首页|'Machine Learning Systems And Methods For Deep Learning Of Genomic Contexts' in Patent Application Approval Process (USPTO 20240312558)
'Machine Learning Systems And Methods For Deep Learning Of Genomic Contexts' in Patent Application Approval Process (USPTO 20240312558)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
A patent application by the inventors Hwang, Yunha (Cambridge, MA, US); Ovchinnikov, Sergey (Cambridge, MA, US), filed on March 14, 2024, was made available online on September 19, 2024, according t o news reporting originating from Washington, D.C., by NewsRx correspondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background informa tion supplied by the inventors: "DNA includes genes and intergenic regions. Gene s can include protein-coding genes and non-coding genes. Intergenic regions are sequences of the DNA that are located between genes." In addition to the background information obtained for this patent application, NewsRx journalists also obtained the inventors' summary information for this pat ent application: "Some aspects provide for a method for generating a contextual embedding of a gene. In some embodiments, the method comprises: using at least o ne computer hardware processor to perform: obtaining information specifying geno mic context of the gene, the genomic context containing a plurality of genes inc luding the gene, the information containing gene sequences for the plurality of genes; encoding the information specifying the genomic context to obtain an init ial encoding of the genomic context, the encoding comprising: mapping the gene s equences to protein sequences; and encoding the protein sequences using a traine d protein language model (pLM) to obtain the initial encoding of the genomic con text; and processing the initial encoding of the genomic context with a genomic language model (gLM) to obtain the contextual embedding of the gene.
NETL
NSTL
