hiraksarkar

Nov-17 09:39:19.048 [main] DEBUG nextflow.cli.Launcher - $> nextflow run maximilian-heeg/xenium-segmentation -r v0.3 --xenium_path /n/fs/ragr-data/users/hirak/10x_colorectal/xenium
Nov-17 09:39:19.289 [main] DEBUG nextflow.cli.CmdRun - N E X T F L O W  ~  version 24.10.0
Nov-17 09:39:19.473 [main] DEBUG nextflow.plugin.PluginsFacade - Setting up plugin manager > mode=prod; embedded=false; plugins-dir=/n/fs/ragr-data/users/hirak/.nextflow/plugins; core-plugins: [email protected],[email protected],[email protected],[email protected],[email protected],[email protected],[email protected],[email protected]
Nov-17 09:39:19.493 [main] INFO  o.pf4j.DefaultPluginStatusProvider - Enabled plugins: []
Nov-17 09:39:19.494 [main] INFO  o.pf4j.DefaultPluginStatusProvider - Disabled plugins: []
Nov-17 09:39:19.497 [main] INFO  org.pf4j.DefaultPluginManager - PF4J version 3.12.0 in 'deployment' mode
Nov-17 09:39:19.521 [main] INFO  org.pf4j.AbstractPluginManager - No plugins
Nov-17 09:39:19.720 [main] DEBUG nextflow.scm.ProviderConfig

hiraksarkar

library(ggplot2)
library(dplyr)
library(ggbump)

tmp.subset = lr_df_merged %>% filter(ligand %in% c('WNT9A','ARTN', 'ANGPTL2') )
tmp.subset = tmp.subset |> arrange(ligand,desc(copula_coeff))

to_nodes = distinct(tmp.subset, receptor) |> mutate(to_y = row_number())
num_senders = (distinct(tmp.subset, ligand) %>% dim)[[1]]
from_nodes = distinct(tmp.subset, ligand) |> mutate(from_y = round(dim(to_nodes)[[1]])/(num_senders+1) + row_number()-1+0.5)

hiraksarkar

Step 0

• MV Gaussian link
• Math4ML video playlist
• Deep Learning foundation and concept book Chapter 1-3
• GLM theory link

Regression and Statistics

The main proofs are to be read from the following order

hiraksarkar

Given the two recent books are out the best is to use them iteratively. I am not gonna add the book by Murphy as I find it not to be self sufficient but rather regard it as a dictionary. Main books

• Understanding deep learning by Prince book and notebook
• Deep Learning foundation and concept book

Murphy's book for reference

• Probabilistic Machine Learning: Advanced Topics book

hiraksarkar

The main proofs are to be read from the following order -- Proofs are given here https://www.statlect.com/fundamentals-of-statistics/ It should be accompanied by the econometrics lecture given here and here

These can be accompanied by the following books

• Foundations of Statistics for Data Scientists R and Python by Agresti and Kateri
• Introductory Econometrics: A Modern Approach by Woodridge

For algorithmic treatment that talks about efficient mechanisms to optimize consult

hiraksarkar

mamba create -n r43
mamba activate r43
mamba install r-essentials=4.3
mamba install r-rjags
export PKG_CONFIG_PATH=/home/user/miniconda3/envs/r43/lib/pkgconfig/:$PKG_CONFIG_PATH

# start R
R

# Install R package

hiraksarkar

Basic

Installing R packages is painful, but conda environment solved a lot of problems. Basically, if you install your own R in conda, and the later R command install.packages() will automatically install the packages in the environment; in addition, conda has many system libraries too for getting away from requiring sudo permissions.

After creating an empty conda environment, you can install a specific version (say 4.2) of R by conda install -c conda-forge r-essentials=4.2. If you are not sure whether that version exists in conda, you can do conda search r-essentials. Using your own R in the conda environment, you can do the normal R installation commands.

Some R packages search system libraries by pkg-config. After you install the required libraries through conda, you can check whether your PKG_CONFIG_PATH includes /envs//lib/pkgconfig, and set the path properly.

hiraksarkar

#!/bin/bash
#SBATCH --mincpus 32
#SBATCH --mem 100G
#SBATCH --time 6-23:59:00
#SBATCH --job-name jupyterlab
#SBATCH --gres=gpu:1
#SBATCH --mail-type=begin        # send email when job begins
#SBATCH --mail-type=end          # send email when job ends
#SBATCH [email protected]
#SBATCH --output jupyter_logs/jupyter-notebook-%J.log

hiraksarkar

#!/bin/bash
#SBATCH --mincpus 16
#SBATCH --mem 64G
#SBATCH --time 5:00:00
#SBATCH --job-name mendel
#SBATCH --mail-type=begin        # send email when job begins
#SBATCH --mail-type=end          # send email when job ends
#SBATCH [email protected]
#SBATCH --output jupyter_logs/jupyter-notebook-%J.log
# get tunneling info

hiraksarkar

#!/bin/bash
## This gist contains instructions about cuda v11.2 and cudnn8.1 installation in Ubuntu 20.04 for Pytorch 1.8 & Tensorflow 2.7.0

### steps ####
# verify the system has a cuda-capable gpu
# download and install the nvidia cuda toolkit and cudnn
# setup environmental variables
# verify the installation
###