More Like this

1. Text mining for modeling of protein complexes enhanced by machine learning

   https://doi.org/10.1093/bioinformatics/btaa823  

   Badal, Varsha D ; Kundrotas, Petras J ; Vakser, Ilya A ( September 2020 , Bioinformatics)

   Elofsson, Arne (Ed.)

   Abstract Motivation Procedures for structural modeling of protein–protein complexes (protein docking) produce a number of models which need to be further analyzed and scored. Scoring can be based on independently determined constraints on the structure of the complex, such as knowledge of amino acids essential for the protein interaction. Previously, we showed that text mining of residues in freely available PubMed abstracts of papers on studies of protein–protein interactions may generate such constraints. However, absence of post-processing of the spotted residues reduced usability of the constraints, as a significant number of the residues were not relevant for the binding of the specific proteins. Results We explored filtering of the irrelevant residues by two machine learning approaches, Deep Recursive Neural Network (DRNN) and Support Vector Machine (SVM) models with different training/testing schemes. The results showed that the DRNN model is superior to the SVM model when training is performed on the PMC-OA full-text articles and applied to classification (interface or non-interface) of the residues spotted in the PubMed abstracts. When both training and testing is performed on full-text articles or on abstracts, the performance of these models is similar. Thus, in such cases, there is no need to utilize computationally demanding DRNN approach, which is computationally expensive especially at the training stage. The reason is that SVM success is often determined by the similarity in data/text patterns in the training and the testing sets, whereas the sentence structures in the abstracts are, in general, different from those in the full text articles. Availabilityand implementation The code and the datasets generated in this study are available at https://gitlab.ku.edu/vakser-lab-public/text-mining/-/tree/2020-09-04. Supplementary information Supplementary data are available at Bioinformatics online. 

   more » « less
2. End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins

   https://doi.org/10.1371/journal.pcbi.1010851  

   Cai, Tian ; Xie, Li ; Zhang, Shuo ; Chen, Muge ; He, Di ; Badkul, Amitesh ; Liu, Yang ; Namballa, Hari Krishna ; Dorogan, Michael ; Harding, Wayne W. ; et al ( January 2023 , PLOS Computational Biology)

   Skolnick, Jeffrey (Ed.)

   Systematically discovering protein-ligand interactions across the entire human and pathogen genomes is critical in chemical genomics, protein function prediction, drug discovery, and many other areas. However, more than 90% of gene families remain “dark”—i.e., their small-molecule ligands are undiscovered due to experimental limitations or human/historical biases. Existing computational approaches typically fail when the dark protein differs from those with known ligands. To address this challenge, we have developed a deep learning framework, called PortalCG, which consists of four novel components: (i) a 3-dimensional ligand binding site enhanced sequence pre-training strategy to encode the evolutionary links between ligand-binding sites across gene families; (ii) an end-to-end pretraining-fine-tuning strategy to reduce the impact of inaccuracy of predicted structures on function predictions by recognizing the sequence-structure-function paradigm; (iii) a new out-of-cluster meta-learning algorithm that extracts and accumulates information learned from predicting ligands of distinct gene families (meta-data) and applies the meta-data to a dark gene family; and (iv) a stress model selection step, using different gene families in the test data from those in the training and development data sets to facilitate model deployment in a real-world scenario. In extensive and rigorous benchmark experiments, PortalCG considerably outperformed state-of-the-art techniques of machine learning and protein-ligand docking when applied to dark gene families, and demonstrated its generalization power for target identifications and compound screenings under out-of-distribution (OOD) scenarios. Furthermore, in an external validation for the multi-target compound screening, the performance of PortalCG surpassed the rational design from medicinal chemists. Our results also suggest that a differentiable sequence-structure-function deep learning framework, where protein structural information serves as an intermediate layer, could be superior to conventional methodology where predicted protein structures were used for the compound screening. We applied PortalCG to two case studies to exemplify its potential in drug discovery: designing selective dual-antagonists of dopamine receptors for the treatment of opioid use disorder (OUD), and illuminating the understudied human genome for target diseases that do not yet have effective and safe therapeutics. Our results suggested that PortalCG is a viable solution to the OOD problem in exploring understudied regions of protein functional space. 

   more » « less
3. Does Inter-Protein Contact Prediction Benefit from Multi-Modal Data and Auxiliary Tasks?

   Talukder, A. ; Yin, R. ; Sun, Y. ; Shen, Y. ; You, Y. ( January 2022 , Machine Learning in Structural Biology Workshop at the 36th Conference on Neural Information Processing Systems)

