Feature/differential expression experiments

.gitignore

@@ -12,4 +12,5 @@ src/api_service/experiments/venv
 docker-compose.yml
 src/secretkey.txt
 docker-compose.mauri_dev.yml
-venv
+venv
+.DS_Store

Dockerfile

@@ -1,47 +1,64 @@
 FROM python:3.12-slim-bookworm
 
 # Docker Files Vars
-ARG LISTEN_PORT 8000
-ARG LISTEN_IP "0.0.0.0"
+ARG LISTEN_PORT=8000
+ARG LISTEN_IP="0.0.0.0"
 
 # Default values for deploying with multiomix image
-ENV LISTEN_PORT $LISTEN_PORT
-ENV LISTEN_IP $LISTEN_IP
-ENV DJANGO_SETTINGS_MODULE "multiomics_intermediate.settings_prod"
-ENV RESULT_DATAFRAME_LIMIT_ROWS 500
-ENV TABLE_PAGE_SIZE 10
+ENV LISTEN_PORT=$LISTEN_PORT
+ENV LISTEN_IP=$LISTEN_IP
+ENV DJANGO_SETTINGS_MODULE="multiomics_intermediate.settings_prod"
+ENV RESULT_DATAFRAME_LIMIT_ROWS=500
+ENV TABLE_PAGE_SIZE=10
 
 # Modulector connection parameters
-ENV MODULECTOR_HOST "127.0.0.1"
-ENV MODULECTOR_PORT "8001"
+ENV MODULECTOR_HOST="127.0.0.1"
+ENV MODULECTOR_PORT="8001"
 
 # BioAPI connection parameters
-ENV BIOAPI_HOST "127.0.0.1"
-ENV BIOAPI_PORT "8002"
+ENV BIOAPI_HOST="127.0.0.1"
+ENV BIOAPI_PORT="8002"
 
 # PostgreSQL DB connection parameters
-ENV POSTGRES_USERNAME "multiomics"
-ENV POSTGRES_PASSWORD "multiomics"
-ENV POSTGRES_HOST "db"
-ENV POSTGRES_PORT 5432
-ENV POSTGRES_DB "multiomics"
+ENV POSTGRES_USERNAME="multiomics"
+ENV POSTGRES_PASSWORD="multiomics"
+ENV POSTGRES_HOST="db"
+ENV POSTGRES_PORT=5432
+ENV POSTGRES_DB="multiomics"
 
 # Mongo DB connection parameters
-ENV MONGO_USERNAME "multiomics"
-ENV MONGO_PASSWORD "multiomics"
-ENV MONGO_HOST "mongo"
-ENV MONGO_PORT 27017
-ENV MONGO_DB "multiomics"
+ENV MONGO_USERNAME="multiomics"
+ENV MONGO_PASSWORD="multiomics"
+ENV MONGO_HOST="mongo"
+ENV MONGO_PORT=27017
+ENV MONGO_DB="multiomics"
 
 # Redis
-ENV REDIS_HOST "redis"
-ENV REDIS_PORT 6379
+ENV REDIS_HOST="redis"
+ENV REDIS_PORT=6379
 
 # Installs system dependencies and Node.js
 RUN apt-get update && apt-get install -y python3-pip curl libcurl4-openssl-dev libssl-dev libxml2-dev \
     && curl -fsSL https://deb.nodesource.com/setup_20.x | bash - && apt-get install -y nodejs && mkdir /config \
     && mkdir /src
 
