Implementation


Virtual Peace (http://virtualpeace.org) is alive as of last evening.

For the last gosh-don’t-recall-how-many-months I’ve been working as a Project Collaborator for a project envisioned by the other half (more than half) of the Jenkins Chair here at Duke, Tim Lenoir.  For those of you who don’t know Tim, he’s been a leading historian of science for decades now, helping found the History and Philosophy of Science program at Stanford.  Tim is notable in part for changing areas of expertise multiple times over his career, and most recently he’s shifted into new media studies.  This is the shift that brought him here to Duke and I can’t say enough how incredible of an opportunity it is to work for him.  We seem to serve a pivotal function for Duke as people who bring together innovation with interdisciplnarianism.

What does that mean? Well, like the things we study, there are no easy simple narratives to cover it.  But I can speak through examples.  And the Virtual Peace Project is one such example.

Tim, in his latest intellectual foray, has developed an uncanny and unparalleled understanding of the role of simulation in society.  He has studies the path, no, wide swath of simulation in the history of personal computing, and he developed a course teaching contemporary video game criticism in relation to the historical context of simulation development.

It’s not enough to just attempt to study these things in some antiquated objective sense, however.  You’ve got to get your hands on these things, do these things, make these things, get some context. And the Virtual Peace project is exactly that. A way for us to understand and a way for us to actually do something, something really fantastic.

The Virtual Peace project is an initiative funded by the MacArthur Foundation and HASTAC through their DML grant program. Tim’s vision was to appropriate the first-person shooter (FPS) interface for immersive collaborative learning.  In particular, Virtual Peace simulates an environment in which multiple agencies coordinate and negotiate relief efforts for the aftermath of Hurricane Mitch in Honduras and Nicaragua.  The simulation, built on the Unreal game engine in collaboration with Virtual Heroes, allows for 16 people to play different roles as representatives of various agencies all trying to maximize the collective outcome of the relief effort.  It’s sort of like Second Life crossed with America’s Army, everyone armed not with guns but with private agendas and a common goal of humanitarian relief. The simulation is designed to take about an hour, perfect for classroom use. And with review components instructors have detailed means for evaluating the efforts and performance of each player.

I can’t say enough how cool this thing is.  Each player has a set of gestures he or she may deploy in front of another player.  The simulation has some new gaming innovations including proximity-based sound attenuation and full-screen full-session multi-POV video capture.  And the instructor can choose form a palette of “curveballs” to make the simulation run interesting.  Those changes to the scenario are communicated to each player through a PDA his or her avatar has. I was pushing for heads-up display but that’s not quite realistic yet I guess. 😉

The project pairs the simulation with a course-oriented website.  While a significant amount of web content is visible to the public, most of the web site is intended as a sort of simulation preparation and role-assignment course site.  We custom-built an authentication and authorization package that is simple and lightweight and user-friendly, a system that allows instructors to assign each student a role in the simulation, track the assignments, distribute hidden documents to people with specific roles, and allow everyone to see everything, including an after-action review, after the simulation run.

Last evening, Wednesday October 08, 2008, the Virtual Peace game simulation enjoyed its first live classroom run at the new Link facility in Perkins Library at Duke University.  A class of Rotary Fellows affiliated with the Duke-UNC Rotary Center were the first players in the simulation and there was much excitement in the air.

Next up:

I never miss a beat here it seems, for now I am already onto my next project, something that has been my main project since starting here: reading research and patent corpora mediated through text mining methods.  Yes that’s right, in an age where we struggle to get people to read at all (imagine what it’s like to be a poet in 2008) we’re moving forward with a new form of reading: reading everything at once, reading across the dimensions of text. I bet you’re wondering what I mean.  Well, I just can’t tell you what I mean, at least, not yet.

