IP Library › Granted Patent US 12,374,428
Granted Patent B2
US 12,374,428 · App. 17/266,689 · Granted Jul 29, 2025

Determining protein distance maps by combining distance maps crops

Inventors: Andrew W. Senior (London, GB); James Kirkpatrick (London, GB); Laurent Sifre (Paris, FR); Richard Andrew Evans (London, GB); Hugo Penedones (Zurich, CH); Chongli Qin (London, GB); Ruoxi Sun (Mountain View, CA); Karen Simonyan (London, GB); John Jumper (London, GB)
Assignee: DeepMind Technologies Limited
G16B40/20G06F18/24147G06N3/044G06N3/045G06N3/047G06N3/08G16B15/20G16H10/40G06N20/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,374,428
App. No.
17/266,689
Granted
Jul 29, 2025
Kind
B2
Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction. In one aspect, a method comprises generating a distance map for a given protein, wherein the given protein is defined by a sequence of amino acid residues arranged in a structure, wherein the distance map characterizes estimated distances between the amino acid residues in the structure, comprising: generating a plurality of distance map crops, wherein each distance map crop characterizes estimated distances between (i) amino acid residues in each of one or more respective first positions in the sequence and (ii) amino acid residues in each of one or more respective second positions in the sequence in the structure of the protein, wherein the first positions are a proper subset of the sequence; and generating the distance map for the given protein using the plurality of distance map crops.

Claims (59)

1. A computer-implemented method comprising:

determining a predicted structure of a protein, comprising:

generating a distance map for the protein, wherein the protein comprises a sequence of amino acid residues, and the distance map characterizes estimated distances between amino acid residues in the predicted structure of the protein, wherein generating the distance map for the protein comprises:

generating a plurality of distance map crops, wherein each distance map crop characterizes estimated distances between (i) amino acid residues in each of one or more respective first positions in the sequence and (ii) amino acid residues in each of one or more respective second positions in the sequence in the structure of the protein, wherein generating a distance map crop comprises:

identifying one or more first positions in the sequence and one or more second positions in the sequence, wherein the first positions are a proper subset of the sequence;

determining a network input from the amino acid residues in the first positions in the sequence and the amino acid residues in the second positions in the sequence; and

providing the network input to a distance prediction neural network, wherein the distance prediction neural network is configured to process the network input in accordance with current values of distance prediction neural network weights to generate a network output comprising the distance map crop, wherein each distance map crop is a two dimensional (2D) array that is a proper subset of the distance map; and

generating the distance map for the protein by fusing the plurality of distance map crops; and

determining the predicted structure of the protein using the distance map for the protein.

2. The method of claim 1 , wherein determining a network input from the amino acid residues in the first positions in the sequence and the amino acid residues in the second positions in the sequence comprises:

extracting components of (i) a representation of the sequence of amino acid residues, and (ii) alignment features derived from a multiple sequence alignment which includes the sequence of amino acid residues, which correspond to the amino acid residues in the first positions in the sequence and the amino acid residues in the second positions in the sequence.

3. The method of claim 1 , wherein identifying one or more first positions in the sequence and one or more second positions in the sequence comprises:

stochastically sampling the first positions as a first sequence of consecutive positions of a first predetermined length; and

stochastically sampling the second positions as a second sequence of consecutive positions of a second predetermined length.

4. The method of claim 1 , wherein generating the distance map for the given protein using the plurality of distance map crops comprises:

averaging the plurality of distance map crops.

5. The method of claim 1 , wherein generating the distance map for the protein using the plurality of distance map crops comprises:

processing the plurality of distance map crops using a fusing neural network in accordance with current values of fusing neural network parameters to generate an output comprising the distance map.

6. The method of claim 1 , wherein each distance map crop defines, for each pair of amino acid residues including a first amino acid residue in a first position and a second amino acid residue in a second position, a respective probability distribution over a predetermined set of distance ranges between the pair of amino acid residues.

7. The method of claim 1 , wherein each distance map crop defines, for each pair of amino acid residues including a first amino acid residue in a first position and a second amino acid residue in a second position, a binary variable indicating whether a distance between the pair of amino acids is less than a predetermined threshold.

8. The method of claim 1 , wherein each distance map crop defines, for each pair of amino acid residues including a first amino acid residue in a first position and a second amino acid residue in a second position, a continuous-valued number defining a distance between the pair of amino acids.