   Approaches to in silico prediction of protein structures have been revolutionized by AlphaFold2, while those to predict interfaces between proteins are relatively underdeveloped, owing to the overly complicated yet relatively limited data of protein–protein complexes. In short, proteins are 1D sequences of amino acids folding into 3D structures, and interact to form assemblies to function. We believe that such intricate scenarios are better modeled with additional indicative information that reflects their multi-modality nature and multi-scale functionality. To improve binary prediction of inter-protein residue-residue contacts, we propose to augment input features with multi-modal representations and to synergize the objective with auxiliary predictive tasks. (i) We first progressively add three protein modalities into models: protein sequences, sequences with evolutionary information, and structure-aware intra-protein residue contact maps. We observe that utilizing all data modalities delivers the best prediction precision. Analysis reveals that evolutionary and structural information benefit predictions on the difficult and rigid protein complexes, respectively, assessed by the resemblance to native residue contacts in bound complex structures. (ii) We next introduce three auxiliary tasks via self-supervised pre-training (binary prediction of protein-protein interaction (PPI)) and multi-task learning (prediction of inter-protein residue–residue distances and angles). Although PPI prediction is reported to benefit from predicting intercontacts (as causal interpretations), it is not found vice versa in our study. Similarly, the finer-grained distance and angle predictions did not appear to uniformly improve contact prediction either. This again reflects the high complexity of protein–protein complex data, for which designing and incorporating synergistic auxiliary tasks remains challenging. 

   more » « less
4. How to choose templates for modeling of protein complexes: Insights from benchmarking template‐based docking

   https://doi.org/10.1002/prot.25875  

   Chakravarty, Devlina ; McElfresh, GW ; Kundrotas, Petras J. ; Vakser, Ilya A. ( February 2020 , Proteins: Structure, Function, and Bioinformatics)

   Comparative docking is based on experimentally determined structures of protein‐protein complexes (templates), following the paradigm that proteins with similar sequences and/or structures form similar complexes. Modeling utilizing structure similarity of target monomers to template complexes significantly expands structural coverage of the interactome. Template‐based docking by structure alignment can be performed for the entire structures or by aligning targets to the bound interfaces of the experimentally determined complexes. Systematic benchmarking of docking protocols based on full and interface structure alignment showed that both protocols perform similarly, with top 1 docking success rate 26%. However, in terms of the models' quality, the interface‐based docking performed marginally better. The interface‐based docking is preferable when one would suspect a significant conformational change in the full protein structure upon binding, for example, a rearrangement of the domains in multidomain proteins. Importantly, if the same structure is selected as the top template by both full and interface alignment, the docking success rate increases 2‐fold for both top 1 and top 10 predictions. Matching structural annotations of the target and template proteins for template detection, as a computationally less expensive alternative to structural alignment, did not improve the docking performance. Sophisticated remote sequence homology detection added templates to the pool of those identified by structure‐based alignment, suggesting that for practical docking, the combination of the structure alignment protocols and the remote sequence homology detection may be useful in order to avoid potential flaws in generation of the structural templates library.

    

   more » « less
5. Cryo-EM Structure of Gokushovirus ΦEC6098 Reveals a Novel Capsid Architecture for a Single-Scaffolding Protein, Microvirus Assembly System

   https://doi.org/10.1128/jvi.00990-22  

   Lee, Hyunwook ; Baxter, Alexis J. ; Bator, Carol M. ; Fane, Bentley A. ; Hafenstein, Susan L. ( November 2022 , Journal of Virology)

   Frappier, Lori (Ed.)

   ABSTRACT Ubiquitous and abundant in ecosystems and microbiomes, gokushoviruses constitute a Microviridae subfamily, distantly related to bacteriophages ΦX174, α3, and G4. A high-resolution cryo-EM structure of gokushovirus ΦEC6098 was determined, and the atomic model was built de novo . Although gokushoviruses lack external scaffolding and spike proteins, which extensively interact with the ΦX174 capsid protein, the core of the ΦEC6098 coat protein (VP1) displayed a similar structure. There are, however, key differences. At each ΦEC6098 icosahedral 3-fold axis, a long insertion loop formed mushroom-like protrusions, which have been noted in lower-resolution gokushovirus structures. Hydrophobic interfaces at the bottom of these protrusions may confer stability to the capsid shell. In ΦX174, the N-terminus of the capsid protein resides directly atop the 3-fold axes of symmetry; however, the ΦEC6098 N-terminus stretched across the inner surface of the capsid shell, reaching nearly to the 5-fold axis of the neighboring pentamer. Thus, this extended N-terminus interconnected pentamers on the inside of the capsid shell, presumably promoting capsid assembly, a function performed by the ΦX174 external scaffolding protein. There were also key differences between the ΦX174-like DNA-binding J proteins and its ΦEC6098 homologue VP8. As seen with the J proteins, C-terminal VP8 residues were bound into a pocket within the major capsid protein; however, its N-terminal residues were disordered, likely due to flexibility. We show that the combined location and interaction of VP8’s C-terminus and a portion of VP1’s N-terminus are reminiscent of those seen with the ΦX174 and α3 J proteins. IMPORTANCE There is a dramatic structural and morphogenetic divide within the Microviridae . The well-studied ΦX174-like viruses have prominent spikes at their icosahedral vertices, which are absent in gokushoviruses. Instead, gokushovirus major coat proteins form extensive mushroom-like protrusions at the 3-fold axes of symmetry. In addition, gokushoviruses lack an external scaffolding protein, the more critical of the two ΦX174 assembly proteins, but retain an internal scaffolding protein. The ΦEC6098 virion suggests that key external scaffolding functions are likely performed by coat protein domains unique to gokushoviruses. Thus, within one family, different assembly paths have been taken, demonstrating how a two-scaffolding protein system can evolve into a one-scaffolding protein system, or vice versa. 

   more » « less