Text-based Similarity Research Articles

Text-based similarity searching for hit- and lead-candidate identification

The Pharmacophore Alignment Search Tool (PhAST) is a string-based approach to virtual screening. Molecules are represented by linear sequences which describe their respective pattern of interaction possibilities. The problem of molecule linearization is tackled by applying Minimum Volume Embedding in combination with a Diffusion Kernel to the molecular graph [1,2]. Linear representations are compared using global pairwise sequence alignment [3]. PhAST exhibited enrichment capabilities comparable or superior to most common virtual screening approaches. Compound rankings were proven to be dissimilar to those of other virtual screening techniques. It was shown that emphasis on key interactions through the application of position specific weights in the alignment process significantly increases enrichment. Significance of chemical similarity was determined in form of p-values of global alignment scores, calculated in an approach that was adapted from its original application to local sequence alignments of protein sequences utilizing Marcov chain Monte Carlo simulation [4]. Bonferroni correction was used to correct p-values with respect to the size of the screening library [5]. PhAST was employed in two prospective applications: A screening for non-nucleoside analogue inhibitors of bacterial thymidine kinase yielded a hit with a distinct structural framework but only weak activity. Screenings for drugs that are not members of the NSAID (non-steroidal anti-inflammatory drug) class as modulators of gamma secretase resulted in a potent modulator with clear structural distinction from the reference compound.

Clustering More than Two Million Biomedical Publications: Comparing the Accuracies of Nine Text-Based Similarity Approaches

BackgroundWe investigate the accuracy of different similarity approaches for clustering over two million biomedical documents. Clustering large sets of text documents is important for a variety of information needs and applications such as collection management and navigation, summary and analysis. The few comparisons of clustering results from different similarity approaches have focused on small literature sets and have given conflicting results. Our study was designed to seek a robust answer to the question of which similarity approach would generate the most coherent clusters of a biomedical literature set of over two million documents.MethodologyWe used a corpus of 2.15 million recent (2004-2008) records from MEDLINE, and generated nine different document-document similarity matrices from information extracted from their bibliographic records, including titles, abstracts and subject headings. The nine approaches were comprised of five different analytical techniques with two data sources. The five analytical techniques are cosine similarity using term frequency-inverse document frequency vectors (tf-idf cosine), latent semantic analysis (LSA), topic modeling, and two Poisson-based language models – BM25 and PMRA (PubMed Related Articles). The two data sources were a) MeSH subject headings, and b) words from titles and abstracts. Each similarity matrix was filtered to keep the top-n highest similarities per document and then clustered using a combination of graph layout and average-link clustering. Cluster results from the nine similarity approaches were compared using (1) within-cluster textual coherence based on the Jensen-Shannon divergence, and (2) two concentration measures based on grant-to-article linkages indexed in MEDLINE.ConclusionsPubMed's own related article approach (PMRA) generated the most coherent and most concentrated cluster solution of the nine text-based similarity approaches tested, followed closely by the BM25 approach using titles and abstracts. Approaches using only MeSH subject headings were not competitive with those based on titles and abstracts.

Pharmacophore alignment search tool: Influence of the third dimension on text‐based similarity searching

Previously (Hähnke et al., J Comput Chem 2010, 31, 2810) we introduced the concept of nonlinear dimensionality reduction for canonization of two-dimensional layouts of molecular graphs as foundation for text-based similarity searching using our Pharmacophore Alignment Search Tool (PhAST), a ligand-based virtual screening method. Here we apply these methods to three-dimensional molecular conformations and investigate the impact of these additional degrees of freedom on virtual screening performance and assess differences in ranking behavior. Best-performing variants of PhAST are compared with 16 state-of-the-art screening methods with respect to significance estimates for differences in screening performance. We show that PhAST sorts new chemotypes on early ranks without sacrificing overall screening performance. We succeeded in combining PhAST with other virtual screening techniques by rank-based data fusion, significantly improving screening capabilities. We also present a parameterization of double dynamic programming for the problem of small molecule comparison, which allows for the calculation of structural similarity between compounds based on one-dimensional representations, opening the door to a holistic approach to molecule comparison based on textual representations.

Pharmacophore alignment search tool: Influence of scoring systems on text-based similarity searching

The text-based similarity searching method Pharmacophore Alignment Search Tool is grounded on pairwise comparisons of potential pharmacophoric points between a query and screening compounds. The underlying scoring matrix is of critical importance for successful virtual screening and hit retrieval from large compound libraries. Here, we compare three conceptually different computational methods for systematic deduction of scoring matrices: assignment-based, alignment-based, and stochastic optimization. All three methods resulted in optimized pharmacophore scoring matrices with significantly superior retrospective performance in comparison with simplistic scoring schemes. Computer-generated similarity matrices of pharmacophoric features turned out to agree well with a manually constructed matrix. We introduce the concept of position-specific scoring to text-based similarity searching so that knowledge about specific ligand-receptor binding patterns can be included and demonstrate its benefit for hit retrieval. The approach was also used for automated pharmacophore elucidation in agonists of peroxisome proliferator activated receptor gamma, successfully identifying key interactions for receptor activation.

“Reinventing the Wheel”: A Novel Approach to Music Player Interfaces

We present a novel interface to (portable) music players that benefit from intelligently structured collections of audio files. For structuring, we calculate similarities between every pair of songs and model a travelling salesman problem (TSP) that is solved to obtain a playlist (i.e., the track ordering during playback) where the average distance between consecutive pieces of music is minimal according to the similarity measure. The similarities are determined using both audio signal analysis of the music tracks and Web-based artist profile comparison. Indeed, we show how to enhance the quality of the well-established methods based on audio signal processing with features derived from Web pages of music artists. Using TSP allows for creating circular playlists that can be easily browsed with a wheel as input device. We investigate the usefulness of four different TSP algorithms for this purpose. For evaluating the quality of the generated playlists, we apply a number of quality measures to two real-world music collections. It turns out that the proposed combination of audio and text-based similarity yields better results than the initial approach based on audio data only. We implemented an audio player as Java applet to demonstrate the benefits of our approach. Furthermore, we present the results of a small user study conducted to evaluate the quality of the generated playlists

Node similarity in the citation graph

Published scientific articles are linked together into a graph, the citation graph, through their citations. This paper explores the notion of similarity based on connectivity alone, and proposes several algorithms to quantify it. Our metrics take advantage of the local neighborhoods of the nodes in the citation graph. Two variants of link-based similarity estimation between two nodes are described, one based on the separate local neighborhoods of the nodes, and another based on the joint local neighborhood expanded from both nodes at the same time. The algorithms are implemented and evaluated on a subgraph of the citation graph of computer science in a retrieval context. The results are compared with text-based similarity, and demonstrate the complementarity of link-based and text-based retrieval.