diff --git a/README.md b/README.md
index c19ca6fffe88d91b2d5b420dbd9458eddd26365c..2421aa5ef3460b20cccc13cdd90522ff7ec16cd6 100644
--- a/README.md
+++ b/README.md
@@ -3,8 +3,10 @@
## Description
## Prerequisites
-1. This project is coded in ```python3.8``` and uses the following modules:
- * SQLite 3
+1. This project is coded in ```python3.8``` and uses the modules listed in `requirements.txt`. To easily install them with pip, enter in your terminal:
+```sh
+pip install -r requirements.txt
+```
2. [PmagicGEO](https://gitbio.ens-lyon.fr/LBMC/regards/pmagicgeo) - a script that allows to obtain metadata associated to a GSE or a GSM ([GEO classification](https://www.ncbi.nlm.nih.gov/geo/))
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3864ef2f61a3af5e388b7b86d033f9e9adeac38f
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,7 @@
+pandas==0.25.3
+biopython==1.75
+tqdm
+numpy
+regex==2020.2.20
+lazyparser==0.2.0
+coloredlogs==10.0
diff --git a/src/db_utils/create_freq_table.py b/src/db_utils/create_freq_table.py
deleted file mode 100755
index a3a8117ce4fd21ecbfc5e9a2ddb06b6389e6dab6..0000000000000000000000000000000000000000
--- a/src/db_utils/create_freq_table.py
+++ /dev/null
@@ -1,118 +0,0 @@
-#!/usr/bin/env python3
-
-# -*- coding: utf-8 -*-
-
-"""
-Description: The goal of this script is to create the tables of frequencies \
-that will be next injected into the web database
-"""
-
-
-from pathlib import Path
-import pandas as pd
-from .creation_of_exon_table import get_ctrl_exon
-from .config import Config, logging_def
-import logging
-import sys
-
-
-def load_bed(bed_file: Path) -> pd.DataFrame:
- """
- Load a bed file.
-
- :param bed_file: A bed file containing exons with a 7th column \
- corresponding to frequencies of in the exon.
- :return: the bed file as a dataframe
- """
- if "orf" in bed_file.name:
- mtype = "orf"
- else:
- mtype = "exon"
- names = ["chr", "start", "stop", "name", "score", "strand", "freq"]
- df = pd.read_csv(bed_file, sep="\t", names=names)
- df = df.loc[:, ["name", "freq"]]
- df["type"] = [mtype] * len(df)
- df.freq = df.freq.apply(eval)
- return df
-
-
-def get_ft_type(bed_type: str, feature: str) -> str:
- """
- Get the feature type of a feature.
-
- :param bed_type: The type of a bed : orf or exon
- :param feature: The feature of interest
- :return: The feature type
- """
- if bed_type == "orf":
- if len(feature) == 1:
- return "aa"
- else:
- return "ft"
- else:
- if len(feature) == 1:
- return "nt"
- elif len(feature) == 2:
- return "dnt"
- else:
- return "tnt"
-
-
-def create_table(df: pd.DataFrame) -> pd.DataFrame:
- """
- Create the table of that that will be inserted in gin database.
-
- :param df: A dataframe of exon and the aa/ft frequencies \
- of their encoded peptide and their nt/dnt/tnt frequencies
- :return: A dataframe
- """
- dic = {"ft": [], "frequency": [], "exon_id": [], "ft_type": []}
- tot = len(df)
- for i in range(len(df)):
- if round(i / tot * 100) in range(101):
- sys.stdout.write(f"Progression : "
- f" {round((i + 1) / (tot / 100))} % \r")
- s = df.iloc[i, :]
- for ft in s.loc["freq"].keys():
- ft_type = get_ft_type(s.loc["type"], ft)
- dic["ft"].append(ft)
- dic["frequency"].append(s.loc["freq"][ft])
- dic["exon_id"].append(s.loc["name"])
- dic["ft_type"].append(ft_type)
- del df
- table = pd.DataFrame(dic)
- return table[["ft_type", "ft", "exon_id", "frequency"]].reset_index()
-
-
-def create_freq_table(bed_orf: Path, bed_exon: Path, ctrl_exon: Path,
- logging_level: str = "DISABLE") -> None:
- """
- From to bed files with as 7th column corresponding to frequency of an \
- exon compute the table that will be used to populate the gin database.
-
- :param bed_orf: A bed file containing only ORF for exons and \
- a 7th column corresponding to the frequency in amino acid or \
- feature in the peptide coded by the exons
- :param bed_exon: A bed file containing exons with a 7th column \
- containing the frequency of nucleotides, di-nucleotides, tri-nucleotides.
- :param ctrl_exon: The file containing control exons
- :param logging_level: The level of information to display
- """
- logging_def(Config.output, logging_level)
- logging.debug(f"Loading {bed_orf}")
- df_orf = load_bed(bed_orf)
- logging.debug(f"Loading {bed_exon}")
- df_exon = load_bed(bed_exon)
- logging.debug("Concatenating load file and filtering on ctrl exons")
- df = pd.concat([df_exon, df_orf], axis=0, ignore_index=True)
- del df_exon
- del df_orf
- ctrl_exon_list = get_ctrl_exon(ctrl_exon)
- df = df.loc[df.name.isin(ctrl_exon_list), :]
- logging.debug(df.head())
- logging.debug("Creating Frequency table")
- final_table = create_table(df)
- logging.debug(final_table.head())
- logging.debug(f"Saving table to {Config.frequency_file}")
- final_table.columns = ["id", "ft_type", "ft", "exon_id", "frequency"]
- final_table.to_csv(Config.frequency_file, sep="\t")