Knowledge-transfer learning for prediction of matrix metalloprotease substrate-cleavage sites

Abstract

Matrix Metalloproteases (MMPs) are an important family of proteases that play crucial roles in key cellular and disease processes. Therefore, MMPs constitute important targets for drug design, development and delivery. Advanced proteomic technologies have identified type-specific target substrates; however, the complete repertoire of MMP substrates remains uncharacterized. Indeed, computational prediction of substrate-cleavage sites associated with MMPs is a challenging problem. This holds especially true when considering MMPs with few experimentally verified cleavage sites, such as for MMP-2, -3, -7, and -8. To fill this gap, we propose a new knowledge-transfer computational framework which effectively utilizes the hidden shared knowledge from some MMP types to enhance predictions of other, distinct target substrate-cleavage sites. Our computational framework uses support vector machines combined with transfer machine learning and feature selection. To demonstrate the value of the model, we extracted a variety of substrate sequence-derived features and compared the performance of our method using both 5-fold cross-validation and independent tests. The results show that our transfer-learning-based method provides a robust performance, which is at least comparable to traditional feature-selection methods for prediction of MMP-2, -3, -7, -8, -9 and -12 substrate-cleavage sites on independent tests. The results also demonstrate that our proposed computational framework provides a useful alternative for the characterization of sequence-level determinants of MMP-substrate specificity.

iProt-Sub: a comprehensive package for accurately mapping and predicting protease-specific substrates and cleavage sites

“…Its accuracy is lowest for matrix metalloproteases, including MMP-2 and MMP-3. The current study and several previous studies [29,52,135] confirmed the prediction of cleavage sites for these proteases to be an especially challenging problem and highlighted the need to develop specialized methods for improved MMP cleavage site prediction.…”

“…If not addressed, this can result in models that favor negative predictions over positive [29,51]. To address this data imbalance issue, we used a down-sampling strategy, randomly discarding from the overrepresented negative samples, to impose a ratio of 1 positive to every 3 negatives, as previously suggested [15,25,29,51,52].…”

Predicting Proteolysis in Complex Proteomes Using Deep Learning

“…Second, the large imbalance between cleavage sites vs. non-cleavage sites (i.e., the number of non-cleavage sites vastly outweighs the number of cleavage sites) resulting in unbalanced datasets. The first challenge was addressed by (i) complimenting the MEROPS cleavage data with data available in the Eckhard 2016 study [ 49 ] and; (ii) using transfer learning approaches, where a general protease cleavage model was pretrained using all the available data (separately for MMPs and other proteases) and subsequently used as a starting point to train protease-specific models (using only the cleavage data for a specific protease) [ 54 ]. The second issue was addressed by weighting the model prior to model training to “pay more attention” to the minority (cleavage sites) class.…”

Predicting and validating protein degradation in proteomes using deep learning

“…To overcome this, we assigned larger weights to cleavage sites than non-cleavage sites, enforcing the classifier to "pay more attention" to the underrepresented class. We also utilised transfer learning to overcome the issue with limited amounts of data available for certain proteases (67). We ensured that the general model and protease-specific model contained the same identities for testing, training, and validating.…”