digital-trial/main_biotransformer.nf

nextflow.enable.dsl=2


process SUPER_TRANSFORMER {
    container "${params.container_biotransformer}"
    containerOptions "${params.containerOptions}"
    publishDir "${params.outdir}/${params.project_name}/receptors", mode: 'copy'
    debug true

    input:
    path smiles_csv

    output:
    path "${smiles_csv.simpleName}_out.csv"

    script:
    """
    #!/bin/bash
    workdir=`pwd`
    cd /home/omic/biotransformer
    ## Predicting Biotransformation Using the Human Super Transformer:
    # This command predicts the biotransformation of molecules from an SDF input (example.csv) using the human super transformer (superbio) and annotates the metabolites with names and database IDs (from PubChem).
    java -jar /home/omic/biotransformer/biotransformer -k pred -b superbio -isdf \$workdir/${smiles_csv.simpleName}.csv -ocsv \${workdir}/${smiles_csv.simpleName}_out.csv -osdf \${workdir}/${smiles_csv.simpleName}.sdf -a
    """
}

process HUMAN_TRANSFORMER {
    memory { params.bt_initial_memory.toFloat().GB + (task.attempt - 1) * params.bt_growth_memory.toFloat().GB }
    errorStrategy { task.attempt <= params.bt_max_retries.toInteger() ? 'retry' : params.bt_fail_action }
    maxRetries params.bt_max_retries.toInteger()
    maxForks params.bt_max_forks.toInteger() ?: null

    container "${params.container_biotransformer}"
    // containerOptions "${params.containerOptions}"
    publishDir "${params.outdir}/${params.project_name}/1_biotransformer", mode: 'copy'
    // // Temporarily disabled debug prints
    // debug true
    // maxForks 5

    input:
    path smiles_csv

    output:
    path "${smiles_csv.simpleName}_out.csv"

    script:
    """
    #!/bin/bash
    set -e
    workdir=\$(pwd)
    cd /home/omic/biotransformer

    # Function to get available memory percentage
    get_available_mem_percent() {
        free | awk '/Mem:/ {print int(\$7/\$2 * 100)}'
    }

    # Function to log memory usage
    log_memory() {
        local pid=\$1
        echo "MEMLOG: Timestamp,BioTransformer Memory (MB),Available System Memory (%)" >&2
        while kill -0 \$pid 2>/dev/null; do
            local biotrans_mem=\$(ps -o rss= -p \$pid | awk '{print \$1/1024}')
            local avail_mem=\$(get_available_mem_percent)
            echo "MEMLOG: \$(date '+%Y-%m-%d %H:%M:%S'),\$biotrans_mem,\$avail_mem" >&2
            if [ \$avail_mem -lt 5 ]; then
                echo "MEMLOG: Available memory below 5%. Terminating process." >&2
                kill -15 \$pid
                wait \$pid
                echo 'PROCESS TERMINATED DUE TO LOW MEMORY' > "\${workdir}/${smiles_csv.simpleName}_out.csv"
                exit 1
            fi
            sleep 1800  # Sleep for 30 minutes
        done
    }

    # Calculate max Java heap size (90% of available memory)
    # max_heap=\$(free -g | awk '/Mem:/ {print int(\$7 * 0.9)}')
    
    #remove unnecessary data to run biotransformer
    head -n 2 "\$workdir/${smiles_csv.simpleName}.csv" > "\$workdir/${smiles_csv.simpleName}_run.csv"

    get_container_mem_bytes() {
        if [ -f /sys/fs/cgroup/memory/memory.limit_in_bytes ]; then
            cat /sys/fs/cgroup/memory/memory.limit_in_bytes
        elif [ -f /sys/fs/cgroup/memory.max ]; then
            # cgroup v2; "max" means no limit
            val=\$(cat /sys/fs/cgroup/memory.max)
            if [ "\$val" = "max" ]; then
                # fall back to host MemTotal
                awk '/MemTotal:/ {print \$2 * 1024}' /proc/meminfo
            else
                echo "\$val"
            fi
        else
            # fallback to host MemTotal
            awk '/MemTotal:/ {print \$2 * 1024}' /proc/meminfo
        fi
    }

