Quantitative Biology
See recent articles
- [1] arXiv:2406.12895 [pdf, html, other]
-
Title: Temporal Complexity of a Hopfield-Type Neural Model in Random and Scale-Free GraphsSubjects: Neurons and Cognition (q-bio.NC); Disordered Systems and Neural Networks (cond-mat.dis-nn); Mathematical Physics (math-ph); Numerical Analysis (math.NA); Adaptation and Self-Organizing Systems (nlin.AO)
The Hopfield network model and its generalizations were introduced as a model of associative, or content-addressable, memory. They were widely investigated both as a unsupervised learning method in artificial intelligence and as a model of biological neural dynamics in computational neuroscience. The complexity features of biological neural networks are attracting the interest of scientific community since the last two decades. More recently, concepts and tools borrowed from complex network theory were applied to artificial neural networks and learning, thus focusing on the topological aspects. However, the temporal structure is also a crucial property displayed by biological neural networks and investigated in the framework of systems displaying complex intermittency. The Intermittency-Driven Complexity (IDC) approach indeed focuses on the metastability of self-organized states, whose signature is a power-decay in the inter-event time distribution or a scaling behavior in the related event-driven diffusion processes. The investigation of IDC in neural dynamics and its relationship with network topology is still in its early stages. In this work we present the preliminary results of a IDC analysis carried out on a bio-inspired Hopfield-type neural network comparing two different connectivities, i.e., scale-free vs. random network topology. We found that random networks can trigger complexity features similar to that of scale-free networks, even if with some differences and for different parameter values, in particular for different noise levels.
- [2] arXiv:2406.12906 [pdf, other]
-
Title: Entropy-statistical approach to phase-locking detection of pulse oscillations: application for the analysis of biosignal synchronizationComments: 23 pages, 12 figures, 3 tablesSubjects: Neurons and Cognition (q-bio.NC); Machine Learning (cs.LG); Adaptation and Self-Organizing Systems (nlin.AO)
In this study a new method for analyzing synchronization in oscillator systems is proposed using the example of modeling the dynamics of a circuit of two resistively coupled pulse oscillators. The dynamic characteristic of synchronization is fuzzy entropy (FuzzyEn) calculated a time series composed of the ratios of the number of pulse periods (subharmonic ratio, SHR) during phase-locking intervals. Low entropy values indicate strong synchronization, whereas high entropy values suggest weak synchronization between the two oscillators. This method effectively visualizes synchronized modes of the circuit using entropy maps of synchronization states. Additionally, a classification of synchronization states is proposed based on the dependencies of FuzzyEn on the length of embedding vectors of SHR time series. An extension of this method for analyzing non-relaxation (non-spike) type signals is illustrated using the example of phase-phase coupling rhythms of local field potential of rat hippocampus. The entropy-statistical approach using rational fractions and pulse signal forms makes this method promising for analyzing biosignal synchronization and implementing the algorithm in mobile digital platforms.
- [3] arXiv:2406.12949 [pdf, html, other]
-
Title: Integrating time-resolved $nrf2$ gene-expression data into a full GUTS model as a proxy for toxicodynamic damage in zebrafish embryoSubjects: Quantitative Methods (q-bio.QM); Dynamical Systems (math.DS); Applications (stat.AP)
The immense production of the chemical industry requires an improved predictive risk assessment that can handle constantly evolving challenges while reducing the dependency of risk assessment on animal testing. Integrating 'omics data into mechanistic models offers a promising solution by linking cellular processes triggered after chemical exposure with observed effects in the organism. With the emerging availability of time-resolved RNA data, the goal of integrating gene expression data into mechanistic models can be approached. We propose a biologically anchored TKTD model, which describes key processes that link the gene expression level of the stress regulator $nrf2$ to detoxification and lethality by associating toxicodynamic damage with $nrf2$ expression. Fitting such a model to complex datasets consisting of multiple endpoints required the combination of methods from molecular biology, mechanistic dynamic systems modeling and Bayesian inference. In this study we successfully integrate time-resolved gene expression data into TKTD models, and thus provide a method for assessing the influence of molecular markers on survival. This novel method was used to test whether, $nrf2$, can be applied to predict lethality in zebrafish embryos. With the presented approach we outline a method to successively approach the goal of a predictive risk assessment based on molecular data.
- [4] arXiv:2406.12950 [pdf, html, other]
-
Title: MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property PredictionSubjects: Quantitative Methods (q-bio.QM); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Computation and Language (cs.CL); Machine Learning (cs.LG)
Molecular property prediction (MPP) is a fundamental and crucial task in drug discovery. However, prior methods are limited by the requirement for a large number of labeled molecules and their restricted ability to generalize for unseen and new tasks, both of which are essential for real-world applications. To address these challenges, we present MolecularGPT for few-shot MPP. From a perspective on instruction tuning, we fine-tune large language models (LLMs) based on curated molecular instructions spanning over 1000 property prediction tasks. This enables building a versatile and specialized LLM that can be adapted to novel MPP tasks without any fine-tuning through zero- and few-shot in-context learning (ICL). MolecularGPT exhibits competitive in-context reasoning capabilities across 10 downstream evaluation datasets, setting new benchmarks for few-shot molecular prediction tasks. More importantly, with just two-shot examples, MolecularGPT can outperform standard supervised graph neural network methods on 4 out of 7 datasets. It also excels state-of-the-art LLM baselines by up to 16.6% increase on classification accuracy and decrease of 199.17 on regression metrics (e.g., RMSE) under zero-shot. This study demonstrates the potential of LLMs as effective few-shot molecular property predictors. The code is available at this https URL.
- [5] arXiv:2406.13141 [pdf, html, other]
-
Title: Implant-to-Wearable Communication through the Human Body: Exploring the Effects of Encapsulated Capacitive and Galvanic TransmittersAnyu Jiang, Cassandra Acebal, Brook Heyd, Trustin White, Gurleen Kainth, Arunashish Datta, Shreyas Sen, Adam Khalifa, Baibhab ChatterjeeSubjects: Tissues and Organs (q-bio.TO)
Data transfer using human-body communication (HBC) represents an actively explored alternative solution to address the challenges related to energy-efficiency, tissue absorption, and security of conventional wireless. Although the use of HBC for wearable-to-wearable communication has been well-explored, different configurations for the transmitter (Tx) and receiver (Rx) for implant-to-wearable HBC needs further studies. This paper substantiates the hypothesis that a fully implanted galvanic Tx is more efficient than a capacitive Tx for interaction with a wearable Rx. Given the practical limitations of implanting an ideal capacitive device, we choose a galvanic device with one electrode encapsulated to model the capacitive scenario. We analyze the lumped circuit model for in-body to out-of-body communication, and perform Circuit-based as well as Finite Element Method (FEM) simulations to explore how the encapsulation thickness affects the received signal levels. We demonstrate in-vivo experimental results on live Sprague Dawley rats to validate the hypothesis, and show that compared to the galvanic Tx, the channel loss will be $\approx$ 20 dB higher with each additional mm thickness of capacitive encapsulation, eventually going below the noise floor for ideal capacitive Tx.
- [6] arXiv:2406.13292 [pdf, html, other]
-
Title: An interpretable generative multimodal neuroimaging-genomics framework for decoding Alzheimer's diseaseGiorgio Dolci (1,2), Federica Cruciani (1), Md Abdur Rahaman (2), Anees Abrol (2), Jiayu Chen (2), Zening Fu (2), Ilaria Boscolo Galazzo (1), Gloria Menegaz (1), Vince D. Calhoun (2) ((1) Department of Engineering for Innovation Medicine, University of Verona, Verona, Italy, (2) Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, USA)Comments: 27 pages, 7 figures, submitted to a journalSubjects: Quantitative Methods (q-bio.QM); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV)
Alzheimer's disease (AD) is the most prevalent form of dementia with a progressive decline in cognitive abilities. The AD continuum encompasses a prodormal stage known as Mild Cognitive Impairment (MCI), where patients may either progress to AD or remain stable. In this study, we leveraged structural and functional MRI to investigate the disease-induced grey matter and functional network connectivity changes. Moreover, considering AD's strong genetic component, we introduce SNPs as a third channel. Given such diverse inputs, missing one or more modalities is a typical concern of multimodal methods. We hence propose a novel deep learning-based classification framework where generative module employing Cycle GANs was adopted to impute missing data within the latent space. Additionally, we adopted an Explainable AI method, Integrated Gradients, to extract input features relevance, enhancing our understanding of the learned representations. Two critical tasks were addressed: AD detection and MCI conversion prediction. Experimental results showed that our model was able to reach the SOA in the classification of CN/AD reaching an average test accuracy of $0.926\pm0.02$. For the MCI task, we achieved an average prediction accuracy of $0.711\pm0.01$ using the pre-trained model for CN/AD. The interpretability analysis revealed significant grey matter modulations in cortical and subcortical brain areas well known for their association with AD. Moreover, impairments in sensory-motor and visual resting state network connectivity along the disease continuum, as well as mutations in SNPs defining biological processes linked to amyloid-beta and cholesterol formation clearance and regulation, were identified as contributors to the achieved performance. Overall, our integrative deep learning approach shows promise for AD detection and MCI prediction, while shading light on important biological insights.
- [7] arXiv:2406.13489 [pdf, html, other]
-
Title: Efficient gPC-based quantification of probabilistic robustness for systems in neuroscienceSubjects: Quantitative Methods (q-bio.QM)
We introduce and analyze generalised polynomial chaos (gPC), considering both intrusive and non-intrusive approaches, as an uncertainty quantification method in studies of probabilistic robustness. The considered gPC methods are complementary to Monte Carlo (MC) methods and are shown to be fast and scalable, allowing for comprehensive and efficient exploration of parameter spaces. These properties enable robustness analysis of a wider set of models, compared to computationally expensive MC methods, while retaining desired levels of accuracy. We discuss the application of gPC methods to systems in biology and neuroscience, notably subject to multiple parametric uncertainties, and we examine a well-known model of neural dynamics as a case study.
