# US 12,217,829 B2 · Artificial intelligence-based analysis of protein three-dimensional (3D) structures > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,217,829 B2 - Document ID: US12217829B2 - Status: Granted - Kind: B2 - Application number: 17/232,056 - Filed: 2021-04-15 - Published: 2022-10-20 - Granted: 2025-02-04 - Earliest claimed: 2021-04-15 - Assignees: Illumina, Inc. - Applicants: Illumina, Inc. - Inventors: Tobias Hamp; Hong Gao; Kai-How Farh - Web page: https://patentgrep.com/patent/US12217829B2 ## CPC - G16B 40/20: Supervised data analysis - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G16B 15/20: Protein or domain folding - G16B 20/20: Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection - G16B 30/00: ICT specially adapted for sequence analysis involving nucleotides or amino acids - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract The technology disclosed relates to determining pathogenicity of variants. In particular, the technology disclosed relates to generating amino acid-wise distance channels for a plurality of amino acids in a protein. Each of the amino acid-wise distance channels has voxel-wise distance values for voxels in a plurality of voxels. A tensor includes the amino acid-wise distance channels and at least an alternative allele of the protein expressed by a variant. A deep convolutional neural network determines a pathogenicity of the variant based at least in part on processing the tensor. The technology disclosed further augments the tensor with supplemental information like a reference allele of the protein, evolutionary conservation data about the protein, annotation data about the protein, and structure confidence data about the protein. ## Claims ### Claim 1 A computer-implemented method, comprising: accessing a three-dimensional structure of a reference amino acid sequence of a protein; mapping atoms of the three-dimensional structure to respective voxels of a three-dimensional voxel grid by associating each atom with an individual voxel of the three-dimensional voxel grid; defining, for each voxel in the three-dimensional voxel grid on an amino acid basis, amino acid-wise distance channels comprising three-dimensional distance values specifying distances from each respective voxel to corresponding atoms mapped to each respective voxel; encoding an alternative allele channel to each voxel in the three-dimensional voxel grid, wherein the alternative allele channel is a three-dimensional representation of a one-hot encoding of a variant amino acid expressed by a variant nucleotide; encoding an evolutionary conservation channel to each sequence of three-dimensional distance values across the amino acid-wise distance channels on a voxel position basis, wherein the evolutionary conservation channel is a three-dimensional representation of amino acid-specific conservation frequencies across a plurality of species, and wherein the amino acid-specific conservation frequencies are selected in dependence upon amino acid proximity to a corresponding voxel; applying three-dimensional convolutions to a tensor that includes the amino acid-wise distance channels encoded with the alternative allele channel and respective evolutionary conservation channels; and determining a pathogenicity of the variant nucleotide based at least in part on the tensor. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising centering the three-dimensional voxel grid on an alpha carbon atom of respective residues of reference amino acids in the reference amino acid sequence. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, further comprising centering the three-dimensional voxel grid on an alpha carbon atom of a residue of a particular reference amino acid that corresponds to the variant amino acid. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, further comprising encoding, in the tensor, a directionality of the reference amino acids in the reference amino acid sequence and a position of the particular reference amino acid by multiplying, with a directionality parameter, three-dimensional distance values for those reference amino acids that precede the particular reference amino acid. ### Claim 5 (depends on 4) The computer-implemented method of claim 4, wherein distances specified by three-dimensional distance values are nearest-atom distances from corresponding voxel centers in the three-dimensional voxel grid to nearest atoms of corresponding reference amino acids. ### Claim 6 (depends on 5) The computer-implemented method of claim 5, wherein the nearest-atom distances are Euclidean distances. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, wherein the nearest-atom distances are normalized by dividing the Euclidean distances with a maximum nearest-atom distance. ### Claim 8 (depends on 5) The computer-implemented method of claim 5, wherein the reference amino acids have alpha carbon atoms and wherein the distances specified by the three-dimensional distance values are nearest-alpha carbon atom distances from the corresponding voxel centers to nearest alpha carbon atoms of the corresponding reference amino acids. ### Claim 9 (depends on 5) The computer-implemented method of claim 5, wherein the reference amino acids have beta carbon atoms and wherein the distances specified by the three-dimensional distance values are nearest-beta carbon atom distances from the corresponding voxel centers to nearest beta carbon atoms of the corresponding reference amino acids. ### Claim 10 (depends on 5) The computer-implemented