Machine Learning – “What if” it enabled exploratory analysis in High Content Screening

January 22nd, 2010 by Tim Moran

A roundtable discussion took place near the close of this year’s HCA meeting in San Francisco. The topics of  Data Analysis and Management,  Image Analysis and Computational Biology were folded into a single discussion. This roundtable was facilitated by Karel Kozak. Participants included:

Karel Kozak (Swiss Fed. Institute Of Technology)

Lisa Smith (Merck)

Peter Horvath (Swiss Fed. Institute Of Technology)

Achim Kirsch (PE/Evotec)

Ghislain Bonamy (Novartis GNF)

Abhay Kini (GE Healthcare)

Jonathan Sexton (North Carolina Central University)

Mark Bray (Broad Institute)

Chris Wood (Stowers Institute for Medical Research)

Pierre Turpin (Molecular Devices)

Mark Collins (ThermoFisher/Cellomics)

The opening shot from Schmerck (Lisa Smith  from Schering now Merck) was fired at the vendors. The bullet in question? “Why tools for pattern recognition and machine learning on image data were not more rapidly addressed for vendor systems?”  Vendors replied with their own question, “Why is this a better approach than algorithmic quantification of a known endpoint?” The result of the ensuing discussion was that the end-users want the ability to extract any additional information from their data that is not derived by the designed analysis algorithm, i.e., look for natural classes in the data, spot outliers, correlate to chemical structure of test compounds, etc. This does not necessarily have to be correlated to known biological endpoints – it can be purely exploratory. Vendors said “that’s why we need companies like Accelrys and products like Pipeline Pilot”. The marketplace needs a third-party environment which provides turnkey or almost-turnkey access to the data, and an exploratory environment like PLP in which users can develop methods to ask “what-if” questions of their data. When users clearly demonstrate that these techniques have merit, they will find their way into the instrument vendors’ products.

One other aspect of the above discussion which became apparent is that many, if not most, HCS users have no idea what the difference is between PCA, Classification, Support Vector Machines, genetic algorithms, Self-organizing maps, etc., let alone where or when to apply these methods. What they want, and need, is a kind of wizard which walks them through a process of determining what they want to learn from their data, and selecting internally the best method to do that. An analogy was drawn to curve-fitting programs which apply hundreds or thousands of models to a data set, and tell the user which ones produced the best fit. This idea of “opening up to the wider science community methods previously available only to discipline experts”, specifically in computational biology, is by no means in its infancy (see The Future of Computational Science, Scientific Computing World: May / June 2004).

The momentum in machine vision – learning, clustering, modeling, predicative science and ease of use was foreshadowed in the HCA East conference held in 2009 and will likely continue to be the area that enables researchers in High Content Screening and Analysis to make better informed decisions earlier in the discovery process.

Special thanks to contributing author Kurt Scudder.

  • Share/Save/Bookmark

The RNA World

October 15th, 2009 by Accelrys Team

This year’s Nobel Prize in Chemistry brought back fond memories of why I chose to study the RNA in the first place for my thesis work. It was in 1989 that Tom Cech, a professor at University of CO, Boulder, had won a Nobel Prize in Chemistry for his discovery of ribozymes. His work, along with many others, had clearly redefined the central dogma that genetic information flow may not be necessarily from DNA to RNA to Proteins. That RNA wasn’t simply a passive carrier of information and that it played an important role in catalytic activity.

I had picked up a book called “The RNA World” (1st edition, 1993) a few days before I was faced with a decision to pick a project for my dissertation back in 1995. Initially, I had joined Wayne State University with an intention to study bioorganic chemistry under Mobashery, but soon realized that I needed to know more about this RNA world which had left me intrigued and interested. Little did I know that the years to follow would have me solving bits of rRNA structure in high resolution using NMR spectroscopy: the 790 loop of 16S rRNA, to be exact. It was intriguing to learn that the sequence of this relatively tiny solvent exposed hairpin loop is so highly conserved across phylogeny that any mutation in the sequence basically shuts down protein synthesis. Why does nature prefer only those nucleotides and what role do they play in protein synthesis? Only the 3D structure of that loop could unravel the mystery.

Thus, my first application of translational research began where our lab collaborated with a biologist who designed this “instant evolution” experiment which allowed us to understand the structure-activity relationship of the tolerated mutations. Structural and biophysical characterization of the hairpin loop and its variants was long and arduous task but revealing exciting results which helped us understand why nature preferred the sequence and its conservation across phylogeny. Biophysical characterization, base pairing and thermodynamic stability explained mismatched mutations.

Feeling quite proud of this year’s winners, Venki Ramakrishnan (UK), Tom Steitz (US)  and Ada Yonath (Israel), I am certain that the recognition of their efforts in understanding the structure and function of the ribosome is shared by many across the globe who have dedicated their lives in studying such a marvelous piece of machinery nature has created! Venki’s parting comment in his interview in Nature video sums it all up pretty well – it’s this kind of fundamental research that will help us discover therapies and drugs which will become billions of dollars of industry eventually.

Congratulations to the winners of 2009 Nobel Prize in Chemistry!

  • Share/Save/Bookmark