diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..13486c54305a559c0a4764fc262916cd781d08ab
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+j2s_old_output.py
+
diff --git a/EXAMPLE/example_input.txt b/EXAMPLE/example_input.txt
new file mode 100644
index 0000000000000000000000000000000000000000..c9c03b695912110be8375a3fdaf97418c78aee98
--- /dev/null
+++ b/EXAMPLE/example_input.txt
@@ -0,0 +1,11 @@
+MarkerName Effect StdErr IntEffect IntStdErr IntCov N
+rs1 0.06464 0.09852999999999999 0.03685 0.1539 -0.009603 302478
+rs2 0.1482 0.0439 0.1071 0.05265 -0.0019219999999999999 551772
+rs3 0.2428 0.06389 0.1027 0.07647999999999999 -0.004072999999999999 537523
+rs4 -0.1821 0.05173 -0.06716 0.06105 -0.002671 540537
+rs5 -0.1665 0.04127 -0.055060000000000005 0.0498 -0.0016920000000000001 527550
+rs6 0.09873 0.0404 -0.0314 0.04846 -0.001627 532076
+rs7 0.2008 0.042910000000000004 -0.1251 0.05058 -0.001835 541066
+rs8 -0.044430000000000004 0.07288 0.07737999999999999 0.0825 -0.005298 391711
+rs9 -0.23199999999999998 0.1064 -0.1964 0.1246 -0.01128 508288
+rs10 0.2414 0.06343 -0.1089 0.07171 -0.004017 401959
diff --git a/EXAMPLE/example_output.txt.gz b/EXAMPLE/example_output.txt.gz
new file mode 100644
index 0000000000000000000000000000000000000000..37a3662bd61863993934943b4714b1ba1f748085
Binary files /dev/null and b/EXAMPLE/example_output.txt.gz differ
diff --git a/HELP.md b/HELP.md
deleted file mode 100644
index 4474ad82b10b76871c7eb87224fb7b5c0183088c..0000000000000000000000000000000000000000
--- a/HELP.md
+++ /dev/null
@@ -1,68 +0,0 @@
-j2s: Deriving stratified effects from joint models investigating Gene-Environment Interactions
-======
-
-The python3 script **j2s.py** allows for the estimation of genetic effect sizes in unexposed and exposed individuals separately from joint models investigating Gene-Environment interactions when the exposure is binary. A pre-print of the publication is available [here](https://www.biorxiv.org/content/10.1101/693218v1).
-
-Prerequisite
-------------
-
-To execute the script, python3 must be installed as weel as the following Python packages:
- + pandas (version 0.22.0)
- + numpy (version 1.13.3)
- + scipy (version 0.19.1)
-
-Execution
-------------
-
-To use the script, type the following command:
-
-``` bash
-python3 INFILE N N_EXPOSED OUTFILE
-```
-
-with:
- * INFILE is the path to the input file describing the summary statitics in the joint model,
- * N is the total sample size,
- * N_EXPO is the number of exposed (E = 1) individuals,
- * OUTFILE is the path to the outputfile.
-
-Description of the input files
-------------
-
-The input file has 7 mandatory columns:
- * the identifier of the variant (e.g rs number) labelled 'MarkerName'
- * the main genetic effect size labelled 'Effect'
- * the standard error of the main genetic effect size labelled 'StdErr'
- * the interaction effect size labelled 'IntEffect'
- * the standard error of the interaction effect size labelled 'IntStdErr'
- * the covariance between the main genetic effect size and the interaction effect size labelled 'IntCov'
- * the sample size of the variant labelled 'N'
-
-| MarkerName | Effect |StdErr |IntEffect |IntStdErr |IntCov |N |
-| ------------ | -------- | ----------- | ----------- | ------------ | -------------| ------ |
-| rs1 | 0.06464 | 0.09853 | 0.03685 | 0.1539 | -0.009603 | 302478 |
-| rs2 | 0.1482 | 0.0439 | 0.1071 | 0.05265 | -0.001922 | 551772 |
-| rs3 | 0.2428 | 0.06389 | 0.1027 | 0.07648 | -0.004073 | 537523 |
-| rs4 | -0.1821 | 0.05173 | -0.06716 | 0.06105 | -0.002671 | 540537 |
-| rs4 | -0.1665 | 0.04127 | -0.05506 | 0.0498 | -0.001692 | 527550 |
-
-This format corresponds to the output of the METAL software performing the joint test ([Manning et al, 2011](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3312394/))
-
-Short tutorial
---------------
-
-
-Bug report / Help
------------------
-
-Please open an issue if you find a bug.
