Solver since 2010

Occupation: Assistant instructor at UT Southwestern medical center
Education: Ph.D in biochemistry
Residence: United States
Challenges awarded: 1

Challenge won: New Innovative Prophylaxis Approaches to Protect Against OP Pesticide Poisoning ($15,000 Challenge)

I’m an assistant instructor at the University of Texas Southwestern Medical Center at Dallas, specializing in bioinformatics and molecular biology. I was born in Castellón, Spain, where I grew up very interested in science, since my father is a biologist and my mother a chemistry teacher. I obtained a B.Sc. in Biochemistry from the University of Barcelona in 1997. While earning my Ph.D. at the University of Valencia, I was privileged to be mentored by Dr. M.D. Ferrando, as well as my own father, who allowed me to open my own research line at one of the Spanish Research Council (CSIC) centers, the Institute of Aquaculture Torre de la Sal, which is located nearby really nice beaches. While working there I realized that innovation was a crucial aspect of science and I began looking for applications of my research into the mechanisms of resistance to oxidative stress and pesticides. That work led to a couple of patents and several papers, one of which was distinguished with the ‘Best Publication Award on Environmental Research’ by the Society of Environmental Toxicology and Chemistry (SETAC) and AstraZeneca. A few months after defending my PhD in 2003, I received a postdoctoral fellowship to study the effects of oxidative stress on gene regulation with Dr. Bruce Demple at the Harvard School of Public Health. In 2006 I got the chance to lead a project to uncover the molecular events driving kidney cancer and I moved with Dr. James Brugarolas to UT Southwestern, where I received another postdoctoral fellowship from Generalitat Valenciana.

My own family, like many others, has felt directly the devastating effects of cancer: Though I could not help my brother, I have the satisfaction of identifying some genes involved in renal cell carcinoma, as well as a novel transcription factor regulated by the mammalian target of rapamycin (mTOR), which plays a critical role in cell growth and is deregulated in about half of human tumors. These findings may create new therapeutic opportunities and someday benefit patients.

The first time I learned about InnoCentive was in an advertisement on nature.com, which got my attention because I knew a good answer to the question it asked. InnoCentive offers a new way of solving problems for companies by reaching out to a wide audience of different backgrounds, but it also gets non-industry-oriented people closer to the issues that really matter to the companies. At the end, innovation promotes the progress of our society and it’s very rewarding to be part of it.

Today’s blog post was written by Tara Crawford, a member of a student team of undergraduates at University of Ottawa that received an award for the Challenge “

We solved the Challenge “Nuclear Test Monitoring and Verification Methods” as a group in a fourth-year Biotechnology course this past year. The criteria for the course was to invent something and file for a patent. Our professor also urged us to look for online Challenges.

We looked at the InnoCentive website and thought that “Nuclear Test Monitoring and Verification Methods” was a good opportunity for us to apply our science background as well as learn new areas (we are a group of five students in Biochemistry, Biomedical Science/Chemistry, Biopharmaceutical science, and chemical engineering). We researched many experts in the field and invited them to be guest speakers in our class so that we could ask them questions about the topics we were trying to apply to our solution. We needed to expand our knowledge into the radionuclides that we wanted to detect and the methods currently available to do that, as well as other possibilities that had not been investigated yet.

Our class consisted of 3 hours of lecture time a week where we initially learnt about patenting, intellectual property, and were able to brainstorm with our groups.  Then we also had an extra 1.5 hours a week to meet in an informal lecture setting and discuss our progress. Outside of class time our group met 1-2 times a week to work more specifically on our solution. This involved a lot of brainstorming and allowed us to bring together all of our individual research.

The experience was a great one for us. We learnt a new way of learning since it was a hands off approach by our professor. Throughout our undergraduate degree we had taken many courses that were very structured, but this allowed us to do whatever topic we wanted. We improved our team building skills and really got an idea of how our previous knowledge could be applied to the real world. We all really enjoyed it, although it required a lot of self discipline to ensure we met deadlines!

