The Rosetta software suite for macromolecular modeling, docking, and design is widely used in pharmaceutical, industrial, academic, non-profit, and government laboratories. Despite its broad modeling capabilities, Rosetta remains consistently among leading software suites when compared to other methods created for highly specialized protein modeling and design tasks. Developed for over two decades by a global community of over 60 laboratories, Rosetta has undergone multiple refactorings, and now comprises over three million lines of code. Here we discuss methods developed in the last five years in Rosetta, involving the latest protocols for structure prediction; protein-protein and protein-small molecule docking; protein structure and interface design; loop modeling; the incorporation of various types of experimental data; modeling of peptides, antibodies and proteins in the immune system, nucleic acids, non-standard chemistries, carbohydrates, and membrane proteins. We briefly discuss improvements to the energy function, user interfaces, and usability of the software. Rosetta is available at www.rosettacommons.org.

Recent massive increases in the number of sequences available in public databases challenges current experimental approaches to determining protein function. These methods are limited by both the large scale of these sequences databases and the diversity of protein functions. We present a deep learning Graph Convolutional Network (GCN) trained on sequence and structural data and evaluate it on~40k proteins with known structures and functions from the Protein Data Bank (PDB). Our GCN predicts functions more accurately than Convolutional Neural Networks trained on sequence data alone and competing methods. Feature extraction via a language model removes the need for constructing multiple sequence alignments or feature engineering. Our model learns general structure-function relationships by robustly predicting functions of proteins with ≤ 30% sequence identity to the training set. Using class activation mapping, we can automatically identify structural regions at the residue-level that lead to each function prediction for every protein confidently predicted, advancing site-specific function prediction. De-noising inherent in the trained model allows an only minor drop in performance when structure predictions are used, including multiple de novo protocols. We use our method to annotate all proteins in the PDB, making several new confident function predictions spanning both fold and function trees.

The rapid increase in the number of proteins in sequence databases and the diversity of their functions challenge computational approaches for automated function prediction. Here, we introduce DeepFRI, a Graph Convolutional Network for predicting protein functions by leveraging sequence features extracted from a protein language model and protein structures. It outperforms current leading methods and sequence-based Convolutional Neural Networks and scales to the size of current sequence repositories. Augmenting the training set of experimental structures with homology models allows us to significantly expand the number of predictable functions. DeepFRI has significant de-noising capability, with only a minor drop in performance when experimental structures are replaced by protein models. Class activation mapping allows function predictions at an unprecedented resolution, allowing site-specific annotations at the residue-level in an automated manner. We show the utility and high performance of our method by annotating structures from the PDB and SWISS-MODEL, making several new confident function predictions. DeepFRI is available as a webserver at https://beta.deepfri.flatironinstitute.org/.

Membrane proteins are critical functional molecules in the human body, constituting more than 30% of open reading frames in the human genome. Unfortunately, a myriad of difficulties in overexpression and reconstitution into membrane mimetics severely limit our ability to determine their structures. Computational tools are therefore instrumental to membrane protein structure prediction, consequently increasing our understanding of membrane protein function and their role in disease. Here, we describe a general framework facilitating membrane protein modeling and design that combines the scientific principles for membrane protein modeling with the flexible software architecture of Rosetta3. This new framework, called RosettaMP, provides a general membrane representation that interfaces with scoring, conformational sampling, and mutation routines that can be easily combined to create new protocols. To demonstrate the capabilities of this implementation, we developed four proof-of-concept applications for (1) prediction of free energy changes upon mutation; (2) high-resolution structural refinement; (3) protein-protein docking; and (4) assembly of symmetric protein complexes, all in the membrane environment. Preliminary data show that these algorithms can produce meaningful scores and structures. The data also suggest needed improvements to both sampling routines and score functions. Importantly, the applications collectively demonstrate the potential of combining the flexible nature of RosettaMP with the power of Rosetta algorithms to facilitate membrane protein modeling and design.