- [8] arXiv:2406.13765 [pdf, html, other]
-
Title: A game of life with dormancySubjects: Populations and Evolution (q-bio.PE)
The factors contributing to the persistence and stability of life are fundamental for understanding complex living systems. Organisms are commonly challenged by harsh and fluctuating environments that are suboptimal for growth and reproduction, which can lead to extinction. Species often contend with unfavorable and noisy conditions by entering a reversible state of reduced metabolic activity, a phenomenon known as dormancy. Here, we develop Spore Life, a model to investigate the effects of dormancy on population dynamics. It is based on Conway's Game of Life, a deterministic cellular automaton where simple rules govern the metabolic state of an individual based on the metabolic state of its neighbors. For individuals that would otherwise die, Spore Life provides a refuge in the form of an inactive state. These dormant individuals (spores) can resuscitate when local conditions improve. The model includes a parameter alpha that controls the survival probability of spores, interpolating between Game of Life (alpha = 0) and Spore Life (alpha = 1), while capturing stochastic dynamics in the intermediate regime (0 < alpha < 1). In addition to identifying the emergence of unique periodic configurations, we find that spore survival increases the average number of active individuals and buffers populations from extinction. Contrary to expectations, the stabilization of the population is not the result of a large and long-lived seed bank. Instead, the demographic patterns in Spore Life only require a small number of resuscitation events. Our approach yields novel insight into what is minimally required for the emergence of complex behaviors associated with dormancy and the seed banks that they generate.
- [9] arXiv:2406.13822 [pdf, other]
-
Title: Association of neighborhood disadvantage with cognitive function and cortical disorganization in an unimpaired cohortApoorva Safai, Erin Jonaitis, Rebecca E Langhough, William R Buckingham, Sterling C. Johnson, W. Ryan Powell, Amy J. H. Kind, Barbara B. Bendlin, Pallavi TiwariSubjects: Neurons and Cognition (q-bio.NC); Applications (stat.AP)
Neighborhood disadvantage is associated with worse health and cognitive outcomes. Morphological similarity network (MSN) is a promising approach to elucidate cortical network patterns underlying complex cognitive functions. We hypothesized that MSNs could capture changes in cortical patterns related to neighborhood disadvantage and cognitive function. This cross-sectional study included cognitively unimpaired participants from two large Alzheimers studies at University of Wisconsin-Madison. Neighborhood disadvantage status was obtained using the Area Deprivation Index (ADI). Cognitive performance was assessed on memory, processing speed and executive function. Morphological Similarity Networks (MSN) were constructed for each participant based on the similarity in distribution of cortical thickness of brain regions, followed by computation of local and global network features. Association of ADI with cognitive scores and MSN features were examined using linear regression and mediation analysis. ADI showed negative association with category fluency,implicit learning speed, story recall and modified pre-clinical Alzheimers cognitive composite scores, indicating worse cognitive function among those living in more disadvantaged neighborhoods. Local network features of frontal and temporal regions differed based on ADI status. Centrality of left lateral orbitofrontal region showed a partial mediating effect between association of neighborhood disadvantage and story recall performance. Our preliminary findings suggest differences in local cortical organization by neighborhood disadvantage, which partially mediated the relationship between ADI and cognitive performance, providing a possible network-based mechanism to, in-part, explain the risk for poor cognitive functioning associated with disadvantaged neighborhoods.
- [10] arXiv:2406.13839 [pdf, html, other]
-
Title: RNA-FrameFlow: Flow Matching for de novo 3D RNA Backbone DesignRishabh Anand, Chaitanya K. Joshi, Alex Morehead, Arian R. Jamasb, Charles Harris, Simon V. Mathis, Kieran Didi, Bryan Hooi, Pietro LiòComments: To be presented as an Oral at ICML 2024 Structured Probabilistic Inference & Generative Modeling Workshop, and a Spotlight at ICML 2024 AI4Science WorkshopSubjects: Biomolecules (q-bio.BM); Machine Learning (cs.LG); Genomics (q-bio.GN)
We introduce RNA-FrameFlow, the first generative model for 3D RNA backbone design. We build upon SE(3) flow matching for protein backbone generation and establish protocols for data preparation and evaluation to address unique challenges posed by RNA modeling. We formulate RNA structures as a set of rigid-body frames and associated loss functions which account for larger, more conformationally flexible RNA backbones (13 atoms per nucleotide) vs. proteins (4 atoms per residue). Toward tackling the lack of diversity in 3D RNA datasets, we explore training with structural clustering and cropping augmentations. Additionally, we define a suite of evaluation metrics to measure whether the generated RNA structures are globally self-consistent (via inverse folding followed by forward folding) and locally recover RNA-specific structural descriptors. The most performant version of RNA-FrameFlow generates locally realistic RNA backbones of 40-150 nucleotides, over 40% of which pass our validity criteria as measured by a self-consistency TM-score >= 0.45, at which two RNAs have the same global fold. Open-source code: this https URL
- [11] arXiv:2406.13889 [pdf, html, other]
-
Title: Network-community analysis of cellular senescenceAlda Sabalic, Victoria Moiseeva, Andres Cisneros, Oleg Deryagin, Eusebio Perdiguero, Pura Muñoz-Canoves, Jordi Garcia-OjalvoComments: 20 pages, 11 figuresSubjects: Quantitative Methods (q-bio.QM)
Most cellular phenotypes are genetically complex. Identifying the set of genes that are most closely associated with a specific cellular state is still an open question in many cases. Here we study the transcriptional profile of cellular senescence using a combination of network-based approaches, which include eigenvector centrality feature selection and community detection. We apply our method to cell-type-resolved RNA sequencing data obtained from injured muscle tissue in mice. The analysis identifies some genetic markers consistent with previous findings, and other previously unidentified ones, which are validated with previously published single-cell RNA sequencing data in a different type of tissue. The key identified genes, both those previously known and the newly identified ones, are transcriptional targets of factors known to be associated with established hallmarks of senescence, and can thus be interpreted as molecular correlates of such hallmarks. The method proposed here could be applied to any complex cellular phenotype even when only bulk RNA sequencing is available, provided the data is resolved by cell type.
- [12] arXiv:2406.14034 [pdf, other]
-
Title: Methylglyoxal induces cardiac dysfunction through mechanisms involving altered intracellular calcium handling in the rat heartHélène Peyret (PPF), Céline Konecki (PPF, CHU Reims), Christine Terryn (PICT), Florine Dubuisson (PPF), Hervé Millart (PPF), Catherine Feliu (PPF, CHU Reims), Zoubir Djerada (PPF, CHU Reims)Journal-ref: Chemico-Biological Interactions, 2024, 394, pp.110949Subjects: Subcellular Processes (q-bio.SC)
Methylglyoxal (MGO) is an endogenous, highly reactive dicarbonyl metabolite generated under hyperglycaemic conditions. MGO plays a role in developing pathophysiological conditions, including diabetic cardiomyopathy. However, the mechanisms involved and the molecular targets of MGO in the heart have not been elucidated. In this work, we studied the exposure-related effects of MGO on cardiac function in an isolated perfused rat heart ex vivo model. The effect of MGO on calcium homeostasis in cardiomyocytes was studied in vitro by the fluorescence indicator of intracellular calcium Fluo-4. We demonstrated that MGO induced cardiac dysfunction, both in contractility and diastolic function. In rat heart, the effects of MGO treatment were significantly limited by aminoguanidine, a scavenger of MGO, ruthenium red, a general cation channel blocker, and verapamil, an L-type voltage-dependent calcium channel blocker, demonstrating that this dysfunction involved alteration of calcium regulation. MGO induced a significant concentration-dependent increase of intracellular calcium in neonatal rat cardiomyocytes, which was limited by aminoguanidine and verapamil. These results suggest that the functionality of various calcium channels is altered by MGO, particularly the L-type calcium channel, thus explaining its cardiac toxicity. Therefore, MGO could participate in the development of diabetic cardiomyopathy through its impact on calcium homeostasis in cardiac cells.
- [13] arXiv:2406.14062 [pdf, html, other]
-
Title: An agent-based model of behaviour change calibrated to reversal learning dataComments: 23 pages, 5 figuresSubjects: Quantitative Methods (q-bio.QM); Biological Physics (physics.bio-ph); Computation (stat.CO)
Behaviour change lies at the heart of many observable collective phenomena such as the transmission and control of infectious diseases, adoption of public health policies, and migration of animals to new habitats. Representing the process of individual behaviour change in computer simulations of these phenomena remains an open challenge. Often, computational models use phenomenological implementations with limited support from behavioural data. Without a strong connection to observable quantities, such models have limited utility for simulating observed and counterfactual scenarios of emergent phenomena because they cannot be validated or calibrated. Here, we present a simple stochastic individual-based model of reversal learning that captures fundamental properties of individual behaviour change, namely, the capacity to learn based on accumulated reward signals, and the transient persistence of learned behaviour after rewards are removed or altered. The model has only two parameters, and we use approximate Bayesian computation to demonstrate that they are fully identifiable from empirical reversal learning time series data. Finally, we demonstrate how the model can be extended to account for the increased complexity of behavioural dynamics over longer time scales involving fluctuating stimuli. This work is a step towards the development and evaluation of fully identifiable individual-level behaviour change models that can function as validated submodels for complex simulations of collective behaviour change.
- [14] arXiv:2406.14100 [pdf, html, other]
-
Title: Self-Attention in Transformer Networks Explains Monkeys' Gaze Pattern in Pac-Man GameSubjects: Neurons and Cognition (q-bio.NC)
We proactively direct our eyes and attention to collect information during problem solving and decision making. Understanding gaze patterns is crucial for gaining insights into the computation underlying the problem-solving process. However, there is a lack of interpretable models that can account for how the brain directs the eyes to collect information and utilize it, especially in the context of complex problem solving. In the current study, we analyzed the gaze patterns of two monkeys playing the Pac-Man game. We trained a transformer network to mimic the monkeys' gameplay and found its attention pattern captures the monkeys' eye movements. In addition, the prediction based on the transformer network's attention outperforms the human subjects' predictions. Importantly, we dissected the computation underlying the attention mechanism of the transformer network, revealing its layered structures reflecting a value-based attention component and a component that captures the interactions between Pac-Man and other game objects. Based on these findings, we built a condensed attention model that is not only as accurate as the transformer network but also fully interpretable. Our results highlight the potential of using transformer neural networks to model and understand the cognitive processes underlying complex problem solving in the brain, opening new avenues for investigating the neural basis of cognition.