At the end of October I’ll be presenting with Tim in Berlin for the “Writing Genomics: Historiographical Challenges for New Historical Developments” workshop at the Max Planck Institute for the History of Science. We’ll be presenting on some results related to our work with the Center for Nanotechnology in Society at UCSB.  Basically we’ll be showing some of our methods for analyzing large document collections (scientific research literature, patents) as applied to the areas of bio/geno/nano/parma both in China and the US. We’ll demonstrate two main areas of interest: our semiotic maps of idea flows over time I’ve developed in working with Tim and Vincent Dorie, and the spike in the Chinese nano scientific literature at the intersection of bio/geno/nano/parma.  This will be perfect for a historiography workshop. The stated purpose of the workshop:

Although a growing corpus of case-studies focusing on different aspects of genomics is now available, the historical narratives continue to be dominated by the “actors” perspective or, in studies of science policy and socio-economical analysis, by stories lacking the fine-grained empirical content demanded by contemporary standards in the history of science.[…] Today, we are at the point in which having comprehensive narratives of the origin and development of this field would be not only possible, but very useful. For scholars in the humanities, this situation is simultaneously a source of difficulties and an opportunity to find new ways of approaching, in an empirically sound manner, the complexities and subtleties of this field.

I can’t express enough how exited I am about this. The end of easy narratives and the opportunity for intradisciplinary work (nod to Oury and Guattari) is just fantastic.  So, to be working on two innovations, platforms of innovation really, in just one week.  I told you my job here was pretty cool. Busy, hectic, breakneck, but also creative and multimodal.

Advertisements

The following comprises a collection of my intuitions and “big picture” insights resulting from graduate study focused on text mining at SILS. These are insights related to feature representation, knowledge engineering, model building, the application of statistics to real-life phenomena, and the greater whole of information science.

Many of these apparently go without saying, yet so many discussions of supposed problems would go away if some of these observations were made explicit. This is my attempt to make them explicit. Maybe it goes without saying that expressing the obvious is sometimes quite necessary.

1. Statistical models often fail because they’re missing key attributes necessary to describe the phenomena they represent

Attributes that are altogether unrecognized, difficult to quantify, difficult to analyze, truncated out, or simply forgotten arguably dominate and confound the predictive/explanatory power of statistical models. These missing variable abound. Their absence dominates to the point where theory itself must give way to empiricism and its sister, skepticism. It also means that we simply don’t see everything and that it never hurts to try and see more things.
2. Feature reduction of highly dimensional linguistic data sets is a misguided, outdated and counterproductive approach

There. I said it.

Claude Shannon’s model of information as that which is located among noise is a metaphor that appears to have been misleading a number of people in information science, particularly those involved with anything even remotely tangential to text mining (or, if you must, “knowledge discovery”). Information in an atomic form (e.g., bits) allows for the differentiation of signal and noise. A bit either is a signal or it isn’t. Attributes of real-life phenomena (e.g., average first down yardage in football for a team) are not like bits, at least not in the way we experience them and interpret those phenomena, whether in written explanations or in databases. “Real-life” phenomenae comprise different sorts of real-world features that can never be honestly reduced to their atomic constituents. And, pragmatically speaking, they won’t be reduced to quantum atomic states any time soon.

Given that every attribute of real-world phenomenae we identify partakes of both signal and noise, the removal of any attribute (save for the case of redundancy) always corresponds to the loss of information. Ultimately the statistical modeling of phenomena such as competitive sports and stock markets and clinical emergency room chief complaints is wholly unlike modeling communication channels. There’s something immediately discontinuous about binary electronic signals while other these other phenomena need dramatic interpretive steps before they can be represented with discontinuous electronic signals. Finally, signal and noise are terms that don’t apply very well because that which we are modeling can only be realistically described by features that are both informative and misleading at the same time.

There’s something rather continuous about language (something that latent semantic indexing attempts to capture) and that even the simplest of approaches, such as applying stop word lists to bag of word representations, lost critical information that dictate the semantics of the document. “Dog,” “a dog” and “the dog” quite clearly mean different things, as do “of the dog”, “out of a dog” and so forth. Representing all of those quotations as “dog” or going a step further and representing all of these quotes with the very same word-sense identifier, dumbs down human language beyond recognition. Garbage in, garbage out is a phrase I learned more than a quarter century ago when learning to program games for the Commodore Vic-20.

Reading a text book from 1993 on the C4.5 algorithm, I came across reflections that some crucial elements of C4.5 appeared to be motivated by economizing on computer resource issues. Not enough memory, too slow of processing, etc. In 2007 high performance computing is a commodity. The pressures for feature reduction in machine learning needed to be heeded 14 years ago, but they’re considerably less of an issue today.