    container_mem_bytes=\$(get_container_mem_bytes)
    # 95% of container memory, in MB (integer)
    heap_mb=\$(awk -v m="\$container_mem_bytes" 'BEGIN { printf "%d", (m*0.95)/(1024*1024) }')

    echo "Using Java heap: \${heap_mb}m (95% of container limit)" >&2

    java -Xmx"\${heap_mb}m" -jar /home/omic/biotransformer/biotransformer \
        -a -k pred -b superbio \
        -isdf "\$workdir/${smiles_csv.simpleName}_run.csv" \
        -ocsv "\${workdir}/${smiles_csv.simpleName}_out.csv" \
        -osdf "\${workdir}/${smiles_csv.simpleName}.sdf" \
        -s 100
    biotrans_pid=\$!

    # Start memory logging in the background
    log_memory \$biotrans_pid &
    log_pid=\$!

    # Wait for the biotransformer process to finish
    wait \$biotrans_pid
    status=\$?

    # Stop the logging process
    kill \$log_pid 2>/dev/null || true

    if [ ! -s "\${workdir}/${smiles_csv.simpleName}_out.csv" ]; then
        if [ \$status -ne 0 ] && [ ! -f "\${workdir}/${smiles_csv.simpleName}_out.csv" ]; then
            echo 'PROCESS FAILED' > "\${workdir}/${smiles_csv.simpleName}_out.csv"
        else
            echo 'NO METABOLITES' > "\${workdir}/${smiles_csv.simpleName}_out.csv"
        fi
    fi
    """
}

process METABOLITES_BY_MASS {
    container "${params.container_biotransformer}"
    containerOptions "${params.containerOptions}"
    publishDir "${params.outdir}/${params.project_name}/graphs", mode: 'copy'
    debug true

    input:
    path smiles_csv

    output:
    path "${smiles_csv.simpleName}_out.csv"

    script:
    """
    #!/bin/bash
    workdir=`pwd`
    cd /home/omic/biotransformer
    ## Identifying Metabolites with Specific Masses:
    # This command identifies all human metabolites of compounds in example.csv with masses 292.0946 Da and 304.0946 Da (max depth = 2), with a mass tolerance of 0.01 Da. It provides annotations when available.
   java -jar /home/omic/biotransformer/biotransformer -k cid -b allHuman -isdf \$workdir/${smiles_csv.simpleName}.csv -ocsv \${workdir}/${smiles_csv.simpleName}_out.csv -osdf \${workdir}/${smiles_csv.simpleName}.sdf -s 2 -m "292.0946;304.0946" -t 0.01 -a
    """
}

process ORDERED_SEQUENCE {
    container "${params.container_biotransformer}"
    containerOptions "${params.containerOptions}"
    publishDir "${params.outdir}/${params.project_name}/screening", mode: 'copy'
    debug true
    errorStrategy 'ignore'

    input:
    path smiles_csv

    output:
    path "${smiles_csv.simpleName}_out.csv"

    script:
    """
    #!/bin/bash
    workdir=`pwd`
    cd /home/omic/biotransformer
    ## Simulating an Ordered Sequence of Metabolism:
   # This command simulates an ordered sequence of metabolism for compounds in example.csv, starting with two steps of CYP450 oxidation, followed by one step of conjugation. The output is saved in an SDF file (output.sdf).
   java -jar /home/omic/biotransformer/biotransformer -isdf \$workdir/${smiles_csv.simpleName}.csv -ocsv \${workdir}/${smiles_csv.simpleName}_out.csv -osdf \${workdir}/${smiles_csv.simpleName}.sdf -k pred -q "cyp450:2; phaseII:1"
    """
}

process GET_FINAL_METABOLITES {
    container "${params.container_biotransformer}"
    containerOptions "${params.containerOptions}"
    publishDir "${params.outdir}/${params.project_name}/screening", mode: 'copy'
    // // Temporarily disabled debug prints
    // debug true
    // maxForks 1
    // errorStrategy 'ignore'

    errorStrategy { task.attempt <= 10 ? 'retry' : 'ignore' }
    maxRetries 10

    input:
    path smiles_csv

    output:
    path "${smiles_csv.simpleName}.txt" 

    script:
    """
    #!/opt/conda/envs/biotransformer/bin/python
    from rdkit import Chem
    import numpy as np
    import pandas as pd
    import requests

