Sign in or Join FriendFeed
FriendFeed is the easiest way to share online. Learn more »
RT @yokofakun: don't say it's a "web service" http://www.rostlab.org/service... , clicking on the buttons, using the POST method, html: this is *not* a web service!
can anybody provide a pointer to ngram tokenization using the tm package? #rstats #textmining
looks like i'm going to have to hunker down and get up to speed with ggplot. To beautiful to pass up #rstats
Pairwise agonist scanning predicts cellular signaling responses to combinatorial stimuli
Nat Biotech, Vol. 28, No. 7. (20 July 2010), pp. 727-732., doi:10.1038/nbt.1642 Prediction of cellular response to multiple stimuli is central to evaluating patient-specific clinical status and to basic understanding of cell biology. Cross-talk between signaling pathways cannot be predicted by studying them in isolation and the combinatorial complexity of multiple agonists acting together prohibits an exhaustive exploration of the complete experimental space. Here we describe pairwise agonist scanning (PAS), a strategy that trains a neural network model based on measurements of cellular responses to individual and all pairwise combinations of input signals. We apply PAS to predict calcium signaling responses of human platelets in EDTA-treated plasma to six different agonists (ADP, convulxin, U46619, SFLLRN, AYPGKF and PGE2) at three concentrations (0.1, 1 and 10 × EC50). The model predicted responses to sequentially added agonists, to ternary combinations of agonists and to 45... - Rajarshi Guha
RT @StatFact: If your research isn't reproducible, you could end up on 60 Minutes. http://simplystatistics.tumblr.com/post...
Depictions from the 70's? http://pubs.acs.org/doi...
Ugh! More like MS-Paint D: (although the paper looks interesting...) - gilleain
A delicious buzz from a pack of Petes Expresso chocolate beans. Yummy!
@NPHard where will the CT R meeting be held?
correlation, causation and all that - random gene sets more predictive of breast cancer than cancer-related gene sets http://blog.f1000.com/2012...
RT @KatieElinSalt: Enjoy this with a bitter bitter laugh. http://twitter.com/KatieEl...
@10705013 thnaks a lot. But looks like SelectAtomGenerator doesn't exist anymore?
@10705013 can you point me to a code example where you're using the cdk 1.4 branch to highlight substructure in depictions? #cdk
@egonwillighgen do you have to code render structure with a substructure highlighted? #cdk
A novel signal detection algorithm for identifying hidden drug-drug interactions in adverse event reports
Journal of the American Medical Informatics Association, Vol. 19, No. 1. (01 January 2012), pp. 79-85. Objective Adverse drug events (ADEs) are common and account for 770 000 injuries and deaths each year and drug interactions account for as much as 30% of these ADEs. Spontaneous reporting systems routinely collect ADEs from patients on complex combinations of medications and provide an opportunity to discover unexpected drug interactions. Unfortunately, current algorithms for such “signal detection” are limited by underreporting of interactions that are not expected. We present a novel method to identify latent drug interaction signals in the case of underreporting.Materials and Methods We identified eight clinically significant adverse events. We used the FDA's Adverse Event Reporting System to build profiles for these adverse events based on the side effects of drugs known to produce them. We then looked for pairs of drugs that match these single-drug profiles in order to predict... - Rajarshi Guha
either publishing is just too slow or else I'm writing too much. I can't remember who/which journal I wrote these proofs for
https://github.com/ down for anybody else?
@Open_PHACTS are tweets going to be available for this meeting? or is it private?
Mammary carcinogen-protein binding potentials: novel and biologically relevant structure-activity relationship model descriptors.
SAR and QSAR in environmental research, Vol. 21, No. 5-6. (July 2010), pp. 463-479. Previously, SAR models for carcinogenesis used descriptors that are essentially chemical descriptors. Herein we report the development of models with the cat-SAR expert system using biological descriptors (i.e., ligand-receptor interactions) rat mammary carcinogens. These new descriptors are derived from the virtual screening for ligand-receptor interactions of carcinogens, non-carcinogens, and mammary carcinogens to a set of 5494 target proteins. Leave-one-out validations of the ligand mammary carcinogen-non-carcinogen model had a concordance between experimental and predicted results of 71%, and the mammary carcinogen-non-mammary carcinogen model was 72% concordant. The development of a hybrid fragment-ligand model improved the concordances to 85 and 83%, respectively. In a separate external validation exercise, hybrid fragment-ligand models had concordances of 81 and 76%. Analyses of example rat... - Rajarshi Guha
RT @CompSciFact: We have an embarrassment of computational riches when we can solve traveling salesmen problems on a phone. http://itunes.apple.com/us... via @informs
swarm behavior with flying robots. Amazingly cool. http://www.gizmag.com/grasp-n...
@GnarusSystems thanks. What classification method are you using? don't have subscription to journal. can you send pdf to guhar@mail.nih.gov?
@neilfws hah. it's horrificly painful I can't believe that #pubchem lasted for so long with this frankenstein'ian concoction of nested tags
What type of QSAR with what descriptors is this? via @GnarusSystems "An in silico toxicity prediction expert system."
@erikacule don't include it in the namespace file #rstats
RT @BicyclingMag: Act Now: Bicycling Under Attack in Congress - A new transportation bill could cut 20 years of progress for bike funding http://bicycling.com/blogs...
RT @WhatTheFFacts: Yo Mama jokes/insults were invented by Shakespeare.
woo hoo. Our book, "Computational Approaches in Cheminformatics & Bioinformatics" is out! http://www.amazon.com/Computa...
@egonwillighagen ha ha. the positive aspect is that 8 books were bought :)
think I'm getting the hang of Java concurrency
Other ways to read this feed:Feed readerFacebook