- [15] arXiv:2406.14142 [pdf, other]
-
Title: Geometric Self-Supervised Pretraining on 3D Protein Structures using SubgraphsSubjects: Quantitative Methods (q-bio.QM); Machine Learning (cs.LG); Biomolecules (q-bio.BM)
Protein representation learning aims to learn informative protein embeddings capable of addressing crucial biological questions, such as protein function prediction. Although sequence-based transformer models have shown promising results by leveraging the vast amount of protein sequence data in a self-supervised way, there is still a gap in applying these methods to 3D protein structures. In this work, we propose a pre-training scheme going beyond trivial masking methods leveraging 3D and hierarchical structures of proteins. We propose a novel self-supervised method to pretrain 3D graph neural networks on 3D protein structures, by predicting the distances between local geometric centroids of protein subgraphs and the global geometric centroid of the protein. The motivation for this method is twofold. First, the relative spatial arrangements and geometric relationships among different regions of a protein are crucial for its function. Moreover, proteins are often organized in a hierarchical manner, where smaller substructures, such as secondary structure elements, assemble into larger domains. By considering subgraphs and their relationships to the global protein structure, the model can learn to reason about these hierarchical levels of organization. We experimentally show that our proposed pertaining strategy leads to significant improvements in the performance of 3D GNNs in various protein classification tasks.
- [16] arXiv:2406.14187 [pdf, other]
-
Title: A mapping-free NLP-based technique for sequence search in Nanopore long-readsComments: 25 pages, 9 figuresSubjects: Genomics (q-bio.GN)
In unforeseen situations, such as nuclear power plant's or civilian radiation accidents, there is a need for effective and computationally inexpensive methods to determine the expression level of a selected gene panel, allowing for rough dose estimates in thousands of donors. The new generation in-situ mapper, fast and of low energy consumption, working at the level of single nanopore output, is in demand. We aim to create a sequence identification tool that utilizes Natural Language Processing (NLP) techniques and ensures a high level of negative predictive value (NPV) compared to the classical approach. The training dataset consisted of RNASeq data from 6 samples. Having tested multiple NLP models, the best configuration analyses the entire sequence and uses a word length of 3 base pairs with one-word neighbor on each side. For the considered FDXR gene, the achieved mean balanced accuracy (BACC) was 98.29% and NPV 99.25%, compared to minimap2's performance in a cross-validation scenario. Reducing the dictionary from 1024 to 145 changed BACC to 96.49% and the NPV to 98.15%. Obtained NLP model, validated on an external independent genome sequencing dataset, gave NPV of 99.64% for complete and 95.87% for reduced dictionary. The salmon-estimated read counts differed from the classical approach on average by 3.48% for the complete dictionary and by 5.82% for the reduced one. We conclude that for long Oxford Nanopore reads, an NLP-based approach can successfully replace classical mapping in case of emergency. The developed NLP model can be easily retrained to identify selected transcripts and/or work with various long-read sequencing techniques. Our results of the study clearly demonstrate the potential of applying techniques known from classical text processing to nucleotide sequences and represent a significant advancement in this field of science.
- [17] arXiv:2406.14246 [pdf, html, other]
-
Title: Non-Negative Universal Differential Equations With Applications in Systems BiologyComments: 6 pages, This work has been submitted to IFAC for possible publication. Initial submission was March 18, 2024Subjects: Quantitative Methods (q-bio.QM); Machine Learning (cs.LG); Dynamical Systems (math.DS); Machine Learning (stat.ML)
Universal differential equations (UDEs) leverage the respective advantages of mechanistic models and artificial neural networks and combine them into one dynamic model. However, these hybrid models can suffer from unrealistic solutions, such as negative values for biochemical quantities. We present non-negative UDE (nUDEs), a constrained UDE variant that guarantees non-negative values. Furthermore, we explore regularisation techniques to improve generalisation and interpretability of UDEs.
- [18] arXiv:2406.14307 [pdf, html, other]
-
Title: QuST-LLM: Integrating Large Language Models for Comprehensive Spatial Transcriptomics AnalysisComments: 12 pages, 7 figuresSubjects: Genomics (q-bio.GN); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
In this paper, we introduce QuST-LLM, an innovative extension of QuPath that utilizes the capabilities of large language models (LLMs) to analyze and interpret spatial transcriptomics (ST) data. This tool effectively simplifies the intricate and high-dimensional nature of ST data by offering a comprehensive workflow that includes data loading, region selection, gene expression analysis, and functional annotation. QuST-LLM employs LLMs to transform complex ST data into understandable and detailed biological narratives based on gene ontology annotations, thereby significantly improving the interpretability of ST data. Consequently, users can interact with their own ST data using natural language. Hence, QuST-LLM provides researchers with a potent functionality to unravel the spatial and functional complexities of tissues, fostering novel insights and advancements in biomedical research.
- [19] arXiv:2406.14358 [pdf, other]
-
Title: The neural correlates of logical-mathematical symbol systems processing resemble that of spatial cognition more than natural language processingSubjects: Neurons and Cognition (q-bio.NC); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
The ability to manipulate logical-mathematical symbols (LMS), encompassing tasks such as calculation, reasoning, and programming, is a cognitive skill arguably unique to humans. Considering the relatively recent emergence of this ability in human evolutionary history, it has been suggested that LMS processing may build upon more fundamental cognitive systems, possibly through neuronal recycling. Previous studies have pinpointed two primary candidates, natural language processing and spatial cognition. Existing comparisons between these domains largely relied on task-level comparison, which may be confounded by task idiosyncrasy. The present study instead compared the neural correlates at the domain level with both automated meta-analysis and synthesized maps based on three representative LMS tasks, reasoning, calculation, and mental programming. Our results revealed a more substantial cortical overlap between LMS processing and spatial cognition, in contrast to language processing. Furthermore, in regions activated by both spatial and language processing, the multivariate activation pattern for LMS processing exhibited greater multivariate similarity to spatial cognition than to language processing. A hierarchical clustering analysis further indicated that typical LMS tasks were indistinguishable from spatial cognition tasks at the neural level, suggesting an inherent connection between these two cognitive processes. Taken together, our findings support the hypothesis that spatial cognition is likely the basis of LMS processing, which may shed light on the limitations of large language models in logical reasoning, particularly those trained exclusively on textual data without explicit emphasis on spatial content.
- [20] arXiv:2406.14432 [pdf, html, other]
-
Title: Inverse population genetic problems with noise: inferring extent and structure of haplotype blocks from point allele frequenciesComments: 7 pages, 2 figuresSubjects: Populations and Evolution (q-bio.PE); Genomics (q-bio.GN)
A haplotype block, or simply a block, is a chromosomal segment, DNA base sequence or string that occurs in only a few variants or types in the genomes of a population of interest, and that has an encapsulated or 'private' frequency distribution of the string types that is not shared by neighbouring blocks or regions on the same chromosome. We consider two inverse problems of genetic interest: from just the frequencies of the symbol types (4 base types, possible single-base alleles) at each position (point, base/nucleotide) along the string, infer the location of the left and right boundaries of the block (block extent), and the number and relative frequencies of the string types occurring in the block (block structure). The large majority of variable positions in human and also other (e.g., fungal) genomes appear to be biallelic, i.e., the position allows only a choice between two possible symbols. The symbols can then be encoded as 0 (major) and 1 (minor), or as $\uparrow$ and $\downarrow$ as in Ising models, so the scenario reduces to problems on Boolean strings/bitstrings and Boolean matrices. The specifying of major allele frequencies (MAF) as used in genetics fits naturally into this framework. A simple example from human chromosome 9 is presented.
- [21] arXiv:2406.14516 [pdf, html, other]
-
Title: Extended error threshold mechanism in {\it quasispecies} theory via population dynamicsComments: 5 pages, 1 figureSubjects: Populations and Evolution (q-bio.PE)
We investigate Eigen's model for the evolution of the genetic code of microorganisms using a novel method based on population dynamics analysis. This model, for a given number of offspring, determines long-term survival as a function of the "genetic" information length and copy error probability. There exists a maximum threshold for the quantity of information that can be consistently preserved through the process of evolution within a population of perfectly replicating sequences, meaning no errors are allowed. With our formula, we expand upon the traditional error threshold formula of Eigen's theory and introduce a new expression for general cases where the self-reproduction process allows up to any integer number of copying errors per digit per replication step.
New submissions for Friday, 21 June 2024 (showing 21 of 21 entries )
- [22] arXiv:2406.12910 (cross-list from cs.LG) [pdf, other]
-
Title: Human-level molecular optimization driven by mol-gene evolutionJiebin Fang (1 and 2), Churu Mao (2), Yuchen Zhu (3), Xiaoming Chen (2), Chang-Yu Hsieh (3), Zhongjun Ma (1 and 2) ((1) Hainan Institute of Zhejiang University, (2) Institute of Marine Biology and Pharmacology, Ocean College, Zhejiang University, (3) College of Pharmaceutical Sciences and Cancer Center, Zhejiang University)Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE); Chemical Physics (physics.chem-ph); Biomolecules (q-bio.BM)
De novo molecule generation allows the search for more drug-like hits across a vast chemical space. However, lead optimization is still required, and the process of optimizing molecular structures faces the challenge of balancing structural novelty with pharmacological properties. This study introduces the Deep Genetic Molecular Modification Algorithm (DGMM), which brings structure modification to the level of medicinal chemists. A discrete variational autoencoder (D-VAE) is used in DGMM to encode molecules as quantization code, mol-gene, which incorporates deep learning into genetic algorithms for flexible structural optimization. The mol-gene allows for the discovery of pharmacologically similar but structurally distinct compounds, and reveals the trade-offs of structural optimization in drug discovery. We demonstrate the effectiveness of the DGMM in several applications.
- [23] arXiv:2406.12919 (cross-list from cs.LG) [pdf, html, other]
-
Title: Understanding active learning of molecular docking and its applicationsSubjects: Machine Learning (cs.LG); Chemical Physics (physics.chem-ph); Biomolecules (q-bio.BM)
With the advancing capabilities of computational methodologies and resources, ultra-large-scale virtual screening via molecular docking has emerged as a prominent strategy for in silico hit discovery. Given the exhaustive nature of ultra-large-scale virtual screening, active learning methodologies have garnered attention as a means to mitigate computational cost through iterative small-scale docking and machine learning model training. While the efficacy of active learning methodologies has been empirically validated in extant literature, a critical investigation remains in how surrogate models can predict docking score without considering three-dimensional structural features, such as receptor conformation and binding poses. In this paper, we thus investigate how active learning methodologies effectively predict docking scores using only 2D structures and under what circumstances they may work particularly well through benchmark studies encompassing six receptor targets. Our findings suggest that surrogate models tend to memorize structural patterns prevalent in high docking scored compounds obtained during acquisition steps. Despite this tendency, surrogate models demonstrate utility in virtual screening, as exemplified in the identification of actives from DUD-E dataset and high docking-scored compounds from EnamineReal library, a significantly larger set than the initial screening pool. Our comprehensive analysis underscores the reliability and potential applicability of active learning methodologies in virtual screening campaigns.