Hello Konstantin. Thank you for taking the time to talk to us about working on the first Prodigy Challenge. Just so we have a bit of background, can you tell us how learned about InnoCentive and what made you become an InnoCentive Solver?

I am always on the lookout for new opportunities in the field of science and I am attracted to the internet as a means of communication. Therefore, as soon as I discovered InnoCentive from a Google search, I knew that this was for me.  What InnoCentive does is globalize R&D and I think that’s great.

Have you worked on any Challenges prior to the Predictive Data Analysis Challenge? If so, can you tell us about them?

Although I have been checking on the challenges posted on InnoCentive for the past couple of years, the Prodigy Challenge was the very first challenge I decided to undertake and formally submit a solution. I guessed I jumped straight into the middle of the ocean…

What attracted you to the Prodigy Challenge?

Ever since I was a child I had a soft spot for scripting, mathematics and challenging problems. As soon as I read the details of the challenge it instantly fit my criteria. This Challenge had a  huge dataset, with more than a million  features out of which only a few carried the information (or part of it) needed for a good prediction, buried within experimental noise, missed measurements and small number of observations sounded just about right, I just couldn’t say no.

What was it like working on the Prodigy Challenge and the rapid feedback it provided? Did the Prodigy make you feel more confident about your solutions? Did it make you feel that you were engaged with other Solvers by knowing (in a strange way) who your competition was? Did it help you avoid incorrect answers?

The Prodigy, for me the best feature ever introduced into a challenge, although it is definitely not for the faint-hearted. I noticed the challenge with a one-month delay. People had already started scoring above the threshold. Initially I was excited and full of momentum. After my initial attempts on the Prodigy, which crashed and burned really badly, I got frustrated and the 0.14 threshold started to seem like a distant dream.

You know, you are working hard on an idea that flashed in your brain the previous night and sounds just about perfect. So perfect actually that you are in a hurry to wrap everything up and have a go in the Prodigy to finally manage to catch the dream, enter the top 10. You are excited, you enter the data, press enter and… boom, your score is 0 and all your excitement turns to dust. I thought of quitting more than once, but I was determined to give everything I had to it, so I just grabbed my pieces and started working all over again. After a lot of hard work I entered the top 10 and then I got even more excited which carried me to the first place. When I got there, I celebrated my “victory” and relaxed for about a day. Then I realized that other people were also working hard and they were catching up with me quickly day by day. The anxiety to maintain the first place was the dominant force, driving me to work even harder, to push the solution even further, make it even better, and make sure that I remained at the top right through the end. The prodigy definitely kept me on the right track offering me instant feedback on every decision I took on my methodology. I do not think that this challenge would have received any serious solutions had it not been for the prodigy. Apart from an invaluable testing tool, prodigy is a feature, driving and boosting productivity and efficiency to the highest possible extent.

Without sharing anything proprietary, can you tell us your inspiration for the solution?

The difficulty of the problem immediately came down to feature selection. Having such a large number of features with only a relatively small number of observations, a combination of techniques such as the ‘least absolute shrinkage and selection operator’ (LASSO) and ‘Principal Component Analysis’ (PCA) provided an efficient means of zeroing in to the most information rich features. The machine learner of choice was a kernel based variant of the well-established Support Vector Machine (SVM) called the ‘Relevance Vector Machine’ (RVM) which uses Bayesian inference to obtain parsimonious solutions for regression and classification. A kernel-based learner was used to compensate for the fact that the RVM (just as the SVM) are linear predictors whereas the relationship of the features to the ‘Y’ trait was not likely to be linear. Out of the reduced feature-set, feature groups of the highest possible predictive value possible where determined through well-established algorithms such as ‘best-first selection’ & ‘backward elimination’. All the models were evaluated by multiple iterations of k-fold cross-validation. Finally the best models were combined, by utilizing the ‘ensemble learning’ paradigm, to provide one powerful predictor.

