The combination of neural networks and quantum Monte Carlo methods has arisen as a promising path forward for highly accurate electronic structure calculations. Previous proposals have combined equivariant neural network layers with a final antisymmetric layer in order to satisfy the antisymmetry requirements of the electronic wavefunction. However, to date it is unclear if one can represent antisymmetric functions of physical interest, and it is difficult to precisely measure the expressiveness of the antisymmetric layer. This work attempts to address this problem by introducing explicitly antisymmetrized universal neural network layers. This approach has a computational cost which increases factorially with respect to the system size, but we are nonetheless able to apply it to small systems to better understand how the structure of the antisymmetric layer affects its performance. We first introduce a generic antisymmetric (GA) neural network layer, which we use to replace the entire antisymmetric layer of the highly accurate ansatz known as the FermiNet. We demonstrate that the resulting FermiNet-GA architecture can yield effectively the exact ground state energy for small atoms and molecules. We then consider a factorized antisymmetric (FA) layer which more directly generalizes the FermiNet by replacing the products of determinants with products of antisymmetrized neural networks. We find, interestingly, that the resulting FermiNet-FA architecture does not outperform the FermiNet. This strongly suggests that the sum of products of antisymmetries is a key limiting aspect of the FermiNet architecture. To explore this further, we investigate a slight modification of the FermiNet, called the full determinant mode, which replaces each product of determinants with a single combined determinant. We find that the full single-determinant FermiNet closes a large part of the gap between the standard single-determinant FermiNet and FermiNet-GA on small atomic and molecular problems. Surprisingly, on the nitrogen molecule at a dissociating bond length of 4.0 Bohr, the full single-determinant FermiNet can significantly outperform the largest standard FermiNet calculation with 64 determinants, yielding an energy within 0.4 kcal/mol of the best available computational benchmark.

MotivationWe present Faucet, a two-pass streaming algorithm for assembly graph construction. Faucet builds an assembly graph incrementally as each read is processed. Thus, reads need not be stored locally, as they can be processed while downloading data and then discarded. We demonstrate this functionality by performing streaming graph assembly of publicly available data, and observe that the ratio of disk use to raw data size decreases as coverage is increased.ResultsFaucet pairs the de Bruijn graph obtained from the reads with additional meta-data derived from them. We show these metadata—coverage counts collected at junction k-mers and connections bridging between junction pairs—contain most salient information needed for assembly, and demonstrate they enable cleaning of metagenome assembly graphs, greatly improving contiguity while maintaining accuracy. We compared Fauceted resource use and assembly quality to state of the art metagenome assemblers, as well as leading resource-efficient genome assemblers. Faucet used orders of magnitude less time and disk space than the specialized metagenome assemblers MetaSPAdes and Megahit, while also improving on their memory use; this broadly matched performance of other assemblers optimizing resource efficiency—namely, Minia and LightAssembler. However, on metagenomes tested, Faucet,o outputs had 14–110% higher mean NGA50 lengths compared with Minia, and 2- to 11-fold higher mean NGA50 lengths compared with LightAssembler, the only other streaming assembler available.Availability and implementationFaucet is available at https://github.com/Shamir-Lab/Faucet Supplementary information Supplementary data are available at Bioinformatics online.

Motivation:We present Faucet, a 2-pass streaming algorithm for assembly graph construction. Faucet builds an assembly graph incrementally as each read is processed. Thus, reads need not be stored locally, as they can be processed while downloading data and then discarded. We demonstrate this functionality by performing streaming graph assembly of publicly available data, and observe that the ratio of disk use to raw data size decreases as coverage is increased. Results:Faucet pairs the de Bruijn graph obtained from the reads with additional meta-data derived from them. We show these metadata -coverage counts collected at junction k-mers and connections bridging between junction pairs -contain most salient information needed for assembly, and demonstrate they enable cleaning of metagenome assembly graphs, greatly improving contiguity while maintaining accuracy. We compared Faucet's resource use and assembly quality to state of the art metagenome assemblers, as well as leading resource-efficient genome assemblers. Faucet used orders of magnitude less time and disk space than the specialized metagenome assemblers MetaSPAdes and Megahit, while also improving on their memory use; this broadly matched performance of other assemblers optimizing resource efficiency -namely, Minia and LightAssembler. However, on metagenomes tested, Faucet's outputs had 14-110% higher mean NGA50 lengths compared to Minia, and 2-11-fold higher mean NGA50 lengths compared to LightAssembler, the only other streaming assembler available.