System and method for diagnosing biological disorders associated with periodic fluctuations in metal metabolism

Abstract

To provide a method for evaluating a subject for a biological condition associated with metal metabolism.SOLUTION: A method includes sampling positions along a biological sample of a subject to obtain a plurality of ion samples. Each ion sample corresponds to a position on the biological sample and each position represents an amount of growth of the biological sample. The method also analyzes the obtained ions with a mass spectrometer to acquire a plurality of traces. Each such trace represents concentration of a corresponding elemental isotope, of a plurality of elemental isotopes, over time. The method further derives a set of features from the traces. Each feature is determined by a variation of a single isotope or a combination of isotopes in the plurality of traces. The method inputs the set of features to a trained classifier to acquire a probability that the subject has a biological condition associated with metal metabolism.SELECTED DRAWING: Figure 2A

Description

[Technical Field]

[0001] Cross-reference of related applications This application claims priority to U.S. Provisional Patent Application No. 62 / 858,260, filed on June 6, 2019, entitled "Systems and Methods for Hair Based Diagnostics for Autism Spectrum Disorders," which is incorporated herein by reference.

[0002] This disclosure generally relates to the diagnosis of biological conditions related to metal metabolism, which is carried out through the analysis of biological samples from subjects tested for such biological conditions. [Background technology]

[0003] Metal ions play a crucial role in many biological processes that are structurally and functionally important to humans. The unbalanced acquisition of specific metal ions, resulting from certain amounts of metals in nutrients or metabolic abnormalities of specific metals, is associated with many biological conditions. This imbalance includes either an excess of a particular metal ion or a deficiency of a particular metal ion. Examples of biological conditions related to metal metabolism include neurological conditions (e.g., autism spectrum disorder, schizophrenia, or attention-deficit / hyperactivity disorder (ADHD)), neurodegenerative conditions (e.g., amyotrophic lateral sclerosis (ALS), Alzheimer's disease, Parkinson's disease, and Huntington's disease), and certain cancers (e.g., childhood cancers).

[0004] Recent studies have shown a link between autism spectrum disorder and metabolic dysfunction, particularly metal dysregulation (see, for example, Cheng et al., “Metabolic Dysfunction Underlying Autism Spectrum Disorder and Potential Treatment Approaches,” Front Mol Neurosci. 10, p. 34, February 2017, and Arora et al., “Fetal and postnatal metal dysregulation in Autism,” Nat.Commun. 8, p. 15493, June 2017). As another example, recent studies have shown a link between neurodegeneration and the biological rhythms of metals detectable from the hair and / or teeth of subjects (see, for example, Appenzeller et al., “Stable Isotope Ratios in Hair and Teeth Reflect Biologic Rhythms,” PLoS ONE 2(7):e636. https: / / doi.org / 10.1371 / journal.pone.0000636, April 2017). However, there is a point in the study that,

[0005] Given the above background, there is a need in this technical field for improved systems and methods to accurately diagnose biological conditions related to metal metabolism. In particular, there is a need for biomarkers that can be detected by non-invasive methods for diagnosing biological conditions related to metal metabolism. [Overview of the Initiative]

[0006] Thus, there is a need for accurate methods and systems for diagnosing biological conditions related to metal metabolism, particularly for non-invasive diagnostics. This disclosure addresses these needs by providing, for example, biomarkers for biosamples for diagnosing biological conditions related to metal metabolism. Biosamples include human biosamples related to growth, containing deposits of specific metals. Such biosamples may be hair shafts, teeth, and nails. The non-invasive biomarkers of this disclosure can be used for the diagnosis of infants, and even infants under one year of age.

[0007] According to some embodiments, a method for evaluating a subject for a first biological state related to metal metabolism includes sampling each of several locations along a baseline on a biological sample of the subject related to metal metabolism, thereby obtaining several ionic samples. Each ionic sample in the several ionic samples corresponds to a different location in the several locations, and each location in the several locations represents a different growth period of the biological sample related to metal metabolism. The method includes analyzing each ionic sample in the several ionic samples (e.g., using a mass spectrometer or other spectroscopic method), thereby obtaining a first dataset containing several traces. Each trace in the several traces is the time-dependent concentration of a corresponding elemental isotope in several elemental isotopes, collectively determined from the several ionic samples. The method includes deriving a second dataset from the several traces, which contains a set of features. Each feature in the set of features is determined by the variation of a single isotope or combination of isotopes in the several traces. The method includes inputting the set of features into a trained classifier, thereby obtaining from the trained classifier the probability that the subject has a first biological state related to metal metabolism.

[0008] In some embodiments, the multiple elemental isotopes are selected from the elemental isotopes listed in Table 1. In some embodiments, the multiple elemental isotopes include at least 22 elemental isotopes from the elemental isotopes listed in Table 1.

[0009] According to some embodiments, each feature within the set of features is associated with a single respective one of the plurality of traces, or with two respective ones of the plurality of traces. In some embodiments, the set of features is selected from the features listed in Table 2, and optionally, the set of features further includes one or more features listed in Table 3. In some embodiments, the set of features includes at least 23 features listed in Table 2.

[0010] In some embodiments, the first biological state associated with metal metabolism is selected from the group consisting of autism spectrum disorder (ADS), attention deficit / hyperactivity disorder (ADHD), amyotrophic lateral sclerosis (ALS), schizophrenia, inflammatory bowel disease (IBD), pediatric kidney transplant rejection, and pediatric cancer.

[0011] In some embodiments, evaluating a subject for the first biological state associated with metal metabolism further includes distinguishing the first biological state associated with metal metabolism from a second biological state associated with metal metabolism that is different from the first biological state associated with metal metabolism. In some embodiments, the first biological state is autism spectrum disorder and the second biological state is attention deficit / hyperactivity disorder.

[0012] In some embodiments, the subject is a human. In some embodiments, the subject is less than 1 year old, less than 2 years old, less than 3 years old, less than 4 years old, or less than 5 years old.

[0013] In some embodiments, the biological sample associated with the subject's metal metabolism is selected from the group consisting of hair shafts, teeth, and nails.

[0014] In some embodiments, the method further includes pretreating the hair shaft of the subject with a solvent and / or irradiating the hair shaft with a low-power laser to remove any debris from the hair shaft before sampling the hair shaft of the subject. In some embodiments, the biological sample related to the metal metabolism of the subject is the hair shaft, and the reference line corresponds to the longitudinal direction of the hair shaft. In some embodiments, the biological sample related to the metal metabolism of the subject is a tooth, and the reference line corresponds to the neonatal line of the tooth on the enamel surface of the tooth.

[0015] In some embodiments, the method further includes pretreating the biological sample related to the metal metabolism of the subject with a solvent or a surfactant before sampling. In some embodiments, the method further includes using a laser to irradiate the biological sample related to the metal metabolism of the subject with a low-power laser to remove any debris from the biological sample related to the metal metabolism of the subject before sampling.

[0016] In some embodiments, sampling includes irradiating the biological sample related to the metal metabolism of the subject with a laser, thereby extracting a plurality of particles from the biological sample related to the metal metabolism of the subject, and ionizing the plurality of particles with an inductively coupled plasma mass spectrometer, thereby obtaining a plurality of ion samples.

[0017] In some embodiments, the plurality of positions are ordered such that a first position at a plurality of positions along the biological sample related to the metal metabolism of the subject corresponds to the position closest to the tip of the biological sample related to the metal metabolism of the subject. In some embodiments, the plurality of positions includes at least 100, 150, 200, 250, 300, 350, 400, 450, or 500 positions.

[0018] In some embodiments, each trace within the plurality of traces includes a plurality of data points. Each data point is an instance of each position at a plurality of positions.

[0019] In some embodiments, deriving a second dataset involves removing data points from a set of data points that do not satisfy a first criterion. The first criterion includes the mean absolute difference between adjacent data points within the set of data points being three times the standard deviation of the mean absolute difference between adjacent points.

[0020] In some embodiments, the concentration of the corresponding elemental isotope corresponds to the relative abundance of the corresponding elemental isotope to the control elemental isotope, and the control elemental isotope is contained in multiple ionic samples. In some embodiments, the control elemental isotope is sulfur.

[0021] In some embodiments, the set of features is selected from mean diagonal length, determinism, recursion time, entropy, trapping time, and laminarity.

[0022] In some embodiments, the trained classifier is

number

[0023] In some embodiments, the method further includes determining that a subject has a first biological state related to metal metabolism, based on the determination that p(subject) exceeds a predetermined threshold.

[0024] In some embodiments, the biological state related to metal metabolism is associated with periodic dysregulation of the metabolism of multiple metals, where the multiple metals correspond to multiple elemental isotopes.

[0025] According to some embodiments, the device for evaluating a subject for a biological state related to metal metabolism includes one or more processors and a memory for storing one or more programs to be executed by the one or more processors. One or more programs include instructions for sampling each of several locations along a baseline on a biological sample related to the metal metabolism of the subject, thereby obtaining several ion samples. Each ion sample in the several ion samples corresponds to a different location in the several locations. Each location in the several locations represents a different growth period of the biological sample related to metal metabolism. One or more programs include instructions for analyzing each ion sample in the several ion samples with a mass spectrometer, thereby obtaining a first dataset containing several traces. Each trace in the several traces is the time-dependent concentration of a corresponding elemental isotope in several elemental isotopes, collectively determined from the several ion samples. One or more programs include instructions for deriving a second dataset from the several traces, which contains a set of features, each feature in the set of features being determined by the variation of a single isotope or combination of isotopes in the several traces. One or more programs include instructions to input a set of features into a trained classifier, thereby obtaining from the trained classifier the probability that a subject has a biological state related to metal metabolism.

[0026] According to some embodiments, a non-temporary computer-readable storage medium embeds one or more computer programs for classification. The one or more computer programs, when executed by a computer system, include instructions causing the computer system to perform a method for evaluating a subject for a biological state related to metal metabolism. The method includes sampling each of several locations along a baseline on a biological sample related to the metal metabolism of the subject, thereby obtaining several ion samples. Each ion sample in the several ion samples corresponds to a different location in the several locations, and each location in the several locations represents a different growth period of the biological sample related to metal metabolism. The method includes analyzing each ion sample in the several ion samples using a mass spectrometer, thereby obtaining a first dataset containing several traces. Each trace in the several traces is the time-dependent concentration of a corresponding elemental isotope in several elemental isotopes, collectively determined from the several ion samples. The method includes deriving a second dataset from the several traces, which contains a set of features. Each feature in the set of features is determined by the variation of a single isotope or combination of isotopes in the several traces. This method involves inputting a set of features into a trained classifier, thereby obtaining from the trained classifier the probability that a subject has a first biological state related to metal metabolism.

