Structural Characterization of Endogenous Tuberous Sclerosis Protein Complex Revealed Potential Polymeric Assembly.

Tuberous sclerosis protein complex (pTSC) nucleates a proteinaceous signaling hub that integrates information about the internal and external energy status of the cell in the regulation of growth and energy consumption. Biochemical and cryo-electron microscopy studies of recombinant pTSC have revealed its structure and stoichiometry and hinted at the possibility that the complex may form large oligomers. Here, we have partially purified endogenous pTSC from fasted mammalian brains of rat and pig by leveraging a recombinant antigen binding fragment (Fab) specific for the TSC2 subunit of pTSC. We demonstrate Fab-dependent purification of pTSC from membrane-solubilized fractions of the brain homogenates. Negative stain electron microscopy of the samples purified from pig brain demonstrates rod-shaped protein particles with a width of 10 nm, a variable length as small as 40 nm, and a high degree of conformational flexibility. Larger filaments are evident with a similar 10 nm width and a ≤1 µm length in linear and weblike organizations prepared from pig brain. Immunogold labeling experiments demonstrate linear aggregates of pTSC purified from mammalian brains. These observations suggest polymerization of endogenous pTSC into filamentous superstructures.

Transfer Learning for Risk Classification of Social Media Posts: Model Evaluation Study.

BACKGROUND: Mental illness affects a significant portion of the worldwide population. Online mental health forums can provide a supportive environment for those afflicted and also generate a large amount of data that can be mined to predict mental health states using machine learning methods. OBJECTIVE: This study aimed to benchmark multiple methods of text feature representation for social media posts and compare their downstream use with automated machine learning (AutoML) tools. We tested on datasets that contain posts labeled for perceived suicide risk or moderator attention in the context of self-harm. Specifically, we assessed the ability of the methods to prioritize posts that a moderator would identify for immediate response. METHODS: We used 1588 labeled posts from the Computational Linguistics and Clinical Psychology (CLPsych) 2017 shared task collected from the Reachout.com forum. Posts were represented using lexicon-based tools, including Valence Aware Dictionary and sEntiment Reasoner, Empath, and Linguistic Inquiry and Word Count, and also using pretrained artificial neural network models, including DeepMoji, Universal Sentence Encoder, and Generative Pretrained Transformer-1 (GPT-1). We used Tree-based Optimization Tool and Auto-Sklearn as AutoML tools to generate classifiers to triage the posts. RESULTS: The top-performing system used features derived from the GPT-1 model, which was fine-tuned on over 150,000 unlabeled posts from Reachout.com. Our top system had a macroaveraged F1 score of 0.572, providing a new state-of-the-art result on the CLPsych 2017 task. This was achieved without additional information from metadata or preceding posts. Error analyses revealed that this top system often misses expressions of hopelessness. In addition, we have presented visualizations that aid in the understanding of the learned classifiers. CONCLUSIONS: In this study, we found that transfer learning is an effective strategy for predicting risk with relatively little labeled data and noted that fine-tuning of pretrained language models provides further gains when large amounts of unlabeled text are available.

Comprehensive mapping of cystic fibrosis mutations to CFTR protein identifies mutation clusters and molecular docking predicts corrector binding site.

Cystic Fibrosis (CF) is caused by mutations in the CFTR gene, of which over 2000 have been reported to date. Mutations have yet to be analyzed in aggregate to assess their distribution across the tertiary structure of the CFTR protein, an approach that could provide valuable insights into the structure-function relationship of CFTR. In addition, the binding site of Class I correctors (VX-809, VX-661, and C18) is not well understood. In this study, exonic CFTR mutations and mutant allele frequencies described in 3 curated databases (ABCMdb, CFTR1, and CFTR2, comprising >130 000 data points) were mapped to 2 different structural models: a homology model of full-length CFTR protein in the open-channel state, and a cryo-electron microscopy core-structure of CFTR in the closed-channel state. Accordingly, residue positions of 6 high-frequency mutant CFTR alleles were found to spatially co-localize in CFTR protein, and a significant cluster was identified at the NBD1:ICL4 interdomain interface. In addition, immunoblotting confirmed the approximate binding site of Class I correctors, demonstrating that these small molecules act via a similar mechanism in vitro, and in silico molecular docking generated binding poses for their complex with the cryo-electron microscopy structure to suggest the putative corrector binding site is a multi-domain pocket near residues F374-L375. These results confirm the significance of interdomain interfaces as susceptible to disruptive mutation, and identify a putative corrector binding site. The structural pharmacogenomics approach of mapping mutation databases to protein models shows promise for facilitating drug discovery and personalized medicine for monogenetic diseases.

