Back to results
US 2020/0050737 A1Published application
Molecular representation
AssigneeInternational Business Machines Corporation
InventorHiroshi Kajino
Life of this patent
Estimating the term…
Loading patent…
Loading patent…
AssigneeInternational Business Machines Corporation
InventorHiroshi Kajino
Estimating the term…
Production rules that represent molecule structures are generated by generating a hypergraph from each of a plurality of molecule structures, performing a tree decomposition of each hypergraph to obtain a syntax tree corresponding to the hypergraph, and extracting a set of production rules for producing each hypergraph, by using connections of nodes in the corresponding tree decomposition.
A computer-implemented method, comprising:
An apparatus comprising:
A computer program product including one or more computer readable storage mediums collectively storing program instructions that are executable by a processor or programmable circuitry to cause the processor or programmable circuitry to perform operations comprising:
Dependencies are inferred from the claim text.
From the US filing history. Foreign family members aren’t listed.
Backward citations are indexed for grants only.
Ict specially adapted for analysing two-dimensional [2d] or three-dimensional [3d] molecular structures
Transformation: tree transformation for tree-structured or markup documents, e.g. XSLT, XSL-FO or stylesheets
Transformation: automatic learning of transformation rules, e.g. from examples
Architecture, e.g. interconnection topology: knowledge-based neural networks; Logical representations of neural networks
Term end not estimated
The following disclosure(s) are submitted under 35 U.S.C. § 102(b)(1)(A):
DISCLOSURE(S): Molecular Hypergraph Grammar, Hiroshi Kajino, May 22, 2018 on the internet (https://confit.atlas.jp/guide/event-img/jsai2018/3E1-04/public/pdf?type=in) and Jun. 7, 2018, 3E1-04, The 32nd Annual Conference of the Japanese Society for Artificial Intelligence, 2018.
The present invention relates to a new molecular representation.
The following description will provide details of preferred embodiments with reference to the following figures wherein:
FIG. 1 shows an exemplary framework, according to an embodiment of the present invention.
FIG. 2 shows an exemplary configuration of an apparatus, according to an embodiment of the present invention.
Embodiments of the present invention include systems and methods that enable computer systems to more efficiently and more accurately provide prediction models of molecule structures. The improvements to a computer's modelling of molecule structures, realized by embodiments of the present invention, permit computer systems to convert latent vectors into valid molecule structures by more accurately reflecting atom valences without requiring large amounts of computational resources to neural networks using, e.g., the SMILES grammar.
Hereinafter, example embodiments of the present invention will be described. The example embodiments shall not limit the invention according to the claims, and the combinations of the features described in the embodiments are not necessarily essential to the invention.
FIG. 1 shows an exemplary framework, according to an embodiment of the present invention. In the framework, molecule structures are utilized after being transformed into latent vectors, and then converted into the molecule structures from the latent vectors.