![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F11902572%2F4029f1faa34bdfd642387696401dc2bd%2FUntitled%201..png?generation=1685474936472289&alt=media\")
The data section mentions that:
\n\n\nTraining Set
\n
\n For the training set, we include all proteins with annotated terms that have been validated by experimental or high-throughput evidence, traceable author statement (evidence code TAS), or inferred by curator (IC). More information about evidence codes can be found here. We use annotations from the UniProtKB release of 2022-11-17. The participants are not required to use these data and are also welcome to use any other data available to them.
I wanted to check and see how many annotations are there for the first protein in the train_terms.tsv file which is A0A009IHW8. This protein has:
It is unclear where these 49 annotations in the train_terms.tsv file originate from. It's worth noting that these annotations are considered high quality and are not electronically assigned. However, only 2 annotations are experimental on QuickGO, the source of the remaining 47 annotations remains unknown. Even 180GB filtered_goa_uniprot_all.gaf or 189GB goa_uniprot_all.gaf don't include these annotations. I would very much appreciate it if you point me in the right direction. Thanks!
", "messages": [ { "id": "2281181", "postDate": "05/30/2023 16:33:24", "content": "The data section mentions that:
\n\n\nTraining Set
\n
\n For the training set, we include all proteins with annotated terms that have been validated by experimental or high-throughput evidence, traceable author statement (evidence code TAS), or inferred by curator (IC). More information about evidence codes can be found here. We use annotations from the UniProtKB release of 2022-11-17. The participants are not required to use these data and are also welcome to use any other data available to them.
I wanted to check and see how many annotations are there for the first protein in the train_terms.tsv file which is A0A009IHW8. This protein has:
It is unclear where these 49 annotations in the train_terms.tsv file originate from. It's worth noting that these annotations are considered high quality and are not electronically assigned. However, only 2 annotations are experimental on QuickGO, the source of the remaining 47 annotations remains unknown. Even 180GB filtered_goa_uniprot_all.gaf or 189GB goa_uniprot_all.gaf don't include these annotations. I would very much appreciate it if you point me in the right direction. Thanks!
", "rawMarkdown": "The data section mentions that: \n> Training Set\nFor the training set, we include all proteins with annotated terms that have been validated by experimental or high-throughput evidence, traceable author statement (evidence code TAS), or inferred by curator (IC). More information about evidence codes can be found here. We use annotations from the UniProtKB release of 2022-11-17. The participants are not required to use these data and are also welcome to use any other data available to them.\n\nI wanted to check and see how many annotations are there for the first protein in the `train_terms.tsv` file which is A0A009IHW8. This protein has:\n* 5 GO annotations in Uniprot website: https://www.uniprot.org/uniprotkb/A0A009IHW8/\n* 2 amigo annotations: http://amigo.geneontology.org/amigo/gene_product/UniProtKB:A0A009IHW8\n* 7 quickgo annotations: https://www.ebi.ac.uk/QuickGO/annotations?geneProductId=A0A009IHW8\n* 9 annotations on http://current.geneontology.org/annotations/filtered_goa_uniprot_all.gaf.gz\n* 7 annotations on ftp://ftp.ebi.ac.uk/pub/databases/GO/goa/UNIPROT/goa_uniprot_all.gaf.gz\n* 49 annotations on train_terms.tsv\n\nIt is unclear where these 49 annotations in the train_terms.tsv file originate from. It's worth noting that these annotations are considered high quality and are not electronically assigned. However, only 2 annotations are experimental on QuickGO, the source of the remaining 47 annotations remains unknown. Even 180GB filtered_goa_uniprot_all.gaf or 189GB goa_uniprot_all.gaf don't include these annotations. I would very much appreciate it if you point me in the right direction. Thanks!", "votes": null }, { "id": "2281269", "postDate": "05/30/2023 18:17:49", "content": "Annotated terms are propagated to ontology roots through \"is a\" and \"part of\" edges. This is because term \"A\" being annotated necessarily implies the protein also has all ancestor terms of term A as functions.
", "rawMarkdown": "Annotated terms are propagated to ontology roots through \"is a\" and \"part of\" edges. This is because term \"A\" being annotated necessarily implies the protein also has all ancestor terms of term A as functions.", "votes": null }, { "id": "2281318", "postDate": "05/30/2023 19:01:22", "content": "Does it mean that term \"propagates\" to ALL (and all levels) of ancestors (which are \"is_a\" and \"part_of\") ?
\nOr there is some selected path for the \"propagation\" ?
See illustration. If a protein is annotated in the GOA file (for example) with terms 1 and 2, those are propagated so that it is also annotated with terms 3,4,5, but not 6.
\n
Great.
\ncan we also convert sequence data as a graph instead using tokenizer?
Annotated terms are propagated to ontology roots through \"is a\" and \"part of\" edges. This is because term \"A\" being annotated necessarily implies the protein also has all ancestor terms of term A as functions.
", "votes": null, "replies": [ { "id": 2281318, "author_name": "alexandervc", "author_url": "", "post_date": "05/30/2023 19:01:22", "content": "Does it mean that term \"propagates\" to ALL (and all levels) of ancestors (which are \"is_a\" and \"part_of\") ?
\nOr there is some selected path for the \"propagation\" ?
See illustration. If a protein is annotated in the GOA file (for example) with terms 1 and 2, those are propagated so that it is also annotated with terms 3,4,5, but not 6.
\n
Great.
\ncan we also convert sequence data as a graph instead using tokenizer?