Pipeline Pilot

Pipeline Pilot is the authoring tool for the Accelrys Enterprise Platform. It is a scientific visual and dataflow programming language, used in various scientific domains, such as cheminformatics and QSAR,^[1][2][3] Next Generation Sequencing,^[4] image analysis,^[5][6] text analytics.^[7]

History

Originally created in 1999 by SciTegic, Pipeline Pilot is now developed by Accelrys.

Pipeline Pilot was used at first in the pharmaceutical and biotechnology industries and by academics and government agencies. Then other industries started to adopt it, but always in science driven sectors such as Chemicals, Energy, Consumer Packaged Goods, Aerospace, Automotive, Electronics.

Basic introduction

Pipeline Pilot includes contextual help that is searchable and interactive; users should refer to it. Reviewing the examples and the documentation is the best place to start.

Components, pipelines, protocols and data records

The graphical user interface, called the Pipeline Pilot Professional Client, allows users to drag and drop components, connect them together in pipelines, and save the application developed as a protocol.

Think of the components as nodes of a directed graph: each one has a specific task on the data. Users have the choice to use predefined components, or to develop their own: components can be chosen from the library, configured, redesigned, or even created from scratch and documented at will. When a new component is made by collapsing a few components together, it is called a subprotocol.

In a typical protocol, the reading components (on the left) send the data records through the pipelines (to the right) for further process, analysis, and reporting.

Component Collections

The components are organised by science in collections.^[8]

The most interesting protocols are often those mixing collections:

• Determine the IC50 by calculating the dose–response relationship directly from information extracted from high-content screening assay images, associated with dilution in the plate layout and chemistry information about the tested compounds (Imaging, Chemistry, Plate Data Analytics)
• Suggest which scientific article to read next, based on a Bayesian model built upon text fingerprints and user's reading list or papers ranking (Text Analytics, Data Modeling)
• Access experiment methods and results from electronic laboratory notebook or laboratory information management system, and report for resource capacity planning (Integration, Reporting)

PilotScript

Many custom script components are available in Pipeline Pilot, allowing experts to include their code directly into the pipelines and maintain a library of components based on their preferred language, such as Perl, Java, VBScript, .NET, JavaScript, Python, Matlab, etc.^[9]

Another option is to use PilotScript, the internal scripting language of Pipeline Pilot, which syntax is based on PLSQL. It can be used in components such as the Custom Manipulator (PilotScript) or the Custom Filter (PilotScript).

Hello := "Hello World!";

This script above will add, to each data record passing through its component, a property named Hello containing the string "Hello World!".

Community

The community forum allows users to share ideas, components, and protocols.

Companies such as ACD/Labs,^[10] BioSolveIT,^[11] ChemAxon,^[12] Cosmologic,^[13] Cresset,^[14] Linguamatics,^[15] Molecular Discovery,^[16] and Molecular Networks,^[17] partner with Accelrys^[18] to develop and provide component collections to interface with their technologies, allowing automation from within Pipeline Pilot.

Oxford Nanopore Technologies offers Pipeline Pilot NGS collection as the preferred and supported solution for secondary and higher level data analysis in their GridION system.^[19][20]

References