HERMES: Holographic Equivariant neuRal network model for Mutational Effect and Stability prediction.

Predicting the stability and fitness effects of amino acid mutations in proteins is a cornerstone of biological discovery and engineering. Various experimental techniques have been developed to measure mutational effects, providing us with extensive datasets across a diverse range of proteins. By training on these data, traditional computational modeling and more recent machine learning approaches have advanced significantly in predicting mutational effects. Here, we introduce HERMES, a 3D rotationally equivariant structure-based neural network model for mutational effect and stability prediction. Pre-trained to predict amino acid propensity from its surrounding 3D structure, HERMES can be fine-tuned for mutational effects using our open-source code. We present a suite of HERMES models, pre-trained with different strategies, and fine-tuned to predict the stability effect of mutations. Benchmarking against other models shows that HERMES often outperforms or matches their performance in predicting mutational effect on stability, binding, and fitness. HERMES offers versatile tools for evaluating mutational effects and can be fine-tuned for specific predictive objectives.

H-Packer: Holographic Rotationally Equivariant Convolutional Neural Network for Protein Side-Chain Packing.

Accurately modeling protein 3D structure is essential for the design of functional proteins. An important sub-task of structure modeling is protein side-chain packing: predicting the conformation of side-chains (rotamers) given the protein's backbone structure and amino-acid sequence. Conventional approaches for this task rely on expensive sampling procedures over hand-crafted energy functions and rotamer libraries. Recently, several deep learning methods have been developed to tackle the problem in a data-driven way, albeit with vastly different formulations (from image-to-image translation to directly predicting atomic coordinates). Here, we frame the problem as a joint regression over the side-chains' true degrees of freedom: the dihedral χ angles. We carefully study possible objective functions for this task, while accounting for the underlying symmetries of the task. We propose Holographic Packer (H-Packer), a novel two-stage algorithm for side-chain packing built on top of two light-weight rotationally equivariant neural networks. We evaluate our method on CASP13 and CASP14 targets. H-Packer is computationally efficient and shows favorable performance against conventional physics-based algorithms and is competitive against alternative deep learning solutions.

A new, cost-effective, battery-powered aspirator for adult mosquito collections.

We report the development of a new mosquito aspirator with the same aspiration capacity (airflow) of the CDC Backpack Aspirator (CDC-BP), but smaller and lighter (0.8 kg without battery), less expensive (US$45-70), easier to build, and compatible with the use of telescoping extension poles to access hard-to-reach locations. The performance of this new aspirator, named "Prokopack," was compared with the CDC-BP in laboratory settings as well as in paired collections in combined sewer overflow (CSO) tunnels in Atlanta, GA, and indoor mosquito collections in Iquitos, Peru. The difference in suction power between both aspirators (average, 0.29-0.43 m/s) was negligible. However, 2.3 times more mosquitoes were collected using the Prokopack in the upper wall (>1.5 m) and ceilings of CSO tunnels than with the CDC-BP in lower walls. Indoor collection in Iquitos yielded significantly more total mosquito numbers [including Culex pipiens complex, Culex (melanoconion) sp., and Mansonia sp.] and Aedes aegypti (L.) in the Prokopack than in the CDC-BP. Our results demonstrate the effectiveness of the Prokopack to collect different mosquito species in different epidemiological settings.

Associate in science degree education programs: organization, structure, and curriculum.

After years of discussion, debate, and study, the respiratory care curriculum has evolved to a minimum of an associate degree for entry into practice. Although programs are at liberty to offer the entry-level or advanced level associate degree, most are at the advanced level. The most popular site for sponsorship of the associate degree in respiratory care is the community college. The basis for community college sponsorship seems to be its comprehensive curriculum, which focuses on a strong academic foundation in writing, communication, and the basic sciences as well as supporting a career-directed focus in respiratory care. Issues facing the community college are tied to literacy, outcomes, assessment, placement,cooperation with the community, partnerships with industry, and articulation arrangements with granting institutions granting baccalaureate degrees. Community colleges must produce a literate graduate capable of thriving in an information-saturated society. Assessment and placement will intensify as the laissez-faire attitudes toward attendance and allowing students to select courses without any accountability and evaluation of outcome become less acceptable. Students will be required to demonstrate steady progress toward established outcomes. Maintaining relations and cooperation with the local community and the health care industry will continue to be a prominent role for the community college. The challenge facing associate degree education in respiratory care at the community college level is the ability to continue to meet the needs of an expanding professional scope of practice and to provide a strong liberal arts or general education core curriculum. The needs for a more demanding and expanding respiratory care curriculum and for a rich general education core curriculum have led to increased interest in baccalaureate and graduate degree education. The value of associate degree education at the community college level is well established. It is affordable, accessible, and responsive to the local health care industry it serves. It is likely to enjoy acceptance and popularity until its curricular limitations and time constraints no longer allow it to meet the needs of the respiratory care profession.