures 220 of the sensor array 110. In some embodiments, the test solution 230 may be administered to the sample 225 to reactwith the fluorophore structures 220 of the sensor array 110. The test solution 230 may include an additive or chemical marker to react with the fluorophore structures 220 to induce spectral changes. The additive may include, for example, a surfactant (e.g., sodium dodecyl sulfate or sodium cholate), a polymer (e.g., polyethylene glycol (PEG), polyvinylpyrrolidone (PVP), and polystyrene sulfonate (PSS)), a functional group (e.g., carboxyl, hydroxyl, or amine), a metal ion (e.g., silver or platinum), a dye (e.g., rhodamine, fluorescein, or cyanine), or biomolecules (e.g., deoxyribonucleic acid (DNA) protein or peptide), among others. In some embodiments, the test solution 230 includes a ligand to bind, conjugate, or otherwise react with the fluorophore structures 220. The ligand may include, for example, a receptor ligand (an agonist or antagonist ligand), an enzyme ligand, a transport protein, an allosteric ligand, or an ionic ligand, among others. The ligand may bind, conjugate, or otherwise react with the recognition agents in the fluorophore structures 220, such as antibodies, aptamers, and molecularly imprinted polymers, among others.

[0078] The test solution 230 can be administered to the sensor array 110 to induce changes to the fluorescence response profile (e.g., spectral changes), unique to the combination of fluorophore structures 220 in the sensor array 110 and the composition of the test solution 230. The spectral changes can serve as a validation technique to verify the authenticity of the sensor array 110. By analyzing the distinct patterns produced by the fluorophore structures 220, it becomes possible to distinguish genuine sensor arrays (e.g., the sensor array 110) from counterfeits. The pattern created by the interaction between the test solution 230 and the fluorophore structures 220 may ensure that authorized entities can accurately reproduce or verify the sensor array 110. The addition of the test solution 230 may provide an additional layer of verification that is difficult to replicate without access to the exact formulation.

[0079] In some embodiments, the fluorophore structures 220 may be conjugated to a recognition agent. The recognition agent may include molecules or compounds to identify or bind to particular targets, be used to induce a particular fluorescence response in the fluorophore structures 220. In some embodiments, the recognition agents may be used to induce a particular fluorescence response in the fluorophore structures 220, when administered with the test solution 230. The recognition agent may include, for example,antibodies, nanobodies, aptamers, DNA, or molecularly imprinted polymers, among others, to selectively bind to target molecules. The conjugation process can include attaching recognition agents to the surface of fluorophore structures 220. For example, antibodies can target and bind specific proteins or antigens, for use of the sensor array 110 in biomedical diagnostics. Nanobodies may be smaller and more stable than antibodies, but they can provide similar binding capabilities with the added advantage of better tissue penetration and reduced immune response. Aptamers can bind to a wide range of targets with high specificity and affinity, providing a versatile tool for detecting various biomolecules. By incorporating recognition agents, the fluorophore structure 220 of the sensor array 110 can become highly selective and capable of detecting minute concentrations of analytes. In some implementations, the test solution 230 may contain ligands specific for the recognition agent, such as antigens complementary to the antibody, complementary DNA sequences, or the template molecule of the molecularly imprinted polymer. The ligands in the test solution 230 can be selected to interact with their corresponding recognition agents on the sensor array 110, thereby reducing the likelihood of false positives or nonspecific binding.[0080J In some embodiments, the specific recognition agent can be added, included, or otherwise disposed in a defined pattern on the sensor array 110. The placement of the recognition agent can be relative to the fluorophore structures 220, such as within, atop of, or adjacent to at least one of the fluorophore structures 220. In some embodiments, multiple recognition agents can be added, included, or otherwise arranged in the fluorophore structures 220 of the sensory array 110. For example, one recognition agent can be printed on the sensor array 110 in one or more of the fluorophore structures 220, and be obscured with other non-specific recognition agents. The placement can allow the specific ligands in the test solution 230 to interact with their corresponding recognition agents, leading to distinct spectral changes. When the ligands bind to their specific recognition agents, the resulting fluorescence pattern can reveal the pre-defined arrangement of the specific recognition agents. The pattern of spectral changes can then serve as a unique validation technique, confirming the authenticity of the sensor array 110. By using a mixture of specific and non-specific recognition agents, it can become difficult for unauthorized parties to replicate the precise pattern and spectral response of the sensor array 110, thereby enhancing the security and reliability of the validation process.

[0081] In some embodiments, the scrambled or random DNA sequences (an example of a recognition agent) may be printed on the sensor array 110 relative to the fluorophore structures 220. For instance, the recognition agent may be printed in a specific pattern (e.g., a brand logo or identifier) atop the fluorophore structures 220 conjugated to a specific DNA sequence. The use of scrambled or random DNA sequences conjugated to fluorophore structures 220 and printed across the sensor array 110 can create a uniform to mask the pattern, enhancing the security of the code, making it challenging for unauthorized entities to discern the exact sequence and pattern of the specific recognition agents.

[0082] Administering the sensor array 110 with the test solution 230 containing complementary DNA can reveal the pattern. The specific pattern (e.g., brand or company logo) printed with fluorophore structures 220 conjugated to DNA sequences, can be revealed when the test solution 230 containing the complementary DNA is applied. The resulting fluorescence pattern can highlight the pattern against the background, providing a clear and unique validation that is difficult to replicate without knowledge of the DNA sequence. The complexity added by the non-specific DNA-conjugated fluorophore structures 220 may obscure the exact composition and arrangement of the specific DNA sequences. The incorporation of non-specific DNA-conjugated fluorophore structures 220 as an additional layer of obfuscation further protects the integrity of the sensor array 110, ensuring that those with the correct test solution 230 can validate the authenticity of the pattern.

