Contract analysis

I. INTRODUCTION Plaintiff Genome Dx Therapeutics Inc. ("GenomeDx") and Defendant Helios Precision Diagnostics, Inc. ("Helios") (collectively, the "Parties") respectfully submit this Joint Claim Construction and Prehearing Statement ("Joint Statement") pursuant to Patent Local Rule 4-3 of the Northern District of California, in advance of the Markman hearing currently scheduled for September 18, 2026 before the Honora

II. THE PATENTS-IN-SUIT A. U.S. Patent No. 10,438,271 ("the '271 Patent") Title: "Methods for Predicting Prostate Cancer Outcomes Using Multi-Gene Expression Classifiers" Filing Date: June 14, 2016 Issue Date: October 8, 2019 Expiration Date: June 14, 2036 Named Inventors: Dr. Rajan Mehta, Dr. Carolyn Xu, and Dr. David Petrossian Asserted Claims: Claims 1, 3, 5, 7, 12, and 18 The '271 Patent is directed to methods fo

III. THE ACCUSED PRODUCT The accused instrumentality in this action is Helios's "ProstaSignal™ Genomic Classifier" (the "ProstaSignal™" test or the "Accused Product"). ProstaSignal™ is a 24-gene expression-based prognostic test designed for prostate cancer patients following radical prostatectomy. Helios commercially launched ProstaSignal™ on October 7, 2024, and has marketed the test to urologists and oncologists th

IV. AGREED CLAIM CONSTRUCTIONS The Parties have conferred in good faith and have reached agreement on the construction of the following six (6) claim terms. The Parties submit that no further briefing, argument, or testimony is required with respect to these terms, and respectfully request that the Court adopt the agreed constructions set forth below. Term 1: "biological sample containing tumor RNA" Patent/Claim(s):

V. DISPUTED CLAIM CONSTRUCTIONS The Parties have been unable to reach agreement on the construction of the following seven (7) claim terms despite good-faith meet-and-confer efforts. The Parties respectfully request that the Court construe these terms at the Markman hearing scheduled for September 18, 2026. For each disputed term, the Parties set forth their respective proposed constructions, the bases for their posi

1. Plaintiff GenomeDx's Proposed Construction Proposed Construction: "A computational model that has been trained on labeled data using any supervised machine-learning algorithm, including but not limited to random forests, gradient-boosted decision trees, support vector machines, neural networks, and logistic regression, to generate a predictive output." Basis for GenomeDx's Proposed Construction: GenomeDx submits t

2. Defendant Helios's Proposed Construction Proposed Construction: "A random-forest or ensemble tree-based classifier that has been trained on labeled genomic data from patient samples to generate a predictive output." Basis for Helios's Proposed Construction: Helios contends that the specification of the '271 Patent, while mentioning multiple machine-learning approaches in a general introductory passage, predominant

3. Significance of Dispute The construction of "trained machine-learning classifier" is of critical importance to the infringement analysis for the '271 Patent. If the Court adopts GenomeDx's proposed construction, Helios's gradient-boosted decision tree classifier (used in ProstaSignal™) would fall within the literal scope of the "trained machine-learning classifier" limitation, and GenomeDx could establish literal

1. Plaintiff GenomeDx's Proposed Construction Proposed Construction: "A classifier using an ensemble of decision trees in which multiple decision trees are constructed during training and the output is determined by aggregating the predictions of the individual trees, including variants and functional equivalents of the random-forest algorithm such as gradient-boosted tree ensembles." Basis for GenomeDx's Proposed Co

2. Defendant Helios's Proposed Construction Proposed Construction: "A classifier that uses the specific random-forest algorithm as described by Breiman (2001), in which multiple decision trees are independently trained on bootstrap samples of the training data and predictions are aggregated by majority vote or averaging, and which does not encompass gradient-boosted decision trees or other sequential ensemble methods

3. Significance of Dispute This is the central claim construction dispute for the '893 Patent. The resolution of this dispute will likely determine whether GenomeDx can establish literal infringement of the '893 Patent claims or must instead rely on the doctrine of equivalents. If the Court adopts GenomeDx's proposed construction, which defines "random-forest classifier" broadly to include gradient-boosted tree ensem

