IP Verse

Methods For Classification Of Tissue Samples As Positive Or Negative For Cancer

Patent No. US12110554 (titled "Methods For Classification Of Tissue Samples As Positive Or Negative For Cancer") was filed by Veracyte Inc on Jan 25, 2021.

What is this patent about?

’554 is related to the field of molecular diagnostics , specifically addressing the challenge of accurately diagnosing thyroid cancer. Current diagnostic methods, such as cytological examination, often suffer from subjective assessments, failure to identify underlying genetic causes, and inability to provide unambiguous diagnoses, leading to unnecessary surgeries and treatment costs. The invention aims to improve the accuracy and objectivity of thyroid cancer diagnosis through molecular profiling.

The underlying idea behind ’554 is to use a combination of gene expression analysis and genetic mutation detection to create a molecular profile of a thyroid tissue sample. This profile is then analyzed using a trained algorithm to classify the sample as either positive or negative for cancer. The key insight is that by integrating both gene expression and mutation data, a more accurate and reliable diagnosis can be achieved, reducing the reliance on subjective cytological assessments.

The claims of ’554 focus on a method for processing a tissue sample, starting with obtaining a tissue sample from a subject and subjecting a portion of it to a diagnostic screening process that indicates the sample as ambiguous or indeterminate. The method then involves assaying nucleic acid molecules derived from the tissue sample to generate a data set. A programmed computer processes this data set to identify the level of expression of one or more gene expression products and one or more genetic mutations . Finally, a trained algorithm uses this information to classify the tissue sample as positive or negative for cancer, and a report is electronically outputted.

In practice, the invention involves extracting RNA and DNA from a thyroid tissue sample, such as a fine needle aspirate. The RNA is analyzed to determine the expression levels of specific genes known to be associated with thyroid cancer, while the DNA is analyzed to detect the presence of mutations in relevant genes. The resulting data is then fed into a trained algorithm, which has been developed using a reference set of known cancerous and non-cancerous samples. The algorithm outputs a classification of the sample as either positive or negative for cancer, along with a confidence level.

This approach differs from prior methods that rely solely on cytological examination or single-marker genetic tests. By combining gene expression and mutation data, the invention provides a more comprehensive molecular profile of the tumor, allowing for a more accurate and objective diagnosis. This can lead to a reduction in false positives and false negatives, improved patient management, and a decrease in unnecessary surgeries and treatments. The use of a trained algorithm also ensures that the diagnostic process is standardized and reproducible, minimizing the impact of subjective interpretation.

How does this patent fit in bigger picture?

Technical landscape at the time

In the late 2000s when ’554 was filed, methods for analyzing gene expression and identifying genetic polymorphisms were well-established, at a time when microarray technology was a common approach for high-throughput analysis of DNA and RNA. At that time, computational methods for analyzing large datasets were also prevalent, when systems commonly relied on statistical algorithms to identify correlations between genetic markers and disease states. Furthermore, when hardware or software constraints made complex data analysis non-trivial, specialized software packages were often employed to normalize and interpret microarray data.

Novelty and Inventive Step

The application was subject to a non-final rejection. Claims were rejected under 35 U.S.C. 101 as being directed to a judicial exception without significantly more, under 35 U.S.C. 112(b) as being indefinite, and under pre-AIA 35 U.S.C. 102(b) and 103(a) as being anticipated or unpatentable over prior art. Claims 34-35 were withdrawn from consideration. The prosecution record does NOT describe the technical reasoning or specific claim changes that led to allowance.

Claims

This patent contains 21 claims, with claim 1 being the only independent claim. Independent claim 1 is directed to a method for processing a tissue sample to classify it as positive or negative for cancer based on gene expression and genetic mutations. The dependent claims generally specify details and limitations to the method of independent claim 1, such as types of mutations, nucleic acids, tissues, cancers, binding agents, genes, accuracy levels, treatments, and screening processes.

Key Claim Terms New

Definitions of key terms used in the patent claims.

Term (Source)Support for SpecificationInterpretation
Diagnostic screening process
(Claim 1)		“In some cases the results of the molecular profiling assays, are entered into a database for access by representatives or agents of the molecular profiling business, the individual, a medical provider, or insurance provider. In some cases assay results include interpretation or diagnosis by a representative, agent or consultant of the business, such as a medical professional. In other cases, a computer or algorithmic analysis of the data is provided automatically.”A process that initially assesses a tissue sample and categorizes it as ambiguous or indeterminate, requiring further analysis.
Gene expression products
(Claim 1)		“The method of diagnosing cancer based on molecular profiling further comprises the steps of detecting gene expression products (i.e. mRNA or protein) and levels of the sample, comparing it to an amount in a normal control sample to determine the differential gene expression product level between the sample and the control; and classifying the test sample by inputting one or more differential gene expression product levels to a trained algorithm of the present invention; validating the sample classification using the selection and classification algorithms of the present invention; and identifying the sample as positive for a genetic disorder or a type of cancer.”mRNA or protein products resulting from gene expression, whose levels are measured to classify tissue samples.
Genetic mutations
(Claim 1)		“In some embodiments, the molecular profiling results are evaluated using methods known to the art for correlating DNA polymorphisms with specific phenotypes such as malignancy, the type of malignancy (e.g. follicular carcinoma), benignancy, or normalcy (e.g. disease or condition free).”Alterations in the DNA sequence of a nucleic acid sample, identified to classify tissue samples.
Trained algorithm
(Claim 1)		“Trained algorithms of the present invention include algorithms that have been developed using a reference set of known malignant, benign, and normal samples including but not limited to the samples listed in Table 2. Algorithms suitable for categorization of samples include but are not limited to k-nearest neighbor algorithms, concept vector algorithms, naive bayesian algorithms, neural network algorithms, hidden markov model algorithms, genetic algorithms, and mutual information feature selection algorithms or any combination thereof.”An algorithm developed using a reference set of known malignant, benign, and normal samples, used to classify molecular profiling results.

Patent Family

Patent Family

File Wrapper

The dossier documents provide a comprehensive record of the patent's prosecution history - including filings, correspondence, and decisions made by patent offices - and are crucial for understanding the patent's legal journey and any challenges it may have faced during examination.

  • Date

    Description

  • Get instant alerts for new documents

US12110554

VERACYTE INC
Application Number
US17157876
Filing Date
Jan 25, 2021
Status
Granted
Expiry Date
Dec 15, 2031
External Links
Slate, USPTO, Google Patents