The key finding in the DNA double helix model is the specific pairing or binding between nucleotides A-T and C-G, and the pairing rules are the molecule basis of genetic code. Unfortunately, no such rules have been discovered for proteins. Here we show that similar rules and intrinsic sequence patterns between intra-protein binding peptide fragments do exist, and they can be extracted using a deep learning algorithm. Multi-millions of binding and non-binding peptide fragments from currently available protein X-ray structures are classified with an accuracy of up to 93%. This discovery has the potential in helping solve protein folding and protein-protein interaction problems, two open and fundamental problems in molecular biology.
Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension
Tsinghua University（清华大学）；University of Washington（华盛顿大学）；Massachusetts Institute of Technology（麻省理工学院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；ByteDance Inc.（字节跳动公司）；Helixon Inc.（Helixon公司）
Mouse prion protein PrP106-126 is a peptide corresponding to the residues 107-127 of human prion protein. It has been shown that PrP106-126 can reproduce the main neuropathological features of prionrelated transmissible spongiform encephalopathies and can form amyloid-like fibrils in vitro. The conformational characteristics of PrP106-126 fibril have been investigated by electron microscopy, CD spectroscopy, NMR and molecular dynamics simulations. Recent researches have found out that PrP106-126 in water assumes a stable structure consisting of two parallel beta-sheets that are tightly packed …
Protein-peptide interactions play a key role in cell functions. Their structural characterization, though challenging, is important for the discovery of new drugs. The CABS-dock web server provides an interface for modeling protein-peptide interactions using a highly efficient protocol for the flexible docking of peptides to proteins. While other docking algorithms require pre-defined localization of the binding site, CABS-dock doesn't require such knowledge. Given a protein receptor structure and a peptide sequence (and starting from random conformations and positions of the peptide), CABS-do…
Protein-peptide interactions play essential functional roles in living organisms and their structural characterization is a hot subject of current experimental and theoretical research. Computational modeling of the structure of protein-peptide interactions is usually divided into two stages: prediction of the binding site at a protein receptor surface, and then docking (and modeling) the peptide structure into the known binding site. This paper presents a comprehensive CABS-dock method for the simultaneous search of binding sites and flexible protein-peptide docking, available as a users frie…
Protein solubility and conformational stability are a result of a balance of interactions both within a protein and between protein and solvent. The electrostatic solvation free energy of oligoglycines, models for the peptide backbone, becomes more favorable with an increasing length, yet longer peptides collapse due to the formation of favorable intrapeptide interactions between CO dipoles, in some cases without hydrogen bonds. The strongly repulsive solvent cavity formation is balanced by van der Waals attractions and electrostatic contributions. In order to investigate the competition betwe…
The protein-protein interactions (PPIs) are crucial for understanding the majority of cellular processes. PPIs play important role in gene transcription regulation, cellular signaling, molecular basis of immune response and more. Moreover, a disruption of hese mechanisms is frequently postulated as a possible cause of diseases such as Alzheimer's or cancer. For many of biologically relevant cases the structure of protein-protein complexes remain unknown. Therefore computational techniques, including molecular docking, have become a valuable part of drug discovery pipelines. Unfortunately, none…
Morphology-Aware Peptide Discovery via Masked Conditional Generative Modeling
Technical University of Munich（慕尼黑技术大学）；TUM School of Engineering and Design（慕尼黑技术大学工程与设计学院）；Department of Engineering Physics and Computation（工程物理与计算系）；Munich Data Science Institute（慕尼黑数据科学研究所）；AMC（原子模型中心）
In multi-domain proteins, the domains are connected by a flexible unstructured region called as protein domain linker. The accurate demarcation of these linkers holds a key to understanding of their biochemical and evolutionary attributes. This knowledge helps in designing a suitable linker for engineering stable multi-domain chimeric proteins. Here we propose a novel method for the demarcation of the linker based on a three-dimensional protein structure and a domain definition. The proposed method is based on biological knowledge about structural flexibility of the linkers. We performed struc…
Collapse of the polypeptide backbone is an integral part of protein folding. Using polyglycine as a probe, we explore the nonequilibrium pathways of protein collapse in water. We find that the collapse depends on the competition between hydration effects and intra-peptide interactions. Once intra-peptide van der Waal interactions dominate, the chain collapses along a nonequilibrium pathway characterized by formation of pearl-necklace-like local clusters as intermediates that eventually coagulate into a single globule. By describing this coarsening through the contact probability as a function …
Iqra University（伊克拉大学）；The University of Western Australia（西澳大利亚大学）
In extreme cold weather, living organisms produce Antifreeze Proteins (AFPs) to counter the otherwise lethal intracellular formation of ice. Structures and sequences of various AFPs exhibit a high degree of heterogeneity, consequently the prediction of the AFPs is considered to be a challenging task. In this research, we propose to handle this arduous manifold learning task using the notion of localized processing. In particular an AFP sequence is segmented into two sub-segments each of which is analyzed for amino acid and di-peptide compositions. We propose to use only the most significant fe…
Two-dimensional partial covariance mass spectrometry (2D-PC-MS) exploits the inherent fluctuations of fragment ion abundances across a series of tandem mass spectra, to identify correlated pairs of fragment ions produced along the same fragmentation pathway of the same parent (e.g. peptide) ion. Here, we apply 2D-PC-MS to the analysis of intact protein ions in a standard linear ion trap mass analyzer, using the fact that the fragment-fragment correlation signals are much more specific to bio-molecular sequence than 1D MS/MS signals at the same mass accuracy and resolution. We show that from th…
Mass spectrometry (MS) is used widely in biomolecular structural analysis and is particularly dominant in the study of proteins. Despite its considerable power, state-of-the-art protein MS frequently suffers from limited reliability of spectrum-to-structure assignments. This could not be solved fully by the dramatic increase in mass accuracy and resolution of modern MS instrumentation or by the introduction of new fragmentation methods. Here we present a new kind of two-dimensional mass spectrometry for high fidelity determination of a biomolecular primary structure based on partial covariance…
Many biologically important ligands of proteins are large, flexible, and often charged molecules that bind to extended regions on the protein surface. It is infeasible or expensive to locate such ligands on proteins with standard methods such as docking or molecular dynamics (MD) simulation. The alternative approach proposed here is the scanning of a spatial and angular grid around the protein with smaller fragments of the large ligand. Energy values for complete grids can be computed efficiently with a well-known Fast Fourier Transform accelerated algorithm and a physically meaningful interac…
UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design
Tsinghua University（清华大学）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；Renmin University of China（中国人民大学）；Bytedance（字节跳动）
