We present a novel, domain-agnostic, model-independent, unsupervised, and universally applicable Machine Learning approach for dimensionality reduction based on the principles of algorithmic complexity. Specifically, but without loss of generality, we focus on addressing the challenge of reducing certain dimensionality aspects, such as the number of edges in a network, while retaining essential features of interest. These features include preserving crucial network properties like degree distribution, clustering coefficient, edge betweenness, and degree and eigenvector centralities but can also go beyond edges to nodes and weights for network pruning and trimming. Our approach outperforms classical statistical Machine Learning techniques and state-of-the-art dimensionality reduction algorithms by preserving a greater number of data features that statistical algorithms would miss, particularly nonlinear patterns stemming from deterministic recursive processes that may look statistically random but are not. Moreover, previous approaches heavily rely on a priori feature selection, which requires constant supervision. Our findings demonstrate the effectiveness of the algorithms in overcoming some of these limitations while maintaining a time-efficient computational profile. Our approach not only matches, but also exceeds, the performance of established and state-of-the-art dimensionality reduction algorithms. We extend the applicability of our method to lossy compression tasks involving images and any multi-dimensional data. This highlights the versatility and broad utility of the approach in multiple domains.

In the era of precision medicine, it is necessary to understand heterogeneity among patients with complex diseases to improve personalized prevention and management strategies. Here, we introduce ClustAll, a Bioconductor package designed for unsupervised patient stratification using clinical data. ClustAll is based on the previously validated methodology ClustAll, a clustering framework that effectively handles intricacies in clinical data, including mixed data types, missing values, and collinearity. Additionally, ClustAll stands out in its ability to identify multiple patient stratifications within the same population while ensuring their robustness. The updated implementation of ClustAll features S4 classes, parallel computing for enhanced computational efficiency, and user-friendly tools for exploring and comparing stratifications against clinical phenotypes. The performance of ClustAll has been validated using two public clinical datasets, confirming its effectiveness in patient stratification and highlighting its potential impact on clinical management. In summary, ClustAll is a powerful tool for patient stratification in personalized medicine.

Srijith Radhakrishnan, Chao-Han Yang, Sumeer Khan, Rohit Kumar, Narsis Kiani, David Gomez-Cabrero, Jesper Tegnér. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

In this work, we explore Parameter-Efficient-Learning (PEL) techniques to repurpose a General-Purpose-Speech (GSM) model for Arabic dialect identification (ADI). Specifically, we investigate different setups to incorporate trainable features into a multi-layer encoder-decoder GSM formulation under frozen pre-trained settings. Our architecture includes residual adapter and model reprogramming (input-prompting). We design a token-level label mapping to condition the GSM for Arabic Dialect Identification (ADI). We achieve new state-of-the-art accuracy on the ADI-17 dataset by vanilla fine-tuning. We further reduce the training budgets with the PEL method, which performs within 1.86% accuracy to fine-tuning using only 2.5% of (extra) network trainable parameters.

A topic of growing interest in computational neuroscience is the discovery of fundamental principles underlying global dynamics and the self-organization of the brain. In particular, the notion that the brain operates near criticality has gained considerable support, and recent work has shown that the dynamics of different brain states may be modeled by pairwise maximum entropy Ising models at various distances from a phase transition, i.e., from criticality. Here we aim to characterize two brain states (psychedelics-induced and placebo) as captured by functional magnetic resonance imaging (fMRI), with features derived from the Ising spin model formalism (system temperature, critical point, susceptibility) and from algorithmic complexity. We hypothesized, along the lines of the entropic brain hypothesis, that psychedelics drive brain dynamics into a more disordered state at a higher Ising temperature and increased complexity. We analyze resting state blood-oxygen-level-dependent (BOLD) fMRI data collected in an earlier study from fifteen subjects in a control condition (placebo) and during ingestion of lysergic acid diethylamide (LSD). Working with the automated anatomical labeling (AAL) brain parcellation, we first create "archetype" Ising models representative of the entire dataset (global) and of the data in each condition. Remarkably, we find that such archetypes exhibit a strong correlation with an average structural connectome template obtained from dMRI (r = 0.6). We compare the archetypes from the two conditions and find that the Ising connectivity in the LSD condition is lower than in the placebo one, especially in homotopic links (interhemispheric connectivity), reflecting a significant decrease of homotopic functional connectivity in the LSD condition. The global archetype is then personalized for each individual and condition by adjusting the system temperature. The resulting temperatures are all near but above the critical point of the model in the paramagnetic (disordered) phase. The individualized Ising temperatures are higher in the LSD condition than in the placebo condition (p = 9 × 10-5). Next, we estimate the Lempel-Ziv-Welch (LZW) complexity of the binarized BOLD data and the synthetic data generated with the individualized model using the Metropolis algorithm for each participant and condition. The LZW complexity computed from experimental data reveals a weak statistical relationship with condition (p = 0.04 one-tailed Wilcoxon test) and none with Ising temperature (r(13) = 0.13, p = 0.65), presumably because of the limited length of the BOLD time series. Similarly, we explore complexity using the block decomposition method (BDM), a more advanced method for estimating algorithmic complexity. The BDM complexity of the experimental data displays a significant correlation with Ising temperature (r(13) = 0.56, p = 0.03) and a weak but significant correlation with condition (p = 0.04, one-tailed Wilcoxon test). This study suggests that the effects of LSD increase the complexity of brain dynamics by loosening interhemispheric connectivity-especially homotopic links. In agreement with earlier work using the Ising formalism with BOLD data, we find the brain state in the placebo condition is already above the critical point, with LSD resulting in a shift further away from criticality into a more disordered state.