The determination of membrane protein (MP) structures has always trailed that of soluble proteins due to difficulties in their overexpression, reconstitution into membrane mimetics, and subsequent structure determination. The percentage of MP structures in the protein databank (PDB) has been at a constant 1-2% for the last decade. In contrast, over half of all drugs target MPs, only highlighting how little we understand about drug-specific effects in the human body. To reduce this gap, researchers have attempted to predict structural features of MPs even before the first structure was experimentally elucidated. In this review, we present current computational methods to predict MP structure, starting with secondary structure prediction, prediction of trans-membrane spans, and topology. Even though these methods generate reliable predictions, challenges such as predicting kinks or precise beginnings and ends of secondary structure elements are still waiting to be addressed. We describe recent developments in the prediction of 3D structures of both α-helical MPs as well as β-barrels using comparative modeling techniques, de novo methods, and molecular dynamics (MD) simulations. The increase of MP structures has (1) facilitated comparative modeling due to availability of more and better templates, and (2) improved the statistics for knowledge-based scoring functions. Moreover, de novo methods have benefitted from the use of correlated mutations as restraints. Finally, we outline current advances that will likely shape the field in the forthcoming decade.

Prediction of transmembrane spans and secondary structure from the protein sequence is generally the first step in the structural characterization of (membrane) proteins. Preference of a stretch of amino acids in a protein to form secondary structure and being placed in the membrane are correlated. Nevertheless, current methods predict either secondary structure or individual transmembrane states. We introduce a method that simultaneously predicts the secondary structure and transmembrane spans from the protein sequence. This approach not only eliminates the necessity to create a consensus prediction from possibly contradicting outputs of several predictors but bears the potential to predict conformational switches, i.e., sequence regions that have a high probability to change for example from a coil conformation in solution to an α-helical transmembrane state. An artificial neural network was trained on databases of 177 membrane proteins and 6048 soluble proteins. The output is a 3 × 3 dimensional probability matrix for each residue in the sequence that combines three secondary structure types (helix, strand, coil) and three environment types (membrane core, interface, solution). The prediction accuracies are 70.3% for nine possible states, 73.2% for three-state secondary structure prediction, and 94.8% for three-state transmembrane span prediction. These accuracies are comparable to state-of-the-art predictors of secondary structure (e.g., Psipred) or transmembrane placement (e.g., OCTOPUS). The method is available as web server and for download at www.meilerlab.org.

The translation of personal genomics to precision medicine depends on the accurate interpretation of the multitude of genetic variants observed for each individual. However, even when genetic variants are predicted to modify a protein, their functional implications may be unclear. Many diseases are caused by genetic variants affecting important protein features, such as enzyme active sites or interaction interfaces. The scientific community has catalogued millions of genetic variants in genomic databases and thousands of protein structures in the Protein Data Bank. Mapping mutations onto three-dimensional (3D) structures enables atomic-level analyses of protein positions that may be important for the stability or formation of interactions; these may explain the effect of mutations and in some cases even open a path for targeted drug development. To accelerate progress in the integration of these data types, we held a two-day Gene Variation to 3D (GVto3D) workshop to report on the latest advances and to discuss unmet needs. The overarching goal of the workshop was to address the question: what can be done together as a community to advance the integration of genetic variants and 3D protein structures that could not be done by a single investigator or laboratory? Here we describe the workshop outcomes, review the state of the field, and propose the development of a framework with which to promote progress in this arena. The framework will include a set of standard formats, common ontologies, a common application programming interface to enable interoperation of the resources, and a Tool Registry to make it easy to find and apply the tools to specific analysis problems. Interoperability will enable integration of diverse data sources and tools and collaborative development of variant effect prediction methods.Electronic supplementary materialThe online version of this article (doi:10.1186/s13073-017-0509-y) contains supplementary material, which is available to authorized users.

Genetics and pharmacology are often seen as two distinct approaches to interrogating, elucidating, and manipulating biological systems. The former is renowned for its precision whereas the latter for its fast kinetics, reversibility, and practicality. Here, we show that both can be joined as "tethered pharmacology", wherein a genetically programmed bioconjugation site provides selectivity and a tethered pharmacophore provides function. The speed of onset, and especially cessation, of pharmacological activity can be greatly enhanced by incorporating photoswitches and using light as the trigger ("tethered photopharmacology"). Genetically encoded, tethered photopharmacology is a variant of optogenetics and could even play a role in medicine wherever gene therapy is viable. However, gene therapy may not be necessary if sufficiently selective tethering strategies that operate on wild-type receptors can be developed.