The software is implemented in the programming language C++ and was developed for the Linux and Mac OS Substructures are returned as SMARTS strings together with their occurrences in the given set of structures. Substructures frequent in the first and infrequent in the second are returned by FTM. This constraint can either refer to the same database/set or to a second one, meaning that all Additional to the minimum frequency support, a maximum frequency constraint canīe set. The substructures are computedīy a depth-first search. Unrooted trees) occurring at a given minimum frequency in a set of molecules.
Fminer run code action free#
The FreeTreeMiner (FTM) software computes all acyclic substructures (in mathematical terms: free or A final crossvalidation run confirms that the novel descriptors render large training setsįeasible which previously might have been intractable for computational models.
Into important properties of the proposed descriptors, such as dataset coverage and class size represented byĮach descriptor. Further analysis using large-scale datasets yields insight Open or closed fragment mining, a large part of the search space can be pruned due to an improved statisticalĬonstraint (dynamic upper bound adjustment), which is also confirmed in the experiments in lower runtimesĬompared to ordinary (static) upper bound pruning. Evaluation using crossvalidation runs shows that their classificationĪccuracy is similar to the complete set of trees but significantly better than that of open trees. Mining and open tree mining, respectively. In theĮxperiments, the proposed method reduces feature set sizes by >90% and >30% compared to complete tree The approach is able to optimize structural inter-įeature entropy as opposed to occurrences, which is characteristic for open or closed fragment mining. (backbone), thereby reducing feature set size and runtime. FMinerįminer is a novel method for efficiently mining relevant tree-shaped subgraph descriptors with minimumįrequency and correlation constraints, each representing a set of fragments sharing a common core structure
A number of descriptor implementations are available. The Chemistry Development Kit (CDK) is a Java library for structural chemo- and bioinformatics. The descriptor calculation is a separate module and packaged in ambit2-descriptors.jar, which depends only on cdk library, core ambit module (ambit2-core.jar) and ambit SMARTS (ambit2-smarts.jar) implementation. The descriptor calculation relies on the CDK library, but also implements several additional descriptors. AMBIT is a software package for chemoinformatic data management.
0 kommentar(er)
