Illumina had 51 patents in artificial intelligence during Q4 2023. The patents filed by Illumina Inc in Q4 2023 focus on utilizing neural networks and machine learning models to improve the accuracy and efficiency of genetic sequencing data analysis. These technologies enable the identification of optimal oligonucleotide probes, correction of error-inducing sequences, and determination of pathogenicity of nucleotide variants. The methods described in the patents leverage FPGA processors, GPU cards, and customized layers to enhance the processing and analysis of genetic data, ultimately leading to more precise results in a cost-effective manner. GlobalData’s report on Illumina gives a 360-degreee view of the company including its patenting strategy. Buy the report here.
Illumina grant share with artificial intelligence as a theme is 29% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Deep learning-based variant classifier (Patent ID: US20230386611A1)
See Also:
The patent filed by Illumina Inc. describes a technology that operates directly on sequencing data to derive feature filters, enhancing recall and precision using lightweight hardware. By processing aligned reads spanning a target base position and encoding them elegantly, the system can train on one million examples of target base variant sites with 50 to 100 reads each on a single GPU card in less than 10 hours, providing efficient and cost-effective analysis accessible to users interested in genetic data. The system utilizes a convolutional neural network to analyze input features from aligned reads, generating classification scores that indicate the likelihood of a candidate variant at the target base position being a true or false variant, homozygous, heterozygous, non-variant, or complex-variant.
Furthermore, the system processes input features through layers of the convolutional neural network, concatenating output features with per-variant characterization data to enhance the accuracy of classification scores. The per-variant characterization data includes empirical variant score (EVS) features for the candidate variant, improving the overall analysis. The technology also involves generating classification scores based on fully connected layers and a classification layer of the convolutional neural network, ensuring comprehensive and detailed analysis of the sequencing data. Overall, the system provides a sophisticated yet accessible method for analyzing genetic data efficiently and accurately, making it a valuable tool for researchers and users in the field of genomics.
To know more about GlobalData’s detailed insights on Illumina, buy the report here.
Premium Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.