Finally, at the very end of my stretch of graduate school studies I accidentally came across a new strategy for feature representation that is so painfully obvious in retrospect it leaves me wondering why no one else has been doing this. Fortunately for Hypothia it spells one very big competitive advantage. But I digress.

3. There’s always something missing from your set of attributes (cf. 1 & 2)

4. There’s no substitute for knowing your data set (cf. 1)I credit this oft-neglected, oft-devalued approach to my first and truly excellent data mining instructor, Miles Efron, who may be to blame for turning me on to text mining in the first place. What have you wrought? He made sure to repeat this lesson of knowing thy data a few times, and the lesson was surely not lost on me. In fact it seems as it it frames and justifies my confidence in my approach.

5. [DELETED] and let your algorithms optimize your attributes for maximal classification margin (cf. 2 & 3)

Can’t say the deleted part yet. But I will, eventually. It probably should be obvious by now. But still I’m not prepared to say.

6. SVM+SMO is very good for binary classification of highly dimensional data (cf. 5)

Improvements to SVM+SMO are always welcome of course, and it appears there are now numerous implementations of SVM that improve. I should note that, according to Eibe Frank, SMO in Weka (written in Java) is just as fast as Joachims’ SVM-light written in C. SMO’s pretty good.

SMO solves the QP problem created by SVM efficiently.

7. You always need more computing power (cf. 2, 5 & 6)

The curse is not dimensionality, the curse is not intellectual. The curse is economic, a problem of resources.
Likely it will be difficult to produce a dataset that is intractable for a good HPC setup running SVM+SMO but it doesn’t exactly hurt to try as long as you’re trying to harness more and more power.

8. You don’t know everything (cf. 3 & 4)

9. models only forecast well in forecast-influenced environments only when the model has an information advantage over other models (information assymetry, competitive advantage)

10. You’ll never get it quite right ( cf. 8 )

11. There always more left to do (cf. 5, 7 & 10)

12. Disambiguation can be better pursued not in any pure sense by machinic strategies but rather by messier approach of utilizing the greater context surrounding term, document, and corpus, which in turns permits some degree of ambiguity, which is necessary for understanding

13. Word sense disambiguation is quite possibly the wrong way to go to conjure semantics in one’s text representation (cf. 2 & 12)

As I’ve written before, there are other approaches available to leverage semantic information that are better than word-sense diambiguation (WSD) .

14. More formally, the incorporation of ambiguity into linguistic representations (i.e, representing all possible word senses/meanings and POSs for any given word) allows for better representations of intelligence than ones produced at least in part through WSD strategies

15. For artificial intelligence to become smarter than humans, it must at least be as smart as humans first.  A person’s ability to understand multiple senses of a given word at once (of which poetry is perhaps the most striking example) is strikingly intelligent and far more intelligent than most WSD approaches I’ve seen (cf. 14).  And when you consider that the basic unit of meaning is truly not the word but the sentence, WSD seems all the more foolish, and yet makes me feel there’s a huge opportunity to understand language from its wholes and holes.  Discourse analysis anyone?

16. Not knowing everything, not always getting it right, and always having more left to do makes the hard work a great deal of fun. Discoveries are everywhere waiting to be written into existence. (cf. 8, 10, 11)

17. Don’t panic, be good, and have fun. (cf. 16)

18. The essence of human language is nothing less than the totality of the human language in all of its past present and future configurations and possibilities.

1. Introduction
Pharmacogenomics experts have recognized that genomics-based approaches to drug discovery appear to suffer from some sort of information overload problem
(A. D. Roses, Burns, Chissoe, Middleton, & Jean, 2005, p. 179). More specifically, the explosion of human genomics information may have been outpaced by a concurrent explosion of noise within that data, leading to a significant attrition rate in the pharmaceutical pipeline (A. D. Roses et al., 2005, p. 179). However, it is not entirely clear how the concepts of information overload and signal-to-noise apply to information-based struggles in pharmacogenomics. In order to improve our understanding of the barriers to optimal use of pharmacogenomics information for drug discovery purposes we must first briefly unpack competing ideas about information overload and signal-to-noise and then contextualize the appropriate ideas within PGx-based drug discovery (henceforth PGx-DD).

