Neoepitope Sequence Screening for Viral Payload Toxicity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining recombinant viral payload toxicity in therapeutic viruses are inadequate, particularly for artificial sequence constructs like neoepitopes, as toxicity is often only evident after large-scale production, leading to reduced expression and potential harm to patient cells.
Innovation Solution
A method involving expression of recombinant nucleic acid sequences in host cells, sequencing, and correlating sequence portions with toxicity measures using machine learning, including various classifiers and autoencoders, to predict and reduce payload toxicity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If recombinant nucleic acid sequences are expressed in host cells for large-scale virus production, then viral titers are improved, but payload toxicity increases causing cell death or reduced expression
Solution Approach 1:
The patent applies preliminary action by performing toxicity assessment through sequencing and machine learning analysis before large-scale virus production. The method predicts potential toxic effects of neoepitope payloads by analyzing recombinant nucleic acid sequences in silico, allowing researchers to identify and eliminate toxic payloads prior to host cell expression and viral production, thereby preventing cell death and ensuring high viral titers without toxicity-related setbacks
Solution Approach 2:
The patent replaces mechanical/experimental toxicity testing with computational prediction methods. Instead of empirically testing payload toxicity through host cell expression and observation (mechanical/biological system), the invention uses machine learning algorithms that analyze sequence features and predict toxic effects in silico (computational system), providing a faster, non-invasive assessment that guides payload selection before production
2Measurement precision
If toxicity assessment is performed after virus generation, then accurate toxicity measurement is improved, but production time and cost increase
Solution Approach 1:
The patent performs toxicity assessment preliminarily by analyzing recombinant nucleic acid sequences using machine learning before virus generation. The method extracts sequence features and predicts toxic effects in silico, providing accurate toxicity measurements without requiring actual host cell expression or viral production, thereby eliminating time losses associated with empirical toxicity testing while maintaining measurement precision
Solution Approach 2:
The patent uses computational copying by creating in silico models of payload toxicity based on sequence features. Instead of physically expressing payloads in host cells to assess toxicity (physical copy), the invention uses machine learning algorithms that process sequence data and predict toxic effects (computational copy), providing accurate toxicity measurements without the time and resource requirements of actual biological experiments
Data Source
AI summary
Systems and methods are presented that allow for determination and prediction of payload toxicity in therapeutic viruses. Contemplated methods of determining payload toxicity of an expressed polypeptide in a cell may comprise the steps of generating or procuring a plurality of expression vectors, each containing a different recombinant nucleic acid sequence that encodes a corresponding recombinant polypeptide; expressing the recombinant nucleic acid sequence in a plurality of host cells while culturing the host cells; sequencing the plurality of expression vectors after culturing the host cells; and correlating at least portions of the recombinant nucleic acid sequence with a toxicity measure.