Kernel learning for ligand-based virtual screening:discovery of a new PPARgamma agonist
- Poster presentation at 5th German Conference on Cheminformatics: 23. CIC-Workshop Goslar, Germany. 8-10 November 2009 We demonstrate the theoretical and practical application of modern kernel-based machine learning methods to ligand-based virtual screening by successful prospective screening for novel agonists of the peroxisome proliferator-activated receptor gamma (PPARgamma) . PPARgamma is a nuclear receptor involved in lipid and glucose metabolism, and related to type-2 diabetes and dyslipidemia. Applied methods included a graph kernel designed for molecular similarity analysis , kernel principle component analysis , multiple kernel learning , and, Gaussian process regression . In the machine learning approach to ligand-based virtual screening, one uses the similarity principle  to identify potentially active compounds based on their similarity to known reference ligands. Kernel-based machine learning  uses the "kernel trick", a systematic approach to the derivation of non-linear versions of linear algorithms like separating hyperplanes and regression. Prerequisites for kernel learning are similarity measures with the mathematical property of positive semidefiniteness (kernels). The iterative similarity optimal assignment graph kernel (ISOAK)  is defined directly on the annotated structure graph, and was designed specifically for the comparison of small molecules. In our virtual screening study, its use improved results, e.g., in principle component analysis-based visualization and Gaussian process regression. Following a thorough retrospective validation using a data set of 176 published PPARgamma agonists , we screened a vendor library for novel agonists. Subsequent testing of 15 compounds in a cell-based transactivation assay  yielded four active compounds. The most interesting hit, a natural product derivative with cyclobutane scaffold, is a full selective PPARgamma agonist (EC50 = 10 ± 0.2 microM, inactive on PPARalpha and PPARbeta/delta at 10 microM). We demonstrate how the interplay of several modern kernel-based machine learning approaches can successfully improve ligand-based virtual screening results.
Spherical harmonics coeffcients for ligand-based virtual screening of cyclooxygenase inhibitors
Carlo Federico Angioni
- Background: Molecular descriptors are essential for many applications in computational chemistry, such as ligand-based similarity searching. Spherical harmonics have previously been suggested as comprehensive descriptors of molecular structure and properties. We investigate a spherical harmonics descriptor for shape-based virtual screening. Methodology/Principal Findings: We introduce and validate a partially rotation-invariant three-dimensional molecular shape descriptor based on the norm of spherical harmonics expansion coefficients. Using this molecular representation, we parameterize molecular surfaces, i.e., isosurfaces of spatial molecular property distributions. We validate the shape descriptor in a comprehensive retrospective virtual screening experiment. In a prospective study, we virtually screen a large compound library for cyclooxygenase inhibitors, using a self-organizing map as a pre-filter and the shape descriptor for candidate prioritization. Conclusions/Significance: 12 compounds were tested in vitro for direct enzyme inhibition and in a whole blood assay. Active compounds containing a triazole scaffold were identified as direct cyclooxygenase-1 inhibitors. This outcome corroborates the usefulness of spherical harmonics for representation of molecular shape in virtual screening of large compound collections. The combination of pharmacophore and shape-based filtering of screening candidates proved to be a straightforward approach to finding novel bioactive chemotypes with minimal experimental effort.
Bioassays to monitor taspase1 function for the identification of pharmacogenetic inhibitors
- Background: Threonine Aspartase 1 (Taspase1) mediates cleavage of the mixed lineage leukemia (MLL) protein and leukemia provoking MLL-fusions. In contrast to other proteases, the understanding of Taspase1's (patho)biological relevance and function is limited, since neither small molecule inhibitors nor cell based functional assays for Taspase1 are currently available. Methodology/Findings: Efficient cell-based assays to probe Taspase1 function in vivo are presented here. These are composed of glutathione S-transferase, autofluorescent protein variants, Taspase1 cleavage sites and rational combinations of nuclear import and export signals. The biosensors localize predominantly to the cytoplasm, whereas expression of biologically active Taspase1 but not of inactive Taspase1 mutants or of the protease Caspase3 triggers their proteolytic cleavage and nuclear accumulation. Compared to in vitro assays using recombinant components the in vivo assay was highly efficient. Employing an optimized nuclear translocation algorithm, the triple-color assay could be adapted to a high-throughput microscopy platform (Z'factor = 0.63). Automated high-content data analysis was used to screen a focused compound library, selected by an in silico pharmacophor screening approach, as well as a collection of fungal extracts. Screening identified two compounds, N-[2-[(4-amino-6-oxo-3H-pyrimidin-2-yl)sulfanyl]ethyl]benzenesulfonamideand 2-benzyltriazole-4,5-dicarboxylic acid, which partially inhibited Taspase1 cleavage in living cells. Additionally, the assay was exploited to probe endogenous Taspase1 in solid tumor cell models and to identify an improved consensus sequence for efficient Taspase1 cleavage. This allowed the in silico identification of novel putative Taspase1 targets. Those include the FERM Domain-Containing Protein 4B, the Tyrosine-Protein Phosphatase Zeta, and DNA Polymerase Zeta. Cleavage site recognition and proteolytic processing of these substrates were verified in the context of the biosensor. Conclusions: The assay not only allows to genetically probe Taspase1 structure function in vivo, but is also applicable for high-content screening to identify Taspase1 inhibitors. Such tools will provide novel insights into Taspase1's function and its potential therapeutic relevance.
DOGS: reaction-driven de novo design of bioactive compounds
- We present a computational method for the reaction-based de novo design of drug-like molecules. The software DOGS (Design of Genuine Structures) features a ligand-based strategy for automated ‘in silico’ assembly of potentially novel bioactive compounds. The quality of the designed compounds is assessed by a graph kernel method measuring their similarity to known bioactive reference ligands in terms of structural and pharmacophoric features. We implemented a deterministic compound construction procedure that explicitly considers compound synthesizability, based on a compilation of 25'144 readily available synthetic building blocks and 58 established reaction principles. This enables the software to suggest a synthesis route for each designed compound. Two prospective case studies are presented together with details on the algorithm and its implementation. De novo designed ligand candidates for the human histamine H4 receptor and γ-secretase were synthesized as suggested by the software. The computational approach proved to be suitable for scaffold-hopping from known ligands to novel chemotypes, and for generating bioactive molecules with drug-like properties.