US5418944A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Knowledge-based molecular retrieval system and method using a hierarchy of molecular structures in the knowledge base
Assignee: International Business Machines Corp
•
Filing: 1992-01-23
•
Granted: 1995-05-23
•
Expires: 2012-01-23
Abstract
Abstract A molecular retrieval system and method answering to similarity queries for retrieving molecular structures, stored into a source database (22) and having a required similarity with an input structure, which can contain a set of property regions. A target database (23) stores the molecular structures described in hierarchical way and a knowledge base (24) stores well-known molecular fragments at different levels of description together with a set of physical and chemical properties associated to each fragment. A fragment recognizer (21) analyzes the fragments of the input structure to represent them in a hierarchical way. A query analyzer (25) analyzes the similarity queries and selects the appropriate level of molecular representation on the basis of the required similarity. Matching means (26, 27, 29), when called by the query analyzer (25), perform a matching of the representation of the input structure against the representations of the molecular structures stored into the target database (23) at the selected level of molecular representation.
Inventors
- 👤 Luigi DiPace
- 👤 Filippo Fabrocini
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-05 19:16
CPC Classifications
G; G16; G16C; G16C20/00; G16C20/40; Y; Y10; Y10S; Y10S707/00; Y10S707/99931; Y10S707/99933; Y10S707/99941; Y10S707/99944; Y10S707/99945
Claims Analysis
Total Claims: 8
Claim 1
Independent Claim
156 words
A molecular retrieval method for retrieving molecular structures, stored in a molecular database and having similarity with an input reference, comprising the steps of: (a) defining a hierarchy of molecular representations at residue, function group, and atom type structural levels; (b) identifying molecular fragments at each structural level of step a) and building a dictionary of said molecular fragments for each structural level; (c) collecting the chemical and physical properties for each molecular fragment of said dictionaries and building a knowledge base; (d) selecting a structual level of molecular representation on the basis of similarity to said input reference; (e) performing a matching between the representation of said input reference against the molecular representations at the level selected in step d) of all the molecular structures stored into said molecular database using said knowledge base; (f) selecting all the molecular structures similar to said input reference, and outputting all the molecular structures selected in step f).
Claim 2
Dependent Claim
156 words
A molecular retrieval method for retrieving molecular structures, stored in a molecular database and having similarity with an input reference, comprising the steps of: (a) defining a hierarchy of molecular representations at residue, function group, and atom type structural levels; (b) identifying molecular fragments at each structural level of step a) and building a dictionary of said molecular fragments for each structural level; (c) collecting the chemical and physical properties for each molecular fragment of said dictionaries and building a knowledge base; (d) selecting a structual level of molecular representation on the basis of similarity to said input reference; (e) performing a matching between the representation of said input reference against the molecular representations at the level selected in step d) of all the molecular structures stored into said molecular database using said knowledge base; (f) selecting all the molecular structures similar to said input reference, and outputting all the molecular structures selected in step f).
Claim 3
Dependent Claim
86 words
The molecular retrieval method of claim 1 wherein said input reference is an input molecule and the matching of step (e) comprises: (i) performing a first matching between a first structural level of said input molecule against the same structual level of the molecular database; and (ii) performing a second matching at the next lower structual level between the different molecular fragments, discovered in said first matching, of said input molecule and the molecular structures stored into said molecular database and represented at the same level.
Claim 4
Dependent Claim
94 words
The molecular retrieval method of claim 1 wherein the input reference is a molecular model, represented as a graph with nodes selected from property regions and molecular fragments, and the matching of step (e) comprises (i) defining a property region, as any molecular fragment that matches a user defined combination of chemical and physical properties; (ii) identifying an ordering in the nodes of said molecular model, using said knowledge base; and (iii) performing matching between each node of said model and all the molecular structures stored into said molecular database, using said knowledge base.
Claim 5
Dependent Claim
159 words
A molecular retrieval system for retrieving molecular structures, stored into a database and having a required similarity with an input reference comprising: (a) a first storage means for storing a hierarchical description of said molecular structures as molecular fragments in different structual levels; (b) a second storage means for storing known molecular fragments at different structual levels and for storing a set of physical and chemical properties associated to each of said fragments; (c) a recognizing means for recognizing the fragments appearing in the input reference so as to represent them in a hierarchical description; (d) an analyzing means for a selecting a structual level of hierarchical description of molecular structures on the basis of similarity to said input reference; (e) a matching means that, when called by said analyzing means, performs a matching of the fragments of said input reference against the fragments of the molecular structures stored into said first storage means at the said structual level.
Claim 6
Dependent Claim
159 words
A molecular retrieval system for retrieving molecular structures, stored into a database and having a required similarity with an input reference comprising: (a) a first storage means for storing a hierarchical description of said molecular structures as molecular fragments in different structual levels; (b) a second storage means for storing known molecular fragments at different structual levels and for storing a set of physical and chemical properties associated to each of said fragments; (c) a recognizing means for recognizing the fragments appearing in the input reference so as to represent them in a hierarchical description; (d) an analyzing means for a selecting a structual level of hierarchical description of molecular structures on the basis of similarity to said input reference; (e) a matching means that, when called by said analyzing means, performs a matching of the fragments of said input reference against the fragments of the molecular structures stored into said first storage means at the said structual level.
Claim 7
Dependent Claim
15 words
The molecular retrieval system of claim 4 wherein said input reference is a molecular structure.
Claim 8
Dependent Claim
17 words
The molecular retrieval system of claim 4 wherein said input reference is a user defined molecular model.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1998-05-22 | 1998-11-21 | 1999-05-23 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2002-05-22 | 2002-11-21 | 2003-05-23 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2006-05-22 | 2006-11-21 | 2007-05-23 | $7700.00 | Window Closed / Lapsed |