Alexander Klenner-Bajaja

Interpreting the rapidly increasing amount of experimental data requires the availability and representation of biological knowledge in a computable form. The Biological expression language (BEL) encodes the data in form of causal relationships, which describe the association between biological events. BEL can successfully be applied to large data and support causal reasoning and hypothesis generation.
With the rapid growth of biomedical literature, automated methods are a crucial… Meer weergeven

Interpreting the rapidly increasing amount of experimental data requires the availability and representation of biological knowledge in a computable form. The Biological expression language (BEL) encodes the data in form of causal relationships, which describe the association between biological events. BEL can successfully be applied to large data and support causal reasoning and hypothesis generation.
With the rapid growth of biomedical literature, automated methods are a crucial prerequisite for handling and encoding the available knowledge. The BioNLP shared tasks support the development of such tools and provide a linguistically motivated format for the annotation of relations. On the other hand, BEL statements and the corresponding evidence sentences might be a valuable resource for future BioNLP shared task training data generation. In this paper, we briefly introduce BEL and investigate how far BioNLP-shared task annotations could be converted to BEL statements and in such a way directly support BEL statement generation. We present the first results of the automatic BEL statement generation and emphasize the need for more training data that captures the underlying biological meaning. Minder weergeven

Interpreting the rapidly increasing amount of experimental data requires the availability and representation of biological knowledge in a computable form. The Biological expression language (BEL) encodes the data in form of causal relationships, which describe the association between biological events. BEL can successfully be applied to large data and support causal reasoning and hypothesis generation.
With the rapid growth of biomedical literature, automated methods are a crucial… Meer weergeven

Interpreting the rapidly increasing amount of experimental data requires the availability and representation of biological knowledge in a computable form. The Biological expression language (BEL) encodes the data in form of causal relationships, which describe the association between biological events. BEL can successfully be applied to large data and support causal reasoning and hypothesis generation.
With the rapid growth of biomedical literature, automated methods are a crucial prerequisite for handling and encoding the available knowledge. The BioNLP shared tasks support the development of such tools and provide a linguistically motivated format for the annotation of relations. On the other hand, BEL statements and the corresponding evidence sentences might be a valuable resource for future BioNLP shared task training data generation. In this paper, we briefly introduce BEL and investigate how far BioNLP-shared task annotations could be converted to BEL statements and in such a way directly support BEL statement generation. We present the first results of the automatic BEL statement generation and emphasize the need for more training data that captures the underlying biological meaning. Minder weergeven

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… Meer weergeven

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. Minder weergeven