+# Install R 4.4.2 from CRAN (Debian bookworm) and system dependencies
+RUN set -eux; \
+  echo "deb http://deb.debian.org/debian sid main" > /etc/apt/sources.list.d/debian-unstable.list; \
+  printf 'APT::Default-Release "%s";\n' "bookworm" > /etc/apt/apt.conf.d/00default-release; \
+  echo 'APT::Install-Recommends "false";' > /etc/apt/apt.conf.d/90no-recommends; \
+  printf 'Package: *\nPin: release a=unstable\nPin-Priority: 50\n' > /etc/apt/preferences.d/99pin-unstable; \
+  apt-get update; \
+  apt-get install -y --no-install-recommends \
+    ca-certificates curl gnupg build-essential gfortran libblas-dev liblapack-dev git \
+    libssl-dev libcurl4-openssl-dev libxml2-dev; \
+  apt-get install -y \
+    r-base=4.2.2.20221110-2 r-base-dev=4.2.2.20221110-2 r-recommended=4.2.2.20221110-2; \
+  rm -rf /var/lib/apt/lists/*
+
+# Install Bioconductor limma (stats and base come with R)
+RUN R -q -e 'options(repos=c(CRAN="https://cloud.r-project.org")); install.packages("BiocManager"); BiocManager::install(version="3.16", ask=FALSE); BiocManager::install("limma", ask=FALSE, update=FALSE)'
+
 # Installs Python dependencies and compiles the frontend
 ADD config/requirements.txt /config/
 WORKDIR /src
@@ -58,4 +75,3 @@ HEALTHCHECK --interval=5m --timeout=30s CMD ["/bin/bash", "-c", "/src/tools/chec
 ENTRYPOINT ["/bin/bash", "-c", "/src/entrypoint.sh"]
 
 EXPOSE $LISTEN_PORT
-

Dockerfile-celery

@@ -1,47 +1,64 @@
 FROM python:3.12-slim-bookworm
 
 # Docker Files Vars
-ARG LISTEN_PORT 8000
-ARG LISTEN_IP "0.0.0.0"
+ARG LISTEN_PORT=8000
+ARG LISTEN_IP="0.0.0.0"
 
 # Default values for deploying with multiomix image
-ENV LISTEN_PORT $LISTEN_PORT
-ENV LISTEN_IP $LISTEN_IP
-ENV DJANGO_SETTINGS_MODULE "multiomics_intermediate.settings_prod"
-ENV RESULT_DATAFRAME_LIMIT_ROWS 500
-ENV TABLE_PAGE_SIZE 10
+ENV LISTEN_PORT=$LISTEN_PORT
+ENV LISTEN_IP=$LISTEN_IP
+ENV DJANGO_SETTINGS_MODULE="multiomics_intermediate.settings_prod"
+ENV RESULT_DATAFRAME_LIMIT_ROWS=500
+ENV TABLE_PAGE_SIZE=10
 
 # Modulector connection parameters
-ENV MODULECTOR_HOST "127.0.0.1"
-ENV MODULECTOR_PORT "8001"
+ENV MODULECTOR_HOST="127.0.0.1"
+ENV MODULECTOR_PORT="8001"
 
 # BioAPI connection parameters
-ENV BIOAPI_HOST "127.0.0.1"
-ENV BIOAPI_PORT "8002"
+ENV BIOAPI_HOST="127.0.0.1"
+ENV BIOAPI_PORT="8002"
 
 # PostgreSQL DB connection parameters
-ENV POSTGRES_USERNAME "multiomics"
-ENV POSTGRES_PASSWORD "multiomics"
-ENV POSTGRES_HOST "db"
-ENV POSTGRES_PORT 5432
-ENV POSTGRES_DB "multiomics"
+ENV POSTGRES_USERNAME="multiomics"
+ENV POSTGRES_PASSWORD="multiomics"
+ENV POSTGRES_HOST="db"
+ENV POSTGRES_PORT=5432
+ENV POSTGRES_DB="multiomics"
 
 # Mongo DB connection parameters
-ENV MONGO_USERNAME "multiomics"
-ENV MONGO_PASSWORD "multiomics"
-ENV MONGO_HOST "mongo"
-ENV MONGO_PORT 27017
-ENV MONGO_DB "multiomics"
+ENV MONGO_USERNAME="multiomics"
+ENV MONGO_PASSWORD="multiomics"
+ENV MONGO_HOST="mongo"
+ENV MONGO_PORT=27017
+ENV MONGO_DB="multiomics"
 
