Diversifying Design of Nucleic Acid Aptamers Using Unsupervised Machine Learning.

Inverse design of short single-stranded RNA and DNA sequences (aptamers) is the task of finding sequences that satisfy a set of desired criteria. Relevant criteria may be, for example, the presence of specific folding motifs, binding to molecular ligands, sensing properties, and so on. Most practical approaches to aptamer design identify a small set of promising candidate sequences using high-throughput experiments (e.g., SELEX) and then optimize performance by introducing only minor modifications to the empirically found candidates. Sequences that possess the desired properties but differ drastically in chemical composition will add diversity to the search space and facilitate the discovery of useful nucleic acid aptamers. Systematic diversification protocols are needed. Here we propose to use an unsupervised machine learning model known as the Potts model to discover new, useful sequences with controllable sequence diversity. We start by training a Potts model using the maximum entropy principle on a small set of empirically identified sequences unified by a common feature. To generate new candidate sequences with a controllable degree of diversity, we take advantage of the model's spectral feature: an "energy" bandgap separating sequences that are similar to the training set from those that are distinct. By controlling the Potts energy range that is sampled, we generate sequences that are distinct from the training set yet still likely to have the encoded features. To demonstrate performance, we apply our approach to design diverse pools of sequences with specified secondary structure motifs in 30-mer RNA and DNA aptamers.

Benchmark of Data Processing Methods and Machine Learning Models for Gut Microbiome-Based Diagnosis of Inflammatory Bowel Disease.

Patients with inflammatory bowel disease (IBD) wait months and undergo numerous invasive procedures between the initial appearance of symptoms and receiving a diagnosis. In order to reduce time until diagnosis and improve patient wellbeing, machine learning algorithms capable of diagnosing IBD from the gut microbiome's composition are currently being explored. To date, these models have had limited clinical application due to decreased performance when applied to a new cohort of patient samples. Various methods have been developed to analyze microbiome data which may improve the generalizability of machine learning IBD diagnostic tests. With an abundance of methods, there is a need to benchmark the performance and generalizability of various machine learning pipelines (from data processing to training a machine learning model) for microbiome-based IBD diagnostic tools. We collected fifteen 16S rRNA microbiome datasets (7,707 samples) from North America to benchmark combinations of gut microbiome features, data normalization and transformation methods, batch effect correction methods, and machine learning models. Pipeline generalizability to new cohorts of patients was evaluated with two binary classification metrics following leave-one-dataset-out cross (LODO) validation, where all samples from one study were left out of the training set and tested upon. We demonstrate that taxonomic features processed with a compositional transformation method and batch effect correction with the naive zero-centering method attain the best classification performance. In addition, machine learning models that identify non-linear decision boundaries between labels are more generalizable than those that are linearly constrained. Lastly, we illustrate the importance of generating a curated training dataset to ensure similar performance across patient demographics. These findings will help improve the generalizability of machine learning models as we move towards non-invasive diagnostic and disease management tools for patients with IBD.

Computational Methods for Continuous Eye-Tracking Perimetry Based on Spatio-Temporal Integration and a Deep Recurrent Neural Network.

The measurement of retinal sensitivity at different visual field locations-perimetry-is a fundamental procedure in ophthalmology. The most common technique for this scope, the Standard Automated Perimetry, suffers from several issues that make it less suitable to test specific clinical populations: it can be tedious, it requires motor manual feedback, and requires from the patient high levels of compliance. Previous studies attempted to create user-friendlier alternatives to Standard Automated Perimetry by employing eye movements reaction times as a substitute for manual responses while keeping the fixed-grid stimuli presentation typical of Standard Automated Perimetry. This approach, however, does not take advantage of the high spatial and temporal resolution enabled by the use of eye-tracking. In this study, we introduce a novel eye-tracking method to perform high-resolution perimetry. This method is based on the continuous gaze-tracking of a stimulus moving along a pseudo-random walk interleaved with saccadic jumps. We then propose two computational methods to obtain visual field maps from the continuous gaze-tracking data: the first is based on the spatio-temporal integration of ocular positional deviations using the threshold free cluster enhancement (TFCE) algorithm; the second is based on using simulated visual field defects to train a deep recurrent neural network (RNN). These two methods have complementary qualities: the TFCE is neurophysiologically plausible and its output significantly correlates with Standard Automated Perimetry performed with the Humphrey Field Analyzer, while the RNN accuracy significantly outperformed the TFCE in reconstructing the simulated scotomas but did not translate as well to the clinical data from glaucoma patients. While both of these methods require further optimization, they show the potential for a more patient-friendly alternative to Standard Automated Perimetry.

Global visual salience of competing stimuli.

Current computational models of visual salience accurately predict the distribution of fixations on isolated visual stimuli. It is not known, however, whether the global salience of a stimulus, that is, its effectiveness in the competition for attention with other stimuli, is a function of the local salience or an independent measure. Further, do task and familiarity with the competing images influence eye movements? Here, we investigated the direction of the first saccade to characterize and analyze the global visual salience of competing stimuli. Participants freely observed pairs of images while eye movements were recorded. The pairs balanced the combinations of new and already seen images, as well as task and task-free trials. Then, we trained a logistic regression model that accurately predicted the location-left or right image-of the first fixation for each stimulus pair, accounting too for the influence of task, familiarity, and lateral bias. The coefficients of the model provided a reliable measure of global salience, which we contrasted with two distinct local salience models, GBVS and Deep Gaze. The lack of correlation of the behavioral data with the former and the small correlation with the latter indicate that global salience cannot be explained by the feature-driven local salience of images. Further, the influence of task and familiarity was rather small, and we reproduced the previously reported left-sided bias. Summarized, we showed that natural stimuli have an intrinsic global salience related to the human initial gaze direction, independent of the local salience and little influenced by task and familiarity.