Query Results

Number of results 1000
Lowest scoring result 67.37486
Abstracts of results results.html
Complete abstracts of the articles in Medline predicted to be relevant (limited number per page).
Abstracts of all results ZIP file or all_results.html
All result abstracts on a single page. (can take a long time to load - downloading the zip file is recommended)
Abstracts of input examples inputs.html
Complete abstracts of the Medline records given as relevant training examples. They have been ranked by classifier scores.
PubMed IDs of results results.txt
PubMed IDs and scores of classifier predictions, ranked by decreasing score.
PubMed IDs of inputs inputs.txt
PubMed IDs and scores of the relevant training examples.
Started at 2009/05/14 11:50:01 GMT
Time at which query was started
Finished at 2009/05/14 11:55:12 GMT
Time at which this file was written.
Feature score method scores_laplace_split
Name of the method used to calculate feature scores. Docstring for the method: For feature probabilities we use a Laplace prior, of 1 success and 1 failure in total, split between the classes according to size. This avoids problems with class skew.
Min Information Gain 2e-05
We exclude features with less than this value of Information Gain.
Base score -33.8239258708
The log likelihood ratio of an empty article (one in which every feature failed to occur).
Prior score -9.37324624933
The log of the prior probability ratio for an article being relevant versus irrelevant (added to log likelihood ratio to obtain the final score). Equals the logit of the estimated prevalence of relevant articles in Medline (which may be estimated from the input size or specified separately).
Limit 1000
The maximum number of results to include.
Threshold -30.0
Default Naive Bayes classification threshold is zero. This threshold is the minimum log probability ratio for predicting an article to be relevant.
Minimum date 20050101
The minimum date considered when parsing Medline (both when making feature counts, and when querying)

Feature Statistics

Quantity Relevant Docs Irrelevant Docs
Number of documents 219 2589236
Number of selected, occurring features 4700 38531
Total occurrences of selected features 21477 183037187
Selected features per Medline record 98.068 70.692
Of the considered feature types, 38587 features are selected out of 2289534 occurring at least once in training data. The aggressivity of selection is 59.334. The complete database lists 3703762 potential features.

Features with high TF.IDF

Features with TF.IDF above 0.2 or 0.3 could make good keywords. TF.IDF is term frequency times inverse document frequency, where we treat the set of input citations as a single document

TF-IDF Type Term Term ID Score Pos Neg
0.03 mesh Proteins 1782 5.49 147 21740
0.03 mesh Databases, Protein 12064 6.37 100 3722
0.03 w Http 42206 5.92 107 6612
0.03 mesh Sequence Analysis, Protein 51007 6.13 91 3997
0.02 w Database 10704 4.32 99 28080
0.02 issn 1362-4962 51097 5.64 70 4303
0.02 w Annotation 28383 5.95 62 2673
0.02 w Sequence 1953 3.65 119 77437
0.02 mesh Internet 16958 4.74 77 12151
0.02 mesh Sequence Alignment 5975 4.46 82 17792
0.02 w Protein 648 3.48 174 274803
0.02 w Proteins 1723 3.22 128 137524
0.02 mesh Software 23437 4.35 71 15947
0.02 w Sequences 1767 3.61 88 46106
0.02 w Web 29283 4.93 57 6566
0.01 w Structural 1762 3.24 85 62872
0.01 w Alignments 53861 5.81 44 1954
0.01 w Prediction 10084 3.86 66 23340
0.01 w Domains 1764 3.64 69 31028
0.01 mesh Protein Structure, Tertiary 1781 3.67 66 28246