- [24] arXiv:2406.13113 (cross-list from cs.CV) [pdf, html, other]
-
Title: CU-Net: a U-Net architecture for efficient brain-tumor segmentation on BraTS 2019 datasetSubjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Neurons and Cognition (q-bio.NC)
Accurately segmenting brain tumors from MRI scans is important for developing effective treatment plans and improving patient outcomes. This study introduces a new implementation of the Columbia-University-Net (CU-Net) architecture for brain tumor segmentation using the BraTS 2019 dataset. The CU-Net model has a symmetrical U-shaped structure and uses convolutional layers, max pooling, and upsampling operations to achieve high-resolution segmentation. Our CU-Net model achieved a Dice score of 82.41%, surpassing two other state-of-the-art models. This improvement in segmentation accuracy highlights the robustness and effectiveness of the model, which helps to accurately delineate tumor boundaries, which is crucial for surgical planning and radiation therapy, and ultimately has the potential to improve patient outcomes.
- [25] arXiv:2406.13133 (cross-list from cs.CL) [pdf, html, other]
-
Title: PathoLM: Identifying pathogenicity from the DNA sequence through the Genome Foundation ModelSajib Acharjee Dip, Uddip Acharjee Shuvo, Tran Chau, Haoqiu Song, Petra Choi, Xuan Wang, Liqing ZhangComments: 9 pages, 3 figuresSubjects: Computation and Language (cs.CL); Machine Learning (cs.LG); Genomics (q-bio.GN)
Pathogen identification is pivotal in diagnosing, treating, and preventing diseases, crucial for controlling infections and safeguarding public health. Traditional alignment-based methods, though widely used, are computationally intense and reliant on extensive reference databases, often failing to detect novel pathogens due to their low sensitivity and specificity. Similarly, conventional machine learning techniques, while promising, require large annotated datasets and extensive feature engineering and are prone to overfitting. Addressing these challenges, we introduce PathoLM, a cutting-edge pathogen language model optimized for the identification of pathogenicity in bacterial and viral sequences. Leveraging the strengths of pre-trained DNA models such as the Nucleotide Transformer, PathoLM requires minimal data for fine-tuning, thereby enhancing pathogen detection capabilities. It effectively captures a broader genomic context, significantly improving the identification of novel and divergent pathogens. We developed a comprehensive data set comprising approximately 30 species of viruses and bacteria, including ESKAPEE pathogens, seven notably virulent bacterial strains resistant to antibiotics. Additionally, we curated a species classification dataset centered specifically on the ESKAPEE group. In comparative assessments, PathoLM dramatically outperforms existing models like DciPatho, demonstrating robust zero-shot and few-shot capabilities. Furthermore, we expanded PathoLM-Sp for ESKAPEE species classification, where it showed superior performance compared to other advanced deep learning methods, despite the complexities of the task.
- [26] arXiv:2406.13162 (cross-list from cs.LG) [pdf, html, other]
-
Title: AntibodyFlow: Normalizing Flow Model for Designing Antibody Complementarity-Determining RegionsSubjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM)
Therapeutic antibodies have been extensively studied in drug discovery and development in the past decades. Antibodies are specialized protective proteins that bind to antigens in a lock-to-key manner. The binding strength/affinity between an antibody and a specific antigen is heavily determined by the complementarity-determining regions (CDRs) on the antibodies. Existing machine learning methods cast in silico development of CDRs as either sequence or 3D graph (with a single chain) generation tasks and have achieved initial success. However, with CDR loops having specific geometry shapes, learning the 3D geometric structures of CDRs remains a challenge. To address this issue, we propose AntibodyFlow, a 3D flow model to design antibody CDR loops. Specifically, AntibodyFlow first constructs the distance matrix, then predicts amino acids conditioned on the distance matrix. Also, AntibodyFlow conducts constraint learning and constrained generation to ensure valid 3D structures. Experimental results indicate that AntibodyFlow outperforms the best baseline consistently with up to 16.0% relative improvement in validity rate and 24.3% relative reduction in geometric graph level error (root mean square deviation, RMSD).
- [27] arXiv:2406.13284 (cross-list from physics.med-ph) [pdf, other]
-
Title: The association of domain-specific physical activity and sedentary activity with stroke: A prospective cohort studySubjects: Medical Physics (physics.med-ph); Quantitative Methods (q-bio.QM)
Background The incidence of stroke places a heavy burden on both society and individuals. Activity is closely related to cardiovascular health. This study aimed to investigate the relationship between the varying domains of PA, like occupation-related Physical Activity (OPA), transportation-related Physical Activity (TPA), leisure-time Physical Activity (LTPA), and Sedentary Activity (SA) with stroke. Methods Our analysis included 30,400 participants aged 20+ years from 2007 to 2018 National Health and Nutrition Examination Survey (NHANES). Stroke was identified based on the participant's self-reported diagnoses from previous medical consultations, and PA and SA were self-reported. Multivariable logistic and restricted cubic spline models were used to assess the associations. Results Participants achieving PA guidelines (performing PA more than 150 min/week) were 35.7% less likely to have a stroke based on both the total PA (odds ratio [OR] 0.643, 95% confidence interval [CI] 0.523-0.790) and LTPA (OR 0.643, 95% CI 0.514-0.805), while OPA or TPA did not demonstrate lower stroke risk. Furthermore, participants with less than 7.5 h/day SA levels were 21.6% (OR 0.784, 95% CI 0.665-0.925) less likely to have a stroke. The intensities of total PA and LTPA exhibited nonlinear U-shaped associations with stroke risk. In contrast, those of OPA and TPA showed negative linear associations, while SA intensities were positively linearly correlated with stroke risk. Conclusions LTPA, but not OPA or TPA, was associated with a lower risk of stroke at any amount, suggesting that significant cardiovascular health would benefit from increased PA. Additionally, the positive association between SA and stroke indicated that prolonged sitting was detrimental to cardiovascular health. Overall, increased PA within a reasonable range reduces the risk of stroke, while increased SA elevates it.
- [28] arXiv:2406.13504 (cross-list from cond-mat.stat-mech) [pdf, html, other]
-
Title: Self-organized transport in noisy dynamic networksComments: 12 pages, 10 figuresSubjects: Statistical Mechanics (cond-mat.stat-mech); Adaptation and Self-Organizing Systems (nlin.AO); Biological Physics (physics.bio-ph); Neurons and Cognition (q-bio.NC)
We present a numerical study of multi-commodity transport in a noisy, nonlinear network. The nonlinearity determines the dynamics of the edge capacities, which can be amplified or suppressed depending on the local current flowing across an edge. We consider network self-organization for three different nonlinear functions: For all three we identify parameter regimes where noise leads to self-organization into more robust topologies, that are not found by the sole noiseless dynamics. Moreover, the interplay between noise and specific functional behavior of the nonlinearity gives rise to different features, such as (i) continuous or discontinuous responses to the demand strength and (ii) either single or multi-stable solutions. Our study shows the crucial role of the activation function on noise-assisted phenomena.
- [29] arXiv:2406.13644 (cross-list from math.NA) [pdf, html, other]
-
Title: Kinetic Monte Carlo methods for three-dimensional diffusive capture problems in exterior domainsComments: 32 pages, 10 figuresSubjects: Numerical Analysis (math.NA); Analysis of PDEs (math.AP); Biological Physics (physics.bio-ph); Quantitative Methods (q-bio.QM)
Cellular scale decision making is modulated by the dynamics of signalling molecules and their diffusive trajectories from a source to small absorbing sites on the cellular surface. Diffusive capture problems are computationally challenging due to the complex geometry and the applied boundary conditions together with intrinsically long transients that occur before a particle is captured. This paper reports on a particle-based Kinetic Monte Carlo (KMC) method that provides rapid accurate simulation of arrival statistics for (i) a half-space bounded by a surface with a finite collection of absorbing traps and (ii) the domain exterior to a convex cell again with absorbing traps. We validate our method by replicating classical results and in addition, newly developed boundary homogenization theories and matched asymptotic expansions on capture rates. In the case of non-spherical domains, we describe a new shielding effect in which geometry can play a role in sharpening cellular estimates on the directionality of diffusive sources.
- [30] arXiv:2406.13730 (cross-list from math.SP) [pdf, html, other]
-
Title: Prescribed exponential stabilization of a one-layer neural network with delayed feedback: Insights in seizure prevention and neural controlSubjects: Spectral Theory (math.SP); Dynamical Systems (math.DS); Optimization and Control (math.OC); Neurons and Cognition (q-bio.NC)
This paper provides control-oriented delay-based modelling of a one-layer neural network of Hopfield-type subject to an external input designed as delayed feedback. The specificity of such a model is that it makes the considered neuron less susceptible to seizure caused by its inherent dynamic instability. This modelling exploits a recently set partial pole placement for linear functional differential equations, which relies on the coexistence of real spectral values, allowing the explicit prescription of the closed-loop solution's exponential decay. The proposed framework improves some pioneering and scarce results from the literature on the characterization of the exact solution's exponential decay when a simple real spectral value exists. Indeed, it improves neural stability when the inherent dynamic is stable and provides insights into the design of a one-layer neural network that can be stabilized exponentially with delayed feedback and with a prescribed decay rate regardless of whether the inherent neuron dynamic is stable or unstable.
- [31] arXiv:2406.13816 (cross-list from physics.soc-ph) [pdf, html, other]
-
Title: The Dangerous Allure of Low FertilityComments: 9 pages, 5 figures, 2 appendices, 1 tableSubjects: Physics and Society (physics.soc-ph); Populations and Evolution (q-bio.PE)
Stochastic population and wealth trajectories for societies as functions of fertility are modeled with a minimal, endogenous model of a simple foraging economy. The model is scaled to match human lifespans and overall death rates. Stochastic population instability at both the high and low ends of fertility are considered. Lower population levels, caused by low fertility, generate concerns on economic growth, military security, and international political power; while also seen by some as reducing ecological and environmental damage. The model shows that increasingly low fertility leads to both higher wealth and lower population levels. As society is encouraged by increasing per capita wealth to continue to decrease fertility, dangerous population regimes are reached where stochastic extinction becomes more and more likely.
