Bio Drug Discovery Pipeline

DNA Sequence → Protein Structure → Drug Docking Score

Step 1
Gene Expression
Waiting
→
Step 2
Structure Predict
Waiting
→
Step 3
Drug Docking
Waiting
1
Gene Expression: DNA → mRNA → Protein

Enter a DNA coding sequence (must start with ATG). The central dogma of molecular biology: DNA is transcribed to mRNA (T→U), then mRNA codons are translated into amino acids using the standard genetic code. Translation stops at a stop codon (UAA, UAG, UGA).

↓
Amino acid sequence feeds into structure prediction
2
Secondary Structure Prediction (Chou-Fasman)

Each amino acid has propensity values for alpha-helix and beta-sheet conformations. A sliding window averages these propensities. Residues above threshold are assigned helix (H) or sheet (E); others become coil (C). This simplified model captures real structural trends.

H Alpha Helix (Pa > 1.03) E Beta Sheet (Pb > 1.05) C Coil/Turn
↓
Protein properties feed into drug docking
3
Drug Candidate Screening

Enter a drug molecule in SMILES notation. We evaluate Lipinski's Rule of Five (drug-likeness filter used in pharmaceutical screening) and compute a simplified binding compatibility score against the target protein based on size, polarity, and flexibility matching.