[0083] In some embodiments, the sensor array 110 may be arranged, disposed of, or otherwise situated within a vessel containing the sample 225. For example, the vessel may be an assay, such as a microtiter plate, and the sensor array 110 may be printed within an inside of a microtiter plate well. Each microtiter plate well can contain a unique sensor array 110 pattern with fluorophore structures 220 conjugated to specific recognition agents, allowing parallel processing of different test solutions 230 and increasing diagnostic efficiency. The fluorescence patterns in each microtiter plate well may be used to identify and validate multiple targets, such as biomolecules, pathogens, or chemical compounds, among others, within the sample 225.

[0084] The light source 115 may radiate, produce, or otherwise emit light to illuminate the sample 225 and the fluorophore structures 220 in the sensor array 110. The light source 115 may facilitate fluorescent imaging, spectroscopy, or microscopy in evaluating a sample. The light may traverse from the radiating end of the light source 115 through the sample 225 and toward the sensor array 110. The light source 115 may include, for example, a mercury arc lamp, a xenon arc lamp, a light emitting diode (LED), or a laser, among others. The light may have any wavelength, such as wavelengths between 250-750 nm (e.g., fluorescent light). In some embodiments, the light emitted by the light source 115 may be dependent on the fluorophores to be targeted. For example, for blue and green fluorophores, the wavelength may be between 515-525 nm; for green fluorophores, between 500-515 nm; or for red fluorophores, between 550-690 nm, among others.

[0085] In producing, the light source 115 may output the light to illuminate the sample 225 and the fluorophore structures 220 in the sensor array 110. The light may arrive or reach the first side 210 of the sensor array 110. The light may reach the set of fluorophore structures 220 of the substrate 205 on the first side 210. In response, each of the fluorophore structures 220 may emit, produce, or otherwise transmit a respective light signal 235A-N (hereinafter generally referred to as a light signal 235). Each fluorophore structure 220 may absorb the light from the light source 115 and may emit the respective light signal 235 in accordance with the associated fluorescence response profile. The properties of the respective light signal 235, such as the color, intensity, and patterns, may be dependent on the molecules of interest in the sample 225.

[0086] The imaging device 120 may obtain, generate, or otherwise acquire at least one image 240 of the set of light signals 235 from the sensor array 110. The set of light signals 235 may correspond to the set of fluorophore structures 220. For example, each light signal 235 may be dependent on the fluorescence response profile of the fluorophore structure 220 from which the light signal 235 was emitted, and may contain different colors, intensities, or patterns, among others. Each light signal 235 may be, for example, fluorescent light having a wavelength between 250-750 nm. The imaging device 120 may acquire the image 240 in accordance with fluorescence imaging, microscopy, or spectroscopy, among others. The image 240 may be in the form of an image file (e.g., witha BMP, TIFF, LJPEG, or PNG, among others). Upon acquisition, the imaging device 120 may send, transmit, or otherwise provide the image 240 to the image processing system 105.

[0087] Referring now to FIG. 3, depicts a block diagram of a process 300 for classifying the molecules of interest in the system for detecting molecules of interest. The process 300 can involve an imaging device 120 and image processing system 105. Under process 300, the image parser 135 executing on the image processing system 105 may identify, retrieve, or otherwise receive, via the imaging device 120, the image 240 of the set of light signals 235. Upon receipt, the image parser 135 may detect or identify the individual set of light signals 235 within the image 240. In some embodiments, the image parser 135 may determine or identify the plurality of light signals 235 of the image 240 as corresponding to the plurality of fluorophore structures 220 based on a position of each light signal 235 of the plurality of light signals 235 in the image 240 and a position of each of the plurality of fluorophore structures 220. For example, the image parser 135 may perform image registration to determine the correspondence between each light signal 235 and the corresponding fluorophore structure 220 based on the positioning. The image registration may be in accordance with any number of techniques, such as intensity-based registration (e.g., mutual information or normalized cross-correlation), feature-based registration (e.g., using object detection, scale-invariant feature transform, or speeded up robust features), or deformable image registration (e.g., using B-spline registration), among others.

[0088] Using the set of light signals 235 in the image 240, the code generator 140 may output, produce, or otherwise generate at least one response code 325. The response code 325 may identify or define a set of responses by the corresponding set of fluorophore structures 220 of the sensor array 110. The set of responses may be due to the respective fluorescence response profile in each fluorophore structure 220. The response code 325 may include one or more values for each light signal 235, and may characterize one or more corresponding parameters (e.g., intensity, a color, or pattern) in the respective light signal 235. To generate, the code generator 140 may traverse through the set of light signals 235 identified from the image 240. For each light signal 235 identified from the image 240, the code generator 140 may determine the parameters of the light signal 235. Based on the parameters, the code generator 140 may determine the corresponding code for the responsecode 325. The determination may be in accordance with a function mapping the parameters to values for creating the response code 325.

[0089] The sample classifier 145 executing on the image processing system 105 may identify or otherwise determine a classification 330 of the molecules of interest of the sample 225 based on the response code 325. The classification 330 may identify the molecules of interest within the sample 225, such as biomarkers for a disease or cancer within the subject, traces for drugs or explosives, and other indications for anti-counterfeit measures, among others. In some embodiments, the classification 330 may identify various characteristics of the disease in the sample 225, such as: a presence or extent of disease, a presence or type of pathogenic organisms, a presence of risk factors or comorbidities, a prediction of prognosis, or other clinically relevant parameters, among others. In some embodiments, the classification 330 may identify various characteristics about the material of the sample 225, such as a presence or concentration of toxic compounds, drugs, explosives, or environmental pollutants, among others. In some embodiments, the classification 330 may identify various biological or chemical properties about the material of the sample 225, such as a pH level, a salt level, a salt type, a redox species, a concentration of a gas (e.g., oxygen), a temperature, a presence of contaminants, or type of cells present, among others. For instance, when a cell or cell growth media is placed in contact with the sensor array 110 as the sample 225, the classification 330 may identify nutrients, metabolites, cell confluency, pH, presence or concentration of toxins, and other biologically relevant parameters, among others.