[0027] According to some embodiments, the classification method is performed on a computer system having one or more processors and memory for storing one or more programs to be executed by the one or more processors. The classification method is performed for each training subject in a plurality of training subjects. A first subset of training subjects in the plurality of training subjects has a first diagnostic status corresponding to having a first biological state related to metal metabolism, and a second subset of training subjects in the plurality of training subjects has a second diagnostic status corresponding to not having the first biological state related to metal metabolism. The classification method includes sampling each position at a plurality of corresponding locations on a corresponding baseline on a corresponding biological sample related to metal metabolism for each training subject, thereby obtaining a plurality of corresponding ion samples. Each ion sample in the plurality of corresponding ion samples is for a different position at the plurality of corresponding locations. Each position at the plurality of corresponding locations represents a different growth period of the corresponding biological sample related to metal metabolism. The classification method includes analyzing each ion sample in the plurality of corresponding ion samples using a mass spectrometer, thereby obtaining each first dataset containing a plurality of corresponding traces. Each trace within a group of corresponding traces represents the time-dependent concentration of a corresponding elemental isotope in a group of elemental isotopes, collectively determined from a group of corresponding ion samples. The classification method involves deriving a second dataset from each of the group of corresponding traces, each containing a corresponding set of features. Each feature within the set of corresponding features is determined by the variation of a single isotope or combination of isotopes within the group of corresponding traces. The classification method involves training an untrained or partially untrained classifier using (i) the corresponding set of features from the second dataset of each of the group of training subjects, and (ii) the corresponding diagnostic status of each of the group of training subjects, selected from a first diagnostic status and a second diagnostic status, thereby obtaining a trained classifier.The classifier provides an indicator of whether the test subject has a first biological state related to metal metabolism, based on the value of a set of features obtained from a biological sample related to the metal metabolism of the test subject.

[0028] In some embodiments, the trained classifier is a neural network algorithm, a support vector machine algorithm, a decision tree algorithm, an unsupervised clustering model algorithm, a supervised clustering model algorithm, or a regression model.

[0029] In some embodiments, the trained classifier is polynomial or binary. In some embodiments, the multiple elemental isotopes are selected from the elemental isotopes listed in Table 1.

[0030] In some embodiments, each feature in the set of features is associated with either a single trace out of multiple traces, or with either two traces out of multiple traces. In some embodiments, the set of features is selected from the features listed in Table 2, and optionally, the set of features further includes one or more features listed in Table 3.

[0031] In some embodiments, the first biological condition related to metal metabolism is selected from the group consisting of autism spectrum disorder (ADS), attention deficit / hyperactivity disorder (ADHD), amyotrophic lateral sclerosis (ALS), schizophrenia, irritable bowel disease (IBD), pediatric kidney transplant rejection, and childhood cancer.

[0032] In some embodiments, evaluating a subject for a first biological state related to metal metabolism further includes distinguishing between a first biological state related to metal metabolism and a second biological state related to metal metabolism that is different from the first biological state related to metal metabolism. In some embodiments, the first biological state is autism spectrum disorder, and the second biological state is attention deficit / hyperactivity disorder.

[0033] In some embodiments, the subject is human. In some embodiments, the subject is under 1 year old, under 2 years old, under 3 years old, under 4 years old, or under 5 years old.

[0034] In some embodiments, the biological sample related to the target metal metabolism is selected from the group consisting of hair shafts, teeth, and nails.

[0035] In some embodiments, the method further includes pre-treating the hair shaft with a solvent and / or irradiating the hair shaft with a low-power laser to remove any debris from the hair shaft before sampling the hair shaft of interest. In some embodiments, the biological sample related to the metal metabolism of interest is a hair shaft, and the reference line corresponds to the longitudinal direction of the hair shaft. In some embodiments, the biological sample related to the metal metabolism of interest is a tooth, and the reference line corresponds to the neonatal line of the tooth on the enamel surface of the tooth.

[0036] In some embodiments, the method further includes pretreatment of the biological sample related to the target metal metabolism with a solvent or surfactant before sampling. In some embodiments, the method further includes irradiating the biological sample related to the target metal metabolism with a low-power laser to remove any debris from the biological sample related to the target metal metabolism before sampling.

[0037] In some embodiments, sampling includes irradiating a biological sample related to the target metal metabolism with a laser to extract multiple particles from the biological sample related to the target metal metabolism, and ionizing the multiple particles with an inductively coupled plasma mass spectrometer to obtain multiple ion samples.

[0038] In some embodiments, the multiple locations are ordered such that the first location among the multiple locations along the biological sample related to the metal metabolism of the subject corresponds to the location closest to the tip of the biological sample related to the metal metabolism of the subject. In some embodiments, the multiple locations include at least 100, 150, 200, 250, 300, 350, 400, 450, or 500 locations.

[0039] In some embodiments, each trace within a set of traces contains multiple data points. Each data point is an instance of a particular location among multiple locations.

[0040] In some embodiments, deriving a second dataset involves removing data points from a set of data points that do not satisfy a first criterion. The first criterion includes the mean absolute difference between adjacent data points within the set of data points being three times the standard deviation of the mean absolute difference between adjacent points.

[0041] In some embodiments, the concentration of the corresponding elemental isotope corresponds to the relative abundance of the corresponding elemental isotope to the control elemental isotope, and the control elemental isotope is contained in multiple ionic samples. In some embodiments, the control elemental isotope is sulfur.

[0042] In some embodiments, the set of features is selected from mean diagonal length, determinism, recursion time, entropy, trapping time, and laminarity.

[0043] In some embodiments, the trained classifier is

number

[0044] In some embodiments, the method further includes determining that a subject has a first biological state related to metal metabolism, based on the determination that p(subject) exceeds a predetermined threshold.

[0045] In some embodiments, the biological state related to metal metabolism is associated with periodic dysregulation of the metabolism of multiple metals, where the multiple metals correspond to multiple elemental isotopes.

[0046] According to some embodiments, the classification device includes one or more processors and a memory for storing one or more programs to be executed by the one or more processors. The one or more programs include instructions for executing a classification method. The classification method is executed for each of the multiple training subjects. A first subset of the training subjects in the multiple training subjects has a first diagnostic status corresponding to having a first biological state related to metal metabolism, and a second subset of the training subjects in the multiple training subjects has a second diagnostic status corresponding to not having the first biological state related to metal metabolism. The classification method includes sampling each position at a corresponding set of corresponding reference lines on a corresponding biological sample related to metal metabolism for each training subject, thereby obtaining a set of corresponding ion samples. Each ion sample in the set of corresponding ion samples is for a different position at the corresponding set of corresponding locations. Each position at the corresponding set of corresponding locations represents a different growth period of the corresponding biological sample related to metal metabolism. The classification method includes analyzing each ion sample in the set of corresponding ion samples using a mass spectrometer, thereby obtaining a first dataset containing a corresponding set of traces. Each trace within a group of corresponding traces represents the time-dependent concentration of a corresponding elemental isotope in a group of elemental isotopes, collectively determined from a group of corresponding ion samples. The classification method involves deriving a second dataset from each of the group of corresponding traces, each containing a corresponding set of features. Each feature within the set of corresponding features is determined by the variation of a single isotope or combination of isotopes within the group of corresponding traces. The classification method involves training an untrained or partially untrained classifier using (i) the corresponding set of features from the second dataset of each of the group of training subjects, and (ii) the corresponding diagnostic status of each of the group of training subjects, selected from a first diagnostic status and a second diagnostic status, thereby obtaining a trained classifier.The classifier provides an indicator of whether the test subject has a first biological state related to metal metabolism, based on the value of a set of features obtained from a biological sample related to the metal metabolism of the test subject.

[0047] According to some embodiments, a non-temporary computer-readable storage medium embeds one or more computer programs for classification. The one or more computer programs, when executed by a computer system, include instructions that cause the computer system to execute a classification method. The classification method is executed for each of the multiple training subjects. A first subset of the training subjects in the multiple training subjects has a first diagnostic status corresponding to having a first biological state related to metal metabolism, and a second subset of the training subjects in the multiple training subjects has a second diagnostic status corresponding to not having the first biological state related to metal metabolism. The classification method includes sampling each position at corresponding locations on a corresponding baseline on a corresponding biological sample related to metal metabolism for each training subject, thereby obtaining a corresponding set of ion samples. Each ion sample in the corresponding set of ion samples is for a different position at the corresponding locations. Each position at the corresponding locations represents a different growth period of the corresponding biological sample related to metal metabolism. The classification method includes analyzing each ion sample in the corresponding set of ion samples using a mass spectrometer, thereby obtaining each first dataset containing a corresponding set of traces. Each trace within a group of corresponding traces represents the time-dependent concentration of a corresponding elemental isotope in a group of elemental isotopes, collectively determined from a group of corresponding ion samples. The classification method involves deriving a second dataset from each of the group of corresponding traces, each containing a corresponding set of features. Each feature within the set of corresponding features is determined by the variation of a single isotope or combination of isotopes within the group of corresponding traces. The classification method involves training an untrained or partially untrained classifier using (i) the corresponding set of features from the second dataset of each of the group of training subjects, and (ii) the corresponding diagnostic status of each of the group of training subjects, selected from a first diagnostic status and a second diagnostic status, thereby obtaining a trained classifier.The classifier provides an indicator of whether the test subject has a first biological state related to metal metabolism, based on the value of a set of features obtained from a biological sample related to the metal metabolism of the test subject.

[0048] As disclosed herein, any embodiment disclosed herein can be applied to any aspect, where applicable.

[0049] Additional aspects and advantages of the present disclosure will be readily apparent to those skilled in the art from the following detailed description. Here, only exemplary embodiments of the present disclosure are shown and described. As will be understood, other different embodiments of the present disclosure are possible, and several of their details can be modified in various obvious ways without departing from the present disclosure. Accordingly, the drawings and description should be considered illustrative and not limiting in nature. [Brief explanation of the drawing]

[0050] [Figure 1A] A block diagram of an exemplary computing device according to some embodiments of this disclosure is shown. [Figure 2A] This disclosure provides a flowchart of a method for evaluating a subject for its biological state, according to some embodiments of this disclosure. [Figure 2B] Exemplary figures of target hair, tooth, and nail samples according to some embodiments of this disclosure are provided. [Figure 2C] This disclosure provides an exemplary schematic diagram of a laser for sampling a target hair shaft according to some embodiments of this disclosure. [Figure 2D] This disclosure provides an illustrative diagram of a trace illustrating the concentration of elemental isotopes over time, according to some embodiments of this disclosure. [Figure 2E] This disclosure provides illustrative figures of features corresponding to single-isotope variations derived from traces, according to some embodiments of this disclosure. [Figure 2F]This disclosure provides a diagram of experimental data for distinguishing autism spectrum disorder from other neurodevelopmental disorders according to certain embodiments of this disclosure. In Figure 2F, cases of autism spectrum disorder (labeled as ASD) are contrasted with cases of attention deficit / hyperactivity disorder (labeled as ADHD), subjects diagnosed with comorbid ASD and ADHD (labeled as CM), and neurotypical subjects (labeled as NT) who have not received a neurodevelopmental disorder diagnosis. [Figure 3A-3E] This disclosure provides a collective flowchart of processes and functions for evaluating a subject for a biological state, according to some embodiments of this disclosure, with any block indicated by a dashed box. [Figure 4] This disclosure provides flowcharts of processes and functions for training a classifier to evaluate a subject for a biological state, according to some embodiments of this disclosure, where any block is indicated by a dashed box. [Figures 5A-5D] Experimental receiver operating characteristic (ROC) curves for evaluating autism spectrum disorder in some embodiments are shown. [Figure 6] ROC curves for evaluating the accuracy of the disclosed method for assessing amyotrophic lateral sclerosis (ALS) in some embodiments are shown. [Figure 7] ROC curves for evaluating the accuracy of the disclosed methods for assessing schizophrenia, according to some embodiments, are shown. [Figure 8] ROC curves for evaluating the accuracy of disclosed methods for assessing irritable bowel disorder in some embodiments are shown. [Figure 9] ROC curves for evaluating the accuracy of the disclosed method for assessing kidney transplant rejection, according to some embodiments, are shown. [Figure 10] ROC curves for evaluating the accuracy of the disclosed method for assessing childhood cancer, according to some embodiments, are shown.

