Efficient sampling from the Boltzmann distribution given its energy function is a key challenge for modeling complex physical systems such as molecules. Boltzmann Generators address this problem by leveraging continuous normalizing flows to transform a simple prior into a distribution that can be reweighted to match the target using sample likelihoods. Despite the elegance of this approach, obtaining these likelihoods requires computing costly Jacobians during integration, which is impractical for large molecular systems. To overcome this difficulty, we train an energy-based model (EBM) to approximate likelihoods using both noise contrastive estimation (NCE) and score matching, which we show outperforms the use of either objective in isolation. On 2D synthetic systems where failure can be easily visualized, NCE improves mode weighting relative to score matching alone. On alanine dipeptide, our method yields free energy profiles and energy distributions that closely match those obtained using exact likelihoods while achieving $100\times$ faster inference. By training on multiple dipeptide systems, we show that our approach also exhibits effective transfer learning, generalizing to new systems at inference time and achieving at least a $6\times$ speedup over standard MD with only a bit of fine-tuning. While many recent efforts in generative modeling have prioritized models with fast sampling, our work demonstrates the design of models with accelerated likelihoods, enabling the application of reweighting schemes that ensure unbiased Boltzmann statistics at scale. Our code is available at https://github.com/RishalAggarwal/BoltzNCE.

UNLABELLED: 3Dmol.js is a modern, object-oriented JavaScript library that uses the latest web technologies to provide interactive, hardware-accelerated three-dimensional representations of molecular data without the need to install browser plugins or Java. 3Dmol.js provides a full featured API for developers as well as a straightforward declarative interface that lets users easily share and embed molecular data in websites. AVAILABILITY AND IMPLEMENTATION: 3Dmol.js is distributed under the permissive BSD open source license. Source code and documentation can be found at http://3Dmol.csb.pitt.edu CONTACT: [email protected].

MOTIVATION: Protein-protein interactions (PPIs) are a promising, but challenging target for pharmaceutical intervention. One approach for addressing these difficult targets is the rational design of small-molecule inhibitors that mimic the chemical and physical properties of small clusters of key residues at the protein-protein interface. The identification of appropriate clusters of interface residues provides starting points for inhibitor design and supports an overall assessment of the susceptibility of PPIs to small-molecule inhibition. RESULTS: We extract Small-Molecule Inhibitor Starting Points (SMISPs) from protein-ligand and protein-protein complexes in the Protein Data Bank (PDB). These SMISPs are used to train two distinct classifiers, a support vector machine and an easy to interpret exhaustive rule classifier. Both classifiers achieve better than 70% leave-one-complex-out cross-validation accuracy and correctly predict SMISPs of known PPI inhibitors not in the training set. A PDB-wide analysis suggests that nearly half of all PPIs may be susceptible to small-molecule inhibition.

Bioinformatics (2011) 28(6), 784–791

Instruction selection is a key component of code generation. High quality instruction selection is of particular importance in the embedded space where complex instruction sets are common and code size is a prime concern. Although instruction selection on tree expressions is a well understood and easily solved problem, instruction selection on directed acyclic graphs is NP-complete. In this paper we present NOLTIS, a near-optimal, linear time instruction selection algorithm for DAG expressions. NOLTIS is easy to implement, fast, and effective with a demonstrated average code size improvement of 5.1% compared to the traditional tree decomposition and tiling approach.

This paper describes a global progressive register allocator, a register allocator that uses an expressive model of the register allocation problem to quickly find a good allocation and then progressively find better allocations until a provably optimal solution is found or a preset time limit is reached. The key contributions of this paper are an expressive model of global register allocation based on multicommodity network flows that explicitly represents spill code optimization, register preferences, copy insertion, and constant rematerialization; two fast, but effective, heuristic allocators based on this model; and a more elaborate progressive allocator that uses Lagrangian relaxation to compute the optimality of its allocations. Our progressive allocator demonstrates code size improvements as large as 16.75% compared to a traditional graph allocator. On average, we observe an initial improvement of 3.47%, which increases progressively to 6.84% as more time is permitted for compilation.

Register allocation is one of the most important optimizations a compiler performs. Conventional graph-coloring based register allocators are fast and do well on regular, RISC-like, architectures, but perform poorly on irregular, CISC-like, architectures with few registers and non-orthogonal instruction sets. At the other extreme, optimal register allocators based on integer linear programming are capable of fully modeling and exploiting the peculiarities of irregular architectures but do not scale well. We introduce the idea of a progressive allocator. A progressive allocator finds an initial allocation of quality comparable to a conventional allocator, but as more time is allowed for computation the quality of the allocation approaches optimal. This paper presents a progressive register allocator which uses a multi-commodity network flow model to elegantly represent the intricacies of irregular architectures. We evaluate our allocator as a substitute for gcc 's local register allocation pass.

Recent omnidirectional camera designs aim a conventional camera at a mirror that expands the camera's field of view. This wide view is ideal for three-dimensional vision tasks such as motion estimation and obstacle detection, but these applications require an accurate model of the imaging process. We present a full model of the imaging process, which includes the rotation and translation between the camera and mirror, and an algorithm that determines this relative position from observations of known points in a single image. We present tests of the model and of the calibration procedure for various amounts of misalignment between the mirror and camera. These tests show that the algorithm recovers the correct relative position, and that by using the full model, accurate shape-from-motion and stereo matching are possible even if the camera and mirror are severely misaligned.