Bikash Kumar Bhandari

The paper introduces a hidden Markov model method for protein identification from noisy signature data, showing good performance on a human protein database under various conditions.

LazyPair predicts protein-protein interactions and their types using random forests trained on residue properties, outperforming existing methods in accuracy and scalability.

The paper shows that modifying synonymous codons in translation initiation sites can tune protein yield in recombinant protein production.

Razor identifies signal peptides from toxins using N-terminal residues, revealing conserved features across kingdoms and discovering toxin-like signal peptides in defensive proteins.

The paper introduces TIsigner and SoDoPE, web tools for optimizing recombinant protein expression and solubility, with linked functionality for gene optimization.

The paper introduces a new predictor, SWI, for protein solubility using B-factors and develops a web tool, SoDoPE, to maximize solubility and expression.