9. The method of claim 1 , wherein the distance prediction neural network is trained on a set of training data comprising a plurality of training examples, wherein each training example comprises: (i) a training network input determined from a sequence of amino acid residues in a training protein, and (ii) a target distance map, wherein the target distance map characterizes actual distances between the amino acid residues in the training protein.

10. The method of claim 1 , wherein the distance prediction neural network is trained on a set of training data comprising a plurality of training examples, wherein each training example comprises: (i) a training network input determined from a sequence of amino acid residues in a training protein, and (ii) a target distance map, wherein the target distance map characterizes estimated distances between the amino acid residues in the training protein and is generated as an output of a teacher neural network by processing the training network input.

11. The method of claim 9 , wherein for a plurality of the training examples, random noise is added to the target distance map.

12. The method of claim 1 , wherein the distance prediction neural network comprises one or more dilated convolutional neural network layers, one or more residual blocks, one or more attention layers, or a combination thereof.

13. The method of claim 11 , wherein the distance prediction neural network is trained to generate an auxiliary output characterizing a secondary structure of the amino acid residues in the first positions in the sequence and the amino acid residues in the second positions in the sequence.

14. The method of claim 1 , wherein the distance prediction neural network is trained to generate an auxiliary output characterizing torsion angles between amino acid residues in the first positions in the sequence and amino acid residues in the second positions in the sequence.

15. The method of claim 1 , further comprising determining a predicted structure of the protein, wherein the predicted structure of the given protein is defined by values of a plurality of structure parameters, the determining comprising:

obtaining initial values of the plurality of structure parameters defining the predicted structure;

updating the initial values of the plurality of structure parameters, comprising, at each of a plurality of update iterations:

determining a quality score characterizing a quality of the predicted structure defined by current values of the structure parameters using the distance map;

for one or more of the plurality of structure parameters:

optimizing the quality score by adjusting the current value of the structure parameter;

determining the predicted structure of the protein to be defined by the current values of the plurality of structure parameters after a final update iteration of the plurality of update iterations.

16. A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising:

determining a predicted structure of a protein, comprising:

generating a distance map for the protein, wherein the protein comprises a sequence of amino acid residues, and the distance map characterizes estimated distances between amino acid residues in the predicted structure of the protein,

generating a plurality of distance map crops, wherein each distance map crop characterizes estimated distances between (i) amino acid residues in each of one or more respective first positions in the sequence and (ii) amino acid residues in each of one or more respective second positions in the sequence in the structure of the protein, wherein generating a distance map crop comprises:

identifying one or more first positions in the sequence and one or more second positions in the sequence, wherein the first positions are a proper subset of the sequence;

determining a network input from the amino acid residues in the first positions in the sequence and the amino acid residues in the second positions in the sequence; and

providing the network input to a distance prediction neural network, wherein the distance prediction neural network is configured to process the network input in accordance with current values of distance prediction neural network weights to generate a network output comprising the distance map crop, wherein each distance map crop is a two-dimensional (2D) array that is a proper subset of the distance map; and

generating the distance map for the protein by fusing the plurality of distance map crops; and

determining the predicted structure of the protein using the distance map for the protein.

17. One or more non-transitory computer storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

determining a predicted structure of a protein, comprising:

generating a distance map for the protein, wherein the protein comprises a sequence of amino acid residues, and the distance map characterizes estimated distances between amino acid residues in the predicted structure of the protein,

generating a plurality of distance map crops, wherein each distance map crop characterizes estimated distances between (i) amino acid residues in each of one or more respective first positions in the sequence and (ii) amino acid residues in each of one or more respective second positions in the sequence in the structure of the protein, wherein generating a distance map crop comprises:

identifying one or more first positions in the sequence and one or more second positions in the sequence, wherein the first positions are a proper subset of the sequence;

determining a network input from the amino acid residues in the first positions in the sequence and the amino acid residues in the second positions in the sequence; and

providing the network input to a distance prediction neural network, wherein the distance prediction neural network is configured to process the network input in accordance with current values of distance prediction neural network weights to generate a network output comprising the distance map crop, wherein each distance map crop is a two-dimensional (2D) array that is a proper subset of the distance map; and

generating the distance map for the protein by fusing the plurality of distance map crops; and

determining the predicted structure of the protein using the distance map for the protein.