- [32] arXiv:2406.13864 (cross-list from cs.LG) [pdf, html, other]
-
Title: Evaluating representation learning on the protein structure universeArian R. Jamasb, Alex Morehead, Chaitanya K. Joshi, Zuobai Zhang, Kieran Didi, Simon V. Mathis, Charles Harris, Jian Tang, Jianlin Cheng, Pietro Lio, Tom L. BlundellComments: ICLR 2024Subjects: Machine Learning (cs.LG); Biomolecules (q-bio.BM)
We introduce ProteinWorkshop, a comprehensive benchmark suite for representation learning on protein structures with Geometric Graph Neural Networks. We consider large-scale pre-training and downstream tasks on both experimental and predicted structures to enable the systematic evaluation of the quality of the learned structural representation and their usefulness in capturing functional relationships for downstream tasks. We find that: (1) large-scale pretraining on AlphaFold structures and auxiliary tasks consistently improve the performance of both rotation-invariant and equivariant GNNs, and (2) more expressive equivariant GNNs benefit from pretraining to a greater extent compared to invariant models. We aim to establish a common ground for the machine learning and computational biology communities to rigorously compare and advance protein structure representation learning. Our open-source codebase reduces the barrier to entry for working with large protein structure datasets by providing: (1) storage-efficient dataloaders for large-scale structural databases including AlphaFoldDB and ESM Atlas, as well as (2) utilities for constructing new tasks from the entire PDB. ProteinWorkshop is available at: this http URL.
- [33] arXiv:2406.13869 (cross-list from cs.LG) [pdf, html, other]
-
Title: Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement LearningDanqing Wang, Antonis Antoniades, Kha-Dinh Luong, Edwin Zhang, Mert Kosan, Jiachen Li, Ambuj Singh, William Yang Wang, Lei LiComments: Accepted by KDD 2024Subjects: Machine Learning (cs.LG); Biomolecules (q-bio.BM)
Counterfactual explanations of Graph Neural Networks (GNNs) offer a powerful way to understand data that can naturally be represented by a graph structure. Furthermore, in many domains, it is highly desirable to derive data-driven global explanations or rules that can better explain the high-level properties of the models and data in question. However, evaluating global counterfactual explanations is hard in real-world datasets due to a lack of human-annotated ground truth, which limits their use in areas like molecular sciences. Additionally, the increasing scale of these datasets provides a challenge for random search-based methods. In this paper, we develop a novel global explanation model RLHEX for molecular property prediction. It aligns the counterfactual explanations with human-defined principles, making the explanations more interpretable and easy for experts to evaluate. RLHEX includes a VAE-based graph generator to generate global explanations and an adapter to adjust the latent representation space to human-defined principles. Optimized by Proximal Policy Optimization (PPO), the global explanations produced by RLHEX cover 4.12% more input graphs and reduce the distance between the counterfactual explanation set and the input set by 0.47% on average across three molecular datasets. RLHEX provides a flexible framework to incorporate different human-designed principles into the counterfactual explanation generation process, aligning these explanations with domain expertise. The code and data are released at this https URL.
- [34] arXiv:2406.14021 (cross-list from cs.CL) [pdf, html, other]
-
Title: HIGHT: Hierarchical Graph Tokenization for Graph-Language AlignmentComments: Preliminary version of an ongoing project: this https URLSubjects: Computation and Language (cs.CL); Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
Recently there has been a surge of interest in extending the success of large language models (LLMs) to graph modality, such as social networks and molecules. As LLMs are predominantly trained with 1D text data, most existing approaches adopt a graph neural network to represent a graph as a series of node tokens and feed these tokens to LLMs for graph-language alignment. Despite achieving some successes, existing approaches have overlooked the hierarchical structures that are inherent in graph data. Especially, in molecular graphs, the high-order structural information contains rich semantics of molecular functional groups, which encode crucial biochemical functionalities of the molecules. We establish a simple benchmark showing that neglecting the hierarchical information in graph tokenization will lead to subpar graph-language alignment and severe hallucination in generated outputs. To address this problem, we propose a novel strategy called HIerarchical GrapH Tokenization (HIGHT). HIGHT employs a hierarchical graph tokenizer that extracts and encodes the hierarchy of node, motif, and graph levels of informative tokens to improve the graph perception of LLMs. HIGHT also adopts an augmented graph-language supervised fine-tuning dataset, enriched with the hierarchical graph information, to further enhance the graph-language alignment. Extensive experiments on 7 molecule-centric benchmarks confirm the effectiveness of HIGHT in reducing hallucination by 40%, as well as significant improvements in various molecule-language downstream tasks.
- [35] arXiv:2406.14234 (cross-list from physics.med-ph) [pdf, html, other]
-
Title: Zero field active shieldingComments: 26 pages, 7 figuresSubjects: Medical Physics (physics.med-ph); Human-Computer Interaction (cs.HC); Signal Processing (eess.SP); Instrumentation and Detectors (physics.ins-det); Neurons and Cognition (q-bio.NC)
Ambient field suppression is critical for accurate magnetic field measurements, and a requirement for certain low-field sensors to operate. The difference in magnitude between noise and signal (up to 10$^9$) makes the problem challenging, and solutions such as passive shielding, post-hoc processing, and most active shielding designs do not address it completely. Zero field active shielding (ZFS) achieves accurate field suppression with a feed-forward structure in which correction coils are fed by reference sensors via a matrix found using data-driven methods. Requirements are a sufficient number of correction coils and reference sensors to span the ambient field at the sensors, and to zero out the coil-to-reference sensor coupling. The solution assumes instantaneous propagation and mixing, but it can be extended to handle convolutional effects. Precise calculations based on sensor and coil geometries are not necessary, other than to improve efficiency and usability. The solution is simulated here but not implemented in hardware.
- [36] arXiv:2406.14287 (cross-list from eess.IV) [pdf, html, other]
-
Title: Segmentation of Non-Small Cell Lung Carcinomas: Introducing DRU-Net and Multi-Lens DistortionSoroush Oskouei, Marit Valla, André Pedersen, Erik Smistad, Vibeke Grotnes Dale, Maren Høibø, Sissel Gyrid Freim Wahl, Mats Dehli Haugum, Thomas Langø, Maria Paula Ramnefjell, Lars Andreas Akslen, Gabriel Kiss, Hanne SorgerComments: 16 pages, 7 figures, submitted to Scientific ReportsSubjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
Considering the increased workload in pathology laboratories today, automated tools such as artificial intelligence models can help pathologists with their tasks and ease the workload. In this paper, we are proposing a segmentation model (DRU-Net) that can provide a delineation of human non-small cell lung carcinomas and an augmentation method that can improve classification results. The proposed model is a fused combination of truncated pre-trained DenseNet201 and ResNet101V2 as a patch-wise classifier followed by a lightweight U-Net as a refinement model. We have used two datasets (Norwegian Lung Cancer Biobank and Haukeland University Hospital lung cancer cohort) to create our proposed model. The DRU-Net model achieves an average of 0.91 Dice similarity coefficient. The proposed spatial augmentation method (multi-lens distortion) improved the network performance by 3%. Our findings show that choosing image patches that specifically include regions of interest leads to better results for the patch-wise classifier compared to other sampling methods. The qualitative analysis showed that the DRU-Net model is generally successful in detecting the tumor. On the test set, some of the cases showed areas of false positive and false negative segmentation in the periphery, particularly in tumors with inflammatory and reactive changes.
- [37] arXiv:2406.14350 (cross-list from physics.bio-ph) [pdf, html, other]
-
Title: A first-principles geometric model for dynamics of motor-driven centrosomal astersComments: 50 pages (double-spaced), eight figures in main text, and four figures in the supplemental materialSubjects: Biological Physics (physics.bio-ph); Adaptation and Self-Organizing Systems (nlin.AO); Subcellular Processes (q-bio.SC)
The centrosomal aster is a mobile cellular organelle that exerts and transmits forces necessary for nuclear migration and spindle positioning. Recent experimental and theoretical studies of nematode and human cells demonstrate that pulling forces on asters by cortical force generators are dominant during such processes. We present a comprehensive investigation of a first-principles model of aster dynamics, the S-model (S for stoichiometry), based solely on such forces. The model evolves the astral centrosome position, a probability field of cell-surface motor occupancy by centrosomal microtubules (under an assumption of stoichiometric binding), and free boundaries of unattached, growing microtubules. We show how cell shape affects the centering stability of the aster, and its transition to oscillations with increasing motor number. Seeking to understand observations in single-cell nematode embryos, we use accurate simulations to examine the nonlinear structures of the bifurcations, and demonstrate the importance of binding domain overlap to interpreting genetic perturbation experiments. We find a rich dynamical landscape, dependent upon cell shape, such as internal equatorial orbits of asters that can be seen as traveling wave solutions. Finally, we study the interactions of multiple asters and demonstrate an effective mutual repulsion due to their competition for cortical force generators. We find, amazingly, that asters can relax onto the vertices of platonic and non-platonic solids, closely mirroring the results of the classical Thomson problem for energy-minimizing configurations of electrons constrained to a sphere and interacting via repulsive Coulomb potentials. Our findings both explain experimental observations, providing insights into the mechanisms governing spindle positioning and cell division dynamics, and show the possibility of new nonlinear phenomena in cell biology.
- [38] arXiv:2406.14427 (cross-list from cs.AI) [pdf, html, other]
-
Title: Control when confidence is costlyComments: 9 pages, 4 figures, submitted to NeurIPS 2024Subjects: Artificial Intelligence (cs.AI); Neurons and Cognition (q-bio.NC)
We develop a version of stochastic control that accounts for computational costs of inference. Past studies identified efficient coding without control, or efficient control that neglects the cost of synthesizing information. Here we combine these concepts into a framework where agents rationally approximate inference for efficient control. Specifically, we study Linear Quadratic Gaussian (LQG) control with an added internal cost on the relative precision of the posterior probability over the world state. This creates a trade-off: an agent can obtain more utility overall by sacrificing some task performance, if doing so saves enough bits during inference. We discover that the rational strategy that solves the joint inference and control problem goes through phase transitions depending on the task demands, switching from a costly but optimal inference to a family of suboptimal inferences related by rotation transformations, each misestimate the stability of the world. In all cases, the agent moves more to think less. This work provides a foundation for a new type of rational computations that could be used by both brains and machines for efficient but computationally constrained control.