[0090] In some embodiments, the sample classifier 145 may identify or determine a classification 330 to identify a validation of the sample 225 as authenticated or unauthenticated based on the response code 325. The classification 330 may indicate whether the sample 225 is inauthentic (e.g., a counterfeit or a forgery) or authentic (e.g., genuine or real). To determine the validation, the sample classifier 145 may compare the determined response code 325 with an expected response code for the sample 225. The expected response code may be identified from a type of object or item for the sample 225. For instance, the user of the image processing system 105 may provide an identification of a product or good. The sample classifier 145 may find or identify the expected response codefor the sample 225 to check against the generated response code 325. When the response codes match, the sample classifier 145 may determine or identify the sample 225 as authenticated. Conversely, when the response codes do not match, the sample classifier 145 may determine or identify the sample 225 as unauthenticated.

[0091] In some embodiments, the sample classifier 145 may determine the classification in accordance with a function of the response code 325. The function may include a mapping between values of the response code 325 with a set of candidate classifications. Using the function, the sample classifier 145 may find the candidate classification 330 matching the response code 325 to identify the molecules of interest in the sample 225. With the determination, the sample classifier 145 may store, using one or more data structures, an association between the sample 225 and the classification 330 of the molecules of interest of the sample 225. The data structures may include, for example, an array, a matrix, a linked list, a stack, a queue, a tree, a graph, or a hash table, among others.

[0092] In some embodiments, the sample classifier 145 may apply the classification model 155 to the response code 325 to determine the classification 330. The classification model 155 may have been initialized, trained, and established using a training dataset (e.g., in accordance with supervised learning). The training dataset may identify or include a set of examples. Each example may include a sample response code and a corresponding classification 330 of the molecules of interest. The sample response of the training dataset may be acquired from an instance of the sensor array 110 with the same arrangement of the set of fluorophore structures 220 with the same fluorescence response profile when reacting to the sample. The sample response in each example may have been applied to the classification model 155 to generate a predicted classification. A loss metric is determined by comparing the predicted classification and the expected classification in the training dataset. Using the loss metric, the classification model 155 may be updated. This process may be repeated until convergence of the classification model 155.

[0093] With the establishment, the sample classifier 145 may input or feed the response code 325 into the classification model 155. In feeding, the sample classifier 145 may process the response code 325 in accordance with the set of weights of theclassification model 155. From processing, the sample classifier 145 may produce, output, or otherwise generate the classification identifying the molecules of interest in the sample 225. With the determination, the sample classifier 145 may store, using one or more data structures, an association between the sample 225 and the classification 330 of the molecules of interest of the sample 225.[0094J The output handler 150 executing on the image processing system 105 may generate or provide an output 340 to identify the classification 330 of the molecules of interest of the sample. In some embodiments, the output handler 150 may format the classification results for presentation or further analysis. The formatting may involve converting the data into a visually accessible format (e.g., charts, graphs, or comprehensive reports). The output 340 can be displayed on a display 125. The display 125 (or a computing device connected thereto) may display, render, or otherwise present the output 340 from the image processing system 105. The output 340 may also include the image 240. In some embodiments, the output handler 150 may provide the output 340 to identify the validation of the sample 225 as one of authenticated or authenticated.[0095J The fluorophore structures 220 of the sensor array 110 may be disposed, positioned, affixed, or otherwise situated on the sample 225 for any number of applications. The fluorophore structure 220 can be printed on or administered to a container to hold the sample 225. The container can include, for example, a cell culture flask, a petri dish, or a roux bottle, among others. The container can be used in laboratory or research setting for the growth of cell cultures, organoids, spheroids, bacteria, or other biological specimens and organisms. The fluorophore structures 220 can first be synthesized and functionalized as described earlier. The fluorophore structures 220 can then be printed or coated onto the inner surfaces of the flasks using techniques such as inkjet printing, micro-pipetting, etc. In some implementations, the fluorophore structures 220 can be utilized in bioreactors to monitor the production of biopharmaceuticals, enabling real-time observation of pH levels, oxygen concentration, and nutrient availability, ensuring optimal growth conditions for the production of vaccines, antibodies, and other therapeutic agents. By incorporating fluorophore structure 220 into the container, the health, growth, and environmental conditions of the specimens (examples of the sample 225) can be monitored (e.g., using thelight signals 235). This application can aid in experimental protocols and can ensure precise control and timely interventions to maintain optimal growth conditions for the biological samples.

[0096] In some embodiments, the sensor array 110 can be affixed, placed, or otherwise attached to produce (e.g., fruits, vegetables, or other plants). The fluorophore structures 220 can be prepared and then applied to the surface of the produce or to containers holding the produce using adhesives or surface treatments that ensure stability and functionality. In some embodiments, the fluorophore structure 220 can be affixed, placed, or otherwise attached to a container, including the produce, to assess ripeness or detect contamination. The quality and safety of the produce can be monitored using the sensor array 110, as the produce is transported through the supply chain. By scanning the light signals 235 from the fluorophore structure 220, users can obtain real-time data on the produce ripeness levels and any signs of contamination. The sensor array 110 can be integrated into irrigation systems to monitor soil moisture levels and nutrient content, ensuring optimal growing conditions and preventing over- or under-watering of crops.

[0097] The sensor array 110 can be used to assess the progress of fermentation in products such as wine, beer, other alcoholic or non-alcoholic beverages, and compost. The fluorophore structures 220 can be integrated, via coating or embedding the fluorophore structures 220, into fermentation tanks, barrels, or compost bins. The fluorophore structure 220 can be applied to fermentation tanks, barrels, or compost bins, where it can interact with the fermenting substrate or the gases released during the fermentation process. This can allow for real-time monitoring of parameters such as pH, temperature, and gas composition that can allow for assessing the progress and quality of fermentation. The fluorophore structure 220 can provide data on the fermentation status by forming distinct fluorescence patterns that correspond to specific measurements, such as sugar levels, alcohol content, and acidity. The fluorescence (e.g., as in the light signals 235) can be scanned and analyzed to identify the presence and concentration of molecules and analytes involved in the fermentation process. In some embodiments, the fluorophore structure 220 can be applied to yogurt and cheese production to monitor the levels of lactic acid bacteria, which can ensure consistent product quality.