    #load biotransformet ouput
    biotransformer = pd.read_csv('$smiles_csv')
   
    #check if metabolites exist
    if biotransformer.shape[0] == 0:
        with open('${smiles_csv.simpleName}.txt', 'w') as f:
            f.write(f"NO_METABOLITES\\n")

    else:
        metabolite_id = biotransformer['Metabolite ID']
        #get only metabolites that are not precursors for next metabolisam step
        last_step_metabolites = biotransformer[[i not in list(biotransformer['Precursor ID']) for i in metabolite_id]]
        last_step_metabolites = last_step_metabolites.drop_duplicates()

        #get only "active" ones
        InChIKey = last_step_metabolites['InChIKey']
        InChIKey = pd.unique(InChIKey)

        #look if metabolite is in chembl
        chembl = []
        for i in InChIKey:
            curl_commend = f"https://www.ebi.ac.uk/chembl/api/data/molecule/{i}"
            c = requests.get(curl_commend)
            if c.status_code == 200:
                #compund exists in chembl
                chembl.append(True)
            else:
                #compund does not exists in chembl
                chembl.append(False)


        ChEMBL_bool = pd.DataFrame([InChIKey, chembl]).T.rename({0:'InChIKey',1:'in_ChEMBL'}, axis = 1)
        last_step_metabolites = last_step_metabolites.merge(ChEMBL_bool, how='inner', on='InChIKey')
        #if in PUBCHEM
        last_step_metabolites['in_PUBCHEM'] = ~last_step_metabolites['PUBCHEM_CID'].isna()
        ##logic
        #if metabolite is not in PUBCHEM pass it to next step. We don't know  if it's "active"
        #has to be in ChEMBL and PUBCHEM to have "activity" 
        mask = (last_step_metabolites['in_PUBCHEM'] == False) | (np.sum(last_step_metabolites[['in_ChEMBL','in_PUBCHEM']], 1) == 2)

        #filtered metabolites
        last_step_metabolites = last_step_metabolites[mask]

        #check for empty smile positions
        last_step_metabolites = last_step_metabolites.reset_index()
        if last_step_metabolites['SMILES'].isnull().any():
            for i in range(len(last_step_metabolites)):
                if pd.isna(last_step_metabolites.at[i, 'SMILES']):
                    last_step_metabolites.at[i, 'SMILES'] = Chem.MolToSmiles(Chem.MolFromInchi(last_step_metabolites.at[i, 'InChI']))
      
        #convert biotransformer smi to canonical smi and eliminate nonsense structures
        metabolite_smi = list(np.unique(last_step_metabolites['SMILES']))
        metabolite_smi = [Chem.CanonSmiles(i) for i in metabolite_smi if Chem.MolFromSmiles(i) != None]

        #final metabolites
        metabolite_smi_filteres = np.array(metabolite_smi) 

        #save smi
        with open('${smiles_csv.simpleName}.txt', 'w') as f:
            if len(metabolite_smi_filteres) == 0:
                f.write(f"NO_METABOLITES\\n")
            else:
                for n, line in enumerate(metabolite_smi_filteres):
                    f.write(f"{line}\\tmetabol_{n}\\n")
    """
}

process GET_FINAL_METABOLITES_STATIC {
    memory 1.GB

    container "${params.container_chembl}"
    containerOptions "${params.containerOptions}"
    publishDir "${params.outdir}/${params.project_name}/1b_final_metabolites", mode: 'copy'

    errorStrategy { task.attempt <= 10 ? 'retry' : 'ignore' }
    maxRetries 10

    input:
    path smiles_csv
    path chembl_db  // Add ChEMBL SQLite database as input

    output:
    path "${smiles_csv.simpleName}.txt" 

    script:
    """
    #!/opt/conda/bin/python
    from rdkit import Chem
    import numpy as np
    import pandas as pd
    import sqlite3

