OBBeC.com

Key features of the new release, which is the next generation of the highly successful Pipeline Pilot platform, include a service oriented architecture environment, enterprise collaborative tools, interactive application building, and workflow parallelization.

Mark J. Emkjer, president and chief executive officer of Accelrys outlined that this release extends the enterprise capabilities of the platform, enabling improve productivity and helping customers make more informed, real time decisions.

With the release of SES 7.0, there are two new component collections available:
Plate Data Analytics Collection for managing and analyzing screening data; And Advanced Modelling Collection for statistical data analysis using recursive partitioning and Pareto optimization techniques.

The Plate Data Analytics Collection provides a data model for plate based data within SciTegic Enterprise Server and provides methods to read, write, report, visualize, manipulate and perform calculations on plate data. The collection allows each record on the data pipeline to carry an entire plate and its associated wells and to perform both plate and well level operations. Harnessing the power of the SciTegic graphical protocol building capabilities, complex data analysis procedures, such as analyzing the results of a screening experiment, can be easily constructed without the need to develop code. Coupled with the integration collection, this plate-based data can easily be inserted into or retrieved from a database.

With the Plate Data Analytics Collection users can:
Define automated procedures to analyze the results of various types of screening experiments; Perform statistical calculations within or across plates including normalizations and calculations of assay quality; Perform Dose-Response calculations using SciTegic, R-statistics, or Graph Pad Prism methods; Visualize large collections of plates and interactively drill-down to plate and well level details; And when coupled with the integration collection, insert or retrieve plate data from databases.

The Pipeline Pilot Advanced Modelling component collection provides methods for Recursive Partitioning (RP) and Multi-objective Pareto Optimization. The Recursive Partitioning components provide a variety of RP methods including single tree and forest of trees learners. The methods can learn on single or multiple response variables. The Pareto Optimization components provide methods for multi-objective optimization problems, provide solutions whose criteria trade off amongst two or more partially conflicting goals.

With the Recursive Partitioning Components users can:
Perform very rapid learning and data mining experiments on very large datasets with very large numbers of descriptors; Learn molecular datasets using fingerprints as descriptors; Visualize trees to understand the relationships between descriptors and responses; Analyze descriptor usage to identify the most discriminating descriptors; And rapidly apply models to new predict new data sets

With the Pareto Optimization Components users can:
Optimize solutions for problems as diverse as combinatorial library design, formulation ingredient optimization or stock portfolio risk management; Find individual samples with a dataset that have the best tradeoff of desired property values; And find subsets of samples from a larger dataset that collectively have the best trade-offs between desired property values.