- [39] arXiv:2406.14442 (cross-list from cs.LG) [pdf, html, other]
-
Title: Graph Representation Learning Strategies for Omics Data: A Case Study on Parkinson's DiseaseElisa Gómez de Lope (1), Saurabh Deshpande (1), Ramón Viñas Torné (2), Pietro Liò (3), Enrico Glaab (1 and 4), Stéphane P. A. Bordas (1) ((1) University of Luxembourg, (2) École polytechnique fédérale de Lausanne (EPFL), (3) University of Cambridge, (4) On behalf of the NCER-PD Consortium)Comments: Submitted to Machine Learning in Computational Biology 2024 as an extended abstract, 2 pages + 1 appendixSubjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Biomolecules (q-bio.BM); Molecular Networks (q-bio.MN)
Omics data analysis is crucial for studying complex diseases, but its high dimensionality and heterogeneity challenge classical statistical and machine learning methods. Graph neural networks have emerged as promising alternatives, yet the optimal strategies for their design and optimization in real-world biomedical challenges remain unclear. This study evaluates various graph representation learning models for case-control classification using high-throughput biological data from Parkinson's disease and control samples. We compare topologies derived from sample similarity networks and molecular interaction networks, including protein-protein and metabolite-metabolite interactions (PPI, MMI). Graph Convolutional Network (GCNs), Chebyshev spectral graph convolution (ChebyNet), and Graph Attention Network (GAT), are evaluated alongside advanced architectures like graph transformers, the graph U-net, and simpler models like multilayer perceptron (MLP).
These models are systematically applied to transcriptomics and metabolomics data independently. Our comparative analysis highlights the benefits and limitations of various architectures in extracting patterns from omics data, paving the way for more accurate and interpretable models in biomedical research. - [40] arXiv:2406.14481 (cross-list from cs.LG) [pdf, html, other]
-
Title: Revealing Vision-Language Integration in the Brain with Multimodal NetworksVighnesh Subramaniam, Colin Conwell, Christopher Wang, Gabriel Kreiman, Boris Katz, Ignacio Cases, Andrei BarbuComments: ICML 2024; 23 pages, 11 figuresSubjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE); Neurons and Cognition (q-bio.NC)
We use (multi)modal deep neural networks (DNNs) to probe for sites of multimodal integration in the human brain by predicting stereoencephalography (SEEG) recordings taken while human subjects watched movies. We operationalize sites of multimodal integration as regions where a multimodal vision-language model predicts recordings better than unimodal language, unimodal vision, or linearly-integrated language-vision models. Our target DNN models span different architectures (e.g., convolutional networks and transformers) and multimodal training techniques (e.g., cross-attention and contrastive learning). As a key enabling step, we first demonstrate that trained vision and language models systematically outperform their randomly initialized counterparts in their ability to predict SEEG signals. We then compare unimodal and multimodal models against one another. Because our target DNN models often have different architectures, number of parameters, and training sets (possibly obscuring those differences attributable to integration), we carry out a controlled comparison of two models (SLIP and SimCLR), which keep all of these attributes the same aside from input modality. Using this approach, we identify a sizable number of neural sites (on average 141 out of 1090 total sites or 12.94%) and brain regions where multimodal integration seems to occur. Additionally, we find that among the variants of multimodal training techniques we assess, CLIP-style training is the best suited for downstream prediction of the neural activity in these sites.
- [41] arXiv:2406.14549 (cross-list from cs.CV) [pdf, html, other]
-
Title: Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Large Language ModelsSubjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC)
The proliferation of large language models has revolutionized natural language processing tasks, yet it raises profound concerns regarding data privacy and security. Language models are trained on extensive corpora including potentially sensitive or proprietary information, and the risk of data leakage -- where the model response reveals pieces of such information -- remains inadequately understood. This study examines susceptibility to data leakage by quantifying the phenomenon of memorization in machine learning models, focusing on the evolution of memorization patterns over training. We investigate how the statistical characteristics of training data influence the memories encoded within the model by evaluating how repetition influences memorization. We reproduce findings that the probability of memorizing a sequence scales logarithmically with the number of times it is present in the data. Furthermore, we find that sequences which are not apparently memorized after the first encounter can be uncovered throughout the course of training even without subsequent encounters. The presence of these latent memorized sequences presents a challenge for data privacy since they may be hidden at the final checkpoint of the model. To this end, we develop a diagnostic test for uncovering these latent memorized sequences by considering their cross entropy loss.
Cross submissions for Friday, 21 June 2024 (showing 20 of 20 entries )
- [42] arXiv:2205.04393 (replaced) [pdf, other]
-
Title: Pre-frontal cortex guides dimension-reducing transformations in the occipito-ventral pathway for categorization behaviorsY. Duan (1), J. Zhan (1), J. Gross (2), R.A.A. Ince (1), P.G. Schyns (1) ((1) School of Psychology and Neuroscience, University of Glasgow, United Kingdom, (2) Institute for Biomagnetism and Biosignalanalysis, University of Münster, Germany)Subjects: Neurons and Cognition (q-bio.NC)
To interpret our surroundings, the brain uses a visual categorization process. Current theories and models suggest that this process comprises a hierarchy of different computations that transforms complex, high-dimensional inputs into lower-dimensional representations (i.e. manifolds) in support of multiple categorization behaviors. Here, we tested this hypothesis by analyzing these transformations reflected in dynamic MEG source activity while individual participants actively categorized the same stimuli according to different tasks: face expression, face gender, pedestrian gender, vehicle type. Results reveal three transformation stages guided by pre-frontal cortex. At Stage 1 (high-dimensional, 50-120ms), occipital sources represent both task-relevant and task-irrelevant stimulus features; task-relevant features advance into higher ventral/dorsal regions whereas task-irrelevant features halt at the occipital-temporal junction. At Stage 2 (121-150ms), stimulus feature representations reduce to lower-dimensional manifolds, which then transform into the task-relevant features underlying categorization behavior over Stage 3 (161-350ms).
- [43] arXiv:2212.14041 (replaced) [pdf, html, other]
-
Title: Deciphering RNA Secondary Structure Prediction: A Probabilistic K-Rook Matching PerspectiveCheng Tan, Zhangyang Gao, Hanqun Cao, Xingran Chen, Ge Wang, Lirong Wu, Jun Xia, Jiangbin Zheng, Stan Z. LiComments: Accepted by ICML 2024Subjects: Biomolecules (q-bio.BM); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
The secondary structure of ribonucleic acid (RNA) is more stable and accessible in the cell than its tertiary structure, making it essential for functional prediction. Although deep learning has shown promising results in this field, current methods suffer from poor generalization and high complexity. In this work, we reformulate the RNA secondary structure prediction as a K-Rook problem, thereby simplifying the prediction process into probabilistic matching within a finite solution space. Building on this innovative perspective, we introduce RFold, a simple yet effective method that learns to predict the most matching K-Rook solution from the given sequence. RFold employs a bi-dimensional optimization strategy that decomposes the probabilistic matching problem into row-wise and column-wise components to reduce the matching complexity, simplifying the solving process while guaranteeing the validity of the output. Extensive experiments demonstrate that RFold achieves competitive performance and about eight times faster inference efficiency than the state-of-the-art approaches. The code and Colab demo are available in (this http URL).
- [44] arXiv:2306.00471 (replaced) [pdf, html, other]
-
Title: Muller's ratchet in a near-critical regime: tournament versus fitness proportional selectionComments: The presentation is now focussed on the forward-in-time approach. The proof of the main result has been re-structured and expandedSubjects: Populations and Evolution (q-bio.PE); Probability (math.PR)
Muller's ratchet, in its prototype version, models a haploid, asexual population whose size~$N$ is constant over the generations. Slightly deleterious mutations are acquired along the lineages at a constant rate, and individuals carrying less mutations have a selective advantage. The classical variant considers {\it fitness proportional} selection, but other fitness schemes are conceivable as well. Inspired by the work of Etheridge et al. ([EPW09]) we propose a parameter scaling which fits well to the ``near-critical'' regime that was in the focus of [EPW09] (and in which the mutation-selection ratio diverges logarithmically as $N\to \infty$). Using a Moran model, we investigate the``rule of thumb'' given in [EPW09] for the click rate of the ``classical ratchet'' by putting it into the context of new results on the long-time evolution of the size of the best class of the ratchet with (binary) tournament selection, which (other than that of the classical ratchet) follows an autonomous dynamics up to the time of its extinction.
In [GSW23] it was discovered that the tournament ratchet has a hierarchy of dual processes which can be constructed on top of an Ancestral Selection graph with a Poisson decoration. For a regime in which the mutation/selection-ratio remains bounded away from 1, this was used in [GSW23] to reveal the asymptotics of the click rates as well as that of the type frequency profile between clicks. We will describe how these ideas can be extended to the near-critical regime in which the mutation-selection ratio of the tournament ratchet converges to 1 as $N\to \infty$. - [45] arXiv:2310.20309 (replaced) [pdf, html, other]
-
Title: Tensor formalism for predicting synaptic connections with ensemble modeling or optimizationComments: 31 pages, 6 figures, 2 tablesSubjects: Neurons and Cognition (q-bio.NC); Disordered Systems and Neural Networks (cond-mat.dis-nn); Biological Physics (physics.bio-ph)
Theoretical neuroscientists often try to understand how the structure of a neural network relates to its function by focusing on structural features that would either follow from optimization or occur consistently across possible implementations. Both optimization theories and ensemble modeling approaches have repeatedly proven their worth, and it would simplify theory building considerably if predictions from both theory types could be derived and tested simultaneously. Here we show how tensor formalism from theoretical physics can be used to unify and solve many optimization and ensemble modeling approaches to predicting synaptic connectivity from neuronal responses. We specifically focus on analyzing the solution space of synaptic weights that allow a threshold-linear neural network to respond in a prescribed way to a limited number of input conditions. For optimization purposes, we compute the synaptic weight vector that minimizes an arbitrary quadratic loss function. For ensemble modeling, we identify synaptic weight features that occur consistently across all solutions bounded by an arbitrary ellipsoid. We derive a common solution to this suite of nonlinear problems by showing how each of them reduces to an equivalent linear problem that can be solved analytically. Although identifying the equivalent linear problem is nontrivial, our tensor formalism provides an elegant geometrical perspective that allows us to solve the problem approximately in an analytical way or exactly using numeric methods. The final algorithm is applicable to a wide range of interesting neuroscience problems, and the associated geometric insights may carry over to other scientific problems that require constrained optimization.
