Alpha transmembrane proteins (αTMPs) profoundly affect many critical biological processes and are major drug targets due to their pivotal protein functions. At present, even though the non-transmembrane secondary structures are highly relevant to the biological functions of αTMPs along with their transmembrane structures, they have not been unified to be studied yet. In this study, we present a novel computational method, TMPSS, to predict the secondary structures in non-transmembrane parts and the topology structures in transmembrane parts of αTMPs. TMPSS applied a Convolutional Neural Network (CNN), combined with an attention-enhanced Bidirectional Long Short-Term Memory (BiLSTM) network, to extract the local contexts and long-distance interdependencies from primary sequences. In addition, a multi-task learning strategy was used to predict the secondary structures and the transmembrane helixes. TMPSS was thoroughly trained and tested against a non-redundant independent dataset, where the Q3 secondary structure prediction accuracy achieved 78% in the non-transmembrane region, and the accuracy of the transmembrane region prediction achieved 90%. In sum, our method showcased a unified model for predicting the secondary structure and topology structure of αTMPs by only utilizing features generated from primary sequences and provided a steady and fast prediction, which promisingly improves the structural studies on αTMPs.

Transmembrane protein (TMP) is an important type of membrane protein that is involved in various biological membranes related biological processes. As major drug targets, TMPs’ surfaces are highly concerned to form the structural biases of their material-bindings for drugs or other biological molecules. However, the quantity of determinate TMP structures is still far less than the requirements, while artificial intelligence technologies provide a promising approach to accurately identify the TMP surfaces, merely depending on their sequences without any feature-engineering. For this purpose, we present an updated TMP surface residue predictor TMP-SSurface2 which achieved an even higher prediction accuracy compared to our previous version. The method uses an attention-enhanced Bidirectional Long Short Term Memory (BiLSTM) network, benefiting from its efficient learning capability, some useful latent information is abstracted from protein sequences, thus improving the Pearson correlation coefficients (CC) value performance of the old version from 0.58 to 0.66 on an independent test dataset. The results demonstrate that TMP-SSurface2 is efficient in predicting the surface of transmembrane proteins, representing new progress in transmembrane protein structure modeling based on primary sequences. TMP-SSurface2 is freely accessible at https://github.com/NENUBioCompute/TMP-SSurface-2.0.

Z-coordinate is an important structural feature of α-helical transmembrane proteins (α-TMPs), which is defined as the distance from a residue to the center of the biological membrane. Since the α-TMP structures from both experimental solved and computational predicted approaches still cannot cover the requirements in relevant research fields, z-coordinate prediction provides an opportunity to partly descript α-TMP structures based on their sequences, further contributes to function annotation and drug target discovery. For the purpose of improving the prediction accuracy and providing a convenient tool, we proposed a deep learning-based predictor (TM-ZC) for the z-coordinate of residues in α-TMPs. TM-ZC used the one-hot code and the PSSM as input features for a convolutional neural network (CNN) regression model. The experimental results demonstrated that TM-ZC was a powerful predictor, which is simple and fast, and achieved a considerable performance: the average error was 1.958, the percent of prediction error within 3Å was 77.461%, and the correlation coefficient (CC) was 0.922. We further discussed the usefulness of TM-ZC predicted z-coordinate and found its high consistency with topology structure and the enhancement of the surface accessibility prediction. INDEX TERMS α-helical transmembrane protein, convolutional neural network (CNN), regression, Z-coordinate of residues.

No abstract

(1) Background: Transmembrane proteins (TMPs) act as gateways connecting the intra- and extra-biomembrane environments, exchanging material and signals crossing the biofilm. Relevant evidence shows that corresponding interactions mostly happen on the TMPs’ surface. Therefore, knowledge of the relative distance among surface residues is critically helpful in discovering the potential local structural characters and setting the foundation for the protein’s interaction with other molecules. However, the prediction of fine-grained distances among residues with sequences remains challenging; (2) Methods: In this study, we proposed a deep-learning method called TMP-SurResD, which capitalized on the combination of the Residual Block (RB) and Squeeze-and-Excitation (SE) for simultaneously predicting the relative distance of functional surface residues based on sequences’ information; (3) Results: The comprehensive evaluation demonstrated that TMP-SurResD could successfully capture the relative distance between residues, with a Pearson Correlation Coefficient (PCC) of 0.7105 and 0.6999 on the validation and independent sets, respectively. In addition, TMP-SurResD outperformed other methods when applied to TMPs surface residue contact prediction, and the maximum Matthews Correlation Coefficient (MCC) reached 0.602 by setting a threshold to the predicted distance of 10; (4) Conclusions: TMP-SurResD can serve as a useful tool in supporting a sequence-based local structural feature construction and exploring the function and biological mechanisms of structure determination in TMPs, which can thus significantly facilitate the research direction of molecular drug action, target design, and disease treatment.