Classification problems in the small data regime (with small data statistic T and relatively large feature space dimension D) impose challenges for the common machine learning (ML) and deep learning (DL) tools. The standard learning methods from these areas tend to show a lack of robustness when applied to data sets with significantly fewer data points than dimensions and quickly reach the overfitting bound, thus leading to poor performance beyond the training set. To tackle this issue, we propose eSPA+, a significant extension of the recently formulated entropy-optimal scalable probabilistic approximation algorithm (eSPA). Specifically, we propose to change the order of the optimization steps and replace the most computationally expensive subproblem of eSPA with its closed-form solution. We prove that with these two enhancements, eSPA+ moves from the polynomial to the linear class of complexity scaling algorithms. On several small data learning benchmarks, we show that the eSPA+ algorithm achieves a many-fold speed-up with respect to eSPA and even better performance results when compared to a wide array of ML and DL tools. In particular, we benchmark eSPA+ against the standard eSPA and the main classes of common learning algorithms in the small data regime: various forms of support vector machines, random forests, and long short-term memory algorithms. In all the considered applications, the common learning methods and eSPA are markedly outperformed by eSPA+, which achieves significantly higher prediction accuracy with an orders-of-magnitude lower computational cost.

Controlling quality of next-generation sequencing (NGS) data files is a necessary but complex task. To address this problem, we statistically characterize common NGS quality features and develop a novel quality control procedure involving tree-based and deep learning classification algorithms. Predictive models, validated on internal and external functional genomics datasets, are to some extent generalizable to data from unseen species. The derived statistical guidelines and predictive models represent a valuable resource for users of NGS data to better understand quality issues and perform automatic quality control. Our guidelines and software are available at https://github.com/salbrec/seqQscorer.

To address the question which neocortical layers and cell types are important for the perception of a sensory stimulus, we performed multielectrode recordings in the barrel cortex of head-fixed mice performing a single-whisker go/no-go detection task with vibrotactile stimuli of differing intensities. We found that behavioral detection probability decreased gradually over the course of each session, which was well explained by a signal detection theory-based model that posits stable psychometric sensitivity and a variable decision criterion updated after each reinforcement, reflecting decreasing motivation. Analysis of multiunit activity demonstrated highest neurometric sensitivity in layer 4, which was achieved within only 30 ms after stimulus onset. At the level of single neurons, we observed substantial heterogeneity of neurometric sensitivity within and across layers, ranging from nonresponsiveness to approaching or even exceeding psychometric sensitivity. In all cortical layers, putative inhibitory interneurons on average proffered higher neurometric sensitivity than putative excitatory neurons. In infragranular layers, neurons increasing firing rate in response to stimulation featured higher sensitivities than neurons decreasing firing rate. Offline machine-learning-based analysis of videos of behavioral sessions showed that mice performed better when not moving, which at the neuronal level, was reflected by increased stimulus-evoked firing rates.

Even as a rare multiple congenital anomalies/mental retardation syndrome, the C-syndrome (CS, or Opitz C-trigonoecephaly syndrome) is, at long last, beginning to attract attention because of its developmental and causal complexity. Also, the possibility that the apparently balanced translocation recently described in an affected Japanese boy may soon provide a molecular/causal insight into this disorder. The manifestations recorded in the previously published patients, those autopsied within recent years, and the unpublished instances in our files suggest that the CS is a heterogeneous genetic disorder, predominantly sporadic but with sufficient familial cases (at times with consanguinity) to allow postulation of an entity due to autosomal dominant mutations with a high rate of germinal mosaicism, or due to both autosomal dominant mutations and an autosomal recessive genocopy. In any event, elucidation of cause and pathogenesis of CS will, in due time, shed light on its developmental pleiotropy, rarity in liveborn infants, prevalence in stillborn fetuses, recurrence risk in humans, and occurrence in other animals (e.g., mice) to further understanding of pathogenesis.

Chromatin immunoprecipitation (ChIP) followed by next generation sequencing (ChIP-Seq) is a powerful technique to study transcriptional regulation. However, the requirement of millions of cells to generate results with high signal-to-noise ratio precludes it in the study of small cell populations. Here, we present a tagmentation-assisted fragmentation ChIP (TAF-ChIP) and sequencing method to generate high-quality histone profiles from low cell numbers. The data obtained from the TAF-ChIP approach are amenable to standard tools for ChIP-Seq analysis, owing to its high signal-to-noise ratio. The epigenetic profiles from TAF-ChIP approach showed high agreement with conventional ChIP-Seq datasets, thereby underlining the utility of this approach.

We propose a pipeline for synthetic generation of personalized Computer Tomography (CT) images, with a radiation exposure evaluation and a lifetime attributable risk (LAR) assessment. We perform a patient-specific performance evaluation for a broad range of denoising algorithms (including the most popular deep learning denoising approaches, wavelets-based methods, methods based on Mumford–Shah denoising, etc.), focusing both on accessing the capability to reduce the patient-specific CT-induced LAR and on computational cost scalability. We introduce a parallel Probabilistic Mumford–Shah denoising model (PMS) and show that it markedly-outperforms the compared common denoising methods in denoising quality and cost scaling. In particular, we show that it allows an approximately 22-fold robust patient-specific LAR reduction for infants and a 10-fold LAR reduction for adults. Using a normal laptop, the proposed algorithm for PMS allows cheap and robust (with a multiscale structural similarity index >90%) denoising of very large 2D videos and 3D images (with over ${10}^7$ voxels) that are subject to ultra-strong noise (Gaussian and non-Gaussian) for signal-to-noise ratios far below 1.0. The code is provided for open access.