- [46] arXiv:2312.01646 (replaced) [pdf, html, other]
-
Title: Enhancing data-limited assessments with random effects: A case study on Korea chub mackerel (Scomber japonicus)Kyuhan Kim (1), Nokuthaba Sibanda (2), Richard Arnold (2), Teresa A'mar (1) ((1) Dragonfly Data Science, Wellington, New Zealand, (2) School of Mathematics and Statistics, Victoria University of Wellington, Wellington, New Zealand)Comments: 78 pages, 21 figuresSubjects: Populations and Evolution (q-bio.PE); Quantitative Methods (q-bio.QM)
In a state-space framework, temporal variations in fishery-dependent processes can be modeled as random effects. This modeling flexibility makes state-space models (SSMs) powerful tools for data-limited assessments. Though SSMs enable the model-based inference of the unobserved processes, their flexibility can lead to overfitting and non-identifiability issues. To address these challenges, we developed a suite of state-space length-based age-structured models and applied them to the Korean chub mackerel (Scomber japonicus) stock. Our research demonstrated that incorporating temporal variations in fishery-dependent processes can rectify model mis-specification but may compromise robustness, which can be diagnosed through a series of model checking processes. To tackle non-identifiability, we used a non-degenerate estimator, implementing a gamma distribution as a penalty for the standard deviation parameters of observation errors. This penalty function enabled the simultaneous estimation of both process and observation error variances with minimal bias, a notably challenging task in SSMs. These results highlight the importance of model checking and the effectiveness of the penalized approach in estimating SSMs. Additionally, we discussed novel assessment outcomes for the mackerel stock.
- [47] arXiv:2312.03489 (replaced) [pdf, html, other]
-
Title: Decomposing Thermodynamic Dissipation of Linear Langevin Systems via Oscillatory Modes and Its Application to Neural DynamicsSubjects: Neurons and Cognition (q-bio.NC); Statistical Mechanics (cond-mat.stat-mech)
Recent developments in stochastic thermodynamics have elucidated various relations between the entropy production rate (thermodynamic dissipation) and the physical limits of information processing in nonequilibrium dynamical systems. These findings have opened new perspectives in analyzing real biological systems. In neuroscience, the importance of quantifying entropy production has attracted attention for understanding information processing in the brain. However, the relationship between the entropy production rate and oscillations, which are common in many biological systems, remains unclear. For instance, neural oscillations like delta, theta, and alpha waves play crucial roles in brain information processing. Here, we derive a novel decomposition of the entropy production rate of linear Langevin systems. We show that one component of the entropy production rate, called the housekeeping entropy production rate, can be decomposed into independent positive contributions from oscillatory modes. Our decomposition enables us to calculate the contribution of oscillatory modes to the housekeeping entropy production rate. In addition, when the noise matrix is diagonal, the contribution of each oscillatory mode can be further decomposed into the contribution of each system element. To demonstrate the utility of our decomposition, we applied it to an electrocorticography (ECoG) dataset recorded during awake and anesthetized conditions in monkeys, where the oscillatory properties change drastically. We showed consistent trends across different monkeys: the contribution of delta band was larger in the anesthetized condition than in the awake condition, while those from higher frequency bands, such as the theta band, were smaller. These results allow us to interpret the changes in neural oscillation in terms of stochastic thermodynamics and the physical limits of information processing.
- [48] arXiv:2312.06824 (replaced) [pdf, html, other]
-
Title: A picture guide to cancer progression and monotonic accumulation models: evolutionary assumptions, plausible interpretations, and alternative usesComments: Abstract 200 words; added details to BML; consistent British spelling. [Previous changes: Iain G. Johnston coauthor; clarified LOD/POM; clarified scenarios by moving some text to new section; comment Schill et al. 2024 selection bias; clarifications and fixed typos; additional annotation in some figures and figure legends. Added URLs and DOIs to references; corrected typos; added URL to software]Subjects: Populations and Evolution (q-bio.PE); Quantitative Methods (q-bio.QM)
Cancer progression and monotonic accumulation models were developed to discover dependencies in the irreversible acquisition of binary traits from cross-sectional data. They have been used in computational oncology and virology but also in widely different problems such as malaria progression. These methods have been applied to predict future states of the system, identify routes of feature acquisition, and improve patient stratification, and they hold promise for evolutionary-based treatments. New methods continue to be developed.
But these methods have shortcomings, which are yet to be systematically critiqued, regarding key evolutionary assumptions and interpretations. After an overview of the available methods, we focus on why inferences might not be about the processes we intend. Using fitness landscapes, we highlight difficulties that arise from bulk sequencing and reciprocal sign epistasis, from conflating lines of descent, path of the maximum, and mutational profiles, and from ambiguous use of the idea of exclusivity. We examine how the previous concerns change when bulk sequencing is explicitly considered, and underline opportunities for addressing dependencies due to frequency-dependent selection. This review identifies major standing issues, and should encourage the use of these methods in other areas with a better alignment between entities and model assumptions. - [49] arXiv:2405.18419 (replaced) [pdf, html, other]
-
Title: Exploring the Evolution of Altruistic Punishment with a PDE Model of Cultural Multilevel SelectionComments: 79 pages, 17 figures v2; Updated version of Section 5 with corrected versions of Figures 5.1 and 5.5, as well as new subsection and figure added to describe multilevel dynamics for Tullock contest function (Figure 5.5 in Section 5.3)Subjects: Populations and Evolution (q-bio.PE); Physics and Society (physics.soc-ph)
Two mechanisms that have been used to study the evolution of cooperative behavior are altruistic punishment, in which cooperative individuals pay additional costs to punish defection, and multilevel selection, in which competition between groups can help to counteract individual-level incentives to cheat. Boyd, Gintis, Bowles, and Richerson have used simulation models of cultural evolution to suggest that altruistic punishment and pairwise group-level competition can work in concert to promote cooperation, even when neither mechanism can do so on its own. In this paper, we formulate a PDE model for multilevel selection motivated by the approach of Boyd and coauthors, modeling individual-level birth-death competition with a replicator equation based on individual payoffs and describing group-level competition with pairwise conflicts based on differences in the average payoffs of the competing groups. Building off of existing PDE models for multilevel selection with frequency-independent group-level competition, we use analytical and numerical techniques to understand how the forms of individual and average payoffs can impact the long-time ability to sustain altruistic punishment in group-structured populations. We find several interesting differences between the behavior of our new PDE model with pairwise group-level competition and existing multilevel PDE models, including the observation that our new model can feature a non-monotonic dependence of the long-time collective payoff on the strength of altruistic punishment. Going forward, our PDE framework can serve as a way to connect and compare disparate approaches for understanding multilevel selection across the literature in evolutionary biology and anthropology.
- [50] arXiv:2405.20203 (replaced) [pdf, html, other]
-
Title: The development of drug resistance in metastatic tumours under chemotherapy: an evolutionary perspectiveComments: 35 pages, 10 Figures, 1 Supplementary materialSubjects: Cell Behavior (q-bio.CB)
We present a mathematical model of the evolutionary dynamics of a metastatic tumour under chemotherapy, comprising non-local partial differential equations for the phenotype-structured cell populations in the primary tumour and its metastasis. These equations are coupled with a physiologically-based pharmacokinetic model of drug delivery, implementing a realistic delivery schedule. The model is carefully calibrated from the literature, focusing on BRAF-mutated melanoma treated with Dabrafenib as a case study. By means of long-time asymptotic analysis, global sensitivity analysis and numerical simulations, we explore the impact of cell migration from the primary to the metastatic site, physiological aspects of the tumour sites and drug dose on the development of drug resistance and treatment efficacy. Our findings provide a possible explanation for empirical evidence indicating that chemotherapy may foster metastatic spread and that metastatic sites may be less impacted by chemotherapy.
- [51] arXiv:2406.10184 (replaced) [pdf, html, other]
-
Title: Hyperbolic embedding of brain networks as a tool for epileptic seizures forecastingSubjects: Neurons and Cognition (q-bio.NC); Data Analysis, Statistics and Probability (physics.data-an)
The evidence indicates that intracranial EEG connectivity, as estimated from daily resting state recordings from epileptic patients, may be capable of identifying preictal states. In this study, we employed hyperbolic embedding of brain networks to capture non-trivial patterns that discriminate between connectivity networks from days with (preictal) and without (interictal) seizure. A statistical model was constructed by combining hyperbolic geometry and machine learning tools, which allowed for the estimation of the probability of an upcoming seizure. The results demonstrated that representing brain networks in a hyperbolic space enabled an accurate discrimination (85%) between interictal (no-seizure) and preictal (seizure within the next 24 hours) states. The proposed method also demonstrated excellent prediction performances, with an overall accuracy of 87% and an F1-score of 89% (mean Brier score and Brier skill score of 0.12 and 0.37, respectively). In conclusion, our findings indicate that representations of brain connectivity in a latent geometry space can reveal a daily and reliable signature of the upcoming seizure(s), thus providing a promising biomarker for seizure forecasting.
- [52] arXiv:2406.12108 (replaced) [pdf, other]
-
Title: Computing in the Life Sciences: From Early Algorithms to Modern AIComments: 53 pages, 4 figures, 10 tablesSubjects: Other Quantitative Biology (q-bio.OT); Artificial Intelligence (cs.AI)
Computing in the life sciences has undergone a transformative evolution, from early computational models in the 1950s to the applications of artificial intelligence (AI) and machine learning (ML) seen today. This paper highlights key milestones and technological advancements through the historical development of computing in the life sciences. The discussion includes the inception of computational models for biological processes, the advent of bioinformatics tools, and the integration of AI/ML in modern life sciences research. Attention is given to AI-enabled tools used in the life sciences, such as scientific large language models and bio-AI tools, examining their capabilities, limitations, and impact to biological risk. This paper seeks to clarify and establish essential terminology and concepts to ensure informed decision-making and effective communication across disciplines.
- [53] arXiv:2201.09812 (replaced) [pdf, html, other]
-
Title: Natural Selection and Random Matrix TheorySubjects: Chaotic Dynamics (nlin.CD); Populations and Evolution (q-bio.PE)
We will study the relationship between two well-known theories, genetic evolution and random matrix theory in the context of many-body systems. We show that the time evolution of certain quantum mechanical toy models is similar to that of a living cell. It is also suggested that genetic evolution can be described by a random matrix theory with statistical distribution in which natural selection acts as a Gross-Witten-Wadia phase transition.
