Protein sequences contain rich information about protein evolution, fitness landscapes, and stability. Here we investigate how latent space models trained using variational auto-encoders can infer these properties from sequences. Using both simulated and real sequences, we show that the low dimensional latent space representation of sequences, calculated using the encoder model, captures both evolutionary and ancestral relationships between sequences. Together with experimental fitness data and Gaussian process regression, the latent space representation also enables learning the protein fitness landscape in a continuous low dimensional space. Moreover, the model is also useful in predicting protein mutational stability landscapes and quantifying the importance of stability in shaping protein evolution. Overall, we illustrate that the latent space models learned using variational auto-encoders provide a mechanism for exploration of the rich data contained in protein sequences regarding evolution, fitness and stability and hence are well-suited to help guide protein engineering efforts.

Recently, several experimental techniques have emerged for probing RNA structures based on high-throughput sequencing. However, most secondary structure prediction tools that incorporate probing data are designed and optimized for particular types of experiments. For example, RNAstructure-Fold is optimized for SHAPE data, while SeqFold is optimized for PARS data. Here, we report a new RNA secondary structure prediction method, restrained MaxExpect (RME), which can incorporate multiple types of experimental probing data and is based on a free energy model and an MEA (maximizing expected accuracy) algorithm. We first demonstrated that RME substantially improved secondary structure prediction with perfect restraints (base pair information of known structures). Next, we collected structure-probing data from diverse experiments (e.g. SHAPE, PARS and DMS-seq) and transformed them into a unified set of pairing probabilities with a posterior probabilistic model. By using the probability scores as restraints in RME, we compared its secondary structure prediction performance with two other well-known tools, RNAstructure-Fold (based on a free energy minimization algorithm) and SeqFold (based on a sampling algorithm). For SHAPE data, RME and RNAstructure-Fold performed better than SeqFold, because they markedly altered the energy model with the experimental restraints. For high-throughput data (e.g. PARS and DMS-seq) with lower probing efficiency, the secondary structure prediction performances of the tested tools were comparable, with performance improvements for only a portion of the tested RNAs. However, when the effects of tertiary structure and protein interactions were removed, RME showed the highest prediction accuracy in the DMS-accessible regions by incorporating in vivo DMS-seq data.

The multistate Bennett acceptance ratio method (MBAR) and unbinned weighted histogram analysis method (UWHAM) are widely employed approaches to calculate relative free energies of multiple thermodynamic states that gain statistical precision by employing free energy contributions from configurations sampled at each of the simulated λ states. With the increasing availability of high throughput computing resources, a large number of configurations can be sampled from hundreds or even thousands of states. Combining sampled configurations from all states to calculate relative free energies requires the iterative solution of large scale MBAR/ UWHAM equations. In the current work, we describe the development of a fast solver to iteratively solve these large scale MBAR/UWHAM equations utilizing our previous findings that the MBAR/UWHAM equations can be derived as a Rao-Blackwell estimator. The solver is implemented and distributed as a Python module called FastMBAR. Our benchmark results show that FastMBAR is more than 2 times faster than the currently, and widely used solver, pymbar, when it runs on a central processing unit (CPU) and more than 100 times faster than pymbar when it runs on a graphical processing unit (GPU). The significant speedup achieved by FastMBAR running on a GPU is useful not only for solving large scale MBAR/UWHAM equations but also for estimating uncertainty of calculated free energies using bootstrapping where the MBAR/ UWHAM equations need to be solved multiple times.

Fast Fourier transform (FFT)-based protein ligand docking together with parallel simulated annealing for both rigid and flexible receptor docking are implemented on graphical processing unit (GPU) accelerated platforms to significantly enhance the throughput of the CDOCKER and flexible CDOCKER  the docking algorithms in the CHARMM program for biomolecule modeling. The FFT-based approach for docking, first applied in protein–protein docking to efficiently search for the binding position and orientation of proteins, is adapted here to search ligand translational and rotational spaces given a ligand conformation in protein–ligand docking. Running on GPUs, our implementation of FFT docking in CDOCKER achieves a 15 000 fold speedup in the ligand translational and rotational space search in protein–ligand docking problems. With this significant speedup it becomes practical to exhaustively search ligand translational and rotational space when docking a rigid ligand into a protein receptor. We demonstrate in this paper that this provides an efficient way to calculate an upper bound for docking accuracy in the assessment of scoring functions for protein–ligand docking, which can be useful for improving scoring functions. The parallel molecular dynamics (MD) simulated annealing, also running on GPUs, aims to accelerate the search algorithm in CDOCKER by running MD simulated annealing in parallel on GPUs. When utilized as part of the general CDOCKER docking protocol, acceleration in excess of 20 times is achieved. With this acceleration, we demonstrate that the performance of CDOCKER for redocking is significantly improved compared with three other popular protein–ligand docking programs on two widely used protein ligand complex data sets: the Astex diverse set and the SB2012 test set. The flexible CDOCKER is similarly improved by the parallel MD simulated annealing on GPUs. Based on the results presented here, we suggest that the accelerated CDOCKER platform provides a highly competitive docking engine for both rigid-receptor and flexible-receptor docking studies and will further facilitate continued improvement in the physics-based scoring function employed in CDOCKER docking studies.