NeuroEvolution is one of the most competitive evolutionary learning strategies for designing novel neural networks for use in specific tasks, such as logic circuit design and digital gaming. However, the application of benchmark methods such as the NeuroEvolution of Augmenting Topologies (NEAT) remains a challenge, in terms of their computational cost and search time inefficiency. This paper advances a method which incorporates a type of topological edge coding, named Reverse Encoding Tree (RET), for evolving scalable neural networks efficiently. Using RET, two types of approaches - NEAT with Binary search encoding (Bi-NEAT) and NEAT with Golden-Section search encoding (GS-NEAT) - have been designed to solve problems in benchmark continuous learning environments such as logic gates, Cartpole, and Lunar Lander, and tested against classical NEAT and FS-NEAT as baselines. Additionally, we conduct a robustness test to evaluate the resilience of the proposed NEAT approaches. The results show that the two proposed approaches deliver improved performance, characterized by (1) a higher accumulated reward within a finite number of time steps; (2) using fewer episodes to solve problems in targeted environments, and (3) maintaining adaptive robustness under noisy perturbations, which outperform the baselines in all tested cases. Our analysis also demonstrates that RET expends potential future research directions in dynamic environments. Code is available from https://github.com/HaolingZHANG/ReverseEncodingTree.

MOTIVATION: The use of differential equations (ODE) is one of the most promising approaches to network inference. The success of ODE-based approaches has, however, been limited, due to the difficulty in estimating parameters and by their lack of scalability. Here, we introduce a novel method and pipeline to reverse engineer gene regulatory networks from gene expression of time series and perturbation data based upon an improvement on the calculation scheme of the derivatives and a pre-filtration step to reduce the number of possible links. The method introduces a linear differential equation model with adaptive numerical differentiation that is scalable to extremely large regulatory networks. RESULTS: We demonstrate the ability of this method to outperform current state-of-the-art methods applied to experimental and synthetic data using test data from the DREAM4 and DREAM5 challenges. Our method displays greater accuracy and scalability. We benchmark the performance of the pipeline with respect to dataset size and levels of noise. We show that the computation time is linear over various network sizes. AVAILABILITY AND IMPLEMENTATION: The Matlab code of the HiDi implementation is available at: www.complexitycalculator.com/HiDiScript.zip. CONTACT: [email protected] or [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Multiple Sclerosis (MS) is an autoimmune disease driving inflammatory and degenerative processes that damage the central nervous system (CNS). However, it is not well understood how these events interact and evolve to evoke such a highly dynamic and heterogeneous disease. We established a hypothesis whereby the variability in the course of MS is driven by the very same pathogenic mechanisms responsible for the disease, the autoimmune attack on the CNS that leads to chronic inflammation, neuroaxonal degeneration and remyelination. We propose that each of these processes acts more or less severely and at different times in each of the clinical subgroups. To test this hypothesis, we developed a mathematical model that was constrained by experimental data (the expanded disability status scale [EDSS] time series) obtained from a retrospective longitudinal cohort of 66 MS patients with a long-term follow-up (up to 20 years). Moreover, we validated this model in a second prospective cohort of 120 MS patients with a three-year follow-up, for which EDSS data and brain volume time series were available. The clinical heterogeneity in the datasets was reduced by grouping the EDSS time series using an unsupervised clustering analysis. We found that by adjusting certain parameters, albeit within their biological range, the mathematical model reproduced the different disease courses, supporting the dynamic CNS damage hypothesis to explain MS heterogeneity. Our analysis suggests that the irreversible axon degeneration produced in the early stages of progressive MS is mainly due to the higher rate of myelinated axon degeneration, coupled to the lower capacity for remyelination. However, and in agreement with recent pathological studies, degeneration of chronically demyelinated axons is not a key feature that distinguishes this phenotype. Moreover, the model reveals that lower rates of axon degeneration and more rapid remyelination make relapsing MS more resilient than the progressive subtype. Therefore, our results support the hypothesis of a common pathogenesis for the different MS subtypes, even in the presence of genetic and environmental heterogeneity. Hence, MS can be considered as a single disease in which specific dynamics can provoke a variety of clinical outcomes in different patient groups. These results have important implications for the design of therapeutic interventions for MS at different stages of the disease.