1. Plaintiff GenomeDx's Proposed Construction Proposed Construction: "A collection of 22 or more genes chosen from a gene set identified and defined in advance, where the gene panel used for expression measurement includes at least 22 genes from the predefined set but may also include additional genes not in the predefined set." Basis for GenomeDx's Proposed Construction: GenomeDx contends that the claim language "a

2. Defendant Helios's Proposed Construction Proposed Construction: "A collection of exactly or more than 22 genes, all of which must be selected exclusively from the predefined gene set identified in the patent specification, such that the panel does not measure genes outside the predefined set for purposes of the classifier." Basis for Helios's Proposed Construction: Helios contends that the phrase "selected from a

3. Significance of Dispute This dispute may be dispositive for literal infringement of '271 Patent Claim 1 and its dependent Claims 3 and 5. The core factual question is how many genes in the ProstaSignal™ panel overlap with the predefined gene set disclosed in Table 1 of the '271 Patent specification. It is undisputed that 19 of ProstaSignal™'s 24 genes overlap with the predefined gene set. Under GenomeDx's proposed

1. Plaintiff GenomeDx's Proposed Construction Proposed Construction: "A computational classifier model that uses expression data from at least 20 genes as input features for generating a genomic risk score." Basis for GenomeDx's Proposed Construction: GenomeDx contends that the term "gene features" refers to gene-expression values used as input variables to the classifier model. The '647 Patent uses a lower minimum t

2. Defendant Helios's Proposed Construction Proposed Construction: "A computational classifier that uses at least 20 specific gene-expression features identified in the patent specification as input variables." Basis for Helios's Proposed Construction: Helios contends that the term "gene features" should be construed to refer to the specific genes disclosed in the '647 Patent specification, and in particular the gene

3. Significance of Dispute ProstaSignal™ uses 24 gene features as inputs to its gradient-boosted decision tree classifier. If the Court adopts GenomeDx's proposed construction — requiring only that the classifier use at least 20 gene-expression inputs, without regard to the identity of the genes — then ProstaSignal™'s use of 24 gene features would satisfy this limitation. If the Court adopts Helios's proposed constru

1. Plaintiff GenomeDx's Proposed Construction Proposed Construction: "A classification group reflecting prognostic risk, such as but not limited to low risk, intermediate risk, or high risk." Basis for GenomeDx's Proposed Construction: GenomeDx contends that the term "risk category" broadly refers to any categorization of patients based on the risk score generated by the classifier. The '271 Patent specification desc

2. Defendant Helios's Proposed Construction Proposed Construction: "A discrete prognostic classification assigned to a patient based on predefined score thresholds validated in a clinical cohort of the type described in the specification." Basis for Helios's Proposed Construction: Helios contends that the term "risk category" carries an implicit requirement that the categories be based on validated thresholds, not ar

3. Significance of Dispute ProstaSignal™ classifies patients into three risk categories: Low, Intermediate, and High. The Parties do not dispute that ProstaSignal™ assigns patients to risk categories. The dispute centers on whether the claim requires the specific validation methodology described in the '271 Patent specification (as Helios contends) or whether any risk categorization based on the classifier's output s

1. Plaintiff GenomeDx's Proposed Construction Proposed Construction: "A single quantitative or semi-quantitative value that integrates information from both the genomic risk score and clinical covariates." Basis for GenomeDx's Proposed Construction: GenomeDx contends that the term "composite risk metric" refers to any integrated output that combines or synthesizes information from the genomic risk score and clinical

2. Defendant Helios's Proposed Construction Proposed Construction: "A single numerical score calculated by a defined mathematical formula that combines the genomic risk score and clinical covariates into one output value." Basis for Helios's Proposed Construction: Helios contends that the "composite risk metric" must be a single computed numerical value — not a qualitative or categorical output, and not merely a side

3. Significance of Dispute This dispute is potentially dispositive for the '647 Patent claims. If the Court adopts Helios's construction — requiring a single numerical score calculated by a defined mathematical formula — GenomeDx must demonstrate that ProstaSignal™ actually performs a mathematical computation that fuses the ProstaScore with Gleason grade group and pre-operative PSA into a single computed number. Base

1. Plaintiff GenomeDx's Proposed Construction Proposed Construction: "Communicating or delivering the composite risk metric to a healthcare provider by any means, including electronic transmission, physical delive