COMTOP: Protein Residue–Residue Contact Prediction through Mixed Integer Linear Optimization

Abstract

Protein contact prediction helps reconstruct the tertiary structure that greatly determines a protein’s function; therefore, contact prediction from the sequence is an important problem. Recently there has been exciting progress on this problem, but many of the existing methods are still low quality of prediction accuracy. In this paper, we present a new mixed integer linear programming (MILP)-based consensus method: a Consensus scheme based On a Mixed integer linear opTimization method for prOtein contact Prediction (COMTOP). The MILP-based consensus method combines the strengths of seven selected protein contact prediction methods, including CCMpred, EVfold, DeepCov, NNcon, PconsC4, plmDCA, and PSICOV, by optimizing the number of correctly predicted contacts and achieving a better prediction accuracy. The proposed hybrid protein residue–residue contact prediction scheme was tested in four independent test sets. For 239 highly non-redundant proteins, the method showed a prediction accuracy of 59.68%, 70.79%, 78.86%, 89.04%, 94.51%, and 97.35% for top-5L, top-3L, top-2L, top-L, top-L/2, and top-L/5 contacts, respectively. When tested on the CASP13 and CASP14 test sets, the proposed method obtained accuracies of 75.91% and 77.49% for top-L/5 predictions, respectively. COMTOP was further tested on 57 non-redundant α-helical transmembrane proteins and achieved prediction accuracies of 64.34% and 73.91% for top-L/2 and top-L/5 predictions, respectively. For all test datasets, the improvement of COMTOP in accuracy over the seven individual methods increased with the increasing number of predicted contacts. For example, COMTOP performed much better for large number of contact predictions (such as top-5L and top-3L) than for small number of contact predictions such as top-L/2 and top-L/5. The results and analysis demonstrate that COMTOP can significantly improve the performance of the individual methods; therefore, COMTOP is more robust against different types of test sets. COMTOP also showed better/comparable predictions when compared with the state-of-the-art predictors.

Inter-Residue Distance Prediction From Duet Deep Learning Models

“…The DL-based contact map prediction algorithms are mainly based on convolutional neural networks (CNN) (such as DeepCov ( Jones and Kandathil, 2018 ), DeepContact ( Liu et al, 2018 ), and DNCON2 ( Adhikari et al, 2018 )), Unet [such as PconsC4 ( Michel et al, 2019 )], residual networks (ResNet) [such as DeepConPred2 ( Ding et al, 2018 ), ResPRE ( Li et al, 2019 ), MapPred ( Wu et al, 2020 ) and TripletRes ( Li et al, 2021 )], ResNet combined with long short-term memory (LSTM) [such as SPOT-Contact ( Hanson et al, 2018 )] and transformers [such as ESM ( Malinin and Gales, 2021 ) and SPOT-Contact-LM ( Singh et al, 2022 )]. COMTOP ( Reza et al, 2021 ) uses the mixed ILP technique to combine different contact predictors (including several DL predictors) to further improve the prediction performance.…”

Metadata analysis to explore hub of the hub-genes highlighting their functions, pathways and regulators for cervical cancer diagnosis and therapies

“…Protein-Protein Interactions (PPI) were previously utilized to identify the hub genes that may be responsible for the disease, and a co-expression network was employed to validate the listed genes using a heat map based on their co-regulation scores [14][15][16][17]. Protein 3D structures are important for the fields in evolutionary biology and biotechnology, such as protein function prediction and drug design [18].…”