-
-Code of conduct
----------------
-
-Please note that this project is released with a [Contributor Code of Conduct](https://gitlab.pasteur.fr/statistical-genetics/j2s/blob/master/code-of-conduct.md). By participating in this project you agree to abide by its terms.
-
-License
--------
-
-This project is licensed under the MIT License - see the [LICENSE.md](https://gitlab.pasteur.fr/statistical-genetics/j2s/blob/master/LICENSE) file for details
diff --git a/README.md b/README.md
index 4474ad82b10b76871c7eb87224fb7b5c0183088c..32cdd0679000dbfd323e1128115e69e1c7ba6d51 100644
--- a/README.md
+++ b/README.md
@@ -26,7 +26,7 @@ with:
* N_EXPO is the number of exposed (E = 1) individuals,
* OUTFILE is the path to the outputfile.
-Description of the input files
+Description of the input file
------------
The input file has 7 mandatory columns:
@@ -48,9 +48,37 @@ The input file has 7 mandatory columns:
This format corresponds to the output of the METAL software performing the joint test ([Manning et al, 2011](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3312394/))
-Short tutorial
+Description of the output file
--------------
+The output file has 13 columns:
+ * the identifier of the variant (e.g rs number) labelled 'MarkerName'
+ * the marginal genetic effect size in exposed individuals labelled 'Exp_eff'
+ * the standard error of the marginal genetic effect size in exposed individuals labelled 'Exp_eff_sd'
+ * the p-value of the marginal genetic effect size in exposed individuals labelled 'Exp_p'
+ * the sample size in exposed individuals labelled 'Exp_N'
+ * the marginal genetic effect size in unexposed individuals labelled 'Unexp_eff'
+ * the standard error of the marginal genetic effect size in unexposed individuals labelled 'Unexp_eff_sd'
+ * the p-value of the marginal genetic effect size in unexposed individuals labelled 'Unexp_p'
+ * the psample size in exposed individuals labelled 'Exp_p'
+ * the marginal genetic effect size in the whole sample labelled 'Marg_eff'
+ * the standard error of the marginal genetic effect size in the whole sample labelled 'Marg_eff_sd'
+ * the p-value of the marginal genetic effect size in the whole sample labelled 'Marg_p'
+ * the sample size in exposed individuals labelled 'Exp_p'
+
+
+ MarkerName | Exp_eff | Exp_eff_sd | Exp_p | Exp_N | Unexp_eff | Unexp_eff_sd | Unexp_p | Unexp_N | Marg_eff | Marg_eff_sd | Marg_p | Marg_N
+ --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | ---
+ rs2 | 0.25529999999999997 | 0.029244358430302427 | 2.5492291647780578e-18 | 235938.0 | 0.1482 | 0.0439 | 0.0007358690030330429 | 315833.0 | 0.1939961385 | 0.02811324629168079 | 5.181096635559163e-12 | 551772
+ rs3 | 0.3455 | 0.04225071005320504 | 2.9008842650020812e-16 | 229845.0 | 0.2428 | 0.06389 | 0.0001445316729934853 | 307677.0 | 0.28671469116666665 | 0.040843280080164183 | 2.2206797794728803e-12 | 537523
+ rs4 | -0.24926 | 0.03257445932014834 | 1.9786602680323982e-14 | 231134.0 | -0.1821 | 0.05173 | 0.00043121980737467655 | 309402.0 | -0.21081772793333334 | 0.032760038001211925 | 1.233026411024831e-10 | 540537
+ rs5 | -0.22156 | 0.028271061175696964 | 4.614778694925717e-15 | 225581.0 | -0.1665 | 0.04127 | 5.474023450141706e-05 | 301968.0 | -0.1900437477666667 | 0.026639580953178844 | 9.757377728977485e-13 | 527550
+ rs6 | 0.06733 | 0.026954250128690283 | 0.01249186364041974 | 227516.0 | 0.09873 | 0.0404 | 0.014533002227448433 | 304559.0 | 0.08530330766666666 | 0.025886829090553485 | 0.000983377501863686 | 532076
