Chunyu Ma

A bug from "infores:ncbi-taxonomy" data source in KG2?

1

Hi @saramsey and @acevedol, I might find a bug for the edge from "infores:ncbi-taxonomy" data source in KG2. I'm wondering whether it is due to the version problem. If so,...

Get action "chemical_gene_regulation_graph_expansion" into ARAX_infer (MVP question #2)

6

This issue summarizes the steps to integrate action `chemical_gene_regulation_graph_expansion` into ARAX_infer: - [x] Train two models (one for predicting `increase gene activity while the other for `decrease ...`) - [x]...

Some issues found that might be associated with Nodesynonymizer from KG2.6.1

4

Also based on the KG2.6.1c (http://kg2canonicalized.rtx.ai:7474/browser/) that @amykglen just built, I found two problems that might be associated with Nodesynonymizer: 1) There are 35 duplicated preferred curies that have same...

Should KEGG:C00161 be treated as a synonym of CHEBI:35910?

10

Hi @edeutsch, Perhaps this might be another issue for NodeSynonymizer. So I tried to check the node source distribution of `biolink:Metabolite` in today's kg2.5.2c. As you can see below, most...

It seems like the `ARAX_expander` module automatically does the subclass reasoning for a query. Example: ``` add_qnode(ids=DRUGBANK:DB01050, key=n00) add_qnode(key=n01) add_qnode(ids=MONDO:0008383, key=n02) add_qedge(subject=n00, object=n01, key=e00) add_qedge(subject=n01, object=n02, key=e01) expand(kp=infores:rtx-kg2) resultify() filter_results(action=limit_number_of_results,...

Should we completely trust `infores:drugcentral`?

22

@dkoslicki @edeutsch, I found the `infores:drugcentral` edge also contains the publication information (see the `infores:drugcentral` edge in [result 69](https://arax.ncats.io/?r=33bda8fc-6a38-4bdf-aef4-0df85ed26dac)). It seems like not all `infores:drugcentral` edges have the publication information....

This issue is created for tracking the progress of retraining xCRG model for KG2.10.0c.

Derived from issue #2334, in the recent AHM meeting, we plan to generate a weight table for different KPs used in ARAX, which will be finally included in the ranking...

Improve ARAX's ranking algorithm

2

This is a super issue for "Better Ranking". I split it into the following few sub-tasks: - [x] Adjust weights in the [ranker](https://github.com/RTXteam/RTX/blob/master/code/ARAX/ARAXQuery/ARAX_ranker.py#L205-L225). See the sub-task in #2300. - [x]...

Currently, the RTX `requirements.txt` uses [scikit-learn==1.5.0](https://github.com/RTXteam/RTX/blob/6478e1042bb7d2b35c58f2512527d555f5f5aab2/requirements.txt#L13) but the xDTD and xCRG build pipeline still uses [the older version](https://github.com/RTXteam/xDTD_training_pipeline/blob/ed50338b0b709c9e111f897d47f0d8d492b621d5/envs/xDTD_training_pipeline_env.yml#L36). I plan to upgrade xDTD and xCRG to match the version used...