Quantitative Biology

We present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction tasks, named MEG (Molecular Explanation Generator). We generate informative counterfactual explanations for a specific prediction under the form of (valid) compounds with high structural similarity and different predicted properties. We discuss preliminary results showing how the model can convey non-ML experts with key insights into the learning model focus in the neighborhood of a molecule.

In this paper, we ask if it is possible to increase the interpretability in multivariate analysis by aligning and projecting covariates onto comparative subspaces. We demonstrate our method as well as the interpretative power of PLS decomposed models and how robust interpretability can lead to quantitative insights. We discuss the statistical properties of the PLS weights, p -values associated with specific axes, as well as their alignment properties. The applicability of this approach within life science is also demonstrated by applying it to three use cases of publically available datasets. Further we present hierarchical pathway enrichment results stemming from aligned p -values, which are compared with results derived from enrichment analysis, as an external validation of our method. We find that the method can uncover known results from genomics for all of the studied use cases, i.e. microarray data from multiple sclerosis and diabetes patients as well as RNA sequencing data from breast cancer patients.

By means of an experimental dataset, we use deep learning to implement an RGB extrapolation of emotions associated to color, and do a mathematical study of the results obtained through this neural network. In particular, we see that males typically associate a given emotion with darker colors while females with brighter colors. A similar trend was observed with older people and associations to lighter colors. Moreover, through our classification matrix, we identify which colors have weak associations to emotions and which colors are typically confused with other colors.

Genomics is changing our understanding of humans, evolution, diseases, and medicines to name but a few. As sequencing technology is developed collecting DNA sequences takes less time thereby generating more genetic data every day. Today the rate of generating genetic data is outpacing the rate of computation power growth. Current sequencing machines can sequence 50 humans genome per day; however, aligning the read sequences against a reference genome and assembling the genome will take 1300 CPU hours. The main step in constructing the genome is aligning the reads against a reference genome. Numerous accelerators have been proposed to accelerate the DNA alignment process. Providing massive parallelism, FPGA-based accelerators have shown great performance in accelerating DNA alignment algorithms. Additionally, FPGA-based accelerators provide better energy efficiency than general-purpose processors. In this survey, we introduce three main DNA alignment algorithms and FPGA-based implementation of these algorithms to accelerate the DNA alignment. We also, compare these three alignment categories and show how accelerators are developing during the time.

A fundamental problem in computational biology is to find a suitable representation of the high-dimensional gene expression data that is consistent with the structural and functional properties of cell types, collectively called their phenotypes. This representation is often sought from a linear transformation of the original data, for the reasons of model interpretability and computational simplicity. Here we propose a novel method of linear dimensionality reduction to address this problem. This method, which we call factorized linear discriminant analysis (FLDA), seeks a linear transformation of gene expressions that varies highly with only one phenotypic feature and minimally with others. We further leverage our approach with a sparsity-based regularization algorithm, which selects a few genes important to a specific phenotypic feature or feature combination. We illustrated this approach by applying it to a single-cell transcriptome dataset of Drosophila T4/T5 neurons. A representation from FLDA captured structures in the data aligned with phenotypic features and revealed critical genes for each phenotype.

We present an automated method to track and identify neurons in C. elegans, called "fast Deep Learning Correspondence" or fDLC, based on the transformer network architecture. The model is trained once on empirically derived synthetic data and then predicts neural correspondence across held-out real animals via transfer learning. The same pre-trained model both tracks neurons across time and identifies corresponding neurons across individuals. Performance is evaluated against hand-annotated datasets, including NeuroPAL [1]. Using only position information, the method achieves 80.0% accuracy at tracking neurons within an individual and 65.8% accuracy at identifying neurons across individuals. Accuracy is even higher on a published dataset [2]. Accuracy reaches 76.5% when using color information from NeuroPAL. Unlike previous methods, fDLC does not require straightening or transforming the animal into a canonical coordinate system. The method is fast and predicts correspondence in 10 ms making it suitable for future real-time applications.