2. Explaining Too Much Information in PGx-based Drug Discovery: Information Theory or Information Overload?

Genomics research pioneer and GSK Senior VP for Genomics Research Allen Roses has recently shed light on why pharmacogenomics-based approaches may not be optimal. According to Roses, who arguably is in a unique position to understand the problem, the central problem is one arising from information struggles. Roses writes,

What factors have limited target selection and drug discovery productivity? Although HTS technologies were successfully implemented and spectacular advances in mining chemical space have been made, the universe for selecting targets expanded, and in turn almost exploded with an inundation of information. Perhaps the best explanation for the initial modest success observed was the dramatic increase in the ‘noise-to-signal’ ratio, which led to a rise in the rate of attrition at considerable expense. The difficulty in making the translation from the identification of all genes to selecting specific disease-relevant targets for drug discovery was not realistically appreciated (A. D. Roses et al., 2005, p. 179).

What Roses calls the “noise-to-signal” ratio sounds like the problem of information overload, yet it also sounds as if it borrows from the language of Information Theory as put forth by Claude Shannon. Roses’ insight seems to corroborate Sean Ekins’ observation that already-extant data is not optimally utilized (2005). Pharmacogenomics is failing to deliver because PGx researchers and organizations utilizing PGx research have been unable to meet the information challenges concomitant with the explosion of data.

The language Allen Roses uses to describe struggles with information in the field of PGx-based drug discovery refers both to a signal-to-noise ratio and to information overload. The terminology appears, however, to be rather ambiguously utilized in the context of PGx-DD. “Noise-to-signal” seems to refer to Claude Shannon’s mathematical theory of communication (Shannon & Weaver, 1949) while the problems described by PGx professionals sound more like cognitive issues related to more formal notions of information overload.

2.1.Shannon’s Mathematical Theory of Communication
In 1948, Claude Shannon of Bell Labs completed work on his mathematical theory of communication. For so doing, Shannon is credited as fathering the field of Information Theory. It is from Shannon’s theory that the notion of signal-to-noise arises, among many other concepts crucial to any understanding of information. In his introduction to the ensuing book publication comprising Shannon’s work on the theory, Warren Weaver explains that the theory was supposed to deal with three distinct levels of communications problems, as follows:

Level A. How accurately can the symbols of communication be transmitted? (The technical problem.)

Level B. How precisely do the transmitted symbols convey the desired meaning? (The semantic problem.)

Level C. How effectively does the received meaning affect conduct in the desired way? (The effectiveness problem.) (Shannon & Weaver, 1949, p. 4)

Information in Shannon’s sense is not used in the ordinary sense of information. While by ‘information’ we ordinarily mean something akin to that which has already been said/written, Shannon means information in the sense of what may possibly be said (Shannon & Weaver, 1949, p. 8). For Shannon, information is a probable message sent over a channel (e.g., a telephone wire) and his concern is with describing general properties of the transmission and interpretation of such electronic signals.

Concerns about the ratio of signal-to-noise with respect to information transmission do originate from Shannon’s own communication theory work. The very ratio of signal-to-noise appears in Shannon’s theoretical examination of channel capacity with power limitation (Shannon & Weaver, 1949, p. 100). Shannon uses the ratio of the power source of the signal (denoted as P) to the power of the noise (denoted as N) in order to provide a general way of calculating how many bits per second any communication pathway can actually transmit. Shannon replaces P with S, the peak allowed transmitter power, in order to adjust channel capacity where peak power limits the rate of the channel to transmit bits. According to Shannon the upper bound rate of a channel is the channel band times the log of the ratio of signal plus noise to noise where the signal-to-noise ratio is low (Shannon & Weaver, 1949, p. 107). Loosely speaking, the rate at which telephone wires, coaxial cables, wireless networks, and the like can transmit messages varies logarithmically with the ratio of peak power (signal) to background noise on the channel (noise).