18. The non-transitory computer storage media of claim 17 , wherein determining a network input from the amino acid residues in the first positions in the sequence and the amino acid residues in the second positions in the sequence comprises:

extracting components of (i) a representation of the sequence of amino acid residues, and (ii) alignment features derived from a multiple sequence alignment which includes the sequence of amino acid residues, which correspond to the amino acid residues in the first positions in the sequence and the amino acid residues in the second positions in the sequence.

19. The non-transitory computer storage media of claim 17 , wherein identifying one or more first positions in the sequence and one or more second positions in the sequence comprises:

stochastically sampling the first positions as a first sequence of consecutive positions of a first predetermined length; and

stochastically sampling the second positions as a second sequence of consecutive positions of a second predetermined length.

20. The non-transitory computer storage media of claim 17 , wherein generating the distance map for the protein using the plurality of distance map crops comprises:

averaging the plurality of distance map crops.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 6, 2025
From: DEEPMIND TECHNOLOGIES LIMITED
To: GDM HOLDING LLC
Reel/Frame 071498/0210 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 12, 2021
From: SENIOR, ANDREW W.; KIRKPATRICK, JAMES; SIFRE, LAURENT; EVANS, RICHARD ANDREW; PENEDONES, HUGO; QIN, CHONGLI; SUN, RUOXI; SIMONYAN, KAREN; JUMPER, JOHN
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 055242/0286 →
Continuity (4)
Provisional Application 62770490 · Nov 21, 2018
Provisional Application 62734773 · Sep 21, 2018
Provisional Application 62734757 · Sep 21, 2018
Related Publication 20210407625A1 · Dec 30, 2021
References Cited (141)
US 20080215301A1 · Eyal et al. · 2008 [cited by applicant]
US 20130303383A1 · Sander et al. · 2013 [cited by applicant]
US 20130304432A1 · Sander et al. · 2013 [cited by applicant]
US 20160077112A1 · Jara et al. · 2016 [cited by applicant]
US 20170249420A1 · Saladi et al. · 2017 [cited by applicant]
US 20170316147A1 · Gao et al. · 2017 [cited by applicant]
US 20170372004A1 · Henriksen et al. · 2017 [cited by applicant]
CN 101294970 · 2008 [cited by applicant]
CN 101647022 · 2010 [cited by applicant]
CN 101794351 · 2010 [cited by applicant]
CN 105046106 · 2015 [cited by applicant]
CN 105468934 · 2016 [cited by applicant]
CN 105740646 · 2016 [cited by applicant]
CN 105808972 · 2016 [cited by applicant]
CN 106372456 · 2017 [cited by applicant]
CN 106503484 · 2017 [cited by applicant]
CN 107330512 · 2017 [cited by applicant]
CN 107506613 · 2017 [cited by applicant]
CN 107622182 · 2018 [cited by applicant]
EP 1482433 · 2004 [cited by applicant]
EP 2728000 · 2014 [cited by applicant]
IN 201641028573 · 2018 [cited by applicant]
JP 1995152775 · 1995 [cited by applicant]
JP H07152775 · 1995 [cited by applicant]
JP 2004258814 · 2004 [cited by applicant]
JP 2017530373 · 2017 [cited by applicant]
KR 20110112664 · 2011 [cited by applicant]
WO WO0214875 · 2002 [cited by applicant]
WO WO2017062382 · 2017 [cited by applicant]
Gao, Y., Wang, S., Deng, M. and Xu, J., Jan. 17, 2018. RaptorX-Angle: real-value prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning. BMC bioinformatics, 19, pp. 73-84.… [cited by examiner]
Office Action in Canadian Appln. No. 3,110,200, dated Feb. 9, 2022, 5 pages. [cited by applicant]
Office Action in Canadian Appln. No. 3,110,242, dated Feb. 9, 2022, 5 pages. [cited by applicant]
Office Action in Canadian Appln. No. 3,110,395, dated Feb. 9, 2022, 4 pages. [cited by applicant]
Zhao et al., “A Position-Specific Distance-Dependent Statistical Potential for Protein Structure and Functional Study,” Structure, Jun. 2012, 20(6):118-1126. [cited by applicant]
Office Action in Chinese Appln. No. 201980054190.6, dated Sep. 1, 2023, 18 pages (with English translation). [cited by applicant]
