liveBook · Manning

Hydrogen bond donor

As explained in Build AI Drug Discovery Pipelines

A hydrogen-bond donor is an electronegative atom or functional group bearing a hydrogen that can donate a hydrogen bond.

A hydrogen-bond donor is an electronegative atom or functional group bearing a transferable hydrogen. Common donor groups include N–H and O–H. section 2.3.1

In drug discovery, donors help determine how strongly a molecule interacts with water. Excessive hydrogen bonding can improve solubility but hinder passage through nonpolar cell membranes. section 2.3.1

Use hydrogen-bond donor counts as one property-based screening criterion:

  • Lipinski’s Rule of Five allows no more than five hydrogen-bond donors. section 2.3.1
  • Donors differ from hydrogen-bond acceptors: donors provide hydrogen, whereas acceptors receive it. section 2.3.1
  • Applying the filter reduced the SPECS library from 212,670 to 199,640 compounds. section 2.3.1
Listing 2.4 Applying an Ro5 Filter
def apply_lipinski_filter(df):
    def count_ro5_violations(row):
        violations = 0
        if row['ExactMolWt'] > 500: violations += 1
        if row['MolLogP'] > 5: violations += 1
        if row['NumHDonors'] > 5: violations += 1
        if row['NumHAcceptors'] > 10: violations += 1
        return violations
    
    df['ro5_violations'] = df.apply(count_ro5_violations, axis=1)
    df['ro5_compliant'] = (    #A
        df['ro5_violations'] <= 1
    )
    
    compliant_df = df[df['ro5_compliant']]
    violated_df = df[~df['ro5_compliant']]
    return df, compliant_df, violated_df
 
specs, specs_ro5_compliant, specs_ro5_violated = \
    apply_lipinski_filter(specs)

The listing counts NumHDonors and flags compounds exceeding the Rule of Five threshold during Pandas-based filtering. section 2.3.1

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines N–H and O–H donors, explains water and membrane effects, and applies a five-donor threshold.
Examples
Uses N–H and O–H groups, the SPECS compound library, and a Pandas Ro5-filtering workflow.
What you can do after
Apply via Pandas by counting NumHDonors and flagging compounds with more than five donors.
How it connects
Connects hydrogen-bond donors with hydrogen-bond acceptors, lipophilicity, solubility, membranes, and Lipinski’s Rule of Five.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.