[0098] The sensor array 110 may be attached to buildings or construction materials such as concrete and wood to detect signs of decomposition, such as gas release, rot, or mold, which can allow for the early detection of structural issues and environmental hazards, helping to maintain building safety and integrity. The fluorophore structures 220 can be embedded or coated onto the construction materials during manufacturing or applied to existing structures (e.g., using adhesives or coatings). The sensor array 110 can be used in smart homes to monitor indoor air quality, detecting pollutants like carbon monoxide, volatile organic compounds (VOCs), and mold spores. The fluorophore structure 220 can be attached to biological implants (e.g., as hip replacements, dental implants, cardiac stents, orthopedic screws, artificial heart valves, pacemakers, etc.), to measure (e.g., using the light signals 235) biological factors in vivo, allowing for continuous monitoring of the implant’s environment and detecting potential issues such as infection, inflammation, or implant degradation. The fluorophore structures 220 can be incorporated into the implant materials during manufacturing or coated onto the implants using biocompatible adhesives.

[0099] The sensor array 110 can be affixed to the inside of sample tubes used to collect patient blood, urine, or saliva samples, allowing for in-line automated measurement and disease diagnosis at sample collection or handling facilities. The fluorophore structure 220 can monitor the stability and integrity of the samples during transport and storage, ensuring that they remain viable for accurate testing. Dip-coating or spraying techniques can be used to coat the inner surfaces of the sample tubes with the fluorophore structures 220. The sensor array 110 can detect (e.g., using the light signals 235) changes in temperature, pH, and other environmental conditions that might compromise the sample, providing alerts if the sample is at risk of degradation. This can streamline the diagnostic process, providing immediate and accurate data on the sample conditions. The fluorophore structure 220 can be used in vaccine vials to monitor the stability and potency of the vaccine during transportation and storage to ensure efficacy upon administration. The fluorophore structure 220 can be affixed to the inside of blood storage containers to measure the quality of blood (e.g., following donation, during long-term storage, etc.). For example, this application can ensure that stored blood maintains its viability and safety for transfusions. The fluorophore structures 220 can be applied to the inner surfaces of blood storage containers (e.g., blood bags, blood collection tubes, plasma bags, platelet storage containers,cryogenic vials, and transfusion sets) using similar coating techniques such as dip-coating, spraying, layer-by-layer assembly, and plasma coating.

[0100] In some embodiments, the sensor array 110 can be affixed to the inside of fish tanks, animal housing, or plant housing to monitor environmental conditions and can allow for continuous observation of factors such as water quality, temperature, and pH levels. The fluorophore structures 220 can be integrated into the materials of the fish tanks, animal housing, or plant housing during production or by applying them with adhesives or coatings to existing structures. For example, the fluorophore structure 220 of the sensor array 110 can be used to detect (e.g., using the light signals 235) the presence of harmful pathogens or contaminants, providing early warnings to prevent the spread of disease among fish, animals, or plants. The fluorophore structure 220 can monitor humidity levels and light exposure, ensuring that optimal conditions are maintained for the health and growth of the organisms. The fluorophore structure 220 can be used to detect (e.g., using the light signals 235) contamination in a liquid. For example, the image processing system 105 can process the light signals 235 reflected from the sensor array 110 placed in a swimming pool to detect contamination in the water. By integrating the fluorophore structure 220 with pool monitoring systems, pool managers can receive real-time data on water quality, including levels of contaminants and chemical balance. In some implementations, the fluorophore structure 220 can be used for monitoring (e.g., using the light signals 235) wastewater purity at chemical manufacturing sites. By attaching the fluorophore structure 220 to wastewater outlets, facilities can continuously monitor the water quality, detecting contamination and ensuring compliance with environmental regulations. For wastewater monitoring, the fluorophore structures 220 can be coated onto the outlet surfaces using techniques that ensure durability and responsiveness to contaminants (e.g., electroplating, sol-gel coating, thermal spraying, and chemical vapor deposition).

[0101] The sensor array 110 can be attached to the walls or ceiling of chemical manufacturing or handling sites to measure environmental conditions (e.g., air quality) and detect contamination and pollution. This application enhances workplace safety by providing real-time data on the presence of harmful substances in the air. The fluorophorestructures 220 can be embedded into the materials of the walls or ceilings during construction or applied as a coating to existing structures. The fluorophore structure 220 can be used to detect (e.g., using the light signals 235) disease or specific molecules in urine via attachment to a toilet, urinal, or catheter, allowing for non-invasive and continuous health monitoring, providing valuable data for early disease detection and management. The fluorophore structures 220 can be applied to the surfaces of these fixtures using biocompatible adhesives or coatings.

[0102] The sensor array 110 can be integrated into wearable health monitoring devices, such as smartwatches, fitness trackers, and skin patches, to continuously monitor physiological parameters. In some implementations, the fluorophore structure 220 can detect early signs of health issues. The wearable health monitoring devices can track parameters such as glucose levels, dehydration, electrolyte balance, and other vital signs. By embedding the fluorophore structures 220 into the wearable health monitoring devices, users can receive real-time feedback on their health status, and can enable proactive health management and timely interventions. For example, athletes can use the wearable health monitoring devices to monitor hydration levels during intense physical activities. Patients with chronic conditions such as diabetes can benefit from continuous glucose monitoring, reducing the risk of complications and improving overall disease management.

