Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

TaxVAMB #204

Merged
merged 25 commits into from
Nov 6, 2023
Merged

TaxVAMB #204

merged 25 commits into from
Nov 6, 2023

Conversation

sgalkina
Copy link
Member

Implementation of the predictor, VAEVAE and hierarchical loss, all in one commit

The squashed version of PR#184. Keeping the old PR to not lose the comments.

@sgalkina sgalkina marked this pull request as ready for review October 26, 2023 14:23
@jakobnissen jakobnissen merged commit 9a8a66d into RasmussenLab:master Nov 6, 2023
5 checks passed
.github/workflows/snakemake_taxvamb.yml Show resolved Hide resolved
vamb/__init__.py Show resolved Hide resolved
vamb/__main__.py Show resolved Hide resolved
vamb/__main__.py Show resolved Hide resolved
vamb/__main__.py Show resolved Hide resolved
Comment on lines +1 to +18
"""
The following code is a modification of a k-means based reclustering algorithm first published at https://github.com/BigDataBiology/SemiBin
The original code is distributed under MIT License.
"""

import os
import subprocess
import tempfile
import sys
import contextlib
from typing import IO
from sklearn.cluster import KMeans
import numpy as np
from collections import defaultdict
import pandas as pd
from sklearn.cluster import DBSCAN
from sklearn.metrics import pairwise_distances
import gzip
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Re this file: Let's discuss the plan for removing it when I'm back in the office. I.e. if we manage to implement SCG in the latent space, how can we excise this module, and all the related functionality in a clean way?

workflow_taxVamb/envs/taxVamb.yaml Show resolved Hide resolved
Comment on lines +1 to +11
#!/usr/bin/bash
module load tools computerome_utils/2.0
module load anaconda3/2023.03
module unload gcc
module load gcc/11.1.0
module load minimap2/2.17r941 samtools/1.10

source ~/.bashrc
conda init bash
conda activate /home/projects/cpr_10006/people/svekut/.conda/vamb

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should all these Computerome scripts be part of the repo? They're very dev-specific for our group. Perhaps have them in their own folder?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nah, they will be deleted

workflow_vaevae/envs/vaevae.yaml Show resolved Hide resolved
workflow_vaevae/src/eval.jl Show resolved Hide resolved
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants