Decoy selection for protein structure prediction via extreme gradient boosting and ranking

Abstract

Background Identifying one or more biologically-active/native decoys from millions of non-native decoys is one of the major challenges in computational structural biology. The extreme lack of balance in positive and negative samples (native and non-native decoys) in a decoy set makes the problem even more complicated. Consensus methods show varied success in handling the challenge of decoy selection despite some issues associated with clustering large decoy sets and decoy sets that do not show much structural similarity. Recent investigations into energy landscape-based decoy selection approaches show promises. However, lack of generalization over varied test cases remains a bottleneck for these methods. Results We propose a novel decoy selection method, ML-Select, a machine learning framework that exploits the energy landscape associated with the structure space probed through a template-free decoy generation. The proposed method outperforms both clustering and energy ranking-based methods, all the while consistently offering better performance on varied test-cases. Moreover, ML-Select shows promising results even for the decoy sets consisting of mostly low-quality decoys. Conclusions ML-Select is a useful method for decoy selection. This work suggests further research in finding more effective ways to adopt machine learning frameworks in achieving robust performance for decoy selection in template-free protein structure prediction.

Fewer Dimensions, More Structures for Improved Discrete Models of Dynamics of Free versus Antigen-Bound Antibody

“…Further details can be found in [ 54 ]. We note that basin finding over conformation-energy samples has been employed by several works for molecular structure–function studies [ 12 , 55 , 56 , 57 ].…”

i4mC-GRU: Identifying DNA N4-Methylcytosine sites in mouse genomes using bidirectional gated recurrent unit and sequence-embedded features

“…Not only is it challenge for our work, but also for other studies, to develop a quality negative set. There are a variety of techniques for generating decoy sequences in computational genomics research (i.e., pseudo-negative samples), for example, randomized matching generation [46] , machine learning-aided selection [47] , background sequence selection [48] , and sequence recombination [48] , [49] . Each technique has its own characteristics, and the optimal strategy will depend on the specifics of the prediction task and the research objectives.…”

Protein quality assessment with a loss function designed for high-quality decoys

“…However, identifying the best structure remains a challenge. Therefore, it is necessary to employ a quality assessment stage to identify high-quality, near-native decoys among the generated decoys ( Akhter et al, 2020) . This remains true even with AlphaFold’s recent breakthrough performance ( Chen et al, 2023) .…”