[0103] In some implementations, the sensor arrays 110 can be integrated into personal protective equipment (PPE) for workers in hazardous environments to continuously monitor exposure to toxic chemicals and provide real-time alerts, enhancing safety protocols. The fluorophore structure 220 can be used in environmental monitoring systems to detect pollutants and hazardous substances in air, soil, and water. By deploying sensor arrays 110 in various locations, environmental agencies can monitor the presence of heavy metals, pesticides, industrial chemicals, or other contaminants, ensuring compliance with environmental regulations and protecting public health. For example, the fluorophore structures 220 can be embedded in buoys for real-time water quality monitoring in lakes and rivers, detecting pollutants (e.g., lead, mercury, nitrates, etc.). In urban settings, the sensor arrays 110 can be installed in storm drains and sewage systems to monitor and control the discharge of harmful substances into natural water bodies.

[0104] Referring now to FIG. 4A, depicted is a diagram 400 of an example diagnostic response code of a sample. The inclusion of analytes in the sample can cause different light signals to show through the sensors. The sensor arrays 110 can detect and analyze various analytes, and can include analytes in complex mediums like serum, saliva, or urine. Each pixel of the sensor array 110 may respond differently to the presence of an analyte due to variations in ink composition. Pixels may contain multiple fluorophores for added complexity and can be applied for anti-counterfeiting or for tuning the fluorescence response to different analytes.

[0105] Referring now to FIG. 4B, depicted is a diagram 405 of a nano-sensor array. The different light signals or codes can be used to detect different types of cancer or diseases in organ tissue. The collective response of the entire array to a specific analyte or mix of analytes can form a unique, distinct fluorescence pattern. The distinct fluorescence patterns can form a QR code or fingerprint. The QR code or fingerprint can be used to identify molecules, specific analytes, patterns, or medical conditions. A neural network can be trained to recognize specific responses from the array. The neural network can be trained using samples known to contain certain analytes (e.g., serum samples from patients with specific medical conditions). The response of the array can be analyzed through various methods, including fluorescent microscopy, CCD cameras, fiber optical devices, or even a mobile phone camera. The nano-sensor in FIG. 4B can detect, using the different collective responses of the entire array, ovarian cancer, breast cancer, bowel cancer, thyroid cancer, or lung cancer.

[0106] Referring now to FIG. 5, depicted is an illustrative flow diagram of a method 500 for detecting molecules of interest. The method 500 can be executed, performed, or otherwise carried out by the system 100 or 700. Under the method 500, a light source may emit light toward a first side of a substrate to illuminate a sample having molecules of interest (505). An imaging device may acquire an image of the light signals (510). A computing system (e.g., the image processing system 105) may receive, via the imaging device, the image of the light signals (515). The computing system may generate a response code (520). The computing system may determine a classification of the molecules of interest of the sample based on the response code (525). The computing system mayprovide an output to identify the classification of the molecules of interest of the sample (530).

[0107] Referring now to FIG. 6, depicted is a flow diagram of a method 600 for validating authenticity of samples. The method 600 can be executed, performed, or otherwise carried out by the system 100 or 700. Under the method 600, a light source may emit light toward a first side of a substrate to illuminate a sample (605). An imaging device may acquire an image of the light signals (610). A computing system (e.g., the image processing system 105) may receive, via the imaging device, the image of the light signals (615). The computing system may generate a response code (620). The computing system may validate the sample as authenticated or unauthenticated based on the response code (625). The computing system may provide an output to identify the validation of the sample as one of authenticated or unauthenticated (630).B. Computing and Network Environment

[0108] Various operations described herein can be implemented on computer systems. FIG. 7 shows a simplified block diagram of a representative server system 700, client computing system 714, and network 726 usable to implement certain embodiments of the present disclosure. In various embodiments, server system 700 or similar systems can implement services or servers described herein or portions thereof. Client computing system 714 or similar systems can implement clients, described herein. The systems 100 described herein can be similar to the server system 700. Server system 700 can have a modular design that incorporates a number of modules 702 (e.g., blades in a blade server embodiment); while two modules 702 are shown, any number can be provided. Each module 702 can include processing unit(s) 704 and local storage 706.

[0109] Processing unit(s) 704 can include a single processor, which can have one or more cores, or multiple processors. In some embodiments, processing unit(s) 704 can include a general-purpose primary processor as well as one or more special-purpose coprocessors, such as graphics processors, digital signal processors, or the like. In some embodiments, some or all processing units 704 can be implemented using customized circuits, such as application specific integrated circuits (ASICs) or field programmable gatearrays (FPGAs). In some embodiments, such integrated circuits execute instructions that are stored on the circuit itself. In other embodiments, processing unit(s) 704 can execute instructions stored in local storage 706. Any type of processors in any combination can be included in processing unit(s) 704.

[0110] Local storage 706 can include volatile storage media (e.g., DRAM, SRAM, SDRAM, or the like) or non-volatile storage media (e.g., magnetic or optical disk, flash memory, or the like). Storage media incorporated in local storage 706 can be fixed, removable, or upgradeable as desired. Local storage 706 can be physically or logically divided into various subunits, such as a system memory, a read-only memory (ROM), and a permanent storage device. The system memory can be a read-and-write memory device or a volatile read-and-write memory, such as dynamic random-access memory. The system memory can store some or all of the instructions and data that processing unit(s) 704 need at runtime. The ROM can store static data and instructions that are needed by processing unit(s) 704. The permanent storage device can be a non-volatile read-and-write memory device that can store instructions and data even when module 702 is powered down. The term “storage medium” as used herein includes any medium in which data can be stored indefinitely (subject to overwriting, electrical disturbance, power loss, or the like) and does not include carrier waves and transitory electronic signals propagating wirelessly or over wired connections.

[0111] In some embodiments, local storage 706 can store one or more software programs to be executed by processing unit(s) 704, such as an operating system or programs implementing various server functions such as functions of the system 100 or any other system described herein, or any other server(s) associated with system 100 or any other system described herein.