Zhang, “The Research and Establishment of Algorithm Model of the Protein Spatial Structure Similarity,” Thesis for the degree of Master, Zhengzhou University, School of Electrical Engineering, May 2016, 80 pages (with E… [cited by applicant]
Abagyan et al., “ICM—a new method for protein modeling and design: applications to docking and structure prediction from the distorted native conformation,” J Comput Chem., May 1994, 15(5):488-506. [cited by applicant]
Altschuh et al., “Correlation of co-ordinated amino acid substitutions with function in viruses related to tobacco mosaic virus,” J. Mol. Biol., Feb. 1987, 193(4):693-707. [cited by applicant]
Altschul et al., “Gapped BLAST and PSI-BLAST: a new generation of protein database search programs,” Nucleic Acids Res., Sep. 1997, 25(17):3389-3402. [cited by applicant]
Aszodi et al., “Estimating polypeptide a-carbon distances from multiple sequence alignments,” J. Math. Chem., Jun. 1995, 17(2):167-184. [cited by applicant]
Aszodi et al., “Global fold determination from a small No. of distance restraints,” J. Mol. Biol., Aug. 1995, 251(2):308-326. [cited by applicant]
Bohr et al., “A novel approach to prediction of the 3-dimensional structures of protein backbones by neural networks,” FEBS Letters, Feb. 1990, 261(1):43-46. [cited by applicant]
Bohr et al., “Protein Structures from Distance Inequalities,” Journal of Molecular Biology, Jun. 1993, 231(3):861-869. [cited by applicant]
Boomsma et al., “A generatiye, probabilistic model of local protein structure,” PNAS, Jul. 2008, 105(26):26:8932-8937. [cited by applicant]
Clevert et al., “Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs),” CoRR, Nov. 2015, arXiv:1511.07289, 14 pages. [cited by applicant]
Cong et al., “An automatic method for CASP9 free modeling structure prediction assessment,” Bioinformatics, Dec. 2011, 27(24):3371-3378. [cited by applicant]
Conway et al., “Relaxation of backbone bond geometry improves protein energy landscape modeling, ” Protein Sci., Oct. 2013, 23(1):47-55. [cited by applicant]
Das et al., “Macromolecular modeling with Rosetta,” Annu. Rev. Biochem., Jul. 2008, 77:363-382. [cited by applicant]
Dawson et al., “CATH: An expanded resource to predict protein function through structure and sequence,” Nucleic Acids Res., Jan. 2017, 45(D1):D289-D295. [cited by applicant]
Derevyanko et al., “Deep convolutional networks for quality assessment of protein folds,” Bioinformatics, Dec. 2018, 34(23):4046-4053. [cited by applicant]
Dill et al., “The protein folding problem,” Annu. Rev. Biophys., Jun. 2008, 37:289-316. [cited by applicant]
Dill et al., “The protein-folding problem, 50 years on,” Science, Nov. 2012, 338(6110):1042-1046. [cited by applicant]
Ekeberg et al., “Improved contact prediction in proteins: Using pseudolikelihoods to infer Potts models,” Physical Review E., 87(1):012707. [cited by applicant]
Fan et al., “Virtual Ligand Screening Against Comparative Protein Structure Models,” Methods in Molecular Biology, Nov. 2011, 819:105-126. [cited by applicant]
Feig, “Computational protein structure refinement: almost there, yet still so far to go,” Computational protein structure refinement, Mar. 2017, 7(3):el307. [cited by applicant]
Fredholm et al., “A Novel Approach to Prediction of the 3-Dimensional Structures of Protein Backbones by Neural Networks,” Advances in Neural Information Processing Systems, 1990, 3:523-9. [cited by applicant]
Gilliland et al., “The Protein Data Bank,” Nucleic Acids Res., Jan. 2000, 28(1):235-242. [cited by applicant]
Gregor et al., “DRAW: a recurrent neural network for image generation,” CoRR, Feb. 2015, arxiv:1502.04623v2, 10 pages. [cited by applicant]
Gregor et al., “Towards conceptual compression,” CoRR, Apr. 2016, arxiv.org/abs/1604.08772, 14 pages. [cited by applicant]
Hamelryck et al., “Sampling realistic protein conformations using local structural bias,” PLoS Comput. Biol., Sep. 2006, 2(9):e131. [cited by applicant]
Hastings, “Monte Carlo sampling methods using Markov chains and their applications,” Biometrika, Apr. 1970, 57(1):97-109. [cited by applicant]