You were clearly at the top of the leader-board proving your aptitude for computational analysis. Is this your primary occupation or hobby? Would this acknowledgment have any effect on your career choices?

Actually data mining & knowledge discovery started as a hobby having roots in my passion for scripting and my love for mathematics. My main occupation is currently irrelevant to the field of computational analysis as I work as a research technician in the genomics and proteomics division of the Foundation of Biomedical Research of the Academy of Athens (http://www.bioacademy.gr). During the last 4 years though, I have made an effort in providing data analysis and bioinformatic support to various groups and projects and the results of this effort have now started to come out. I definitely intend to make bioinformatics and computational analysis my full-time main occupation, and hopefully this acknowledgement will back-up my decision.

This Challenge was related to genomics; do you have any experience in this field?

As I mentioned earlier I am currently providing computational analysis support to various groups mainly working on genomics. My primary tasks are to perform quality control and knowledge discovery on projects concerned with a) differential gene expression (DNA-microarrays), b) genomic copy number variation (aCGH) and c) Whole Genome Association Studies (SNP Genotyping). Finally, I am currently working on distributed computing and GPU utilization from within R, which is the statistical computing environment I use 99% of the time.

What was your experience on working with InnoCentive? Would you work on another Challenge?

It was a very fulfilling experience because through it, I had the opportunity to expand my horizons. I learned new things, not only about computing and science, but about myself and my limits. I will definitely do it again.

For the last three years, InnoCentive has been posting marketing Challenges that showcase the diversity and creativity of InnoCentive Solvers, and to drive InnoCentive’s market awareness. These Challenges are aimed at not only involving the “artistic temperament” of our Solvers, but also to demonstrate to our Seekers that the InnoCentive Solver Community is a great resource for “voice of the customer” input for Challenges that are considered to be part of more “traditional” business domains, such as marketing.

Well, we’ve just posted our Fourth Annual InnoCentive Video Challenge! It’s called The Uniquely Prepared Mind, where we ask you to demonstrate the idea that a uniquely prepared mind is capable of solving even the most demanding Challenges the world has to offer. This is why the InnoCentive Solver is the perfect person to create this video – you know Solvers best and you are always up for a Challenge – pardon the pun.

This year, we’re guaranteeing $10,000 in awards for the best 30-second shorts that nail the 2011 Video Theme, The Uniquely Prepared Mind.

The first prize will receive a minimum of $5,000, and we’re guaranteeing $10,000 in awards. The top 20 runners-up will receive IC-branded shirts with the website’s new look and feel! Visit YouTube to see the 2010 winner and runners-up from previous years, then prepare your mind and submit a winner.

Clock is ticking! Check it out, open a Project Room, and share it, too!

Greetings, InnoCentive Solvers—

Quick note to inform you that we’ve posted two new Emergency Response 2.0 Challenges around the Gulf Oil Spill disaster: Emergency Response 2.0: Oil Detection on Ocean Surfaces; and Emergency Response 2.0: Oil Collection in Gulf of Mexico.

Innovative solutions to these Challenges will help the organizers and crews clean the water and beaches in the short and medium terms.

For the Oil Detection on Ocean Surfaces Challenge we’re looking for new ways to improve the conventional imaging processes that are currently being deployed, i.e., satellite radar, visual, LIDAR, etc. We are also looking for ways to improve aerial tools aboard helicopters and aircrafts, and, to a lesser degree, surface spotting techniques.

For the Oil Collection in the Gulf of Mexico Challenge we’re looking for commercially available equipment, technology and ideas that would enable the rapid conversion of commercial vessels (e.g., fishing) into oil recovery units.

On the back-end, a board of advisers, currently being assembled, will review the submissions from both Challenges.

That said we also want to take advantage of the perspectives, skills, and talents in the InnoCentive network. In order to accomplish that, we have activated the discussion board within the project rooms.

Please take a look as soon as you can.

Best,

JD