MOTIVATION: Longitudinal microbiome studies (LMS) are increasingly common but have analytic challenges including nonindependent data requiring mixed-effects models. Furthermore, large amounts of data motivate exploratory analysis to identify factors related to outcome variables. Although change analysis (i.e. calculating feature changes between timepoints) can be powerful, how to best conduct these analyses is often unclear. For example, observational LMS measurements show natural fluctuations, so baseline might not be a reference of primary interest, whereas for interventional LMS, baseline is typically a key reference point, often indicating the start of treatment. RESULTS: To address these challenges, a feature selection workflow, called EXPLANA (EXPLoratory ANAlysis), was developed for LMS that supports numerical and categorical data, and also accommodates cross-sectional studies. Machine learning methods were combined with different types of change calculations and downstream interpretation methods to identify statistically meaningful variables and explain their relationship to outcomes. EXPLANA generates an interactive report that textually and graphically summarizes methods and results. EXPLANA had good performance on simulated longitudinal data, with a balanced accuracy score of 0.91 (range: 0.79-1.00, SD = 0.05), outperformed an existing tool, QIIME 2 feature-volatility (balanced accuracy: 0.95 versus 0.56) and identified novel order-dependent categorical feature changes (e.g. different effect for A_B versus B_A). EXPLANA is broadly applicable and simplifies analytics for identifying features related to outcomes of interest. AVAILABILITY AND IMPLEMENTATION: Software is available at https://github.com/JTFouquier/explana and https://zenodo.org/records/17478745 (10.5281/zenodo.17478744). Documentation and demos are available at www.explana.io.

Passage retrieval (already operational for lawyers) has advantages in output form over reference retrieval and is economically feasible. Previous experiments in passage retrieval for scientists have demonstrated recall and false retrieval rates as good or better than those of present reference retrieval services. The present experiment involved a greater variety of forms of retrieval question. In addition, search words were selected independently by two different people for each retrieval question. The search words selected, in combination with the computer procedures used for passage retrieval, produced average recall ratios of 72 and 67%, respectively, for the two selectors. The false retrieval rates were (except for one predictably difficult question) respectively 13 and 10 falsely retrieved sentences per answer-paper retrieved.

Abstract Some new text searching retrieval techniques are described which retrieve not documents but sentences from documents and sometimes (on occasions determined by the computer) multi‐sentence sequences. Since the goal of the techniques is retrieval of answer‐providing documents, “answer‐passages” are retrieved. An “answer‐passage” is a passage which is either answer‐providing or “answer‐indicative,” i.e., it permits inferring that the document containing it is answer‐provding. In most cases answer‐sentences, i.e., single‐sentence answer‐passages, are retrieved. This has great advantages for screening retrieval output. Two new automatic procedures for measuring closeness of relation between clue words in a sentence are described. One approximates syntactic closeness by counting the number of intervening “syntactic joints” (roughly speaking, prepositions, conjunctions and punctuation marks) between successive clue words. The other measure uses word proximity in a new way. The two measures perform about equally well. The computer uses “enclosure” and “connector words” for determining when a multi‐sentence passage should be retrieved. However, no procedure was found in this study for retrieving multi‐paragraph answer‐passages, which were the only answer‐passages occurring in 6% of the papers. In a test of the techniques they failed to retrieve two answer‐providing documents (7% of those to be retrieved) because of one multi‐paragraph answer‐passage and one complete failure of clue word selection. For the other answer‐providing documents they retrieved at all recall levels with greater precision than SMART, which has produced the best previously reported recall‐precision results. The retrieval questions (mostly from real users) and documents used in this study were from the field of information science. The results of the study are surprisingly good for retrieval in such a “soft science,” and it is reasonable to hope that in less “soft” sciences and technologies the techniques described will work even better. On this basis a dissemination and retrieval system of the near future is predicted.

Two subject index terms (toxicity and penicillin) from an operating retrieval system were studied intensively to determine how well a computer could assign them.The humanly produced indexing for the system was used as a standard, with some checking for indexer errors.Thesaurus rules failed to identify one fourth of the toxicity papers.A new rule, using "connection forms", worked for almost all of the nonthesaurus papers.The combined rules identified toxicity papers as well as or better than the human indexers.However, these rules falsely selected as many papers as they correctly identified.False selection was reduced to this level by the use of two new indexing rules, relative frequency, and two methods previously proposed but not tested.The latter are emphasis measures by syntactic centrality and by first sentencefirst paragraph position.The rules for reducing false selection did not work as well for penicillin as for toxicity.Comparisons are made with previous empirical studies.Some possible limitations of thesaurus methods, statistical association, etc. are indicated.Some affirmative suggestions are also made.

Methods of mechanized indexing (subject indexing by computer) which have been proposed are systematically summarized.Every suggested method consists of some document preparation process (mostly or wholly mechanical) followed by the application of indexing rules to the prepared document.A comprehensive document preparation is described from which proposed methods can be derived by selection.It includes full text input, document place (title, abstract, etc.) marking, sentence and paragraph marking, pronoun replacement, and other syntactic marking.It also includes addition of thesaurus headings, position numbers, weighted frequencies, closely associated expressions, importance measures, and reference information.Three kinds of indexing rules are then distinguished and illustrated.Several general comments on mechanized indexing include remarks on the argument that good mechanized indexing is not feasible, and the argument that mechanized indexing has the advantage, compared to human indexing, of consistency.Some problems of testing mechanized (or any other) indexing quality by the quality of the retrieval it permits are described.Index duplication studies are suggested as an alternative kind of empirical investigation of mechanized indexing methods. HUMANS, TUBERCULOSIS, BACTERIA, WOUNDS AND INJURIES~ INFECTION, TOX~ICITY~ CHILDREN.In many, or most such systems the indexing is done by subject specialists.Such people are in short supply and are relatively expensive.One estimate is that subject indexing accounts for about three quarters of the cost of operating a retrieval system.Accordingly, in recent years a number of methods have been proposed for subject indexing by computer (mechanized indexing).Most of these techniques require that the full texts of documents be in machine-readable form.At present This research was sponsored by the Information Systems Branch, Office of Naval Research (Contract Nonr 4183(00)) and by the Information Research Division, Air Force Office of Scientific Research under Contr.No. AF 49((638)-1300).Reproduction in whole or in part is permitted for any purpose of the United States Government.