fixing the compilation errors

aligness instructions.rtf

@@ -0,0 +1,32 @@
+{\rtf1\ansi\ansicpg1252\cocoartf2821
+\cocoatextscaling0\cocoaplatform0{\fonttbl\f0\fswiss\fcharset0 Helvetica;\f1\fnil\fcharset0 Menlo-Regular;}
+{\colortbl;\red255\green255\blue255;\red0\green0\blue0;\red255\green255\blue255;\red0\green0\blue0;
+}
+{\*\expandedcolortbl;;\csgenericrgb\c0\c0\c0\c85000;\csgenericrgb\c100000\c100000\c100000;\csgray\c0;
+}
+\paperw11900\paperh16840\margl1440\margr1440\vieww11520\viewh8400\viewkind0
+\pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\pardirnatural\partightenfactor0
+
+\f0\fs24 \cf0 #From nextflow results directory\
+\
+\pard\tx593\pardeftab593\partightenfactor0
+
+\f1 \cf2 \cb3 git clone https://github.com/nagadhia/alignESS.git\
+cd alignESS\
+\pard\tx560\tx1120\tx1680\tx2240\tx2800\tx3360\tx3920\tx4480\tx5040\tx5600\tx6160\tx6720\pardirnatural\partightenfactor0
+
+\fs22 \cf4 \cb1 \ul \ulc4 \CocoaLigature0 conda crea\ulnone te -n aligness python=3.9\
+conda env update --file conda_env_simple.yml\
+\
+Mkdir aligness_outputs\
+Gunzip ../picrust/picrust2-2.5.2/EC_predicted.tsv\
+\
+#1st arg is a file where EC predictions are the columns for each ASV, 2nd arg is output file\
+python aligness_preprocess.py ../picrust/picrust2-2.5.2/EC_predicted.tsv aligness_strings.txt\
+\
+python alignESS.py dbalign aligness_strings.txt -nproc 8 -t 1\
+\
+#Creates similarity matrix - arguments are \
+python aligness_to_matrix.py output.txt ../../../dada2/ASV_table.tsv \
+\
+}

aligness_preprocess.py

@@ -0,0 +1,55 @@
+import pandas as pd
+import sys
+
+def process_ec_data(input_filepath, output_filepath):
+    """
+    Processes EC data from a TSV file and writes the results to a text file.
+
+    Args:
+        input_filepath (str): Path to the input TSV file.
+        output_filepath (str): Path to the output text file.
+    """
+
+    # Read and prepare output of picrust
+    function_per_species_df = pd.read_csv(input_filepath, sep="\t")
+    d = function_per_species_df.drop("sequence", axis=1)
+    d = d.to_numpy()
+
+    # Get strings in the format aligness takes it - at depth of 3 EC numbers eg 2.1.3
+    function_per_species_dict = {}
+    for i in range(len(function_per_species_df)):
+        func_str_list = []
+        for j in range(len(function_per_species_df.columns[1:])):
+            if d[i][j] > 0:
+                s = function_per_species_df.columns[1:][j]
+                l0, l1, l2, l3 = s.split(".")
+                func_str = l0[-1] + "." + l1 + "." + l2
+                func_str_list.append(func_str)
+
+        all_func_str = ""
+        for funcs in list(set(func_str_list)):
+            all_func_str += funcs
+            all_func_str += ":"
+        function_per_species_dict[function_per_species_df["sequence"][i]] = all_func_str
+
+    # Combine into a single string
+    ec_strings = []
+    for s in list(function_per_species_dict.values()):
+        s = s[:-1]
+        ec_strings.append(s)
+
+    # Write strings into txt file with strings of each species in a new line
+    with open(output_filepath, mode="w", encoding="utf-8") as myfile:
+        for i in range(len(ec_strings)):
+            item = ec_strings[i]
+            sp_id = function_per_species_df["sequence"][i]
+            myfile.write(f"{sp_id}\t{item}\n")
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        print("Usage: python script.py <input_filepath> <output_filepath>")
+        sys.exit(1)
+
+    input_filepath = sys.argv[1]
+    output_filepath = sys.argv[2]
+    process_ec_data(input_filepath, output_filepath)

conda_env_simple.yml

@@ -0,0 +1,17 @@
+name: ess-env
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - python=3.10
+  - pip
+  - numpy
+  - pandas
+  - matplotlib
+  - seaborn
+  - scipy
+  - biopython
+  - scikit-learn
+
+