Tag Results

Creator:

Marco Roos

AIDA toolbox

Created: 01/08/08 @ 11:33:03 | Updated: 01/08/08 @ 11:54:45

8 items in this pack

Comments: 0 | Viewed: 92 times |

Uploader:

Marco Roos

Discover_proteins_from_text (v2)

Created: 15/11/07 @ 08:58:00 | Updated: 15/11/07 @ 09:12:34

Credits: Marco Roos AID

License: Creative Commons Attribution-Share Alike 3.0 License

This workflow discovers proteins from plain text. It is built around the AIDA 'Named Entity Recognize' web service by Sophia Katrenko (service based on LingPipe), from which output it filters out proteins. The Named Recognizer services uses the pre-learned genomics model, named 'MedLine', to find genomics concepts in plain text.

Rating: 0.0 / 5 (0 ratings) | Versions: 2 | Reviews: 0 | Comments: 0 | Citations: 0

Viewed: 693 times | Downloaded: 608 times

Uploader:

Marco Roos

BioAID_protein_discovery (v1)

Created: 14/11/07 @ 12:46:33 | Updated: 15/11/07 @ 09:01:12

Credits: Marco Roos AID

License: Creative Commons Attribution-Share Alike 3.0 License

This workflow finds proteins relevant to the query string via the following steps: 1. A user query: a list of terms or boolean query - look at the Apache Lucene project for all details. E.g.: EZH2 OR "Enhancer of Zeste" +(mutation chromatin) -clinical 2. Retrieve documents: finds relevant documents (abstract+title) based on query (edit maxHits to change the default maximum number of documents returned) 3. Discover proteins: extract proteins discovered in the set of relevant abstracts. Servic...

Rating: 0.0 / 5 (0 ratings) | Versions: 1 | Reviews: 0 | Comments: 0 | Citations: 0

Viewed: 480 times | Downloaded: 540 times

Uploader:

Marco Roos

DiscoverProteinLink (v2)

Created: 03/10/07 @ 18:36:12 | Updated: 15/11/07 @ 09:02:44

Credits: Marco Roos AID

License: Creative Commons Attribution-Share Alike 3.0 License

COMPETITION: For friends only: If you find any two topics that return true positives with this workflow I will buy you a bottle of wine (or equivalent). Terms: if we confirm that the protein was indeed never mentioned together with both input topics in one article, we will publish this together. ---- This workflow implements Swanson's prinicple with services from the AIDA toolbox. It tries to find proteins that link two topics, while they never mentioned together with both topics in ...

Rating: 0.0 / 5 (0 ratings) | Versions: 2 | Reviews: 0 | Comments: 0 | Citations: 0

Viewed: 746 times | Downloaded: 624 times

Uploader:

Marco Roos

BioAID_DiseaseDiscovery_count (v3)

Created: 22/11/07 @ 12:09:20 | Updated: 05/12/07 @ 23:09:13

Credits: Marco Roos AID

Attributions: BioAID_DiseaseDiscovery

License: Creative Commons Attribution-Share Alike 3.0 License

This adds counting to BioAID_DiseaseDiscovery, which allows you to check the results more properly. A major issue is that some false positives among the discovered proteins may have a disproportionate effect on the number of diseases found. We therefore advice to use 'BioAID_DiseaseDiscovery_byHumanUniprot' if you main interest is human proteins and diseases. This workflow finds disease relevant to the query string via the following steps: 1. A user query: a list of terms or boolean query - ...

Rating: 5.0 / 5 (1 rating) | Versions: 3 | Reviews: 0 | Comments: 0 | Citations: 0

Viewed: 906 times | Downloaded: 725 times

Uploader:

Marco Roos

BioAID_ProteinDiscovery_filterOnHumanUniprot_perDoc_html (v8)

Created: 29/02/08 @ 01:34:46 | Updated: 28/07/08 @ 21:43:42

Credits: Marco Roos Martijn Schuemie AID AID_myGrid_collaboration

Attributions: BioAID_DiseaseDiscovery

License: Creative Commons Attribution-Share Alike 3.0 License

This workflow finds proteins relevant to the query string via the following steps: 1. A user query: a single gene/protein name. E.g.: (EZH2 OR "Enhancer of Zeste"). 2. Retrieve documents: finds 'maximumNumberOfHits' relevant documents (abstract+title) based on query (the AIDA service inside is based on Apache's Lucene) 3. Discover proteins: extract proteins discovered in the set of relevant abstracts with a 'named entity recognizer' trained on genomic terms using a Bayesian approach; the AIDA...

Rating: 0.0 / 5 (0 ratings) | Versions: 8 | Reviews: 0 | Comments: 0 | Citations: 0

Viewed: 728 times | Downloaded: 580 times