[0112] Software” refers generally to sequences of instructions that, when executed by processing unit(s) 704, cause server system 700 (or portions thereof) to perform various operations, thus defining one or more specific machine embodiments that execute and perform the operations of the software programs. The instructions can be stored as firmware residing in read-only memory or program code stored in non-volatile storage media that can be read into volatile working memory for execution by processing unit(s)704. Software can be implemented as a single program or a collection of separate programs or program modules that interact as desired. From local storage 706 (or non-local storage described below), processing unit(s) 704 can retrieve program instructions to execute and data to process in order to execute various operations described above.

[0113] In some server systems 700, multiple modules 702 can be interconnected via a bus or other interconnect 708, forming a local area network that supports communication between modules 702 and other components of server system 700. Interconnect 708 can be implemented using various technologies including server racks, hubs, routers, etc.

[0114] A wide area network (WAN) interface 710 can provide data communication capability between the local area network (interconnect 708) and the network 726, such as the Internet. Technologies can be used, including wired (e.g., Ethernet, IEEE 802.3 standards) or wireless technologies (e.g., Wi-Fi, IEEE 802.11 standards).

[0115] In some embodiments, local storage 706 is intended to provide working memory for processing unit(s) 704, providing fast access to programs or data to be processed while reducing traffic on interconnect 708. Storage for larger quantities of data can be provided on the local area network by one or more mass storage subsystems 712 that can be connected to interconnect 708. Mass storage subsystem 712 can be based on magnetic, optical, semiconductor, or other data storage media. Direct attached storage, storage area networks, network-attached storage, and the like can be used. Any data stores or other collections of data described herein as being produced, consumed, or maintained by a service or server can be stored in mass storage subsystem 712. In some embodiments, additional data storage resources may be accessible via WAN interface 710 (potentially with increased latency).

[0116] Server system 700 can operate in response to requests received via WAN interface 710. For example, one of the modules 702 can implement a supervisory function and assign discrete tasks to other modules 702 in response to received requests. Work allocation techniques can be used. As requests are processed, results can be returned to the requester via WAN interface 710. Such operation can generally be automated. Further, in some embodiments, WAN interface 710 can connect multiple server systems 700 to eachother, providing scalable systems capable of managing high volumes of activity. Other techniques for managing server systems and server farms (collections of server systems that cooperate) can be used, including dynamic resource allocation and reallocation.10117] Server system 700 can interact with various user-owned or user-operated devices via a wide-area network such as the Internet. An example of a user-operated device is shown in FIG. 7 as client computing system 714. Client computing system 714 can be implemented, for example, as a consumer device such as a smartphone, other mobile phone, tablet computer, wearable computing device (e.g., smart watch, eyeglasses), desktop computer, laptop computer, and so on.

[0118] For example, client computing system 714 can communicate via WAN interface 710. Client computing system 714 can include computer components such as processing unit(s) 716, storage device 718, network interface 720, user input device 722, and user output device 737. Client computing system 714 can be a computing device implemented in a variety of form factors, such as a desktop computer, laptop computer, tablet computer, smartphone, other mobile computing device, wearable computing device, or the like.

[0119] Processing unit(s) 716 and storage device 718 can be similar to processing unit(s) 704 and local storage 706 described above. Suitable devices can be selected based on the demands to be placed on client computing system 714; for example, client computing system 714 can be implemented as a “thin” client with limited processing capability or as a high-powered computing device. Client computing system 714 can be provisioned with program code executable by processing unit(s) 716 to enable various interactions with server system 700.

[0120] Network interface 720 can provide a connection to the network 726, such as a wide area network (e.g., the Internet) to which WAN interface 710 of server system 700 is also connected. In various embodiments, network interface 720 can include a wired interface (e.g., Ethernet) or a wireless interface implementing various RF data communication standards, such as Wi-Fi, Bluetooth, or cellular data network standards (e g., 3G, 4G, LTE, etc ).

[0121] User input device 722 can include any device (or devices) via which a user can provide signals to client computing system 714; client computing system 714 can interpret the signals as indicative of particular user requests or information. In various embodiments, user input device 722 can include any or all of a keyboard, touch pad, touch screen, mouse or other pointing device, scroll wheel, click wheel, dial, button, switch, keypad, microphone, and so on.

[0122] User output device 737 can include any device via which client computing system 714 can provide information to a user. For example, user output device 737 can include display-to-display images generated by or delivered to client computing system 714. The display can incorporate various image generation technologies, e.g., a liquid crystal display (LCD), light-emitting diode (LED), including organic light-emitting diodes (OLED), projection system, cathode ray tube (CRT), or the like, together with supporting electronics (e.g., digital -to-analog or analog-to-digital converters, signal processors, or the like). Some embodiments can include a device such as a touchscreen that functions as both input and output device. In some embodiments, other user output devices 737 can be provided in addition to or instead of a display. Examples include indicator lights, speakers, tactile “display” devices, printers, and so on.

[0123] Some embodiments include electronic components, such as microprocessors, storage, and memory that store computer program instructions in a computer readable storage medium. Many of the features described in this specification can be implemented as processes that are specified as a set of program instructions encoded on a computer readable storage medium. When these program instructions are executed by one or more processing units, they cause the processing unit(s) to perform various operations indicated in the program instructions. Examples of program instructions or computer code include machine code, such as is produced by a compiler, and files including higher-level code that are executed by a computer, an electronic component, or a microprocessor using an interpreter. Through suitable programming, processing unit(s) 704 and 716 can provide various functionality for server system 700 and client computing system 714, including any of the functionality described herein as being performed by a server or client, or other functionality.

[0124] It will be appreciated that server system 700 and client computing system 714 are illustrative and that variations and modifications are possible. Computer systems used in connection with embodiments of the present disclosure can have other capabilities not specifically described here. Further, while server system 700 and client computing system 714 are described with reference to particular blocks, it is to be understood that these blocks are defined for convenience of description and are not intended to imply a particular physical arrangement of component parts. For instance, different blocks can be but need not be located in the same facility, in the same server rack, or on the same motherboard. Further, the blocks need not correspond to physically distinct components. Blocks can be configured to perform various operations, e.g., by programming a processor or providing appropriate control circuitry, and various blocks might or might not be reconfigurable depending on how the initial configuration is obtained. Embodiments of the present disclosure can be realized in a variety of apparatus including electronic devices implemented using any combination of circuitry and software.