Computational proteome-wide screening predicts neurotoxic drug-protein interactome for the investigational analgesic BIA 10-2474.

The investigational compound BIA 10-2474, designed as a long-acting and reversible inhibitor of fatty acid amide hydrolase for the treatment of neuropathic pain, led to the death of one participant and hospitalization of five others due to intracranial hemorrhage in a Phase I clinical trial. Putative off-target activities of BIA 10-2474 have been suggested to be major contributing factors to the observed neurotoxicity in humans, motivating our study's proteome-wide screening approach to investigate its polypharmacology. Accordingly, we performed an in silico screen against 80,923 protein structures reported in the Protein Data Bank. The resulting list of 284 unique human interactors was further refined using target-disease association analyses to a subset of proteins previously linked to neurological, intracranial, inflammatory, hemorrhagic or clotting processes and/or diseases. Eleven proteins were identified as potential targets of BIA 10-2474, and the two highest-scoring proteins, Factor VII and thrombin, both essential blood-clotting factors, were predicted to be inhibited by BIA 10-2474 and suggest a plausible mechanism of toxicity. Once this small molecule becomes commercially available, future studies will be conducted to evaluate the predicted inhibitory effect of BIA 10-2474 on blood clot formation specifically in the brain.

AlignOT: An Optimal Transport Based Algorithm for Fast 3D Alignment With Applications to Cryogenic Electron Microscopy Density Maps.

Aligning electron density maps from Cryogenic electron microscopy (cryo-EM) is a first key step for studying multiple conformations of a biomolecule. As this step remains costly and challenging, with standard alignment tools being potentially stuck in local minima, we propose here a new procedure, called AlignOT, which relies on the use of computational optimal transport (OT) to align EM maps in 3D space. By embedding a fast estimation of OT maps within a stochastic gradient descent algorithm, our method searches for a rotation that minimizes the Wasserstein distance between two maps, represented as point clouds. We quantify the impact of various parameters on the precision and accuracy of the alignment, and show that AlignOT can outperform the standard local alignment methods, with an increased range of rotation angles leading to proper alignment. We further benchmark AlignOT on various pairs of experimental maps, which account for different types of conformational heterogeneities and geometric properties. As our experiments show good performance, we anticipate that our method can be broadly applied to align 3D EM maps.

Application of transport-based metric for continuous interpolation between cryo-EM density maps.

Cryogenic electron microscopy (cryo-EM) has become widely used for the past few years in structural biology, to collect single images of macromolecules "frozen in time". As this technique facilitates the identification of multiple conformational states adopted by the same molecule, a direct product of it is a set of 3D volumes, also called EM maps. To gain more insights on the possible mechanisms that govern transitions between different states, and hence the mode of action of a molecule, we recently introduced a bioinformatic tool that interpolates and generates morphing trajectories joining two given EM maps. This tool is based on recent advances made in optimal transport, that allow efficient evaluation of Wasserstein barycenters of 3D shapes. As the overall performance of the method depends on various key parameters, including the sensitivity of the regularization parameter, we performed various numerical experiments to demonstrate how MorphOT can be applied in different contexts and settings. Finally, we discuss current limitations and further potential connections between other optimal transport theories and the conformational heterogeneity problem inherent with cryo-EM data.

Structure and intrinsic disorder in protein autoinhibition.

Autoinhibition plays a significant role in the regulation of many proteins. By analyzing autoinhibited proteins, we demonstrate that these proteins are enriched in intrinsic disorder because of the properties of their inhibitory modules (IMs). A comparison of autoinhibited proteins with structured and intrinsically disordered IMs revealed that in the latter group (1) multiple phosphorylation sites are highly abundant; (2) splice variants occur in greater number than in their structured cousins; and (3) activation is often associated with changes in secondary structure in the IM. Analyses of families of autoinhibited proteins revealed that the levels of disorder in IMs can vary significantly throughout homologous proteins, whereas residues located at the interfaces between the IMs and inhibited domains are conserved. Our findings suggest that intrinsically disordered IMs provide advantages over structured ones that are likely to be exploited in the fine-tuning of the equilibrium between active and inactive states of autoinhibited proteins.