Ross Altman

Recent work in applying deep learning models has demonstrated that endophenotypes, such as RNA transcript abundance, can be predicted from an organism's regulatory DNA. However, due to the vast amount of labelled data required to train previous types of deep learning models, this work has been constrained to species with large amounts of data labelled for a particular task. Here, we present FloraBERT, a transfer-learning based deep learning model that is able to improve predictions of gene… Show more

Recent work in applying deep learning models has demonstrated that endophenotypes, such as RNA transcript abundance, can be predicted from an organism's regulatory DNA. However, due to the vast amount of labelled data required to train previous types of deep learning models, this work has been constrained to species with large amounts of data labelled for a particular task. Here, we present FloraBERT, a transfer-learning based deep learning model that is able to improve predictions of gene expression in a single target species, and it does so by exploiting cross-species genomic information in the form of genome assemblies from all of plantae. FloraBERT significantly outperforms simple bag-of-k-mers baseline models and achieves comparable performance to prior work that concerns less complex species. Furthermore, investigation of the learned parameters of FloraBERT reveals that the training process encodes biologically salient information, such as taxonomic similarity between species and positional relevance of nucleotides within a promoter. To facilitate future research, we have made the source code and model weights publicly available on https://github.com/benlevyx/florabert. Show less

We establish an orientifold Calabi-Yau threefold database for h1,1(X) ≤ 6 by considering non-trivial ℤ2 divisor exchange involutions, using a toric Calabi-Yau database (http://www.rossealtman.com/toriccy/). We first determine the topology for each individual divisor (Hodge diamond), then identify and classify the proper involutions which are globally consistent across all disjoint phases of the Kähler cone for each unique geometry. Each of the proper involutions will result in an orientifold… Show more

We establish an orientifold Calabi-Yau threefold database for h1,1(X) ≤ 6 by considering non-trivial ℤ2 divisor exchange involutions, using a toric Calabi-Yau database (http://www.rossealtman.com/toriccy/). We first determine the topology for each individual divisor (Hodge diamond), then identify and classify the proper involutions which are globally consistent across all disjoint phases of the Kähler cone for each unique geometry. Each of the proper involutions will result in an orientifold Calabi-Yau manifold. Then we clarify all possible fixed loci under the proper involution, thereby determining the locations of different types of O-planes. It is shown that under the proper involutions, one typically ends up with a system of O3/O7-planes, and most of these will further admit naive Type IIB string vacua. The geometries with freely acting involutions are also determined. We further determine the splitting of the Hodge numbers into odd/even parity in the orbifold limit. The final result is a class of orientifold Calabi-Yau threefolds with non-trivial odd class cohomology ((X/σ*) ≠ 0). Show less

We provide the first estimate of the number of fine, regular, star triangulations of the four-dimensional reflexive polytopes, as classified by Kreuzer and Skarke (KS). This provides an upper bound on the number of Calabi-Yau threefold hypersurfaces in toric varieties. The estimate is performed with deep learning, specifically the novel equation learner (EQL) architecture. We demonstrate that EQL networks accurately predict numbers of triangulations far beyond the h1,1 training region, allowing… Show more

We provide the first estimate of the number of fine, regular, star triangulations of the four-dimensional reflexive polytopes, as classified by Kreuzer and Skarke (KS). This provides an upper bound on the number of Calabi-Yau threefold hypersurfaces in toric varieties. The estimate is performed with deep learning, specifically the novel equation learner (EQL) architecture. We demonstrate that EQL networks accurately predict numbers of triangulations far beyond the h1,1 training region, allowing for reliable extrapolation. We estimate that number of triangulations in the KS dataset is 10^10,505, dominated by the polytope with the highest h1,1 value. Show less

In previous work, we have commenced the task of unpacking the 473,800,776 reflexive polyhedra by Kreuzer and Skarke into a database of Calabi-Yau threefolds. In this paper, following a pedagogical introduction, we present a new algorithm to isolate Swiss cheese solutions characterized by "holes," or small 4-cycles, descending from the toric divisors inherent to the original four dimensional reflexive polyhedra. Implementing these methods, we find 2,268 explicit Swiss cheese manifolds, over half… Show more

In previous work, we have commenced the task of unpacking the 473,800,776 reflexive polyhedra by Kreuzer and Skarke into a database of Calabi-Yau threefolds. In this paper, following a pedagogical introduction, we present a new algorithm to isolate Swiss cheese solutions characterized by "holes," or small 4-cycles, descending from the toric divisors inherent to the original four dimensional reflexive polyhedra. Implementing these methods, we find 2,268 explicit Swiss cheese manifolds, over half of which have h11=6. Many of our solutions have multiple large cycles. Such Swiss cheese geometries facilitate moduli stabilization in string compactifications and provide flat directions for cosmological inflation. Show less

Kreuzer and Skarke famously produced the largest known database of Calabi-Yau threefolds by providing a complete construction of all 473,800,776 reflexive polyhedra that exist in four dimensions. These polyhedra describe the singular limits of ambient toric varieties in which Calabi-Yau threefolds can exist as hypersurfaces. In this paper, we review how to extract topological and geometric information about Calabi-Yau threefolds using the toric construction, and we provide, in a companion… Show more

Kreuzer and Skarke famously produced the largest known database of Calabi-Yau threefolds by providing a complete construction of all 473,800,776 reflexive polyhedra that exist in four dimensions. These polyhedra describe the singular limits of ambient toric varieties in which Calabi-Yau threefolds can exist as hypersurfaces. In this paper, we review how to extract topological and geometric information about Calabi-Yau threefolds using the toric construction, and we provide, in a companion online database (http://nuweb1.neu.edu/cydatabase/), a detailed inventory of these quantities which are of interest to physicists. Many of the singular ambient spaces described by the Kreuzer-Skarke list can be smoothed out into multiple distinct toric ambient spaces describing different Calabi-Yau threefolds. We provide a list of the different Calabi-Yau threefolds which can be obtained from each polytope, up to current computational limits. We then give the details of a variety of quantities associated to each of these Calabi-Yau such as Chern classes, intersection numbers, and the Kahler and Mori cones, in addition to the Hodge data. This data forms a useful starting point for a number of physical applications of the Kreuzer-Skarke list. Show less