[0051] Similar reference numbers refer to the corresponding parts across multiple views of the drawing. The drawing is not drawn to scale. [Modes for carrying out the invention]

[0052] This disclosure provides a system and method for evaluating a subject's biological state related to metal metabolism from a biological sample related to the subject's metal metabolism. In particular, the disclosed method provides a biological sample biomarker that can be obtained non-invasively from the subject. The method can be applied to evaluate subjects of any age and is particularly useful for the diagnosis of children, and even infants under one year of age, to enable early treatment and intervention.

[0053] Definition. The terms used in this disclosure are for the sole purpose of describing specific embodiments and are not intended to limit the invention. Where used in the description of the invention and in the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural form unless the context expressly indicates otherwise. Where used herein, the terms “and / or” will also be understood to mean and encompass any and all possible combinations of one or more of the enumerated items relating to the invention. Where used herein, the terms “comprises” and / or “comprising” specify the presence of the described features, integers, steps, actions, elements, and / or components, but will not be understood to exclude the presence or addition of one or more other features, integers, steps, actions, elements, components, and / or groups thereof.

[0054] As used herein, the term "if" may, depending on the context, be interpreted as meaning "when," "upon," "upon a decision," or "upon detection." Similarly, the phrase "when it is decided" or "[the described condition or event] is detected" may, depending on the context, be interpreted as meaning "when it is decided," "upon a decision," "[the described condition or event] is detected," or "[the described condition or event]."

[0055] As used herein, a biological condition related to metal metabolism (also referred to as a metal metabolism disorder) means a biological condition related to, or caused by, a periodic dysregulation of the metabolism of a particular metal. Periodic dysregulation may manifest as a periodic decrease in the uptake of one or more metals (e.g., deficiency), a periodic increase in the uptake of one or more metals, or a combination of periodic decreases and periodic increases in the uptake of one or more metals. Non-exclusive examples of biological conditions related to metal metabolism include autism spectrum disorder (ADS), attention deficit / hyperactivity disorder (ADHD), amyotrophic lateral sclerosis (ALS), schizophrenia, kidney transplant rejection, certain types of cancer, Alzheimer's disease, Parkinson's disease, Huntington's disease, metabolic disorders (obesity and irritable bowel disease (IBD)), and / or any condition or disorder related to metal metabolism.

[0056] As used herein, a biosample related to metal metabolism refers to a human biosample related to growth (e.g., hair, nails, and teeth) that includes deposits of a particular metal. The biosamples related to metal metabolism in this disclosure have the requirement that growth occurs along a baseline so that the abundance of a deposit of a certain metal is detectable with respect to time. These biosamples related to metal metabolism thereby facilitate the detection of periodic fluctuations in the abundance of a particular metal. In some embodiments, the biosample related to metal metabolism includes a hair shaft in which the baseline corresponds to a line along the longitudinal direction of the hair shaft. In some embodiments, the biosample related to metal metabolism includes a tooth in which the baseline corresponds to a neonatal line of the tooth on the enamel surface of the tooth. In some embodiments, the biosample related to metal metabolism includes a nail in which the baseline corresponds to a line in the direction of nail growth. For example, the baseline extends from the base of the nail to the tip of the nail.

[0057] As used herein, the term “trained classifier” refers to a model (e.g., a machine learning algorithm such as logistic regression, neural networks, regression, support vector machines, clustering algorithms, or decision trees) with specific parameters (weights) and thresholds that is ready to be applied to samples that have not been seen before.

[0058] As used herein, the term “untrained classifier or partially trained classifier” means a model (e.g., a machine learning algorithm such as logistic regression, neural networks, regression, support vector machines, clustering algorithms, or decision trees) that has at least some unfixed parameters (weights) and thresholds, and is ready to be trained on a training set for optimization and fixing of the parameters and thresholds.

[0059] Terms such as "first," "second," etc., may be used herein to describe various elements, but it should be understood that these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, the first subject may be referred to as the second subject without departing from the scope of this disclosure, and similarly, the second subject may be referred to as the first subject. The first and second subjects are both subjects, but they are not the same subject. Furthermore, the terms "subject," "user," and "patient" are used synonymously herein.

[0060] As used herein, the term “subject” refers to a human being (e.g., a male human, a female human, a fetus, a pregnant woman, a child, etc.). In some embodiments, the subject is a male or female at any stage (e.g., a male, a female, or a child).

[0061] As used herein, the term “autism spectrum disorder” refers to a set of neurodevelopmental conditions associated with impairments in social interaction, developmental language and communication skills, and repetitive behaviors. For example, the Centers for Disease Control and Prevention (CDC) standardized criteria for diagnosing autism spectrum disorder include 1) persistent deficits in social communication and social interaction, and 2) restricted, repetitive patterns of behavior, interests, or activities. Autism spectrum disorder includes, for example, autistic disorder (also known as “classical autism”), Asperger's syndrome, and systemic developmental disorder (also known as “atypical” autism).

[0062] As used herein, the term “Recursive Quantitative Analysis” (“RQA”) refers to a nonlinear data analysis that quantifies the number and duration of recurrences in a dynamic system. RQA is used to characterize the behavior of a dynamic system in phase space.

[0063] As used herein, the term “recursive plot” refers to a graphical visualization of time-dependent periodic structures in experimental data.

[0064] As used herein, the term “trace” refers to the time-dependent abundance (or concentration) of an elemental isotope. A trace comprises multiple data points, each associated with a time scale and an abundance scale.

[0065] As used herein, the term “feature” refers, for example, to a dynamic periodic feature extracted from a time-dependent abundance trace of an elemental isotope, or a combination of two or more time-dependent abundance traces of an elemental isotope, by using RQA.

[0066] As used herein, the term “Mean Diagonal Length” (“MDL”) refers to a key measure derived from RQA, reflecting a direct measurement of the average length of the diagonals present in a two-dimensional recursive plot. This measure can be considered an absolute indicator of the duration of the periodic components in a given signal.

[0067] As used herein, the term “determinism” in relation to mean diagonal length refers to the relative ratio of periodic to non-periodic components in a recursive analysis. Determinism indicates the overall periodic content of a given signal.

[0068] As used herein, the term “recurrence time” (“RT2”) refers to the average time interval between diagonal elements, i.e., the interval between periodicities.

[0069] As used herein, the term "entropy" refers to the variability in the distribution of mean diagonal length, where low-entropy signals show little complexity in the distribution of periodic components, and high-entropy signals show diversity in short and long periods.

[0070] As used herein, the term “trapping time” (“TT”) refers to the average length of a layered (vertical or horizontal) structure in a two-dimensional recursive plot that exhibits a stable state, analogous to how the average diagonal length captures the duration of a periodic process.

[0071] As used herein, the term “laminarity” refers to an overall measure of signal stability. Laminarity quantifies the ratio of recurring points belonging to a laminar structure to the total frequency of recurring points.

[0072] The terms used herein are for the sole purpose of describing specific cases and are not intended to be limiting. Where used herein, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context explicitly indicates otherwise. Furthermore, "including," "includes," "having," "has," "with," or any variation thereof, are intended to be comprehensive in the same manner as the term "comprising," to the extent that they are used in either the detailed description and / or the claims.

[0073] Multiple embodiments are described below with reference to illustrative uses. It should be understood that numerous specific details, relationships, and methods are described in order to provide a complete understanding of the features described herein. However, those skilled in the art will readily recognize that the features described herein may be implemented without one or more specific details, or by other means. Since some actions may occur in a different order and / or simultaneously with other actions or events, the features described herein are not limited by the order of the illustrated actions or events. Furthermore, not all illustrated actions or events are required to implement the methodology in accordance with the features described herein.

[0074] Embodiments are described in detail here, examples of which are illustrated in the accompanying figures. In the following detailed description, numerous specific details are given in order to provide a complete understanding of the Disclosure. However, it will be apparent to those skilled in the art that the Disclosure can be implemented without these specific details. In other cases, well-known methods, procedures, components, circuits, and networks are not described in detail so as not to unnecessarily obscure the aspects of the embodiments.

[0075] An exemplary embodiment of the system. Herein, an overview of some aspects of the present disclosure is provided, and details of an exemplary system are described in conjunction with Figure 1. Figure 1A shows a block diagram of an exemplary computing device 100 according to some embodiments of the present disclosure. In some implementations, the device 100 includes one or more processing unit CPUs 102 (also referred to as processors), one or more network interfaces 104, a user interface 106, non-persistent memory 111, persistent memory 112, and one or more communication buses 114 for interconnecting these components. The one or more communication buses 114 optionally include circuits (sometimes referred to as chipsets) that interconnect and control communication between system components. Non-persistent memory 111 typically includes high-speed random-access memory such as DRAM, SRAM, DDR RAM, ROM, EEPROM, and flash memory, while persistent memory 112 typically includes CD-ROMs, digital multi-purpose discs (DVDs) or other optical storage devices, magnetic cassettes, magnetic tapes, magnetic disk storage devices or other magnetic storage devices, magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state storage devices. Persistent memory 112 optionally includes one or more storage devices located away from the CPU 102. Non-volatile memory devices in persistent memory 112 and non-persistent memory 112 include non-temporary computer-readable storage media. In some implementations, non-persistent memory 111 or alternatively, non-temporary computer-readable storage media store the following programs, modules, and data structures, or subsets thereof, possibly in combination with persistent memory 112. ●Any operating system 116 including procedures for handling various basic system services and procedures for performing hardware-dependent tasks. ● Any network communication module (or instruction) 118 for connecting system 100 to other devices and / or communication network 104 ● An optional classifier training module 120 for training classifiers to evaluate subjects regarding biological conditions related to metal metabolism. ●Optional datastore for a dataset of biological samples from training subjects 122, including feature data for one or more training subjects 124, wherein the feature data includes parameters associated with each of the features 126, and a diagnostic status 128 (e.g., an indicator of whether each training subject is diagnosed with a biological condition related to metal metabolism or not), ● An arbitrary classifier validation module 130 for validating classifiers that distinguish biological states related to metal metabolism. ●Any data store for the dataset of biological samples from 132 subjects of verification ● For example, any patient classification module 134 for classifying subjects having a biological condition related to metal metabolism, as trained using the classifier training module 120.

