GSI Technology. has been granted a patent for a protein searcher that utilizes a pre-trained convolutional neural network (CNN) and a K nearest neighbor (KNN) searcher. This system identifies amino acid sequences by extracting feature vectors and matching them with stored data to classify or tag sequences. GlobalData’s report on GSI Technology gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on GSI Technology, Convolutional neural networks (CNNs) was a key innovation area identified from patents. GSI Technology's grant share as of June 2024 was 57%. Grant share is based on the ratio of number of grants to total number of patents.
Protein searcher using cnn and knn for amino acids
The granted patent US12027238B2 introduces a novel protein searcher that utilizes a pre-trained convolutional neural network (CNN) to analyze unidentified amino acid sequences. The system is designed to extract feature vectors from these sequences and compare them against a database containing both trained and untrained amino acid sequences. The searcher employs a K nearest neighbor (KNN) algorithm to identify and output the associated classes or tags of the closest feature vectors. Notably, the patent outlines the potential application of this technology in identifying variants of the SARS-CoV-2 virus, emphasizing its relevance in the context of ongoing viral research.
Additionally, the patent details the architecture of the protein searcher, which includes an associative processing unit (APU) that integrates a memory array for efficient data storage and retrieval. This memory array is structured into sections for feature vectors, associated classes, and KNN search operations, facilitating streamlined searches. The method for protein searching encompasses the steps of receiving an amino acid sequence, extracting its feature vector, storing relevant data, and executing the KNN search. The claims also highlight the possibility of performing zero-shot searches and the option for partial training of the CNN, enhancing the system's adaptability and effectiveness in various protein analysis scenarios.
To know more about GlobalData’s detailed insights on GSI Technology, buy the report here.
Data 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.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