He et al., “Deep Residual Learning for Image Recognition,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770-778. [cited by applicant]
Jaderberg et al., “Population based training of neural networks,” arXiv:1711.09846, Nov. 2017, 21 pages. [cited by applicant]
Jones et al., “High precision in protein contact prediction using fully convolutional neural networks and minimal sequence features,” Bioinformatics 2018, 34(19):3308-3315. [cited by applicant]
Jones et al., “MetaPSICOV: Combining coevolution methods for accurate prediction of contacts and long range hydrogen bonding in proteins,” Bioinformatics 2015, 31(7):999-1006. [cited by applicant]
Jones et al., “Predicting novel protein folds by using FRAGFOLD,” Proteins: Structure, Function, and Bioinformatics, Jan. 2002, 45(S5):127-132. [cited by applicant]
Jones et al., “PSICOV: Precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments,” Bioinformatics 28(2):184-190. [cited by applicant]
Kabsch et al., “Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features,” Biopolymers, 1983, 22:2577-2637. [cited by applicant]
Kandathil et al., “DMPfold: a new deep learning-based method for protein tertiary structure prediction and mode refinement,” CASP13 Abstracts, Dec. 2018, pp. 84-85. [cited by applicant]
Kirkpatrick et al., “Optimization by simulated annealing,” Science, May 1983, 220(4598):671-680. [cited by applicant]
Kirkwood, “Statistical mechanics of fluid mixtures,” J. Chem. Phys., 1935, 3:300-313. [cited by applicant]
Konagurthu et al., “Minimum message length inference of secondary structure from protein coordinate data. Bioinformatics,” ISMB, 2012, 28:i97-i105. [cited by applicant]
Kulkic et al., “Toward an accurate prediction of inter-residue distances in proteins using 2D recursive neural networks,” Bioinformatics, Jan. 2014, 15(6):15 pages. [cited by applicant]
Liu et al., “On the limited memory BFGS method for large scale optimization,” Math. Program., Aug. 1989, 45(1-3):503-528. [cited by applicant]
Mariani et al., “IDDT: a local superposition-free score for comparing protein structures and models using distance difference tests,” Bioinformatics, 29(21):2722-2728. [cited by applicant]
Metropolis et al., “Equation of state calculations by fast computing machines,” J. Chem. Phys., 1953, 21(6):1087-1092. [cited by applicant]
Mirdita et al., “Uniclust databases of clustered and deeply annotated protein sequences and alignments,” Nucleic Acids Res., 45(D1):D170-D176. [cited by applicant]
Morcos et al., “Direct-coupling analysis of residue coevolution captures native contacts across many protein families,” PNAS, Dec. 2011, 108(49):E1293-E1301. [cited by applicant]
Moult et al., “Critical assessment of methods of protein structure prediction (CASP)—Round XII,” Proteins: Structure, Function, and Bioinformatics, Feb. 2018, 82:1-6. [cited by applicant]
O'Meara et al., “Combined covalent-electrostatic model of hydrogen bonding improves structure prediction with Rosetta,” J. Chem. Theory Comput., 11(2):609-622. [cited by applicant]
Oord et al., “Wavenet: A generative model for raw audio,” arXiv preprint arXiv:1609.03499, 2016, 15 pages. [cited by applicant]
Ovchinnikov et al., “Improved de novo structure prediction in CASP by incorporating coevolution information into Rosetta,” Proteins: Structure, Function, and Bioinformatics, Sep. 2016, 84(S1):67-75. [cited by applicant]
Ovchinnikov et al., “Robust and accurate prediction of residue-residue interactions across protein interfaces using evolutionary information,” Elife, May 2014, 3:e02030. [cited by applicant]
PCT International Preliminary Report on Patentability in International Appln. No. PCT/EP2019/074670, dated Apr. 1, 2021, 18 pages. [cited by applicant]
PCT International Preliminary Report on Patentability in International Appln. No. PCT/EP2019/074674, dated Apr. 1, 2021, 17 pages. [cited by applicant]
PCT International Preliminary Report on Patentability in International Appln. No. PCT/EP2019/074676, dated Apr. 1, 2021, 17 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2019/074670, dated Dec. 5, 2019, 26 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2019/074674, dated Dec. 13, 2019, 24 pages. [cited by applicant]
