Capturing, sharing and analysing biophysical data from protein engineering and protein characterization studies

Abstract

Large amounts of data are being generated annually on the connection between the sequence, structure and function of proteins using site-directed mutagenesis, protein design and directed evolution techniques. These data provide the fundamental building blocks for our understanding of protein function, molecular biology and living organisms in general. However, much experimental data are never deposited in databases and is thus 'lost' in journal publications or in PhD theses. At the same time theoretical scientists are in need of large amounts of experimental data for benchmarking and calibrating novel predictive algorithms, and theoretical progress is therefore often hampered by the lack of suitable data to validate or disprove a theoretical assumption. We present PEAT (Protein Engineering Analysis Tool), an application that integrates data deposition, storage and analysis for researchers carrying out protein engineering projects or biophysical characterization of proteins. PEAT contains modules for DNA sequence manipulation, primer design, fitting of biophysical characterization data (enzyme kinetics, circular dichroism spectroscopy, NMR titration data, etc.), and facilitates sharing of experimental data and analyses for a typical university-based research group. PEAT is freely available to academic researchers at http://enzyme.ucd.ie/PEAT.

Figure 1.

PEAT may be used to visualize changes in structure alongside changes in various biophysical characteristics. The figure shows the structure of HEWL and its D52N mutant (mutated residue marked in red). Plots of three experimental properties are displayed alongside: 15N and 1HN NMR titration curves for the ASP48 residue and kinetics data. In each case curves for wild type and mutant are overlayed. Plots can be changed interactively to show all other available datasets; if the structure is displayed, data labels are interpreted as residue numbers and marked for easy identification.

Figure 2.

The PEAT main window is organized much like a spreadsheet with rows holding the data for a single protein. Each column is of a specific data type and right-clicking on the cell will provide the options specific to that field type. For typical protein studies each row/record is a protein, having a sequence, structure or other data associated it with it. The screenshot presented here is a view of the contents of Titration_DB (39).

Figure 3.

How the various components relate to each other in PEAT. The ‘backend’ database/server components inside the dashed box are not directly seen by the end-user and can in principle be replaced by another data storage/sharing solution without substantially affecting the other components. Plugins can be flexibly developed with knowledge of python. Developing a set of export tools would in principle be necessary for data sharing with standard databases.

Figure 4.

Sequencing with DNAtool. The wild-type DNA sequence is shown in green, with the corresponding amino acid sequence in black underneath. The mutant DNA sequence is shown in purple and the mutagenic primer in blue. Changes in the nucleotide sequence are highlighted in red (primer and mutant DNA sequence) and the corresponding positions in the wild-type DNA sequence are shown in brown. The wild-type restriction digest pattern is shown above the primer, and changes in restriction digest patterns when incorporating the mutagenic primer are highlighted below the sequence, with ‘+’ or ‘–’ indicating the addition or removal of a restriction site.

Figure 5.

Comparison of multiple NMR titration datasets in Ekin. On the left side are data entry and fitting panels. On the right multiple selected datasets can be compared/overlayed. Fitting curves are interactively updated in the plot window.

Figure 6.

A typical workflow illustrating how one might complement experimental work with PEAT. A protein is sequenced and mutagenic primers are designed in DNATool. The mutant clones are created and sequenced and sequences are checked in DNATool. Progress information on each clone is kept in the Labbook and is updated as a clone proceeds through various stages towards expression. The data collected from the various biophysical measurements and kinetic assays is imported into Ekin and fit to yield the desired parameters. Data for multiple mutants can then be compared within the application. Multiple users in parallel doing different assays on the same protein/mutants or handling different mutants would all share the same database.