Protein/Peptide Isoelectric Point Calculator (ProtPIC)

ProtPIC (Protein and Peptide Isoelectric Point Calculator) is a machine-learning-based bioinformatics tool designed to predict the isoelectric point (pI) of proteins and peptides, as well as residue-level pKa values. The tool automatically identifies input sequence type: short sequences (<=60 aa) use the peptide model and require only amino acid sequences; long sequences (>60 aa) use the protein model, which incorporates structural features (RSA, pLDDT, and secondary structure) into the calculation.

The page returns the predicted pI, and for proteins, it also returns pKa values of charged residues.

1. Amino Acid Sequences (up to 10 FASTA entries):

Parsed sequences: 0, total residues: 0



Technical Highlights

  • Structural feature fusion: integrates RSA (relative solvent accessibility), pLDDT (structure confidence), and secondary-structure features
  • Physical-prior integration: incorporates Henderson-Hasselbalch theoretical estimates as features
  • High-accuracy prediction: pKa prediction MAE = 0.338 pH; protein pI prediction MAE = 0.581 pH; peptide pI prediction MAE = 0.118 pH

Model Performance Metrics

Performance Comparison (vs IPC 2.0)

 ------------------------------------------------------------
 [pKa Prediction]  Rosetta dataset, 260 residues
 ------------------------------------------------------------
   Metric             IPC 2.0       ProtPIC (ours)
 ------------------------------------------------------------
   MAE                  0.3364        0.338
   RMSE                 0.5762        0.624
   Outliers (>0.5)      54(20.8%)     48(18.7%)
 ------------------------------------------------------------

  ------------------------------------------------------------
 [Protein pI Prediction]  581 proteins, IPC2.protein.svr.19
 ------------------------------------------------------------
   Metric             IPC 2.0       ProtPIC (ours)
 ------------------------------------------------------------
   MAE                 0.5906        0.581
   RMSE                0.8479        0.839
   R²                  0.5934        0.623
   Outliers (>0.5)    247(42.5%)    247(42.5%)
 ------------------------------------------------------------

 ------------------------------------------------------------
 [Peptide pI Prediction]  29,774 peptides, IPC2.peptide.Conv2D
 ------------------------------------------------------------
   Metric             IPC 2.0       ProtPIC (ours)
 ------------------------------------------------------------
   MAE                 0.1216        0.118
   RMSE                0.2216        0.228
   R²                  0.9761        0.975
   Outliers (>0.25)   2691(9.0%)    2878(9.7%)
 ------------------------------------------------------------

 Performance by pKa / pI range
  ------------------------------------------------------------
 [pKa]  ProtPIC (ours), 257 residues
 ------------------------------------------------------------
   pKa Range            Count    MAE    RMSE    Outliers (>0.5)
 ------------------------------------------------------------
   pKa < 4                90    0.339   0.761      15 (16.7%)
   pKa 4-6                63    0.190   0.386       3  (4.8%)
   pKa 6-8                60    0.370   0.555      13 (21.7%)
   pKa 8-10                6    0.538   0.726       3 (50.0%)
   pKa > 10               38    0.502   0.668      14 (36.8%)
 ------------------------------------------------------------

 ------------------------------------------------------------
 [Protein pI]  ProtPIC (ours), 581 proteins
 ------------------------------------------------------------
   pI Range             Count    MAE    RMSE    Outliers (>0.5)
 ------------------------------------------------------------
   Acidic (<5)            162   0.602   0.814      81 (50.0%)
   Neutral (5-7)          313   0.393   0.542      90 (28.8%)
   Basic (7-9)             86   0.949   1.211      57 (66.3%)
   Very Basic (>9)         20   1.776   2.041      19 (95.0%)
 ------------------------------------------------------------

 ------------------------------------------------------------
 [Peptide pI]  ProtPIC (ours), 29,774 peptides
 ------------------------------------------------------------
   pI Range             Count    MAE    RMSE    Outliers (>0.25)
 ------------------------------------------------------------
   Very Acidic (<4)      4,578   0.064   0.098     130  (2.8%)
   Acidic (4-5)          9,879   0.087   0.156     330  (3.3%)
   Neutral-Acidic (5-6)  2,160   0.323   0.423    1167 (54.0%)
   Neutral (6-7)         7,297   0.145   0.273     818 (11.2%)
   Basic (7-9)           5,795   0.099   0.230     373  (6.4%)
   Very Basic (>9)          65   0.534   0.630      60 (92.3%)
 ------------------------------------------------------------

        

Last updated: 2026-05-03

References

Kozlowski LP. IPC 2.0: prediction of isoelectric point and pKa dissociation constants. Nucleic Acids Res. 2021 Jul 2;49(W1):W285-W292. doi: 10.1093/nar/gkab295. PMID: 33905510; PMCID: PMC8262712.