[0076] In various implementations, one or more of the elements identified above are stored in one or more of the aforementioned memory devices and correspond to a set of instructions for performing the functions described above. The modules, data, or programs (e.g., instruction sets) identified above do not need to be implemented as separate software programs, procedures, datasets, or modules; therefore, various subsets of these modules and data may be combined or rearranged in various implementations. In some implementations, non-persistent memory 111 optionally stores a subset of the modules and data structures identified above. Furthermore, in some embodiments, the memory stores additional modules and data structures not described above. In some embodiments, one or more of the identified elements are stored in a computer system other than that of the visualization system 100 and are addressable by the visualization system 100. As a result, the visualization system 100 can retrieve all or part of such data when needed.

[0077] In some embodiments, the system 100 is connected to or includes one or more analytical devices for performing chemical analysis. For example, an optional network communication module (or instruction) 118 is configured to connect the system 100 to one or more analytical devices, for example, via a communication network 104. In some embodiments, one or more analytical devices include a laser-induced inductively coupled plasma mass spectrometer (LA-ICP-MS).

[0078] Figure 1 shows "System 100," but the figure is intended not as a structural schematic of the implementation described herein, but as a functional description of various features that may be present in the computer system. In practice, as will be recognized by those skilled in the art, items shown separately can be combined, and some items can be separated. Furthermore, although Figure 1 depicts certain data and modules in non-persistent memory 111, some or all of this data and modules may be in persistent memory 112.

[0079] Classification method. The system disclosed herein is shown with reference to Figure 1, but the detailed processes and functions of Method 200 for evaluating a subject for the biological state related to metal metabolism from a biological sample are provided in conjunction with Figures 2A to 2F.

[0080] As defined above, biomaterials related to metal metabolism (also referred to herein as “biological materials”) include human biomaterials associated with deposits of a particular metal and associated with growth (e.g., hair, nails, and teeth). Biomaterials related to metal metabolism in this disclosure have the requirement that growth manifests along a baseline such that the abundance of a deposit of a certain metal is detectable with respect to time. In some embodiments, biomaterials related to metal metabolism include hair shafts in which the baseline corresponds to a line along the longitudinal direction of the hair shaft. In some embodiments, biomaterials related to metal metabolism include teeth in which the baseline corresponds to a neonatal line of the tooth on the enamel surface of the tooth. In some embodiments, biomaterials related to metal metabolism include nails in which the baseline corresponds to a line in the direction of nail growth. For example, the baseline extends from the base of the nail to the tip of the nail.

[0081] In some embodiments, method 200 includes obtaining a biological sample (e.g., a strand of hair including the hair shaft) (202). The subject is human. In some embodiments, the subject is a child under 5 years of age (e.g., the child is under 5 years, 4 years, 3 years, 2 years, 1 year, 9 months, 6 months, 3 months, or 1 month). In some embodiments, the subject is an adult. Section I of Figure 2B provides exemplary images of a hair sample of a subject including the hair shaft according to some embodiments of the present disclosure. The hair sample may be simply cut from the subject (e.g., with the help of scissors). Thus, the method of obtaining the hair sample is non-invasive. The obtained hair sample has a minimum length of 1 cm (e.g., the hair sample is 1 cm, 2 cm, 3 cm, 4 cm, or 5 cm in length). The hair sample may include any part of the hair (e.g., the tip or the part between the tip and the hair follicle). In particular, there is no special requirement that the hair sample include the hair follicle. Section II of Figure 2B provides exemplary images of a tooth sample according to certain embodiments of the present disclosure. Section III of Figure 2B provides exemplary images of a nail sample according to certain embodiments of the present disclosure. In the example of teeth or hair, obtaining a biological sample refers to positioning the subject so that the teeth or nails can be sampled.

[0082] In some embodiments, the obtained biological sample is pretreated (204) by washing the biological sample with one or more solvents and / or surfactants and drying it. In the example where the biological sample is hair, the hair sample is washed with TRITON X-100 (registered trademark) and ultrapure metal-free water (e.g., MILLI-Q (registered trademark) water) and dried overnight in an oven (e.g., 60 °C). The pretreatment further includes preparing the hair shaft for measurement by placing the hair shaft on a slide glass (e.g., a microscope slide glass) having an adhesive film (e.g., double-sided tape). The hair shaft is positioned such that the hair shaft is substantially straight. Then, the slide glass with the hair shaft is placed into a laser ablation inductively coupled plasma mass spectrometer (LA-ICP-MS) for performing analysis (206). When the biological sample is a tooth or a nail, the surface of the biological sample is washed (e.g., with a surfactant, water, or one or more solvents). The subject is positioned near the LA-ICP-MS for performing analysis.

[0083] In some embodiments, the LA-ICP-MS analysis includes pre-ablating the biological sample to remove surface debris and / or impurities from the biological sample. The pre-ablating is performed using a very low laser energy such that particles are emitted only from the surface of the biological sample and not from beneath the surface of the biological sample. For example, the pre-ablating is performed using a laser wavelength of 193 nm and a laser energy of less than 0.4 J / cm 2 (e.g., the laser energy is 0.4 J / cm 2 , 0.3 J / cm 2 , 0.2 J / cm 2 , or 0.1 J / cm​​​​​​​​​After pre-ablation, method 200 includes laser sampling of the biological sample to obtain ion samples from each position along a reference line of the biological sample (208). As described above, in the example of a hair shaft, the reference line corresponds to a line along the longitudinal direction of the hair shaft. For example, section A of Figure 2B shows a hair shaft with a reference line 201 along the longitudinal direction of the hair shaft. In the example of a tooth, the reference line corresponds to the neonatal line of the tooth on the enamel surface of the tooth. For example, section II of Figure 2B shows a tooth 220 including portions of enamel 226 and primary dentin 224. The reference line 222 corresponds to the neonatal line of tooth 220. Neonatal line as used herein refers to a specific band of growth lines on the enamel portion of the tooth. In the example of a nail, the reference line corresponds to a line in the direction of nail growth. For example, section II of Figure 2B shows a nail 230 with a reference line 232 extending from the base of the nail to the tip of the nail. Sampling involves irradiating a biological sample with a laser beam (e.g., a laser to ablate the hair shaft) and ionizing multiple particles with an inductively coupled plasma mass spectrometer. For example, regions 200A and 200B in section I of Figure 2B correspond to exemplary locations along the hair shaft irradiated with the laser during laser ablation. The mass spectrometer analyzes the ionized samples acquired from each location (210). Figure 2C provides an exemplary schematic diagram of a laser sampling a target hair shaft according to some embodiments of the present disclosure. The laser 202 in Figure 2C irradiates region 200C on the hair shaft, thereby emitting particles 204. The particles 204 are ionized by an inductively coupled plasma (ICP) and further analyzed by a mass spectrometer (MS).

[0085] In some embodiments, the laser irradiation is at a wavelength of 193 nm and 0.6-1.5 J / cm². 2 Laser energy in the range of (for example, laser energy is 0.6 J / cm²) 2 , 0.7 J / cm 2 , 0.8 J / cm 2 , 0.9 J / cm 2 1.0 J / cm 2 , 1.1 J / cm 2 , 1.2 J / cm 2 , 1.3J / cm2 1.4 J / cm 2 , or 1.5 J / cm 2 This is done using a laser having ( ). In some embodiments, the laser energy is 0.9 to 1.3 J / cm 2 The range is as follows: In some embodiments, the laser has a beam diameter in the range of 25 to 35 micrometers (e.g., 25, 27.5, 30, 32.5, or 35 micrometers). In some embodiments, the laser has a beam diameter of 30 micrometers. In the example of sampling hair shafts, the size, wavelength, and / or laser energy of the laser beam are adjusted so that the laser sampling ablates the majority of the hair shaft and does not emit particles from the adhesive film and / or slide glass holding the hair shaft.

[0086] Laser irradiation is repeated, and elemental isotope data is sequentially collected at multiple locations along the biological sample (e.g., regions 200A and 200B of the hair shaft in section I of Figure 2B). In some embodiments, the multiple locations along the baseline of the biological sample include at least 100 locations (e.g., locations 100, 150, 200, 250, 300, 350, 400, 450, or 500). In some embodiments, each location (e.g., regions 200A and 200B in section I of Figure 2B) is adjacent to one another. By this method, each region corresponding to a different location on the biological sample (e.g., regions 200A and 200B) is associated with the abundance of elemental isotopes (e.g., the metallic isotopes Zn, Fe, Pb, and Mn shown in Figure 2C). In some embodiments, each location is separated by a predetermined distance. In some embodiments, sampling is performed along a baseline of the biological sample, starting from each location closest to the hair tip (e.g., the location corresponding to the youngest age of the subject). Generally, sampling can be performed starting from each location closest to the tip or root, provided that the sampling direction is known and an appropriate trained classifier is used for analysis.

[0087] Laser sampling generates a set of data points. Each set of data points corresponds to the abundance (e.g., concentration) of each elemental isotope measured at multiple locations along the biological sample. Each location on the baseline of the biological sample corresponds to a specific growth time of the biological sample. In some embodiments, in the case of a hair shaft, each location corresponds to a period of approximately 130 minutes of hair growth (e.g., a period of hair growth calculated using a laser beam size of 30 micrometers and an average hair growth rate of 1 cm per month). By correlating multiple locations along the baseline of the biological sample to the corresponding periods of growth, a first dataset containing multiple traces is obtained. Each trace contains the time-dependent abundance of each elemental isotope measured from the biological sample.

[0088] Figure 2D provides an exemplary diagram of trace 208 according to certain embodiments of the present disclosure. Each data point in Figure 2D corresponds to the abundance (i.e., count ratio on the y-axis) of a particular elemental isotope measured at multiple locations along the biological sample (i.e., laser distance on the bottom x-axis). The distance traveled by the laser along the biological sample corresponds to the estimated growth (i.e., biological time) of the biological sample, as shown on the top x-axis. For example, Figure 2D shows the abundance of a particular elemental isotope measured for a hair along a distance of 1.2 cm (12,000 micrometers). Such a distance corresponds to a biological time of approximately 35 days. The biological time is estimated using the average rate of hair growth (e.g., 1 cm per month).