BACKGROUND: Network inference deals with the reconstruction of molecular networks from experimental data. Given N molecular species, the challenge is to find the underlying network. Due to data limitations, this typically is an ill-posed problem, and requires the integration of prior biological knowledge or strong regularization. We here focus on the situation when time-resolved measurements of a system's response after systematic perturbations are available. RESULTS: We present a novel method to infer signaling networks from time-course perturbation data. We utilize dynamic Bayesian networks with probabilistic Boolean threshold functions to describe protein activation. The model posterior distribution is analyzed using evolutionary MCMC sampling and subsequent clustering, resulting in probability distributions over alternative networks. We evaluate our method on simulated data, and study its performance with respect to data set size and levels of noise. We then use our method to study EGF-mediated signaling in the ERBB pathway. CONCLUSIONS: Dynamic Probabilistic Threshold Networks is a new method to infer signaling networks from time-series perturbation data. It exploits the dynamic response of a system after external perturbation for network reconstruction. On simulated data, we show that the approach outperforms current state of the art methods. On the ERBB data, our approach recovers a significant fraction of the known interactions, and predicts novel mechanisms in the ERBB pathway.

Representing biological systems as networks has proved to be very powerful. For example, local graph analysis of substructures such as subgraph over representation (or motifs) has elucidated different sub-types of networks. Here we report that using numerical approximations of Kolmogorov complexity, by means of algorithmic probability, clusters different classes of networks. For this, we numerically estimate the algorithmic probability of the sub-matrices from the adjacency matrix of the original network (hence including motifs). We conclude that algorithmic information theory is a powerful tool supplementing other network analysis techniques.

BACKGROUND: High-content, high-throughput RNA interference (RNAi) offers unprecedented possibilities to elucidate gene function and involvement in biological processes. Microscopy based screening allows phenotypic observations at the level of individual cells. It was recently shown that a cell's population context significantly influences results. However, standard analysis methods for cellular screens do not currently take individual cell data into account unless this is important for the phenotype of interest, i.e. when studying cell morphology. RESULTS: We present a method that normalizes and statistically scores microscopy based RNAi screens, exploiting individual cell information of hundreds of cells per knockdown. Each cell's individual population context is employed in normalization. We present results on two infection screens for hepatitis C and dengue virus, both showing considerable effects on observed phenotypes due to population context. In addition, we show on a non-virus screen that these effects can be found also in RNAi data in the absence of any virus. Using our approach to normalize against these effects we achieve improved performance in comparison to an analysis without this normalization and hit scoring strategy. Furthermore, our approach results in the identification of considerably more significantly enriched pathways in hepatitis C virus replication than using a standard analysis approach. CONCLUSIONS: Using a cell-based analysis and normalization for population context, we achieve improved sensitivity and specificity not only on a individual protein level, but especially also on a pathway level. This leads to the identification of new host dependency factors of the hepatitis C and dengue viruses and higher reproducibility of results.

In this paper, by a definite linear function for ranking symmetric triangular fuzzy numbers, in a Fuzzy Linear Programming problem (FLP) model, we introduced a Fuzzy Degenerate Solution (FDS). In the physical meaning, occurrence of degeneracy in a Fuzzy Minimal Cost Flow Network is investigated. To prevent of falling into Cycling phenomenon in optimization process, we defined two new techniques of Cycling prevention proper to fuzzy environment.