Purpose: Previously-developed Voxel Spread Function (VSF) method (Yablonskiy, et al, MRM, 2013;70:1283) provides means to correct artifacts induced by macroscopic magnetic field inhomogeneities in the images obtained by multi-Gradient-Recalled-Echo (mGRE) techniques. The goal of this study is to develop a library-driven approach for fast VSF implementation. Methods: The VSF approach describes the contribution of the magnetic field inhomogeneity effects on the mGRE signal decay in terms of the F-function calculated from mGRE phase and magnitude images. A pre-calculated library accounting for a variety of background field gradients caused by magnetic field inhomogeneities was used herein to speed up calculation of the F-function and to generate quantitative R2* maps from the mGRE data collected from two healthy volunteers. Results: As compared with direct calculation of the F-function based on a voxel-wise approach, the new library-driven method substantially reduces computational time from several hours to few minutes, while, at the same time, providing similar accuracy of R2* mapping. Conclusion: The new procedure proposed in this study provides a fast post-processing algorithm that can be incorporated in the quantitative analysis of mGRE data to account for background field inhomogeneity artifacts, thus can facilitate the applications of mGRE-based quantitative techniques in clinical practices.

Light-sheet fluorescence microscopy (LSFM) enables real-time whole-brain functional imaging in zebrafish larvae. Conventional one photon LSFM can however induce undesirable visual stimulation due to the use of visible excitation light. The use of two-photon (2P) excitation, employing near-infrared invisible light, provides unbiased investigation of neuronal circuit dynamics. However, due to the low efficiency of the 2P absorption process, the imaging speed of this technique is typically limited by the signal-to-noise-ratio. Here, we describe a 2P LSFM setup designed for non-invasive imaging that enables quintuplicating state-of-the-art volumetric acquisition rate of the larval zebrafish brain (5 Hz) while keeping low the laser intensity on the specimen. We applied our system to the study of pharmacologically-induced acute seizures, characterizing the spatial-temporal dynamics of pathological activity and describing for the first time the appearance of caudo-rostral ictal waves (CRIWs).

Analyzing the dynamical properties of mobile objects requires to extract trajectories from recordings, which is often done by tracking movies. We compiled a database of two-dimensional movies for very different biological and physical systems spanning a wide range of length scales and developed a general-purpose, optimized, open-source, cross-platform, easy to install and use, self-updating software called FastTrack. It can handle a changing number of deformable objects in a region of interest, and is particularly suitable for animal and cell tracking in two-dimensions. Furthermore, we introduce the probability of incursions as a new measure of a movie's trackability that doesn't require the knowledge of ground truth trajectories, since it is resilient to small amounts of errors and can be computed on the basis of an ad hoc tracking. We also leveraged the versatility and speed of FastTrack to implement an iterative algorithm determining a set of nearly-optimized tracking parameters -- yet further reducing the amount of human intervention -- and demonstrate that FastTrack can be used to explore the space of tracking parameters to optimize the number of swaps for a batch of similar movies. A benchmark shows that FastTrack is orders of magnitude faster than state-of-the-art tracking algorithms, with a comparable tracking accuracy. The source code is available under the GNU GPLv3 at this https URL and pre-compiled binaries for Windows, Mac and Linux are available at this http URL.

The present study evaluates the removal capacity of two high rate algae ponds (HRAPs) to eliminate 12 pharmaceuticals (PhACs) and 26 of their corresponding main metabolites and transformation products. The efficiency of these ponds, operating with and without primary treatment, was compared in order to study their capacity under the best performance conditions (highest solar irradiance). Concentrations of all the target compounds were determined in both water and biomass samples. Removal rates ranged from moderate (40-60%) to high (>60%) for most of them, with the exception of the psychiatric drugs carbamazepine, the beta-blocking agent metoprolol and its metabolite, metoprolol acid. O-desmethylvenlafaxine, despite its very low biodegradability in conventional wastewater treatment plants, was removed to certain extent (13-39%) Biomass concentrations suggested that bioadsorption/bioaccumulation to microalgae biomass was decisive regarding the elimination of some non-biodegradable compounds such as venlafaxine and its main metabolites. HRAP treatment with and without primary treatment did not yield significant differences in terms of PhACs removal efficiency. The implementation of HRAPs as secondary treatment is a viable alternative to CAS in terms of overall wastewater treatment (including organic micropollutants), with generally higher removal performances and implying a green, low-cost and more sustainable technology.