[0089] In some embodiments, the multiple elemental isotopes are selected from the elemental isotopes listed in Table 1. In some embodiments, the multiple elemental isotopes comprise at least 50%, 60%, 70%, 80%, or 90% of the isotopes included in Table 1. [Table 1]

[0090] In some embodiments, method 200 includes analyzing a first dataset containing multiple acquired traces (212), where each trace corresponds to a time-dependent abundance (e.g., time-dependent concentration) of a respective elemental isotope. In some embodiments, analyzing the data includes performing customized operations to clean the data (214). In some embodiments, cleaning the data includes smoothing the data over a period of time and / or removing data points that are above or below a predetermined threshold. In some embodiments, data analysis includes removing data points from a trace where the mean absolute difference between adjacent data points is three times the standard deviation of the mean absolute difference between adjacent points. Figure 2D illustrates the operation of removing data points above a predetermined threshold. Peak 210 corresponds to a data point where the mean absolute difference between adjacent data points is three times or more the standard deviation of the mean absolute difference between adjacent points. Therefore, peak 210 is removed from trace 208.

[0091] In some embodiments, analyzing the dataset further includes normalizing each trace against an internal standard. In some embodiments, in the example where the sample is a hair shaft, the internal standard may be sulfur, the most abundant elemental isotope in the hair, and therefore can be used as a measure of hair density and / or hardness. However, in practice, any element detected in a sample that is evenly incorporated during the development / growth of a biological sample that does not fluctuate with environmental exposure (e.g., diet) may serve as an internal standard, including any of the elements disclosed in the table of this disclosure. For example, if the sample is a tooth, bismuth-209 may be used as the internal standard.

[0092] Method 200 involves performing recursive quantification analysis (RQA) to analyze a first dataset containing time-dependent traces of elemental isotopes and obtain a set of features that describe the dynamic periodic properties of the traces. RQA measures the variation of the time-dependent traces of elemental isotopes. RQA involves estimating features that describe the periodic properties in a given waveform, including determinism, mean diagonal length, and entropy. The RQA method and features are described, for example, in Webber et al., “Simpler Methods Do It Better: Success of Recurrence Quantification Analysis as a General Purpose Data Analysis Tool,” Physics Letters A 373, 3753-3756 (2009), and Marwan et al., “Recurrence Plots for the Analysis of Complex Systems,” Physics Reports 438, 237-239 (2007), the contents of each of these are incorporated herein by reference in their entirety. In some embodiments, the time-dependent traces of elemental isotopes are analyzed using other analytical methods known in the art, such as Fourier transforms, wavelet analysis, and Kossiner analysis. Such methods may be applied to derive similar metrics, including spectral analysis of frequency components and their associated powers. These metrics and related derived metrics may be used instead of features derived from RQA to analyze the time-dependent traces of elemental isotopes obtained from biological samples for predictive classification purposes.

[0093] RQA includes constructing recursive plots (216) to visualize and analyze the dynamic temporal structure in each acquired trace. Figure 2E provides an exemplary figure of the variation in the abundance of a single isotope derived from each trace, according to some embodiments of the present disclosure. Section I of Figure 2E shows traces corresponding to the time-dependent abundance (or concentration) of copper (Cu) measured from the hair stalk of interest. The y-axis represents the measured abundance of copper, and the x-axis represents the continuous measurements along the hair stalk, reflecting the longitudinal increment in time. Section II of Figure 2E is a phase portrait derived from the traces of Section I. From the one-dimensional traces measured from the hair stalk, additional dimensions are computationally derived to embed the traces in a higher-dimensional space referred to as the phase portrait, where t refers to the values ​​of the original trace, and the dimensions (t+τ) and (t+2τ) are derived from delaying the original time series by intervals τ. Subsequent analysis is then performed on the embedded phase portrait to construct recursive plots and recursive quantitative analyses. Section III shows recursive quantification plots of copper isotopes derived from the phase portraits shown in Section II. The RQA method examines the delay intervals between states in a given system, and the black dots reflect the time intervals when the system revisited the same state. Periodic processes in which the system continuously repeats a given pattern of states appear as diagonal black lines in the recursive plot, stable periods appear as square structures, spurious repeats appear as black dots, and intrinsic events appear as white spaces.

[0094] In some embodiments, the recursive plot is constructed for a trace of a single elemental isotope (for example, for an elemental isotope selected from Table 1) or for a combination of two elemental isotopes. For example, Figure 2E shows a recursive plot of copper isotopes. Alternatively, the recursive plot is constructed to visualize a periodic pattern of interaction between two elemental isotopes. In some embodiments, the recursive plot is constructed for a combination of three or more elemental isotopes.

[0095] Method 200 further includes analyzing the recursive plot to obtain a set of features associated with the recursive plot (218). These features, which may interchangeably be called “tunic features” or “dynamic features,” provide a quantitative measure that describes the periodicity present across multiple traces. Features are selected from mean diagonal length (MDL), determinism (or predictability), recursion time (RT), entropy, trapping time (TT), and laminarity. The definition of each of these feature types is given in the definitions section above.

[0096] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of two elemental isotopes, or a combination of more than two elemental isotopes) is selected from the features listed in Table 2.

[0097] In some embodiments, the set of features includes all the features listed in Table 2.

[0098] In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Table 2. In some embodiments, the features thus derived from Table 2 are considered “core” features for evaluating a subject for a first biological condition (e.g., autism spectrum disorder) as per this disclosure. In some embodiments, the set of features further includes one or more features listed in Table 3 (in addition to the core features). [Table 2] [Table 3-1] [Table 3-2] [Table 3-3] [Table 3-4] [Table 3-5]

[0099] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of three elemental isotopes, or a combination of two or more elemental isotopes) is selected from the features listed in Table 2. In some embodiments, the set of features includes all the features listed in Table 3. In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Table 3.

[0100] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of two elemental isotopes, or a combination of more than two elemental isotopes) is selected from the features listed in Tables 2 and 3. In some embodiments, the set of features includes all the features listed in Tables 2 and 3. In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Tables 2 and 3.

[0101] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of two elemental isotopes, or a combination of more than two elemental isotopes) is selected from the features listed in Table 4. In some embodiments, the set of features includes all the features listed in Table 4. In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Table 4.

[0102] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of two elemental isotopes, or a combination of more than two elemental isotopes) is selected from the features listed in Table 5. In some embodiments, the set of features includes all the features listed in Table 5. In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Table 5.

[0103] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of two elemental isotopes, or a combination of more than two elemental isotopes) is selected from the features listed in Table 6. In some embodiments, the set of features includes all the features listed in Table 6. In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Table 6.

[0104] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of two elemental isotopes, or a combination of more than two elemental isotopes) is selected from the features listed in Table 7. In some embodiments, the set of features includes all the features listed in Table 7. In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Table 7.

[0105] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of two elemental isotopes, or a combination of more than two elemental isotopes) is selected from the features listed in Table 8. In some embodiments, the set of features includes all the features listed in Table 8. In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Table 8.

[0106] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of two elemental isotopes, or a combination of more than two elemental isotopes) is selected from the features listed in Table 9. In some embodiments, the set of features includes all the features listed in Table 9. In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Table 9.

[0107] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of two elemental isotopes, or a combination of more than two elemental isotopes) is selected from the features listed in Table 10. In some embodiments, the set of features includes all the features listed in Table 10. In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Table 10.

[0108] In some embodiments, a set of features in which each feature is associated with a specific elemental isotope or combination of elemental isotopes (e.g., a combination of two elemental isotopes, or a combination of more than two elemental isotopes) is selected from features listed in any combination of Tables 2, 3, 4, 5, 6, 7, 8, 9, and 10. In some embodiments, the set of features includes all features listed in Tables 2, 3, 4, 5, 6, 7, 8, 9, and 10. In some embodiments, the set of features includes at least 5%, 10%, 15%, 20%, or 25% of the features listed in Tables 2, 3, 4, 5, 6, 7, 8, 9, and 10.

[0109] Method 200 further includes inputting the acquired set of features into a trained classifier (220). In some embodiments, the trained classifier includes a predictive computation algorithm for acquiring the probability of objects having a biological state related to metal metabolism (222). In some embodiments, the predictive computation algorithm computes Equation 1.

number

[0110] Features 1-k are those listed in Table 2, and are arbitrarily selected from Table 3. Weight parameter β 1,…,k The probability p(subject) is defined based on the training of the classifier. The probability p(subject) is provided as a number in the range of 0 to 1, where 1 corresponds to a 100% probability that the subject has a biological condition related to metal metabolism.

[0111] In some embodiments, method 200 also includes applying a predetermined threshold to the obtained probability p(subject) (224). If the obtained probability p(subject) exceeds the predetermined threshold, the subject is evaluated as having a biological state related to metal metabolism. If the obtained probability is less than the predetermined threshold, the subject is evaluated as not having a biological state related to metal metabolism. In some embodiments, the predetermined threshold is 0.3 to 0.6 (for example, the predetermined threshold is 0.3, 0.35, 0.4, 0.45, 0.5, 0.55, or 0.6). In some embodiments, the predetermined threshold is 0.45. In some embodiments, the obtained probability is expressed in terms of the relevant odds (for example, an odds ratio (OR) that can be derived from the probability such that OR = p / (1-p)). For example, the evaluation includes evaluating the odds that the subject has a biological state related to metal metabolism.

[0112] In some embodiments, Method 200 further includes distinguishing a first biological state related to metal metabolism from an alternative state, e.g., a second biological state related to metal metabolism. In some embodiments, the alternative state is associated with the absence of a known state (e.g., neuronal type (NT)). In some embodiments, the first biological state related to metal metabolism is associated with autism spectrum disorder (ASD), and the alternative state is associated with attention deficit / hyperactivity disorder (ADHD). In some embodiments, the alternative state is any other neurodevelopmental state, or a comorbid diagnosis of two neurodevelopmental states. Figure 2F provides a diagram of experimental data illustrating the distinction between autism spectrum disorder (ASD) and other neurodevelopmental disorders according to some embodiments of the present disclosure. Based on the experimental data shown in Figure 2F, Method 200 of the present disclosure can distinguish between autism spectrum disorder and ADHD. As shown, the present disclosure can also distinguish autism spectrum disorder from comorbidity (CM) cases diagnosed for both autism spectrum disorder and ADHD.

[0113] Here, details of the process and function of Method 200 for evaluating a subject for a biological state related to metal metabolism from a biological sample are disclosed with reference to Figure 2, and Figures 3A to 3E collectively provide flowcharts of the basic process and function of Method 3000 for evaluating a subject for a biological sample related to metal metabolism, according to some embodiments of this disclosure, where any block is indicated by a dashed box. In some embodiments, Method 3000 corresponds to Method 200.