PCT International Search Report and Written Opinion in International Appln. No. PCT/EP2019/074676, dated Dec. 16, 2019, 23 pages. [cited by applicant]
Quraishi, “End-to-end di erentiable learning of protein structure,” Cell Systems, Apr. 2019, 8(4):292-301.e3. [cited by applicant]
Reczko et al., “Recurrent Neural Networks for Protein Distance Matrix Prediction,” Protein Structure by Distance Analysis, Dec. 1994, pp. 87-97. [cited by applicant]
Remmert et al., “HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment,” Nature Methods, Feb. 2012, 9(2):173-178. [cited by applicant]
Rezende et al., “Stochastic backpropagation and approximate inference in deep generative models,” Proceedings of the 31st International Conference on Machine Learning, 2014, 32(2):1278-1286. [cited by applicant]
Sali et al., “Comparative Protein Modelling by Satisfaction of Spatial Restraints,” Journal of Molecular Biology, Dec. 1993, 234(3):779-815. [cited by applicant]
Schaarschmidt et al., “Assessment of contact predictions in CASP12: Co-evolution and deep learning coming of age,” Proteins: Structure, Function, and Bioinformatics, Oct. 2017, 86(S1):51-66. [cited by applicant]
Seemayer et al., “CCMpred: fast and precise prediction of protein residue-residue contacts from correlated mutations,” Bioinformatics, Nov. 2014, 30(21):3128-3130. [cited by applicant]
Shrestha et al., “Improving fragment quality for de novo structure prediction,” Proteins: Structure, Function, and Bioinformatics, Apr. 2014, 82(9):2240-2252. [cited by applicant]
Silver et al., “Mastering the game of go without human knowledge,” Nature, Oct. 2017, 550:354-359. [cited by applicant]
Simons et al., “Assembly of Protein Tertiary Structures from Fragments with Similar Local Sequences using Simulated Annealing and Bayesian Scoring Functions,” J. Mol. Biol., Apr. 1997, 268(1):209- 225. [cited by applicant]
Soding et al., “The HHpred interactive server for protein homology detection and structure prediction,” Nucleic Acids Research, Jul. 2005, 33(suppl 2):W244-W248. [cited by applicant]
Uziela et al., “ProQ3D: improved model quality assessments using deep learning,” Bioinformatics, Jan. 2017, 33(10):1578-1580. [cited by applicant]
Van den Oord et al., “Wavenet: A Generative Model for Raw Audio,” CoRR, Sep. 2016, arxiv.org/abs/1609.03499, 15 pages. [cited by applicant]
Wang et al., “Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model,” PLoS Computational Biology, Jan. 2017, 13(1):e1005324. [cited by applicant]
Xu, “Distance-based Protein Folding Powered by Deep Learning,” PNAS, Aug. 2019, 116(34):16856-16865. [cited by applicant]
Xu, “Protein structure modeling by predicted distance instead of contacts,” CASP13 Abstracts, Dec. 2018, pp. 146-147. [cited by applicant]
Yang et al., “Sixty-five years of the long march in protein secondary structure prediction: the final stretch?,” Briefings Bioinf., 2018, 19(3):482-494. [cited by applicant]
Yu et al., “Multi-scale context aggregation by dilated convolutions,” arXiv:1511.07122, Apr. 2016, 13 pages. [cited by applicant]
Zemla et al., “Processing and analysis of CASP3 protein structure predictions,” Proteins: Structure, Function, and Genetics, 1999, 3:22-29. [cited by applicant]
Zhang et al., “Contact map prediction by deep residual fully convolutional neural network with only evolutionary coupling features derived from deep multiple sequence alignment,” CASP13 Abstracts, Dec. 2018, pp. 181-182. [cited by applicant]
Zhang et al., “Scoring function for automated assessment of protein structure template quality,” Proteins, Oct. 2004, 57(4):702-710. [cited by applicant]
Zhang et al., “Template-based and free modeling of I-TASSER and QUARK pipelines using predicted contact maps in CASP12,” Proteins, Mar. 2018, 86(S1):136-151. [cited by applicant]
Zhao et al., “A Position-Specific Distance-Dependent Statistical Potential for Protein Structure and Functional Study,” Structure, Jun. 2012, 20(6):1118-1126. [cited by applicant]
Zhu et al., “Protein threading using residue co-variation and deep learning,” Bioinformatics, Jul. 2018, 34(13):i263-i273. [cited by applicant]