method of claim 5, wherein the reference amino acids have backbone atoms and wherein the distances specified by the three-dimensional distance values are nearest-backbone atom distances from the corresponding voxel centers to nearest backbone atoms of the corresponding reference amino acids. ### Claim 11 (depends on 5) The computer-implemented method of claim 5, wherein the reference amino acids have sidechain atoms and wherein the distances specified by the three-dimensional distance values are nearest-sidechain atom distances from the corresponding voxel centers to nearest sidechain atoms of the corresponding reference amino acids. ### Claim 12 (depends on 3) The computer-implemented method of claim 3, further comprising encoding, in the tensor, a nearest atom channel that specifies a distance from each voxel to a nearest atom, wherein the nearest atom is selected irrespective of the reference amino acids and atomic elements of the reference amino acids. ### Claim 13 (depends on 12) The computer-implemented method of claim 12, wherein the distance is a Euclidean distance. ### Claim 14 (depends on 13) The computer-implemented method of claim 13, wherein the distance is normalized by dividing the Euclidean distance with a maximum distance. ### Claim 15 (depends on 12) The computer-implemented method of claim 12, wherein the reference amino acids include non-standard amino acids. ### Claim 16 (depends on 1) The computer-implemented method of claim 1, wherein the tensor further includes an absentee atom channel that specifies atoms not found within a predefined radius of a voxel center. ### Claim 17 (depends on 16) The computer-implemented method of claim 16, wherein the absentee atom channel is one-hot encoded. ### Claim 18 (depends on 1) The computer-implemented method of claim 1, further comprising voxel-wise encoding a reference allele channel to each voxel in the three-dimensional voxel grid. ### Claim 19 (depends on 18) The computer-implemented method of claim 18, wherein a reference allele amino acid for the reference allele channel is a three-dimensional representation of a one-hot encoding of a reference amino acid that experiences the variant amino acid. ### Claim 20 (depends on 1) The computer-implemented method of claim 1, wherein the amino acid-specific conservation frequencies specify conservation levels of respective amino acids across the plurality of species. ### Claim 21 (depends on 20) The computer-implemented method of claim 20, further comprising encoding the evolutionary conservation channel to each sequence of three-dimensional distance values by: selecting a nearest atom to the corresponding voxel across reference amino acids from the reference amino acid sequence and atom categories, selecting pan-amino acid conservation frequencies for a residue of a reference amino acid that includes the nearest atom, and using a three-dimensional representation of the pan-amino acid conservation frequencies as the evolutionary conservation channel. ### Claim 22 (depends on 21) The computer-implemented method of claim 21, wherein the pan-amino acid conservation frequencies are configured for a particular position of the residue as observed in the plurality of species. ### Claim 23 (depends on 21) The computer-implemented method of claim 21, wherein the pan-amino acid conservation frequencies specify whether there is a missing conservation frequency for a particular reference amino acid. ### Claim 24 (depends on 21) The computer-implemented method of claim 21, further comprising: selecting respective nearest atoms to the corresponding voxel in respective ones of the reference amino acids, selecting respective per-amino acid conservation frequencies for respective residues of the reference amino acids that include nearest atoms, and using a three-dimensional representation of the respective per-amino acid conservation frequencies as the evolutionary conservation channel. ### Claim 25 (depends on 24) The computer-implemented method of claim 24, wherein the respective per-amino acid conservation frequencies are configured for a particular position of the respective residues as observed in the plurality of species. ### Claim 26 (depends on 24) The computer-implemented method of claim 24, wherein the respective per-amino acid conservation frequencies specify whether there is a missing conservation frequency for a particular reference amino acid. ### Claim 27 (depends on 1) The computer-implemented method of claim 1, further comprising voxel-wise encoding one or more annotation channels to each voxel in the three-dimensional voxel grid, wherein the one or more annotation channels are three-dimensional representations of a one-hot encoding of residue annotations. ### Claim 28 (depends on 27) The computer-implemented method of claim 27, wherein the one or more annotation channels are molecular processing annotations that include initiator methionine, signal, transit peptide, propeptide, chain, and peptide. ### Claim 29 (depends on 27) The computer-implemented method of claim 27, wherein the one or more annotation channels are regions annotations that include topological domain, transmembrane, intramembrane, domain, repeat, calcium binding, zinc finger, deoxyribonucleic acid (DNA) binding, nucleotide binding, region, coiled coil, motif, and compositional bias. ### Claim 30 (depends on 27) The computer-implemented method of claim 27, wherein the one or more annotation channels are sites annotations that include active site, metal binding, binding site, and site.