[0114] Block 3100 in Figure 3A. Method 3000 includes, for example, using a laser (e.g., LA-ICP-MS) to sample each of the locations at multiple positions along a reference line on a biological sample related to the metal metabolism of the subject, thereby obtaining multiple ionic samples (e.g., regions 200A and 200B of the hair shaft in section I of Figure 2B). Each ionic sample in the multiple ionic samples corresponds to a different position at the multiple locations, and each position at the multiple locations represents a different growth period of the biological sample related to metal metabolism.

[0115] Block 3200 in Figure 3A. Method 3000 includes analyzing each ionic sample in multiple ionic samples using a mass spectrometer to obtain a first dataset. The first dataset includes multiple traces (e.g., trace 208 in Figure 2D). Each trace in the multiple traces is the time-course concentration of the corresponding elemental isotope in multiple elemental isotopes, collectively determined from the multiple ionic samples.

[0116] Block 3300 in Figure 3A. Method 3000 involves deriving a second dataset from multiple traces containing a set of features (e.g., a set of features selected from the features listed in Table 2). Each feature in the set of features is determined by the variation of a single isotope or combination of isotopes across the multiple traces. For example, Section III in Figure 2E shows a recursive plot of copper isotopes derived from the traces in Section II of Figure 2E. The variation in copper isotope abundance is observed as a diagonal pattern in the recursive plot.

[0117] Block 3400 in Figure 3A. In some embodiments, method 3000 also includes inputting a set of features into a trained classifier, thereby obtaining from the trained classifier the probability that a subject has a first biological state related to metal metabolism. In some embodiments, the trained classifier is a neural network algorithm, a support vector machine algorithm, a decision tree algorithm, an unsupervised clustering model algorithm, a supervised clustering model algorithm, or a regression model.

[0118] Block 3110 in Figure 3B. In some embodiments, sampling includes using a laser to irradiate a biological sample related to the target metal metabolism with a laser, thereby extracting multiple particles from the biological sample related to the target metal metabolism, and ionizing the multiple particles with an inductively coupled plasma mass spectrometer, thereby obtaining multiple ion samples (e.g., Figure 2C).

[0119] Block 3120 in Figure 3B. In some embodiments, multiple locations along the hair shaft (e.g., regions 200A and 200B of the hair shaft in section I of Figure 2B) are ordered such that the first location among the multiple locations along the biological sample related to the metal metabolism of the subject corresponds to the location closest to the tip of the biological sample related to the metal metabolism of the subject.

[0120] Block 3130 in Figure 3B. Method 3000 also includes a biological sample associated with the metal metabolism of the target and the solvent or surfactant before sampling the target hair shaft. For example, the hair shaft is washed with TRITON X-100® and ultra-high purity metal-free water (e.g., MILLI-Q® water) and dried overnight in an oven (e.g., 60°C).

[0121] Block 3140 in Figure 3B. Method 3000 also includes irradiating a biological sample related to the metal metabolism of the target with a low-power laser before sampling the hair shaft of the target to remove any debris from the biological sample related to the metal metabolism of the target (e.g., pre-removal of hair shafts, teeth, or nails). For example, pre-ablation is performed with a laser wavelength of 193 nm and 0.4 J / cm². 2 Laser energy less than (for example, laser energy is 0.4 J / cm²) 2 , 0.3 J / cm 2 , 0.2 J / cm 2 , or 0.1 J / cm² 2 ) is performed using. In some embodiments, the laser energy is 0.2 J / cm 2 ~0.4J / cm 2 It is within the range.

[0122] Block 3141 in Figure 3B. The biological specimens related to the target metal metabolism are selected from the group consisting of hair shafts, teeth, and nails (for example, hair shafts, teeth, and nails exemplified in sections I, II, and III of Figure 2B, respectively).

[0123] Block 3141-1 in Figure 3B. The biological sample related to the target metal metabolism is the hair shaft, and the reference line corresponds to the longitudinal direction of the hair shaft (e.g., reference line 201 in section I of Figure 2B).

[0124] Block 3141-1 in Figure 3B. The biological sample related to the metal metabolism of the subject is a tooth, and the reference line corresponds to the neonatal line of the tooth on the enamel surface of the tooth (e.g., reference line 222 along the neonatal line of tooth 220 in section II of Figure 2B). In some embodiments, the biological sample related to the metal metabolism of the subject is a nail, and the reference line corresponds to a line extending from the base of the nail to the tip of the nail (e.g., reference line 232 of nail 230 in section III of Figure 2B).

[0125] Block 3210 in Figure 3C. Multiple elemental isotopes are selected from the elemental isotopes listed in Table 1. In some embodiments, multiple elemental isotopes include at least 50%, 60%, 70%, 80%, or 90% of the isotopes included in Table 1.

[0126] Block 3220 in Figure 3C. Each trace within the multiple traces contains multiple data points. Each data point is an instance of each position at multiple locations. In some embodiments, each trace contains at least 100 locations (e.g., 100, 150, 200, 250, 300, 350, 400, 450, or 500 locations). In some embodiments, each data point corresponds to a period of approximately 130 minutes of hair growth (e.g., the period of hair growth is calculated using a laser beam size of 30 micrometers and an average hair growth rate of 1 cm per month).

[0127] Block 3230 in Figure 3C. The concentration of the corresponding elemental isotope corresponds to the relative abundance of the corresponding elemental isotope relative to the control elemental isotope. The control elemental isotope is contained in multiple ionic samples. In some embodiments, the control elemental isotope is sulfur.

[0128] Block 3310 in Figure 3D. The set of features is selected from the features listed in Table 2. In some embodiments, the set of features includes the features listed in Table 2. In some embodiments, the set of features includes at least 50%, 60%, 70%, 80%, or 90% of the features listed in Table 2. Each feature in the set of features is associated with each of a single trace among a group of traces, or with each of two of a group of traces.

[0129] Block 3320 in Figure 3D. The set of features includes, in addition to the features selected from those listed in Table 2, one or more features listed in Table 3.

[0130] Block 3330 in Figure 3D. The derivation of the second dataset involves removing data points from a set of data points that do not satisfy the first criterion. In some embodiments, the first criterion includes the mean absolute difference between adjacent data points in a set of data points being three times the standard deviation of the mean absolute difference between adjacent points (for example, peak 210 is removed from trace 208 in Figure 2D).

[0131] Block 3340 in Figure 3D. The set of features is selected from mean diagonal length, determinism, recursion time, entropy, trapping time, and laminarity.

[0132] Block 3410 in Figure 3E. In some embodiments, the trained classifier is

number

[0133] Block 3420 in Figure 3E. As p (the subject) is determined to exceed a predetermined threshold, the subject is determined to have a biological state related to metal metabolism.

[0134] Block 3500 in Figure 3E. In some embodiments, evaluating a subject for a biological state related to metal metabolism further includes distinguishing between a first biological state related to metal metabolism and a second biological state related to metal metabolism that is different from the first biological state related to metal metabolism.

[0135] Block 3510 in Figure 3E. In some embodiments, the first biological state is autism spectrum disorder, and the second biological state is attention deficit / hyperactivity disorder.

[0136] Block 3510 in Figure 3E. In some embodiments, the first biological condition related to metal metabolism is selected from the group consisting of autism spectrum disorder (ADS), attention deficit / hyperactivity disorder (ADHD), amyotrophic lateral sclerosis (ALS), schizophrenia, irritable bowel disease (IBD), pediatric kidney transplant rejection, and childhood cancer.

[0137] In some embodiments, the method 3000 described with respect to Figures 3A to 3E is executed by a device that runs one or more programs (for example, one or more programs stored in non-persistent memory 111 or persistent memory 112 in Figure 1) that include instructions for performing the method 3000. In some embodiments, the method 3000 is executed by a system that includes at least one processor (for example, a processing core 102) and memory (for example, one or more programs stored in non-persistent memory 111 or persistent memory 112) that include instructions for performing the method 3000.

[0138] Training of classifiers. Herein, the method and features of Method 3000 are disclosed with reference to Figures 3A to 3E, and Figure 4 provides a flowchart of the process and function of Method 4000 for training a classifier to evaluate a subject for a biological condition related to metal metabolism, according to some embodiments of the present disclosure, where any block is indicated by a dashed box. The method for training a classifier includes collecting biological samples related to metal metabolism from a plurality of training subjects, each training subject, and training a classifier using the collected biological samples. The training subjects are humans. Each training has a diagnostic status indicating that it has been diagnosed with a biological condition related to metal metabolism or not diagnosed with a biological condition related to metal metabolism. In some embodiments, the training subjects are children aged 5 years or younger (e.g., 5 years, 4 years, 3 years, 2 years, 1 year, 9 months, 6 months, 3 months, or 1 month or younger). With respect to blocks 4100 to 4300, the steps of Method 4000 are performed for each training subject in a plurality of training subjects.

[0139] Block 4100 in Figure 4. Method 4000 includes using a laser to sample each position at corresponding locations on corresponding reference lines on corresponding biological samples related to the metal metabolism of each subject to training, thereby obtaining corresponding ionic samples: each ionic sample in the corresponding ionic samples for different positions at corresponding locations, and each position at corresponding locations representing different growth periods of the corresponding biological sample related to metal metabolism.

[0140] Block 4200 in Figure 4. Method 4000 involves using a mass spectrometer to obtain each ion sample in a group of corresponding ion samples, thereby acquiring each first dataset containing a group of corresponding traces. Each trace in the group of corresponding traces is the time-dependent concentration of the corresponding elemental isotope in a group of elemental isotopes, collectively determined from the group of corresponding ion samples.

[0141] Block 4300 in Figure 4. Method 4000 involves deriving each second dataset from a group of corresponding traces containing a corresponding set of features, where each feature in the corresponding set of features is determined by the variation of a single isotope or combination of isotopes in the group of corresponding traces.

[0142] Block 4400 in Figure 4. Method 4000 further includes training an untrained or partially untrained classifier using (i) a corresponding set of features from a second dataset of each of the multiple training subjects, and (ii) a corresponding diagnostic status of each of the multiple training subjects, selected from a first diagnostic status and a second diagnostic status, thereby obtaining a trained classifier. The trained classifier provides an index of whether a test subject has a first biological state related to metal metabolism, based on the feature values ​​of a set of features obtained from a biological sample of the test subject related to metal metabolism. In some embodiments (Block 4410), the trained classifier is a neural network algorithm, a convolutional neural network algorithm, a support vector machine algorithm, a decision tree algorithm, an unsupervised clustering model algorithm, a supervised clustering model algorithm, or a regression model. In some embodiments (Block 4420), the trained classifier is polynomial or binary. In some embodiments, a trained classifier can be used to make a binary prediction as to whether a sample originated from an object having a first biological state related to metal metabolism, or it may be a polynomial classifier, where objects without a diagnosis are distinguished from objects having a first biological state related to metal metabolism or a second biological state related to metal metabolism, where the second biological state is different from the first biological state.

