Novel Descriptors and Digital Signal Processing- Based Method for Protein Sequence Activity Relationship Study

Abstract

The work aiming to unravel the correlation between protein sequence and function in the absence of structural information can be highly rewarding. We present a new way of considering descriptors from the amino acids index database for modeling and predicting the fitness value of a polypeptide chain. This approach includes the following steps: (i) Calculating Q elementary numerical sequences (Ele_SEQ) depending on the encoding of the amino acid residues, (ii) determining an extended numerical sequence (Ext_SEQ) by concatenating the Q elementary numerical sequences, wherein at least one elementary numerical sequence is a protein spectrum obtained by applying fast Fourier transformation (FFT), and (iii) predicting a value of fitness for polypeptide variants (train and/or validation set). These new descriptors were tested on four sets of proteins of different lengths (GLP-2, TNF alpha, cytochrome P450, and epoxide hydrolase) and activities (cAMP activation, binding affinity, thermostability and enantioselectivity). We show that the use of multiple physicochemical descriptors coupled with the implementation of the FFT, taking into account the interactions between residues of amino acids within the protein sequence, could lead to very significant improvement in the quality of models and predictions. The choice of the descriptor or of the combination of descriptors and/or FFT is dependent on the couple protein/fitness. This approach can provide potential users with value added to existing mutant libraries where screening efforts have so far been unsuccessful in finding improved polypeptide mutants for useful applications.

PyPEF—An Integrated Framework for Data-Driven Protein Engineering

“…48,72 A structureindependent mutant library screening machine learning approach termed innov'SAR appeared recently. 73 The innov'SAR 37,41,74,75 pipeline applies featurization by Fouriertransforming numerical indices, which represent physicochemical and biochemical properties for each amino acid, taken from the amino acid index (AAindex) database. 76,77 After fast Fourier transform (FFT) processing, a spectral form of the protein is generated and used as the input for subsequent statistical modeling.…”

Machine Learning Enables Selection of Epistatic Enzyme Mutants for Stability Against Unfolding and Detrimental Aggregation

“…The ML procedure relies on the encoding phase, the modelling phase comprising a digital signal process (Fourier Transform), and the predictive phase. All steps from data encoding to model building with the implementation of the whole machine learning procedure, and model evaluation have been described in detail in previous papers and in experimental application case studies [7,[15][16] including multi-parameter optimization. [26] The new descriptors and the ML approach are fully described in the "Material and Methods" section of supporting information.…”

“…[7] Indeed, a concatenation of multiples indices, that is, an extended_sequence (Ext_SEQ), is evaluated as descriptor (as exemplified in Figure 1). In the most recent contribution, [16] we showed that the use of multiple physicochemical indices coupled with the implementation of the FFT, taking into account the interactions between residues of amino acids within the protein sequence, [7,17] leads to very significant improvement in the quality of models. The choice of the descriptor (i. e., combination of indices) with or without applying FFT, during the statistical modelling, is dependent of the couple protein/fitness, thereby improving the prediction of enzyme activity.…”

“…The choice of the descriptor (i. e., combination of indices) with or without applying FFT, during the statistical modelling, is dependent of the couple protein/fitness, thereby improving the prediction of enzyme activity. [16] Undesired protein aggregation is a phenomenon prevalent in diseases such as Alzheimer and in biotechnological applications of enzymes as well. In the present ML study, we address the persisting question of how to prevent detrimental enzyme aggregation following unfolding, which causes a decrease or even shutdown in biocatalytic performance.…”

In silico prediction of Severe Acute Respiratory Syndrome Coronavirus 2 main protease cleavage sites

“…There have been many different methods for transforming the amino acids to numerical values. The mostly well‐employed methods in the literature include the binary encoding approach, 19 the descriptor encoding approach 20–22 and the profile encoding approach, 6,23 to name a few.…”