Decision to Grant Patent in Japanese Appln. No. 2021-509152, dated Jul. 19, 2024, 6 pages (with English translation). [cited by applicant]
Extended Search Report in European Appln. No. 24180923.5, dated Sep. 12, 2024, 17 pages. [cited by applicant]
Ferreira, Leonardo G., et al. “Molecular docking and structure-based drug design strategies.” Molecules 20.7 (2015): 13384-13421. (Year: 2015). [cited by applicant]
Watanabe et al., “An attempt to predict the three-dimensional structure of a protein using a neural network,” Proceedings for nationwide lecture meeting (1) Architecture, Software science and engineering, Database and m… [cited by applicant]
Deng et al., “Protein Structure Prediction,” Int. J. Mod. Phys. B, Jul. 2018, 32(18):18 pages. [cited by applicant]
Kikuchi, “Development of genome sequence analysis methods using Kikuchi-shi, average distance statistics between amino acids of proteins,” Kurashiki University of Science and the Arts, 2008, pp. 184-186 (with English ab… [cited by applicant]
Matsunaga, “Conformational Transmistion Pathways in Proteins Explored by the String Method,” Proceedings of the Institute of Statistical Mathematics, 2014, 62(2):285-299 (with English abstract). [cited by applicant]
Office Action in Japanese Appln. No. 2021-509152, dated Mar. 28, 2022, 7 pages (with English translation). [cited by applicant]
Office Action in Japanese Appln. No. 2021-509189, dated Mar. 28, 2022, 6 pages (with English translation). [cited by applicant]
Office Action in Japanese Appln. No. 2021-509217, dated Mar. 28, 2022, 8 pages (with English translation). [cited by applicant]
Office Action in Japanese Appln. No. 2022-130054, dated Jul. 10, 2023, 5 pages. [cited by applicant]
Al-Lazikani et al., “Protein structure prediction,” Current Opinion in Chemical Biology, 2001, 5:51-56. [cited by applicant]
Boomsma et al., “A generative, probabilistic model of local protein structure,” PNAS, Jul. 1, 2008, 105(26):8932-8937. [cited by applicant]
Office Action in Chinese Appln. No. 201980054143.1, dated Dec. 19, 2023, 29 pages (with English translation). [cited by applicant]
Office Action in Chinese Appln. No. 201980054171.3, dated Dec. 28, 2023, 34 pages (with English translation). [cited by applicant]
Office Action in European Appln. No. 19769469.8, dated Dec. 1, 2023, 8 pages. [cited by applicant]
Senior et al., “Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13),” Proteins: Structure, Function, and Bioinformatics, Oct. 10, 201… [cited by applicant]
Sheng et al., “Distance constrains model based hybrid monte carlo sampling algorithm in protein structure prediction,” Chinese Journal of Bioinformatics, Jun. 2016, 14(2):6 pages (with English abstract). [cited by applicant]
Wang et al., “New Deep Neural Networks for Protein Model Evaluation,” 2017 International Conference on Tools with Artificial Intelligence, Nov. 6, 2017, pp. 309-313. [cited by applicant]
Decision to Grant Patent in Japanese Appln. No. 2022-130054, dated Oct. 23, 2023, 5 pages (with English translation). [cited by applicant]
Decision to Grant a Patent in Japanese Appln. No. 2021-509152, dated Jul. 19, 2022, 6 pages. [cited by applicant]
Decision to Grant a Patent in Japanese Appln. No. 2021-509189, dated Aug. 1, 2022, 5 pages. [cited by applicant]
Decision to Grant a Patent in Japanese Appln. No. 2021-509217, dated Jul. 19, 2022, 5 pages. [cited by applicant]
Evans et al., “De novo structure prediction with deep-learning based scoring,” ResearchGate, Dec. 2018, 3 pages. [cited by applicant]
Notice of Allowance in Chinese Appln. No. 201980054190.6, dated May 15, 2024, 6 pages (with English translation). [cited by applicant]
Office Action in Chinese Appln. No. 201980054171.3, dated May 17, 2024, 14 pages (with English translation). [cited by applicant]
Office Action in Indian Appln. No. 202127003862, dated Jan. 7, 2022, 9 pages (with English translation). [cited by applicant]
Office Action in Indian Appln. No. 202127004079, dated Jan. 19, 2022, 6 pages (with English translation). [cited by applicant]