Accenture / Accenture/AmpliGraph

Can we pass custom trained embedding as entity and then train the model?

Open
#270 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.2k
Forks
257
PR merge metrics
No merged PRs in 30d

Description

Hi, we are working on a link prediction task using ampligraph, the triple basically looks like,

protein_sequence, i.e KFLEACD (subject) ---> positive(predicate) ---> assay_1(object)

we already have a better representation of the protein sequence stored as embedding, is it possible to pass those embedding directly as an entity like,

protein_embedding(subject) ---> positive(predicate) ---> assay_1(object)

Please clarify, thanks in advance.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are named. Start by locating AmpliGraph’s entity-representation and model-training APIs, then determine how externally supplied protein embeddings would participate in link-prediction training and what validation would confirm support.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.