Shannon & Weaver’s specified problem set does not accurately match the sort of problem a drug discovery researcher is facing, not at least without a considerable stretch. Shannon’s sense of information in his definitive work on communication theory does not seem quite the same as the sort of information we are dealing with when we speak of genomics research data. Finally, Shannon’s notion of signal-to-noise can at best only loosely apply to notions of researchers struggling with too much information in their hands. Shannon is writing about communication channels, not people.

Efforts Shannon may have made to model specifically human communication in his theoretical work appears to be at best tertiary to the central thrust of his work, which was to generalize the properties of electronic communications systems. In short, Information Theory as proffered by Shannon does not appear to apply in any straightforward way to the sort of “noise-to-signal” problem Allen Roses describes or any other human communication problems that can occur independently of electronic signals. The signal-to-noise problem Roses reports is an information problem to be sure but it appears to be an information problem unlikely to be either explained or resolved through the lens of Shannon’s communication theory.

2.2.Information Overload
The concept of the possibility of too much information dates back to ancient times (Bawden, Holtham, & Courtney, 1999, p. 249). The recurring concern of information overload stems from the general notion that a person’s work becomes inefficient from increasing difficulty experienced in locating the best pieces of information. With the advent of computer-based information retrieval systems in the 1950s (Bawden et al., 1999, p. 249) as well as the beginnings of the mass proliferation of scientific research literature (Ziman, 1980), the concern became more frequently and more directly articulated and investigated. While any exact definition of information overload is elusive issues of relevance and efficiency are commonly notes as are issues of both data management and psychic strain (Bawden et al., 1999, p. 250). The constant problem however is that information overload stands for a struggle—a struggle that increases as a collection of information grows beyond human tractability. The recurring solution inevitably takes the form of methods or techniques that allow a person to locate some tractable set of pieces of information of sufficient quality in a reasonable amount of time in order to aid the person in completing the task.

3. Impact of information overload on PGx-based drug discovery
Information overload describes the general problem of “noise-to-signal” referred to by Allen Roses. Roses characterizes the information problem facing PGx-DD as having increased the rate of attrition of drug candidates in the pharmaceutical pipeline. Further, he states that the solution to the problem is an increase in “specific, disease-relevant targets” relative to all genomic data (A. D. Roses et al., 2005, p. 179). In other words, the proliferation of genomic data has drowned out this highly specific disease-relevant genomic information to the point that it increases drug discovery failure. The way to resolve the issue is to reduce information overload in PGx-DD by restricting the flow of information to PGx researchers to highly specific disease-relevant genomic information. As Roses says, providing researchers with validating evidence is crucial.

4. Validating evidence, novelty, and a PGx-info quality model
What, however, frames, delimits, or describes validating evidence for candidate targets? Roses states that disease-specific targets chosen based on well-trod beliefs “have a significant probability of being the totally wrong target” (A. D. Roses et al., 2005, p. 180). It is therefore not enough to identify highly specific disease relevant data efficiently; the data must support infrequent or entirely novel theories. The data must in essence have the characteristic of supporting novelty, of supporting ideas not commonly held, of bolstering theories that appear to be unreasonable.

The quality of PGx information should be evaluated using the following three criteria:

(a) the disease-relevance of the information,

(b) the specificity of the information, and

(c) the novelty of the information or the novelty of the theory supported by the information.

Sources

Bawden, D., Holtham, C., & Courtney, N. (1999). Perspectives on information overload. Aslib Proceedings, 51(8), 249-255.

Ekins, S., Bugrim, A., Nikolsky, Y., & Nikolskaya, T. (2005). Systems biology: Applications in drug discovery. In S. C. Gad (Ed.), Drug discovery handbook (pp. 123-183). Hoboken, New Jersey: Wiley Interscience.

Roses, A. D., Burns, D. K., Chissoe, S., Middleton, L., & Jean, P. S. (2005). Disease-specific target selection: A critical first step down the right road. Drug Discovery Today, 10(3), 177-189.

Shannon, C. E., & Weaver, W. (1949). The mathematical theory of communication. Urbana and Chicago: University of Illinois Press.

Ziman, J. M. (1980). The proliferation of scientific literature – a natural process. Science, 208(4442), 369-371.

(NOTE: the preceding document is a revised expert from my master’s thesis.)