[0125] While the disclosure has been described with respect to specific embodiments, one skilled in the art will recognize that numerous modifications are possible. Embodiments of the disclosure can be realized using a variety of computer systems and communication technologies, including, but not limited to, specific examples described herein. Embodiments of the present disclosure can be realized using any combination of dedicated components, programmable processors, or other programmable devices. The various processes described herein can be implemented on the same processor or different processors in any combination. Where components are described as being configured to perform certain operations, such configuration can be accomplished, e.g., by designing electronic circuits to perform the operation, by programming programmable electronic circuits (such as microprocessors) to perform the operation, or any combination thereof. Further, while the embodiments described above may refer to specific hardware and software components, those skilled in the art will appreciate that different combinations of hardware or software components may also be used and that particular operations described as being implemented in hardware might also be implemented in software or vice versa.

[0126] Computer programs incorporating various features of the present disclosure may be encoded and stored on various computer readable storage media; suitable media includes magnetic disk or tape, optical storage media such as compact disk (CD) or digital versatile disk (DVD), flash memory, and other non-transitory media. Computer readable media encoded with the program code may be packaged with a compatible electronic device, or the program code may be provided separately from electronic devices (e.g., via Internet download or as a separately packaged computer-readable storage medium).

[0127] Thus, although the disclosure has been described with respect to specific embodiments, it will be appreciated that the disclosure is intended to cover all modifications and equivalents within the scope of the following claims.

Claims

WHAT IS CLAIMED IS:

1. A system for classifying molecules of interest, comprising: a sensor array comprising: a substrate having a side upon which a sample having molecules of interest is configured to be disposed; and a plurality of fluorophore structures arranged along the side of the substrate, each of the plurality of fluorophore structures having a respective fluorescence response profile in reacting to the sample; a light source configured to emit the fluorescent light toward the substrate to illuminate the sample having molecules of interest; an imaging device configured to acquire an image of a plurality of light signals corresponding to the plurality of fluorophore structures; and a computing system having one or more processors coupled with memory in communication with the imaging device, configured to: receive, via the imaging device, the image of the plurality of light signals from the plurality of fluorophore structures; generate, using the plurality of light signals of the image, a response code defining a plurality of responses by the corresponding plurality of fluorophore structures to the fluorescent light due to the respective fluorescence response profile in each fluorophore structure of the plurality of fluorophore structures; determine a classification of the molecules of interest of the sample based on the response code; and provide an output to identify the classification of the molecules of interest of the sample.

2. The system of claim 1, wherein at least one of the plurality of fluorophore structures is configured with an environmental sensitivity with respect to fluorescence in at least one of a spatial or temporal domain, wherein the environmental sensitivity comprises a change in at least one of an absorbance intensity or a spectral characteristic.

3. The system of any one of claims 1 or 2, wherein each of the plurality of fluorophore structures comprises at least one of a carbon nanotube, a polymer dot, a quantum dot, or a fluorescent dye.

4. The system of any one or more of the preceding claims, wherein the respective fluorescence response profile of each of the plurality of fluorophore structures differs from at least one other fluorophore structure of the plurality of fluorophore structures.

5. The system of any one or more of the preceding claims, wherein at least one fluorophore structure of the plurality of fluorophore structures comprises a carbon nanotube, and wherein the respective fluorescence response profile of the at least one fluorophore structure is based on at least one of a structural defect, chirality, single-walled, multi-walled, polymer coating, surfactant, peptide, protein, saccharide in the carbon nanotube.

6. The system of any one or more of the preceding claims, wherein the plurality of fluorophore structures are grafted to, confined within, adjacent to, or otherwise colocalized with a binding agent, wherein the binding agent comprises at least one of antibodies, nanobodies, antigens, enzymes, aptamers, or molecularly imprinted polymers.

7. The system of any one or more of the preceding claims, wherein the plurality of fluorophore structures are arranged in a one-dimensional line, a two-dimensional area, or three-dimensional volume of the substrate.

8. The system of any one or more of the preceding claims, wherein the substrate is formed from at least one of a paper material, plastic material, a metal material, a glass material, a fabric material, a leather material, a semiconductor material, a metal oxide material, a polymer material, epidermis, lateral flow strip, aerogel, or a composite.

9. The system of any one or more of the preceding claims, wherein the imaging device further comprises at least one of fluorescence microscope, a charge-coupled device (CCD), or a fiber optical device.

10. The system of any one or more of the preceding claims, wherein the computing system is further configured to apply a machine learning model to the plurality of responses of the response code to determine the classification of the molecules of interest in the sample.

11. The system of any one or more of the preceding claims, wherein the computing system is further configured to identify the plurality of light signals of the image as corresponding to the plurality of fluorophore structures based on a position of each light signal of the plurality of light signals in the image and a position of each of the plurality of fluorophore structures on the substrate.

12. The system of any one or more of the preceding claims, wherein the computing system is further configured to store, using one or more data structures, an association between the sample and the classification of the molecules of interest of the sample.

13. The system of any one or more of the preceding claims, wherein the classification identifies at least one of: presence or extent of disease, presence or type of pathogenic organisms, presence of risk factors or comorbidities, prediction of prognosis, or clinically relevant parameters.

14. The system of any one or more of the preceding claims, wherein the classification identifies at least one of: presence or concentration of toxic compounds, drugs, explosives, or environmental pollutants.

15. The system of any one or more of the preceding claims, wherein the classification identifies at least one of: pH level, salt level or salt type, redox species, concentration of oxygen or other gas, temperature, presence of contaminants, or type of cells present.

16. The system of any one or more of the preceding claims, wherein the sample comprises at least one of a cell or a cell growth medium, and wherein the classification identifies at least one of: a presence or concentration of nutrients, presence or concentration ofmetabolites, cell confluency; pH, presence, or concentration of toxins, or a biological parameter.