[0143] In some embodiments, the classifier is a neural network or a convolutional neural network. See Vincent et al., 2010, “Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion,” J Mach Learn Res 11, pp. 3371-3408, Larochelle et al., 2009, “Exploring strategies for training deep neural networks,” J Mach Learn Res 10, pp. 1-40, and Hassoun, 1995, Fundamentals of Artificial Neural Networks, Massachusetts Institute of Technology. Each of these is incorporated herein by reference.

[0144] SVM is an SVM, Cristianini and Shawe-Taylor, 2000, “An Introduction to Support Vector Machines,” Cambridge University Press, Cambridge, Boser et al., 1992, “A training algorithm for optimal margin classifiers,” in Proceedings of the 5 thThis is described in *Annual ACM Workshop on Computational Learning Theory*, ACM Press, Pittsburgh, Pa., pp. 142-152; *Vapnik*, 1998, *Statistical Learning Theory*, Wiley, New York; *Mount*, 2001, *Bioinformatics: Sequence and Genome Analysis*, Cold Spring Harbor Laboratory Press, Cold Spring Harbor, NY, Duda; *Pattern Classification*, Second Edition, 2001, John Wiley & Sons, Inc., pp. 259, 262-265; and *Hastie*, 2001, *The Elements of Statistical Learning*, Springer, New York; and *Furey et al.*, 2000, *Bioinformatics* 16, 906-914, each of which is incorporated herein by reference in its entirety. When used for classification, SVM separates a given set of binary-labeled data using a hyperplane furthest away from the labeled data. When linear separation is not possible, SVM can work in combination with "kernel" techniques that automatically implement nonlinear mapping to the feature space. The hyperplane found by the SVM in the feature space corresponds to the nonlinear decision boundary in the input space.

[0145] Decision trees are generally described in Duda, 2001, Pattern Classification, John Wiley & Sons, Inc., New York, pp. 395–396, and are incorporated herein by reference. Tree-based methods divide the feature space into a set of rectangles and then fit a model (such as a constant) to each. In some embodiments, the decision tree is a random forest regression. One specific algorithm that can be used is Classification and Regression Tree (CART). Other specific decision tree algorithms include, but are not limited to, ID3, C4.5, MART, and Random Forest. CART, ID3, and C4.5 are described in Duda, 2001, Pattern Classification, John Wiley & Sons, Inc., New York, pp. 396–408 and pp. 411–412, and are incorporated herein by reference. CART, MART, and C4.5 are described in Hastie et al., 2001, The Elements of Statistical Learning, Springer-Verlag, New York, Chapter 9, which is incorporated herein by reference in its entirety. Random forests are described in Breiman, 1999, “Random Forests--Random Features,” Technical Report 567, Statistics Department, UC Berkeley, September 1999, which is incorporated herein by reference in its entirety.

[0146] Clustering (e.g., unsupervised clustering model algorithms and supervised clustering model algorithms) is described on pages 211–256 of Duda and Hart, Pattern Classification and Scene Analysis, 1973, John Wiley & Sons, Inc., New York, (hereinafter “Duda 1973”), which is incorporated herein by reference in its entirety. As described in section 6.7 of Duda 1973, the problem of clustering is described as finding natural groupings within a dataset. Two problems are addressed in identifying natural groupings. First, a method is determined for measuring the similarity (or dissimilarity) between two samples. This metric (similarity measure) is used to ensure that samples in one cluster are more similar to each other than samples in other clusters. Second, the similarity measure is used to determine a mechanism for dividing the data into clusters. Similarity measures are discussed in section 6.7 of Duda 1973, where it is stated that one way to begin a clustering investigation is to define a distance function and compute a matrix of distances between samples of all pairs in the training set. If distance is a good measure of similarity, the distances between reference entities within the same cluster will be significantly shorter than the distances between reference entities in different clusters. However, as noted on page 215 of Duda 1973, clustering does not require the use of a distance metric. For example, a nonmetric similarity function s(x,x') can be used to compare two vectors x and x'. Traditionally, s(x,x') is a symmetric function with a large value when x and x' are "similar" in some way. An example of a nonmetric similarity function (x,x') is provided on page 218 of Duda 1973. Once a method for measuring "similarity" or "dissimilarity" between points in the dataset is chosen, clustering requires a criterion function to measure the clustering quality of any partition of the data. Partitions of a dataset that make the baseline function extreme are used to cluster the data. See page 217 of Duda 1973.The reference function is discussed in section 6.8 of Duda 1973. More recently, see Duda et al., Pattern Classification, 2. nd The edition published by John Wiley & Sons, Inc., New York, contains details of clustering on pages 537–563. Further details on clustering techniques are found in Kaufman and Rousseeuw, 1990, Finding Groups in Data: An Introduction to Cluster Analysis, Wiley, New York, NY; Everitt, 1993, Cluster analysis (3rd ed.), Wiley, New York, NY; and Backer, 1995, Computer-Assisted Reasoning in Cluster Analysis, Prentice Hall, Upper Saddle River, New Jersey, each of which is incorporated herein by reference. Specific exemplary clustering techniques that may be used in this disclosure include, but are not limited to, hierarchical clustering (accumulated clustering using nearest neighbor algorithms, farthest neighbor algorithms, mean-connected algorithms, centroid algorithms, or sum-of-squares algorithms), k-means clustering, fuzzy k-means clustering algorithms, and Jarvis-Patrick clustering. In some embodiments, clustering includes unsupervised clustering, where there is no preconceived notion of which clusters should be formed when the training set is clustered.

[0147] Regression models for multi-category logit models are described in Agresti, An Introduction to Categorical Data Analysis, 1996, John Wiley & Sons, Inc., New York, Chapter 8, and are incorporated herein by reference in their entirety. In some embodiments, the classifier uses a regression model disclosed in Hastie et al., 2001, The Elements of Statistical Learning, Springer-Verlag, New York.

[0148] In some embodiments, the method 4000 described with respect to Figure 4 is executed by a device that runs one or more programs (e.g., one or more programs stored in non-persistent memory 111 or persistent memory 112 in Figure 1) that include instructions for performing the method 4000. In some embodiments, the method 4000 is executed by a system that includes at least one processor (e.g., a processing core 102) and memory (e.g., one or more programs stored in non-persistent memory 111 or persistent memory 112) that include instructions for performing the method 4000. [Examples]

[0149] Examples Example 1 - Evaluation of a subject with autism spectrum disorder Two subjects (Subject 1 and Subject 2) were evaluated for autism spectrum disorder using Method 200, as described in Figures 2A-2F. Table 4 shows the results, including the features in Table 2 (e.g., column “Feature”) associated with each parameter estimate β obtained from the training set, and the empirical results (e.g., x-values) for Subject 1 and Subject 2. The β-values ​​are obtained by estimating each feature in the training dataset, which describes the change in log odds for autism spectrum disorder status associated with a one-unit change in each feature. The estimated parameter β and x-value for each subject are input into an algorithm that calculates p(Subject) for each subject (see Equation 1 above), given the calculated α parameter 36.31. For Subject 1, the estimated parameter β and experimental result x yielded an estimated probability p(Subject 1) of 2.28% that Subject 1 has autism spectrum disorder. For Subject 2, the estimated parameter β and experimental result x yielded an estimated probability p(Subject 2) of 96.9% that Subject 2 has autism spectrum disorder. Therefore, at a predetermined threshold of 50%, Subject 1 was assessed as not having autism spectrum disorder, and Subject 2 was assessed as having autism spectrum disorder. Furthermore, the odds for Subject 1 having autism spectrum disorder were equal to 0.023, and the odds for Subject 2 having autism spectrum disorder were equal to 31.2. The odds are calculated from the probabilities using Equation 2.

number

[0150] Example 2 - Receiver Operating Characteristic (ROC) curve. Figure 5A shows an experimental receiver operating characteristic (ROC) curve for evaluating the accuracy of the disclosed method for assessing subjects with autism spectrum disorder, according to one embodiment. In the experiment described with respect to Figure 5A, the assessment is performed by measuring the hair shaft of the subject. The ROC curve can be used to evaluate the performance of a binary classifier. The ROC curve is plotted as sensitivity (also called true positivity) against specificity (also called true negativity). A perfect classifier would have 100% sensitivity and 100% specificity, and an area under the curve (AUC) corresponding to 1. As shown in Figure 5A, the ROC curve derived from experimental data for evaluating the performance of the disclosed classification method has an AUC corresponding to 0.947, indicating that the disclosed method has an accuracy of over 90% for assessing whether a subject has autism spectrum disorder.

[0151] Example 3 - Evaluation of subjects for autism spectrum disorder from hair samples of one or two parents To develop a classifier capable of determining whether or not a subject has autism spectrum disorder, a Sweden-based study (Roots of Autism and ADHD Study in Sweden-RATSS; Marwan et al., 2007, “Recurrence plots for the analysis of complex systems,” Phys.Rep.438, 237-329.) collected hair samples from the parents (biological mother and father) of twins. The aim of this study was to predict the diagnosis of autism spectrum disorder (ASD) in children based solely on parental hair. The children underwent clinical testing for autism. This analysis did not use any data about the children other than the diagnosis. Three classifiers were developed to predict autism in children: a) a classifier using only maternal hair (n=29; 14 ASD cases, 15 controls), b) a classifier using only paternal hair (n=23; 9 ASD cases, 14 controls), and c) a classifier using both maternal and paternal hair (n=52; 23 ASD cases, 29 controls).

[0152] Table 5 shows the features and their β values ​​used for the maternal hair cohort, the paternal hair cohort, and combinations of the maternal and paternal hair cohorts. The β values ​​are obtained by estimating each feature in each cohort, which describes the change in log odds for autism spectrum disorder status associated with a one-unit change in each feature.

[0153] Figures 5B, 5C, and 5D show experimental ROC curves for evaluating the accuracy of a trained classifier for autism spectrum disorder based on maternal hair, paternal hair, and combinations of maternal and paternal hair, respectively, according to some embodiments. As shown in Figure 5B, the ROC curve derived from experimental data for evaluating the performance of the disclosed classification method has an AUC corresponding to 0.886, indicating that the disclosed method has an accuracy of over 85% for evaluating whether a subject has autism spectrum disorder based on a sample of the subject's maternal hair. As shown in Figure 5C, the ROC curve derived from experimental data for evaluating the performance of the disclosed classification method has an AUC corresponding to 0.800, indicating that the disclosed method has an accuracy of over 80% for evaluating whether a subject has autism spectrum disorder based on a sample of the subject's paternal hair. As shown in Figure 5D, the ROC curve derived from experimental data to evaluate the performance of the disclosed classification method has an AUC corresponding to 0.859, indicating that the disclosed method has an accuracy of over 85% for assessing whether a subject has autism spectrum disorder based on a combination of a subject's maternal hair sample and a subject's father's hair sample. [Table 5-1] [Table 5-2] [Table 5-3] [Table 5-4]

[0154] Example 4 - Amyotrophic Lateral Sclerosis (ALS) ALS participants meeting the revised EI Escorial Word Federation of Neurology criteria (N=36) were recruited at an ALS clinic. Clinical and family history data were collected. Age- and sex-matched control participants were recruited at an oral surgery clinic. Controls (N=31) were excluded if they or any first- or second-degree relatives had a neurodegenerative disease. Informed consent was provided to participants or their immediate family members.