+ rs7 | 0.07570000000000002 | 0.02701119212474709 | 0.005070161655305943 | 231360.0 | 0.2008 | 0.04291 | 2.8748859265040098e-06 | 309705.0 | 0.14730703150000002 | 0.027198241852565627 | 6.093014771116645e-08 | 541066
+ rs8 | 0.03294999999999999 | 0.03900954242233562 | 0.39829783686389786 | 167496.0 | -0.04443 | 0.07288 | 0.5421054285558802 | 224214.0 | -0.011342183033333335 | 0.04500115076521829 | 0.8010085487588172 | 391711
+ rs9 | -0.4284 | 0.06546846569150679 | 6.005193234873927e-11 | 217344.0 | -0.232 | 0.1064 | 0.029224037771486945 | 290943.0 | -0.31598096733333336 | 0.06717839018056906 | 2.5560091937373993e-06 | 508288
+ rs10 | 0.1325 | 0.03364058560726908 | 8.192605950085655e-05 | 171878.0 | 0.2414 | 0.06343 | 0.00014136362518112045 | 230080.0 | 0.1948341785 | 0.0390928641631008 | 6.232145316728965e-07 | 401959
+
Bug report / Help
-----------------
diff --git a/example_input.txt b/example_input.txt
new file mode 100644
index 0000000000000000000000000000000000000000..c9c03b695912110be8375a3fdaf97418c78aee98
--- /dev/null
+++ b/example_input.txt
@@ -0,0 +1,11 @@
+MarkerName Effect StdErr IntEffect IntStdErr IntCov N
+rs1 0.06464 0.09852999999999999 0.03685 0.1539 -0.009603 302478
+rs2 0.1482 0.0439 0.1071 0.05265 -0.0019219999999999999 551772
+rs3 0.2428 0.06389 0.1027 0.07647999999999999 -0.004072999999999999 537523
+rs4 -0.1821 0.05173 -0.06716 0.06105 -0.002671 540537
+rs5 -0.1665 0.04127 -0.055060000000000005 0.0498 -0.0016920000000000001 527550
+rs6 0.09873 0.0404 -0.0314 0.04846 -0.001627 532076
+rs7 0.2008 0.042910000000000004 -0.1251 0.05058 -0.001835 541066
+rs8 -0.044430000000000004 0.07288 0.07737999999999999 0.0825 -0.005298 391711
+rs9 -0.23199999999999998 0.1064 -0.1964 0.1246 -0.01128 508288
+rs10 0.2414 0.06343 -0.1089 0.07171 -0.004017 401959
diff --git a/example_output.txt.gz b/example_output.txt.gz
new file mode 100644
index 0000000000000000000000000000000000000000..37a3662bd61863993934943b4714b1ba1f748085
Binary files /dev/null and b/example_output.txt.gz differ
diff --git a/j2s.py b/j2s.py
index 02065c39db0c8667c9faf7a93120b9ae146d0f03..617309b69e27db2b451116255149684999b6693d 100644
--- a/j2s.py
+++ b/j2s.py
@@ -12,7 +12,7 @@ stt = time.time()
# Checking number of arguments (4 expected)
-if len(sys.argv) != 4 :
+if len(sys.argv) != 5 :
print("Incorrect call: wrong number of arguments\n")
sys.exit(1)
@@ -24,7 +24,7 @@ outfile = sys.argv[4]
print("Arguments passed:")
print("\tSample size = " + str(samplesize))
print("\tN exposed = " + str(Nexpo))
-print("Output file = " + outfile + "\n")
+print("\tOutput file = " + outfile + "\n")
print("\n")
meanE = Nexpo / samplesize
@@ -56,6 +56,6 @@ df['Marg_p'] = chi2.sf((df['Marg_eff'] / df['Marg_eff_sd']) ** 2, 1)
df['Marg_N'] = df['N']
# Writing output file
-df.loc[:,['rsID', 'Chr', 'BP', 'MarkerName', 'Allele1', 'Allele2', 'Freq1', 'Exp_eff', 'Exp_eff_sd', 'Exp_p', 'Exp_N', 'Unexp_eff', 'Unexp_eff_sd', 'Unexp_p', 'Unexp_N', 'Marg_eff', 'Marg_eff_sd', 'Marg_p' , 'Marg_N']].to_csv(outfile, sep = '\t', index = False, header = True, compression = 'gzip')
+df.loc[:,['MarkerName', 'Exp_eff', 'Exp_eff_sd', 'Exp_p', 'Exp_N', 'Unexp_eff', 'Unexp_eff_sd', 'Unexp_p', 'Unexp_N', 'Marg_eff', 'Marg_eff_sd', 'Marg_p' , 'Marg_N']].to_csv(outfile, sep = '\t', index = False, header = True, compression = 'gzip')
print("Analysis finished ")