    # Connect to ChEMBL database
    conn = sqlite3.connect('file:$chembl_db?mode=ro&immutable=1', uri=True)
    # conn = sqlite3.connect('$chembl_db')
    
    cursor = conn.cursor()

    # Load biotransformer output
    biotransformer = pd.read_csv('$smiles_csv')
   
    # Check if metabolites exist
    if biotransformer.shape[0] == 0:
        with open('${smiles_csv.simpleName}.txt', 'w') as f:
            f.write(f"NO_METABOLITES\\n")

    else:
        # metabolite_id = biotransformer['Metabolite ID']
        # # Get only metabolites that are not precursors for next metabolism step
        # last_step_metabolites = biotransformer[[i not in list(biotransformer['Precursor ID']) for i in metabolite_id]]
        # last_step_metabolites = last_step_metabolites.drop_duplicates()
        
        # Get metabolite IDs that are NOT precursors for other metabolites
        metabolite_id = biotransformer['Metabolite ID']
        precursor_ids = set(biotransformer['Precursor ID'].dropna())  # Remove NaN values
        final_metabolite_mask = ~metabolite_id.isin(precursor_ids)
        
        # Filter to get only final metabolites
        last_step_metabolites = biotransformer[final_metabolite_mask].copy()
        last_step_metabolites = last_step_metabolites.drop_duplicates()

        # Get only "active" ones
        InChIKey = last_step_metabolites['InChIKey']
        InChIKey = pd.unique(InChIKey)

        # Look if metabolite is in ChEMBL using local database
        chembl = []
        for inchikey in InChIKey:
            # Query ChEMBL SQLite database for the InChIKey
            # The standard InChIKey is stored in COMPOUND_STRUCTURES table
            cursor.execute(\"""
                SELECT COUNT(*) 
                FROM COMPOUND_STRUCTURES 
                WHERE STANDARD_INCHI_KEY = ?
                LIMIT 1
            \""", (inchikey,))
            
            result = cursor.fetchone()
            chembl.append(result[0] > 0)

        # ChEMBL_bool = pd.DataFrame([InChIKey, chembl]).T.rename({0:'InChIKey',1:'in_ChEMBL'}, axis=1)
        ChEMBL_bool = pd.DataFrame({
            'InChIKey': InChIKey,
            'in_ChEMBL': chembl
        })
        last_step_metabolites = last_step_metabolites.merge(ChEMBL_bool, how='inner', on='InChIKey')
        
        # If in PUBCHEM
        last_step_metabolites['in_PUBCHEM'] = ~last_step_metabolites['PUBCHEM_CID'].isna()
        
        # Logic
        # If metabolite is not in PUBCHEM pass it to next step. We don't know if it's "active"
        # Has to be in ChEMBL and PUBCHEM to have "activity" 
        mask = (last_step_metabolites['in_PUBCHEM'] == False) | (np.sum(last_step_metabolites[['in_ChEMBL','in_PUBCHEM']], 1) == 2)

        # Filtered metabolites
        last_step_metabolites = last_step_metabolites[mask]

        # Check for empty smile positions
        last_step_metabolites = last_step_metabolites.reset_index()
        if last_step_metabolites['SMILES'].isnull().any():
            for i in range(len(last_step_metabolites)):
                if pd.isna(last_step_metabolites.at[i, 'SMILES']):
                    last_step_metabolites.at[i, 'SMILES'] = Chem.MolToSmiles(Chem.MolFromInchi(last_step_metabolites.at[i, 'InChI']))
      
        # Convert biotransformer smi to canonical smi and eliminate nonsense structures
        metabolite_smi = list(np.unique(last_step_metabolites['SMILES']))
        metabolite_smi = [Chem.CanonSmiles(i) for i in metabolite_smi if Chem.MolFromSmiles(i) != None]

        # Final metabolites
        metabolite_smi_filteres = np.array(metabolite_smi) 

        # Save smi
        with open('${smiles_csv.simpleName}.txt', 'w') as f:
            if len(metabolite_smi_filteres) == 0:
                f.write(f"NO_METABOLITES\\n")
            else:
                for n, line in enumerate(metabolite_smi_filteres):
                    f.write(f"{line}\\tmetabol_{n}\\n")

    # Close database connection
    conn.close()
    """
}