[0155] ALS was assessed from dental samples. Table 6 shows the features used and their corresponding β values. The β values ​​are obtained by estimating each feature in each cohort, describing the change in the log odds of ALS status associated with a one-unit change for each feature. Figure 6 shows experimental ROC curves to assess the accuracy of the disclosed method for assessing ALS across cohorts. As shown in Figure 6, the ROC curves derived from experimental data to assess the performance of the disclosed classification method have an AUC corresponding to 0.869, indicating that the disclosed method has an 85% accuracy across cohorts for assessing ALS based on dental samples. [Table 6]

[0156] Example 5 - Schizophrenia Participants with a DSM-IV diagnosis of schizophrenia were selected from the Genetic Risk and Outcomes for Psychosis (GROUP) study (n=20), with unaffected siblings used as controls (n=7). Severity of positive and negative symptoms, and general psychopathology, was assessed using the Positive and Negative Symptom Scale (PANSS). Additionally, participants with a DSM-IV diagnosis of schizophrenia (n=25) and controls (n=24) were selected from the Avon Longitudinal Study of Parents and Children (ALSPAC), a UK-based prospective longitudinal cohort study. The presence of DSM-IV schizophrenia in ALSAPAC was determined at ages 18 and 24 using semi-structured interviews based on the Schedule for Clinical Assessment of Neuropsychiatry (Scan Version 2.0).

[0157] Schizophrenia was assessed using dental samples. Table 7 shows the features used and their corresponding β values. The β values ​​are obtained by estimating each feature in each cohort, describing the change in the log odds of schizophrenia status associated with a 1-unit change in each feature. Figure 7 shows the experimental ROC curve for assessing schizophrenia across the entire cohort. As shown in Figure 7, the ROC curve has an AUC corresponding to 1.000, indicating that the disclosed method has 100% accuracy in determining schizophrenia based on dental samples across the entire cohort. [Table 7-1] [Table 7-2]

[0158] Example 6 - Irritable Bowel Disease (IBD) The subjects were selected from a study based in Portugal. Dental samples were obtained from 11 patients diagnosed with IBD (Crohn's disease = 6, ulcerative colitis / nonspecific colitis = 5) and 16 unaffected controls. All participants were born and raised in the same Portuguese province. Each subject was evaluated for IBD using the same method described above for Examples 2 and 3. IBD was evaluated from the dental samples. Table 8 shows the features used and their corresponding β values. The β values ​​are obtained by estimating each feature in each cohort, describing the change in the log odds of IBD status associated with a 1-unit change for each feature.

[0159] Figure 8 shows the experimental ROC curve for evaluating the accuracy of the disclosed method for assessing subjects with schizophrenia. As shown in Figure 8, the ROC curve derived from experimental data for evaluating the performance of the disclosed classification method has an AUC corresponding to 0.915, indicating that the disclosed method has an accuracy of over 90% for IBD measurements based on dental samples. [Table 8-1] [Table 8-2] [Table 8-3] [Table 8-4] [Table 8-5] [Table 8-6] [Table 8-7] [Table 8-8] [Table 8-9] [Table 8-10] [Table 8-11] [Table 8-12]

[0160] Example 7 - Prediction of kidney transplant rejection Hair samples were collected from kidney transplant recipients at the time of acute rejection confirmed by biopsy (n=6), and from age- and sex-matched control kidney transplant recipients (n=5) who did not have acute rejection on concurrent surveillance biopsy after transplantation. All participants were recruited from Mount Sinai Hospital. Table 9 shows the features used and their corresponding β values. β values ​​were obtained by estimating each feature in each cohort, describing the change in log odds of kidney graft status associated with a 1-unit change for each feature.

[0161] Figure 9 shows the ROC curve for evaluating the accuracy of the disclosed method for assessing subjects for kidney transplant rejection. As shown in Figure 9, the ROC curve derived from experimental data for evaluating the performance of the disclosed classification method has an AUC corresponding to 0.900, indicating that the disclosed method has a 90% accuracy for assessing kidney transplant rejection based on hair samples. [Table 9-1] [Table 9-2]

[0162] Example 8 - Childhood Cancer In Examples 2 and 3, subjects were evaluated for childhood cancer using the same method described above. A total of 28 children were recruited from cancer centers. There were 22 cases of childhood cancer and 6 in the control group. Diagnosis was made using standard clinical protocols—blood tests and histopathology—and confirmed by an oncologist. Table 10 shows the features used and their corresponding β values. The β values ​​are obtained by estimating each feature in each cohort, describing the change in the log odds of childhood cancer status associated with a 1-unit change in each feature.

[0163] Figure 10 shows the ROC curve for evaluating the accuracy of the disclosed method for assessing the target population for childhood cancer. As shown in Figure 10, the ROC curve derived from experimental data to evaluate the performance of the disclosed classification method has an AUC corresponding to 0.962, indicating that the disclosed method has an accuracy of over 95% across the entire cohort of 28 children with childhood cancer, based on tooth sampling. [Table 10-1] [Table 10-2] [Table 10-3] [Table 10-4] [Table 10-5] [Table 10-6] [Table 10-7] [Table 10-8] [Table 10-9]

[0164] References and Alternative Embodiments All references cited herein are incorporated herein by reference in their entirety for any purpose as if each individual publication or patent or patent application were specifically and individually indicated to be incorporated in their entirety by reference for any purpose.

[0165] Many modifications and variations of the present invention can be made without departing from its spirit and scope, as will be apparent to those skilled in the art. The specific embodiments described herein are provided only as examples. The embodiments are selected and described to best illustrate the principles of the present invention and its practical applications, so that those skilled in the art can best utilize the present invention and its various embodiments with various modifications suitable for the specific application intended. The present invention is limited only by the conditions of the appended claims, along with the entire scope of equivalents to which such claims are entitled.

Claims

1. A method for evaluating a subject in terms of its biological state, To provide biological samples from the aforementioned subjects, The method involves sampling the biological sample along multiple locations on the biological sample to collect multiple ion samples, wherein each ion sample in the multiple ion samples corresponds to a different location among the multiple locations. The method involves analyzing the plurality of ion samples using a mass spectrometer to obtain a first dataset containing a plurality of traces, wherein each trace in the plurality of traces is a concentration of the corresponding elemental isotope in a plurality of elemental isotopes as a function of time, collectively determined from the plurality of ion samples. Deriving a second dataset from multiple traces containing a set of features, wherein each feature in the set of features originates from a temporal variation pattern of a single isotope or combination of isotopes in the multiple traces, and A method comprising inputting the aforementioned set of features into a model and obtaining from the model the probability that the subject has a biological state.

2. The method according to claim 1, further comprising pre-treating the biological sample with a solvent or surfactant before sampling.

3. The method according to claim 1 or 2, wherein the biological sample includes a hair shaft.

4. The method according to any one of claims 1 to 3, wherein the plurality of ion samples are collected along a reference line on the biological sample.

5. The method according to claim 4, wherein the reference line corresponds to the neonatal line of the tooth on the enamel surface of the tooth.

6. The method according to claim 4, wherein the reference line corresponds to the longitudinal direction of the hair shaft.

7. The method according to claim 4, wherein the reference line corresponds to the line of nail growth direction.

8. The method according to any one of claims 1 to 7, wherein the subject is a human.

9. The method according to claim 8, wherein the person is under 5 years of age.

10. The method according to claim 9, wherein the human is less than one year old.

11. The method according to any one of claims 1 to 10, wherein the sampling includes sampling the biological sample using a laser.

12. The method according to any one of claims 1 to 11, wherein the mass spectrometer includes an inductively coupled plasma mass spectrometer.

13. The method according to any one of claims 1 to 12, wherein a single isotope or combination of isotopes for each feature is listed in Table 2, 3, 4, 5, 6, 7, 8, 9, or 10. Table 2 Table 3-1 Table 3-2 Table 3-3 Table 3-4 Table 3-5 Table 4 Table 5-1 Table 5-2 Table 5-3 Table 5-4 Table 6 Table 7-1 Table 7-2 Table 8-1 Table 8-2 Table 8-3 Table 8-4 Table 8-5 Table 8-6 Table 8-7 Table 8-8 Table 8-9 Table 8-10 Table 8-11 Table 8-12 Table 9-1 Table 9-2 Table 10-1 Table 10-2 Table 10-3 Table 10-4 Table 10-5 Table 10-6 Table 10-7 Table 10-8 Table 10-9

14. The method according to claim 1, wherein the concentration of the corresponding elemental isotope corresponds to the relative abundance of the corresponding elemental isotope with respect to a control elemental isotope, and the control elemental isotope is included in the plurality of ion samples.

15. The method according to claim 14, wherein the control element isotope is sulfur.

16. The method according to any one of claims 1 to 12, wherein the biological state is a neurological state.

17. The method according to any one of claims 1 to 16, wherein the set of features includes one or more features obtained from an analysis of a temporal change pattern, the one or more features including mean diagonal length, determinism, recurrence time, entropy, trapping time, or laminarity.

18. The method according to any one of claims 1 to 12, wherein the biological condition is autism spectrum disorder.

19. The method according to any one of claims 1 to 12, wherein the biological condition is attention deficit / hyperactivity disorder.

20. The method according to any one of claims 1 to 12, wherein the biological condition is a neurodegenerative disease.

21. The method according to any one of claims 1 to 12, wherein the biological condition is amyotrophic lateral sclerosis.

22. The method according to any one of claims 1 to 12, wherein the biological condition is schizophrenia.

23. The method according to any one of claims 1 to 12, wherein the biological condition is Parkinson's disease.

24. The method according to any one of claims 1 to 12, wherein the biological condition is Alzheimer's disease.

25. The method according to any one of claims 1 to 12, wherein the biological condition is Huntington's disease.

26. The method according to any one of claims 1 to 12, wherein the biological condition is irritable bowel disease.

27. ​​The method according to any one of claims 1 to 12, wherein the biological condition is a pediatric kidney transplant rejection reaction.

28. The method according to any one of claims 1 to 12, wherein the biological condition is childhood cancer.

29. The method according to claim 1 or 2, wherein the biological sample includes teeth.

30. The method according to claim 1 or 2, wherein the biological sample includes a fingernail.

Images