Stigmata:  An Algorithm To Determine Structural Commonalities in Diverse Datasets

Shemetulskis, Norah E.; Weininger, David; Blankley, C.John; Yang, Jeremy J.; Humblet, Christine

doi:10.1021/ci950169+

Cited by 102 publications

(105 citation statements)

References 16 publications

Supporting

Mentioning

104

Contrasting

Unclassified

Order By: Relevance

“…The single fingerprint approach was first described by Shemetulskis et al in their work on Stigmata [14]. The method generates a modal fingerprint from an input set of molecules that seeks to capture the common chemical features present in the members of this training-set.…”

Section: Modal Fingerprint Methodsmentioning

confidence: 99%

Ligand-based virtual screening using binary kernel discrimination

Chen

Harrison

Hert

et al. 2005

Molecular Simulation

View full text Add to dashboard Cite

ABSTRACT. This paper discusses the use of a machine-learning technique called binary kernel discrimination for virtual screening in drug-and pesticide-discovery programmes. Binary kernel discrimination is compared with several other ligand-based tools for virtual screening in databases of 2D structure represented by fragment bit-strings, and is shown to provide an effective, and reasonably efficient, way of prioritising compounds for biological screening.

show abstract

Section: Modal Fingerprint Methodsmentioning

confidence: 99%

Ligand-based virtual screening using binary kernel discrimination

Chen

Harrison

Hert

et al. 2005

Molecular Simulation

View full text Add to dashboard Cite

show abstract

“…[3,5] However, compared with single reference structures, fingerprint searching often becomes more effective when different query molecules are available, [4,5] owing to an increase in information content of the calculations. Accordingly, for multiple template-based fingerprint searching, a number of different approaches have been introduced including consensus [6] or averaged [7] fingerprints, scaling procedures, [8] or nearestneighbor methods. [7,9,10] In this study, we focus on a performance evaluation of multiple-template similarity searching using state-of-the-art 2D fingerprints for two reasons: 2D fingerprints are surprisingly effective in many search situations in comparison with more complex 3D designs [2][3][4] and because we engage in the development of novel 2D fingerprints.…”

Section: Introductionmentioning

confidence: 99%

Comparison of 2D Fingerprint Methods for Multiple‐Template Similarity Searching on Compound Activity Classes of Increasing Structural Diversity

2007

View full text Add to dashboard Cite

We studied the similarity search performance of differently designed molecular fingerprints using multiple reference structures and different search strategies. For this purpose, nine compound activity classes were assembled that exclusively consisted of molecules with different core structures and that represented different levels of intra-class structural diversity. Thus, there was a strict one-to-one correspondence between test compounds and core structures. Analysis of unique core structures was found to be a better measure of class diversity than distributions of simplified scaffolds. On increasingly diverse classes, a trainable fingerprint using a unique search strategy performed better than others tested herein. Overall, clear preferences were detected for nearest-neighbor search strategies over fingerprint-averaging techniques. Nearest-neighbor searching that relied on selecting database compounds most similar to one of the reference structures often improved compound recovery over other averaging methods, but at the cost of decreasing the ability to detect hits that were structurally distinct from reference molecules.

show abstract

“…With even greater generality, we can consider a weighted MinMax Tversky similarity of the form (15) with the generalized bounds (16) which can again be shown using somer algebra and noticing that the derivative of Equation 15 is positive with respect to Σ i min(A ij B j ) and that Σ i min(A ij B j ) ≤ min(A i , B).…”

Section: Bounds On Aggregated Similarity For Multiple-molecule Querymentioning

confidence: 99%

Bounds and Algorithms for Fast Exact Searches of Chemical Fingerprints in Linear and Sublinear Time.

Swamidass¹,

Baldi²

2007

ChemInform

View full text Add to dashboard Cite

Chemical fingerprint are used to represent chemical molecules by recording the presence or absence, or by counting the number of occurrences, of particular features or substructures, such as labeled paths in the 2D graph of bonds, of the corresponding molecule. These fingerprint vectors are used to search large databases of small molecules, currently containing millions of entries, using various similarity measures, such as the Tanimoto or Tversky's measures and their variants. Here we derive simple bounds on these similarity measures, and show how these bounds can be used to considerably reduce the subset of molecules that need to be searched. We consider both the case of single-molecule and multiple-molecule queries, as well as queries based on fixed similarity thresholds or aimed at retrieving the top K hits. We study the speedup as a function of query size and distribution, fingerprint length, similarity threshold, and database size |D| and derive analytical formula that are in excellent agreement with empirical values. The theoretical considerations and experiments show that this approach can provide linear speedups of one or more orders of magnitude in the case of searches with fixed threshold, and achieve sublinear speedups in the range of O(|D| 0.6 ) for the top K hits in current large databases. This pruning approach yields subsecond search times across the 5M compounds in the ChemDB database, without any loss of accuracy.

show abstract

Stigmata: An Algorithm To Determine Structural Commonalities in Diverse Datasets

Cited by 102 publications

References 16 publications

Ligand-based virtual screening using binary kernel discrimination

Ligand-based virtual screening using binary kernel discrimination

Comparison of 2D Fingerprint Methods for Multiple‐Template Similarity Searching on Compound Activity Classes of Increasing Structural Diversity

Bounds and Algorithms for Fast Exact Searches of Chemical Fingerprints in Linear and Sublinear Time.

Contact Info

Product

Resources

About