Epistasis analysis is an essential tool of classical genetics. We propose a conceptually new probabilistic approach to gene network inference from quantitative interaction data. The approach is founded on joint treatment of the mutant phenotype data with a factorized model and probabilistic scoring of pairwise gene relationships that are inferred from the latent gene representation. In an experimental study, we show that the proposed approach can accurately reconstruct several known pathways and that it surpasses the accuracy of current approaches.
COBISS.SI-ID: 10624852
We developed a new algorithm for counting the graphlet frequencies and orbits in sparse large graphs. The algorithm is applicable to many areas, in particular in the field of bioinformatics. Its time complexity is smaller than that of the existing algorithms for an order of magnitude; in practical terms, the execution times are hundred-fold shorter on the graphs we typically encounter in bioinformatics.
COBISS.SI-ID: 10322516
The vastness of chemical space and the relatively small coverage by experimental data recording molecular properties require us to identify subspaces, or domains, for which we can confidently apply QSAR models. In the paper we propose methods that quantify prediction confidence through estimation of the prediction error at the point of interest. Our experimental results indicate that these new alternative approaches can outperform standard reliability scores that rely only on similarity to compounds in the training set.
COBISS.SI-ID: 10466388