 # Redis
-ENV REDIS_HOST "redis"
-ENV REDIS_PORT 6379
+ENV REDIS_HOST="redis"
+ENV REDIS_PORT=6379
 
 # Installs system dependencies
 RUN apt-get update && apt-get install -y python3-pip curl libcurl4-openssl-dev libssl-dev libxml2-dev \
     && mkdir /config \
     && mkdir /src
 
+# Install R 4.4.2 from CRAN (Debian bookworm) and system dependencies
+RUN set -eux; \
+  echo "deb http://deb.debian.org/debian sid main" > /etc/apt/sources.list.d/debian-unstable.list; \
+  printf 'APT::Default-Release "%s";\n' "bookworm" > /etc/apt/apt.conf.d/00default-release; \
+  echo 'APT::Install-Recommends "false";' > /etc/apt/apt.conf.d/90no-recommends; \
+  printf 'Package: *\nPin: release a=unstable\nPin-Priority: 50\n' > /etc/apt/preferences.d/99pin-unstable; \
+  apt-get update; \
+  apt-get install -y --no-install-recommends \
+    ca-certificates curl gnupg build-essential gfortran libblas-dev liblapack-dev git \
+    libssl-dev libcurl4-openssl-dev libxml2-dev; \
+  apt-get install -y \
+    r-base=4.2.2.20221110-2 r-base-dev=4.2.2.20221110-2 r-recommended=4.2.2.20221110-2; \
+  rm -rf /var/lib/apt/lists/*
+
+# Install Bioconductor limma (stats and base come with R)
+RUN R -q -e 'options(repos=c(CRAN="https://cloud.r-project.org")); install.packages("BiocManager"); BiocManager::install(version="3.16", ask=FALSE); BiocManager::install("limma", ask=FALSE, update=FALSE)'
+
 # Installs Python dependencies
 ADD config/requirements_celery.txt /config/requirements.txt
 RUN pip install --upgrade pip && pip3 install -r /config/requirements.txt

README.md

@@ -1,4 +1,4 @@
-<img align="right" src="src/frontend/static/frontend/img/logo-readme.png" alt="Multiomix logo">
+<img style="float: right" src="src/frontend/static/frontend/img/logo-readme.png" alt="Multiomix logo">
 
 # Multiomix
 
@@ -15,6 +15,7 @@ This document is focused on the **development** of the system. If you are lookin
 - Node JS >= `20.x` (tested version: `20.x`)
 - [Modulector][modulector] `2.2.0`
 - [BioAPI][bioapi] `1.2.1`
+- R `4.4.2` (required for `differential-expression`)
 
 
 ## Installation 
@@ -66,6 +67,7 @@ Every time you want to work with Multiomix, you need to follow the below steps:
    1. `python3 -m celery -A multiomics_intermediate worker -l info -Q stats`
    1. `python3 -m celery -A multiomics_intermediate worker -l info -Q inference`
    1. `python3 -m celery -A multiomics_intermediate worker -l info -Q sync_datasets`
+   1. `python3 -m celery -A multiomics_intermediate worker -l info -Q differential_expression`
    1. If you want to check Task in the GUI you can run [Flower](https://flower.readthedocs.io/en/latest/index.html) `python3 -m celery -A multiomics_intermediate flower`
 
     **NOTE:** maybe in Windows is needed to add `--pool=solo` to the previous commands. Example: `python3 -m celery -A multiomics_intermediate worker -l info -Q correlation_analysis --concurrency 1 --pool=solo`

config/requirements.txt

@@ -28,3 +28,5 @@ scipy==1.13.0
 statsmodels==0.14.2
 xlrd==2.0.1
 openpyxl==3.1.5
+rpy2==3.6.1
+urllib3==2.5.0

config/requirements_celery.txt

@@ -25,3 +25,5 @@ scipy==1.13.0
 statsmodels==0.14.2
 xlrd==2.0.1
 openpyxl==3.1.5
+rpy2==3.6.1
+urllib3==2.5.0

docker-compose_dist.yml

@@ -233,6 +233,21 @@ services:
             # REDIS_HOST: 'redis'
             # REDIS_PORT: 6379
 
