New York

Engineering/Life Science process automation

In addition to deal with large volumes of data many modern enterprises cope with a data rich environment. Meaning that a wide variety of data need to be processed by domain experts from different fields. Typically data processing is laborious, because not well integrated. Such situation can significantly impairs productivity.

Solutions for data rich environment

Data rich environment in the pharmaceutical industry. Data is collected at the molecurlar, cell, tissue and organ levels, with various modalities, and interpreted by several domain experts.

Data rich problematic

We are already familiar with the big data problematic, i.e., large volume of data that need to be stored/retrieved rapidly, mined, and analyzed in various ways. A data rich environment rather refers to a wide variety of data that need to be processed by professionals, in many instances experts, with different domain expertise. More than other industries, the pharmaceutical industry is more extensively exposed to such problematic. For example, the molecular mechanisms of diseases are studied with gene sequencers, microarrays, biomarkers and various biomedical imaging modalities. When designing a compound, X-ray, and NMR data need to be processed and visualized to study structure. Molecular dynamic simulations can be performed to study ligand-target interactions. And, in subsequent phases the effect of modulating a drug target is assessed by characterizing a physiological function at the cell, tissue, organ, or whole organism levels. This may involve analyzing medical images or time series collected on various sensors. Furthermore, the output of one process is an input for a subsequent one.

Problems firms are encountering is that an application does not provide all necessary graphic support to the experts. This may be adressed by adding graphic applications, but this increases the number of manipulations. The data processing tools utilized do no speak the language of the experts. In many instances the learning curve for learning using theses tools appropriately is quite extensive. As a result efforts involved in data manipulation is considerable. This impairs produtivity in several ways: time on task is not optimal, users may have to devise workarounds for some tasks not well supported by existing tools, creativity is affected because too much efforts is reuired to collect information.

Process automation

The term process automation is

Our solution

  1. Work flow
  2. Scientific data
  3. Visualization
  4. Instructions

Problems: Th The visualization of scientific data including among many other tasks, images manipulation, their annotation, and features extraction or other form of measurement is critical since it is the most important support for decision making. Problems encountered in data rich are