Frequently asked questions:

If you cannot find an answer to your question, please contact us.

SMAFIRA Tool

General issues:

Does the tool collect any information from the user?
Does the tool use cookies or similar technical elements?

Search and processing:

Which types of search are possible?
Which PMIDs are allowed in the search?
Which articles are considered by SMAFIRA (coverage)?
May I enter more than one PMID in a query?
Which processing is performed on the articles?
Can I start my search from a project summary in other languages than English?

List of results:

What information is shown for each citation in the list?
SMAFIRA presents the following information:
- Rank (number) of the citation in the list, according to the chosen method.
- PMID, with a link to the side-by-side visualization of the reference and similar abstract (user opinion page).
- External link to the article in PubMed®. ()
- SMAFIRA Rank (default ranking): rank of the citation according to the SMAFIRA re-ranking.
- PubMed® Rank: rank of the citation according to PubMed®.
- My Rank: an icon that indicates the similarity between the reference abstract and the current abstract as judged by the user. This icon is only available after a user has activated the respective checkbox on the side-by-side comparison of a single article with the abstract.
- Title of the cited article.
- Labels: one or more icons that indicate the assigned classes of experimental models that were automatically predicted (indicated by ) or specified by the user (no cogwheel icon).
- If available, icons that indicate whether the article is a review (, as specified in PubMed®) or that no abstract is available ().
Why are some filters disabled (icon ) sometimes?
How are the citations ranked?
Why are similar articles without abstracts included in the list of results?
What exactly does each label mean?
We give a short definition below, please refer to our publication for details.
- in vivo: living vertebrates (including cephalopodes)
- tissue/biopsy: isolated vertebrate organs and tissues
- primary cell: freshly isolated vertebrate primary or stem cells
- immortal cell: established vertebrate cancer or immortal cell lines
- invertebrate: invertebrates or invertebrate material (excluding cephalopods)
- human: human/patients and or any kind of human material (including organs/tissues, primary cells and immortal cells)
- virtual model: computer simulations
- others: any other kind of experiments
How were the filters (labels) decided?
May I come back to my results later? Or share it with someone else?
Can I download or export the list of results?

Visualization of a citation in the list:

Which information is shown in the visualization?
We show a side-by-side visualization with the reference abstract (on the left) and the abstract from the currently chosen citation (on the right). On the top left is a link to go back to the list of citations, while on the top right are navigational links to the previous (if available) and the next (if available) citation. The page includes the possibility to give feedback on the similarity between the two abstracts (see details below). For each abstract, we present the following information:
- Information about the automatically predicted classes of experimental models (indicated with the icon ).
- PMID of the citation and link to it in PubMed®.
- Title of the corresponding article, as available in PubMed®.
Can I change the automatically predicted class(es) of experimental model(s)?
When are two articles similar?
How to give a feedback about the similarity?
How can the user feedback be used?

Methods and data

Prediction of the methods:

How does the prediction of the class of experimental model (label) work?
What data was used for training the models?
How good are the predictions? Should I trust them?
The performance of our current model, in terms of the F-score metric is the following:
- in vivo: 0.88
- invertebrate: 0.95
- immortal cell line: 0.83
- primary cell line: 0.75
- tissue/biopsy: 0.82
- virtual model: 0.75
- human: 0.86
- others: 0.76
The F-score is the harmonic mean of the precision (specificity) and recall (sensitivity). Considering that there is no huge difference between the precision and recall for our labels, for instance, for a F-Score of 0.80:
- specificity: 1 in every 5 predictions might be wrong, i.e., a wrong label was predicted for the article
- sensitivity: 1 in every 5 articles has been missed, i.e., a particular label has not been predicted for it
Please refer to our publication for details.
What if the prediction is wrong?
May I get an explanation why a particular label was (or not) assigned to an article?

Re-ranking:

The icons in this application were made by Freepik, Good Ware, juicy_fish, Roundicons from www.flaticon.com.