+    # Celery worker for differential expression
+    differential-expression-worker:
+        image: omicsdatascience/multiomix:5.6.0-celery
+        restart: 'always'
+        depends_on:
+            - db
+            - mongo
+        volumes:
+            - media_data:/src/media
+        environment:
+            <<: *common-variables
+            QUEUE_NAME: 'differential_expression'  # This MUST NOT be changed
+            CONCURRENCY: 2
+            # PostgreSQL, Mongo y Redis usan los valores por defecto del resto de servicios
+
     # Django backend service
     multiomix:
         image: omicsdatascience/multiomix:5.6.0
@@ -290,6 +305,7 @@ services:
             - stats-worker
             - inference-worker
             - sync-datasets-worker
+            - differential-expression-worker
 
 volumes:
     mongo_data:

src/api_service/migrations/0062_alter_experiment_clinical_source_and_more.py

@@ -0,0 +1,142 @@
+# Generated by Django 4.2.19 on 2026-01-14 21:38
+
+from django.db import migrations, models
+import django.db.models.deletion
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        (
+            "datasets_synchronization",
+            "0036_alter_cgdsstudy_clinical_patient_dataset_and_more",
+        ),
+        ("genes", "0002_auto_20210114_2331"),
+        ("user_files", "0015_alter_userfile_options"),
+        ("api_service", "0061_alter_experiment_shared_users"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="experiment",
+            name="clinical_source",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                related_name="experiments_as_clinical_source",
+                to="api_service.experimentclinicalsource",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="experiment",
+            name="gem_source",
+            field=models.ForeignKey(
+                on_delete=django.db.models.deletion.CASCADE,
+                related_name="experiments_as_gem_source",
+                to="api_service.experimentsource",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="experiment",
+            name="mRNA_source",
+            field=models.ForeignKey(
+                on_delete=django.db.models.deletion.CASCADE,
+                related_name="experiments_as_mrna_source",
+                to="api_service.experimentsource",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="experimentclinicalsource",
+            name="extra_cgds_dataset",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.CASCADE,
+                related_name="experiment_clinical_sources_as_extra_cgds_dataset",
+                to="datasets_synchronization.cgdsdataset",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="experimentsource",
+            name="cgds_dataset",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.CASCADE,
+                related_name="experiment_sources_as_cgds_dataset",
+                to="datasets_synchronization.cgdsdataset",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="experimentsource",
+            name="user_file",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.CASCADE,
+                related_name="experiment_sources_as_user_file",
+                to="user_files.userfile",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="genecnacombination",
+            name="experiment",
+            field=models.ForeignKey(
+                on_delete=django.db.models.deletion.CASCADE,
+                related_name="%(class)ss",
+                to="api_service.experiment",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="genecnacombination",
+            name="gene",
+            field=models.ForeignKey(
+                db_column="gene",
+                db_constraint=False,
+                on_delete=django.db.models.deletion.DO_NOTHING,
+                related_name="%(class)ss_as_gene",
+                to="genes.gene",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="genemethylationcombination",
+            name="experiment",
+            field=models.ForeignKey(
+                on_delete=django.db.models.deletion.CASCADE,
+                related_name="%(class)ss",
+                to="api_service.experiment",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="genemethylationcombination",
+            name="gene",
+            field=models.ForeignKey(
+                db_column="gene",
+                db_constraint=False,
+                on_delete=django.db.models.deletion.DO_NOTHING,
+                related_name="%(class)ss_as_gene",
+                to="genes.gene",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="genemirnacombination",
+            name="experiment",
+            field=models.ForeignKey(
+                on_delete=django.db.models.deletion.CASCADE,
+                related_name="%(class)ss",
+                to="api_service.experiment",
+            ),
+        ),
+        migrations.AlterField(
+            model_name="genemirnacombination",
+            name="gene",
+            field=models.ForeignKey(
+                db_column="gene",
+                db_constraint=False,
+                on_delete=django.db.models.deletion.DO_NOTHING,
+                related_name="%(class)ss_as_gene",
+                to="genes.gene",
+            ),
+        ),
+    ]