Search for: All records

Protein language models (pLMs) have emerged as potent tools for predicting and designing protein structure and function, and the degree to which these models fundamentally understand the inherent biophysics of protein structure stands as an open question. Motivated by a finding that pLM-based structure predictors erroneously predict nonphysical structures for protein isoforms, we investigated the nature of sequence context needed for contact predictions in the pLM Evolutionary Scale Modeling (ESM-2). We demonstrate by use of a “categorical Jacobian” calculation that ESM-2 stores statistics of coevolving residues, analogously to simpler modeling approaches like Markov Random Fields and Multivariate Gaussian models. We further investigated how ESM-2 “stores” information needed to predict contacts by comparing sequence masking strategies, and found that providing local windows of sequence information allowed ESM-2 to best recover predicted contacts. This suggests that pLMs predict contacts by storing motifs of pairwise contacts. Our investigation highlights the limitations of current pLMs and underscores the importance of understanding the underlying mechanisms of these models. 

The Seebeck coefficient of Ni–Fe, the metallic alloy proposed for active cooling applications, shows a higher Seebeck coefficient compared to its constituent elements and demonstrates agreement between ML predictions and experimental results. 

The first investigation on the properties of intermetallic YbZn₁₁for active cooling: an unconventional thermoelectric application. 

Low-power computer vision on embedded devices has many applications. This paper describes a low-power technique for the object re-identification (reID) problem: matching a query image against a gallery of previously-seen images. State-of-the-art techniques rely on large, computationally-intensive Deep Neural Networks (DNNs). We propose a novel hierarchical DNN architecture that uses attribute labels in the training dataset to perform efficient object reID. At each node in the hierarchy, a small DNN identifies a different attribute of the query image. The small DNN at each leaf node is specialized to re-identify a subset of the gallery---only the images with the attributes identified along the path from the root to a leaf. Thus, a query image is re-identified accurately after processing with a few small DNNs. We compare our method with state-of-the-art object reID techniques. With a ~4% loss in accuracy, our approach realizes significant resource savings: 74% less memory, 72% fewer operations, and 67% lower query latency, yielding 65% less energy consumption. 

Abstract Cas9 has made a wide range of genomic manipulation possible. However, its specificity continues to be a challenge. Non-canonical gRNAs and new engineered variants of Cas9 have been developed to improve specificity, but at the cost of the on-target activity. DNA unwinding is a checkpoint before cleavage by Cas9, and was shown to be made more sensitive to sequence mismatches by specificity-enhancing mutations in engineered Cas9s. Here we performed single-molecule FRET-based DNA unwinding experiments using various combinations of non-canonical gRNAs and different Cas9s. All engineered Cas9s were less promiscuous than wild type when canonical gRNA was used, but HypaCas9 had much-reduced on-target unwinding. Cas9-HF1 and eCas9 showed the best balance between low promiscuity and high on-target activity with canonical gRNA. When extended gRNAs with one or two non-matching guanines added to the 5′ end were used, Sniper1-Cas9 showed the lowest promiscuity while maintaining high on-target activity. Truncated gRNA generally reduced unwinding and adding a non-matching guanine to the 5′ end of gRNA influenced unwinding in a sequence-context dependent manner. Our results are consistent with cell-based cleavage data and provide a mechanistic understanding of how various Cas9/gRNA combinations perform in genome engineering.