17. The system of any one or more of the preceding claims, wherein the sample comprises at least one of skin, saliva, blood, plasma, serum, urine, feces, sweat, breath, tears, serous fluids, subcutaneous fluid, biopsy samples, bacteria, viruses, fungus, drugs, cultured cells, or cell media, wherein the sample is obtained from one of a human subject or an animal subject.

18. The system of any one or more of the preceding claims, wherein the sample comprises at least one of a food substance, oil, a perfume, a beverage, a construction material, or a storage container.

19. The system of any one or more of the preceding claims, wherein the sensor array is administered with a solution to modify the respective fluorescence response profile in each of the plurality of fluorophore structures.

20. The system of any one or more of the preceding claims, wherein the solution administered to the sensor array comprises at least one of a ligand for a recognition agent in at least one of the plurality of fluorophore structures.

21. The system of any one or more of the preceding claims, wherein at least one of the plurality of fluorophore structures includes a recognition agent.

22. A system for validating authenticity of samples, comprising: a sensor array disposed on a sample, the sensory array comprising a plurality of fluorophore structures arranged in accordance with a pattern along a side of the substrate, each of the plurality of fluorophore structures having a respective fluorescence response profile in reacting to the sample; a light source configured to emit the fluorescent light toward the substrate to illuminate the sample;an imaging device configured to acquire an image of a plurality of light signals corresponding to the plurality of fluorophore structures; and a computing system having one or more processors coupled with memory in communication with the imaging device, configured to: receive, via the imaging device, the image of the plurality of light signals from the plurality of fluorophore structures, the plurality of light signals capturing the pattern; generate, using the plurality of light signals of the image, a response code corresponding to the pattern, the response code defining a plurality of responses by the corresponding plurality of fluorophore structures to the fluorescent light due to the respective fluorescence response profile in each fluorophore structure of the plurality of fluorophore structures; determine a validation of the plurality of fluorophore structures of the sample as one of authenticated or unauthenticated based on the response code; and provide an output to identify the validation of the sample as one of authenticated or unauthenticated.

23. The system of claim 22, wherein the pattern is configured to at least one of (i) establish an identity, (ii) validate an authenticity, or (iii) track a chain of ownership of the sample.

24. The system of any one of claims 22 or 23, wherein the plurality of fluorophore structures arranged in the pattern is configured to respond with a unique fluorescence spectra to the emitted light.

25. The system of any one of claims 22-24, wherein the computing system is further configured to store, using one or more data structures, an association between the sample and the response code corresponding to the pattern.

26. A method of classifying molecules of interest (MOI), comprising: disposing, onto a side of a substrate of a sensor array, a sample having molecules of interest, the sensor array comprising a plurality of fluorophore structures arranged along theside of the substrate, each of the plurality of fluorophore structures having a respective fluorescence response profile in reacting to the sample; emitting, by a light source, fluorescent light toward a side of a substrate to illuminate a sample having molecules of interest; acquiring, by an imaging device, an image of a plurality of light signals corresponding to the plurality of fluorophore structures; receiving, by a computing system, via the imaging device, the image of the plurality of light signals from the plurality of fluorophore structures; generating, by the computing system, using the plurality of light signals of the image, a response code defining a plurality of responses by the corresponding plurality of fluorophore structures to the fluorescent light due to the respective fluorescence response profile in each fluorophore structure of the plurality of fluorophore structures; determining, by the computing system, a classification of the molecules of interest of the sample based on the response code; and providing, by the computing system, an output to identify the classification of the molecules of interest of the sample.

27. The method of claim 26, further comprising administering, on the sensor array, a solution to modify the respective fluorescence response profile in each of the plurality of fluorophore structures.

28. A method of validating authenticity of samples, comprising: emitting, by a light source, fluorescent light toward a sensor array to illuminate a sample, the sensor array comprising a plurality of fluorophore structures arranged in accordance with a pattern along the side of the substrate, each of the plurality of fluorophore structures having a respective fluorescence response profile in reacting to the sample; acquiring, by an imaging device, an image of a plurality of light signals corresponding to the plurality of fluorophore structures, the plurality of light signals capturing the pattern on the sample; receiving, by a computing system, via the imaging device, the image of the plurality of light signals from the plurality of fluorophore structures;generating, by the computing system, using the plurality of light signals of the image, a response code corresponding to the pattern, the response code defining a plurality of responses by the corresponding plurality of fluorophore structures to the fluorescent light due to the respective fluorescence response profile in each fluorophore structure of the plurality of fluorophore structures; determining, by the computing system, a validation of the sample as one of authenticated or unauthenticated based on the response code; and providing, by the computing system, an output to identify the validation of the sample as one of authenticated or unauthenticated.

29. The method of claim 28, further comprising using a fluorophore mixture to generate the pattern on the sample using a fluorophore solution.

30. The method of any one or more of claims 28 or 29, further comprising modifying the fluorophore mixture using at least one of: an inclusion of additives, a purification of the solution, a size separation, chromatography, or a light treatment.

31. The method of any one or more of claims 28-30, wherein the purification of the solution further comprises separation of carbon nanotubes with different chirality, surface treatment, and length or chemical modification.

32. The method of any one or more of claims 28-31, further comprising administering, on the sensor array, a solution to modify the respective fluorescence response profile in each of the plurality of fluorophore structures.

33. A sensor array comprising: a substrate having an area configured to be disposed on a sample; and a plurality of fluorophore structures arranged along the area of the substrate in accordance with a pattern, each of the plurality of fluorophore structures having a respective fluorescence response profile in reacting to the sample, each of the plurality of fluorophore structures configured to emit a corresponding light signal of a plurality of light signals to beused to determine a classification of molecule of interest in the sample or to indicate a validity of an authenticity of the sample.

34. The sensor array of claim 33, wherein at least one of the plurality of fluorophore structures is administered with a solution to modify the respective fluorescence response profile.

Images