- [54] arXiv:2307.12044 (replaced) [pdf, html, other]
-
Title: Kinetic description of swarming dynamics with topological interaction and transient leadersSubjects: Numerical Analysis (math.NA); Populations and Evolution (q-bio.PE)
In this paper, we present a model describing the collective motion of birds. The model introduces spontaneous changes in direction which are initialized by few agents, here referred as leaders, whose influence act on their nearest neighbors, in the following referred as followers. Starting at the microscopic level, we develop a kinetic model that characterizes the behaviour of large flocks with transient leadership. One significant challenge lies in managing topological interactions, as identifying nearest neighbors in extensive systems can be computationally expensive. To address this, we propose a novel stochastic particle method to simulate the mesoscopic dynamics and reduce the computational cost of identifying closer agents from quadratic to logarithmic complexity using a $k$-nearest neighbours search algorithm with a binary tree. Lastly, we conduct various numerical experiments for different scenarios to validate the algorithm's effectiveness and investigate collective dynamics in both two and three dimensions.
- [55] arXiv:2310.16113 (replaced) [pdf, other]
-
Title: Compressed representation of brain genetic transcriptionJames K Ruffle, Henry Watkins, Robert J Gray, Harpreet Hyare, Michel Thiebaut de Schotten, Parashkev NachevComments: 22 pages, 5 main figures, 1 supplementary figureSubjects: Machine Learning (cs.LG); Genomics (q-bio.GN); Neurons and Cognition (q-bio.NC)
The architecture of the brain is too complex to be intuitively surveyable without the use of compressed representations that project its variation into a compact, navigable space. The task is especially challenging with high-dimensional data, such as gene expression, where the joint complexity of anatomical and transcriptional patterns demands maximum compression. Established practice is to use standard principal component analysis (PCA), whose computational felicity is offset by limited expressivity, especially at great compression ratios. Employing whole-brain, voxel-wise Allen Brain Atlas transcription data, here we systematically compare compressed representations based on the most widely supported linear and non-linear methods-PCA, kernel PCA, non-negative matrix factorization (NMF), t-stochastic neighbour embedding (t-SNE), uniform manifold approximation and projection (UMAP), and deep auto-encoding-quantifying reconstruction fidelity, anatomical coherence, and predictive utility with respect to signalling, microstructural, and metabolic targets. We show that deep auto-encoders yield superior representations across all metrics of performance and target domains, supporting their use as the reference standard for representing transcription patterns in the human brain.
- [56] arXiv:2311.02596 (replaced) [pdf, html, other]
-
Title: Embedding of Markov matrices for $d\leqslant 4$Michael Baake (Bielefeld), Jeremy Sumner (Hobart)Comments: 41 pages, 2 tables; revised and improved versionSubjects: Probability (math.PR); Populations and Evolution (q-bio.PE)
The embedding problem of Markov matrices in Markov semigroups is a classic problem that regained a lot of impetus and activities through recent needs in phylogeny and population genetics. Here, we give an account for dimensions $d\leqslant 4$, including a complete and simplified treatment of the case $d=3$, and derive the results in a systematic fashion, with an eye on the potential applications.
Further, we reconsider the setup of the corresponding problem for time-inhomogeneous Markov chains, which is needed for real-world applications because transition rates need not be constant over time. Additional cases of this more general embedding occur for any $d\geqslant 3$. We review the known case of $d=3$ and describe the setting for future work on $d=4$. - [57] arXiv:2311.13870 (replaced) [pdf, html, other]
-
Title: Multi-intention Inverse Q-learning for Interpretable Behavior RepresentationHao Zhu, Brice De La Crompe, Gabriel Kalweit, Artur Schneider, Maria Kalweit, Ilka Diester, Joschka BoedeckerSubjects: Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC)
In advancing the understanding of natural decision-making processes, inverse reinforcement learning (IRL) methods have proven instrumental in reconstructing animal's intentions underlying complex behaviors. Given the recent development of a continuous-time multi-intention IRL framework, there has been persistent inquiry into inferring discrete time-varying rewards with IRL. To address this challenge, we introduce the class of hierarchical inverse Q-learning (HIQL) algorithms. Through an unsupervised learning process, HIQL divides expert trajectories into multiple intention segments, and solves the IRL problem independently for each. Applying HIQL to simulated experiments and several real animal behavior datasets, our approach outperforms current benchmarks in behavior prediction and produces interpretable reward functions. Our results suggest that the intention transition dynamics underlying complex decision-making behavior is better modeled by a step function instead of a smoothly varying function. This advancement holds promise for neuroscience and cognitive science, contributing to a deeper understanding of decision-making and uncovering underlying brain mechanisms.
- [58] arXiv:2402.01542 (replaced) [pdf, html, other]
-
Title: Learning Collective Variables with Synthetic Data Augmentation through Physics-inspired Geodesic InterpolationSubjects: Chemical Physics (physics.chem-ph); Machine Learning (cs.LG); Biomolecules (q-bio.BM)
In molecular dynamics simulations, rare events, such as protein folding, are typically studied using enhanced sampling techniques, most of which are based on the definition of a collective variable (CV) along which acceleration occurs. Obtaining an expressive CV is crucial, but often hindered by the lack of information about the particular event, e.g., the transition from unfolded to folded conformation. We propose a simulation-free data augmentation strategy using physics-inspired metrics to generate geodesic interpolations resembling protein folding transitions, thereby improving sampling efficiency without true transition state samples. This new data can be used to improve the accuracy of classifier-based methods. Alternatively, a regression-based learning scheme for CV models can be adopted by leveraging the interpolation progress parameter.
- [59] arXiv:2402.11729 (replaced) [pdf, html, other]
-
Title: Prospector Heads: Generalized Feature Attribution for Large Models & DataGautam Machiraju, Alexander Derry, Arjun Desai, Neel Guha, Amir-Hossein Karimi, James Zou, Russ Altman, Christopher Ré, Parag MallickComments: 30 pages, 16 figures, 8 tables. Accepted to ICML 2024Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM)
Feature attribution, the ability to localize regions of the input data that are relevant for classification, is an important capability for ML models in scientific and biomedical domains. Current methods for feature attribution, which rely on "explaining" the predictions of end-to-end classifiers, suffer from imprecise feature localization and are inadequate for use with small sample sizes and high-dimensional datasets due to computational challenges. We introduce prospector heads, an efficient and interpretable alternative to explanation-based attribution methods that can be applied to any encoder and any data modality. Prospector heads generalize across modalities through experiments on sequences (text), images (pathology), and graphs (protein structures), outperforming baseline attribution methods by up to 26.3 points in mean localization AUPRC. We also demonstrate how prospector heads enable improved interpretation and discovery of class-specific patterns in input data. Through their high performance, flexibility, and generalizability, prospectors provide a framework for improving trust and transparency for ML models in complex domains.
- [60] arXiv:2402.16711 (replaced) [pdf, html, other]
-
Title: Action potential propagation properties of 4D, 3D and 2D Hodgkin-Huxley type modelsComments: 8 pages, 12 figuresSubjects: Biological Physics (physics.bio-ph); Neurons and Cognition (q-bio.NC)
We explore the relationship between sodium (Na$^+$) and potassium (K$^+$) gating variables in the 4-dimensional (4D) Hodgkin-Huxley (HH) electrophysiology model and reduce its complexity by deriving new 3D and 2D models that retain the original model's dynamic properties. The new 3D and 2D models are based on the relationship $h \simeq c - n$ between the gating variables $h$ and $n$ of the 4D HH model, where $c$ is a constant, which suggests an interdependence between the dynamics of Na$^+$ and K$^+$ transmembrane voltage-gated channels. We derive the corresponding cable equations for the three HH-type models and demonstrate that the action potential propagates along the axon at a speed described by $v(R, C_m) = \alpha / (C_m R^{\beta}) = \gamma D^{\beta}$, where $\alpha > 0$, $0 < \beta < 1$, and $\gamma$ are constants independent of the local stimulus intensity, $D$ is the diffusion coefficient of the electric signal along the axon, $C_m$ is the axon transmembrane capacitance, and $R$ is the axon conducting resistivity. The width $w$ of the action potential spikes is inversely related to the resistivity of the axon, with $w = \alpha_2 / R^{\beta_2}$, where $\alpha_2 > 0$ and $\beta_2 > 0$.
- [61] arXiv:2405.18051 (replaced) [pdf, other]
-
Title: Predicting Progression Events in Multiple Myeloma from Routine Blood WorkMaximilian Ferle, Nora Grieb, Markus Kreuz, Uwe Platzbecker, Thomas Neumuth, Kristin Reiche, Alexander Oeser, Maximilian MerzComments: 18 pages, 8 figures, 4, tablesSubjects: Applications (stat.AP); Quantitative Methods (q-bio.QM)
The ability to accurately predict disease progression is paramount for optimizing multiple myeloma patient care. This study introduces a hybrid neural network architecture, combining Long Short-Term Memory networks with a Conditional Restricted Boltzmann Machine, to predict future blood work of affected patients from a series of historical laboratory results. We demonstrate that our model can replicate the statistical moments of the time series ($0.95~\pm~0.01~\geq~R^2~\geq~0.83~\pm~0.03$) and forecast future blood work features with high correlation to actual patient data ($0.92\pm0.02~\geq~r~\geq~0.52~\pm~0.09$). Subsequently, a second Long Short-Term Memory network is employed to detect and annotate disease progression events within the forecasted blood work time series. We show that these annotations enable the prediction of progression events with significant reliability (AUROC$~=~0.88~\pm~0.01$), up to 12 months in advance (AUROC($t+12~$mos)$~=0.65~\pm~0.01$). Our system is designed in a modular fashion, featuring separate entities for forecasting and progression event annotation. This structure not only enhances interpretability but also facilitates the integration of additional modules to perform subsequent operations on the generated outputs. Our approach utilizes a minimal set of routine blood work measurements, which avoids the need for expensive or resource-intensive tests and ensures accessibility of the system in clinical routine. This capability allows for individualized risk assessment and making informed treatment decisions tailored to a patient's unique disease kinetics. The represented approach contributes to the development of a scalable and cost-effective virtual human twin system for optimized healthcare resource utilization and improved patient outcomes in multiple myeloma care.
- [62] arXiv:2406.06393 (replaced) [pdf, html, other]
-
Title: STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomicsSubjects: Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL); Genomics (q-bio.GN)
Recent advances in multi-modal algorithms have driven and been driven by the increasing availability of large image-text datasets, leading to significant strides in various fields, including computational pathology. However, in most existing medical image-text datasets, the text typically provides high-level summaries that may not sufficiently describe sub-tile regions within a large pathology image. For example, an image might cover an extensive tissue area containing cancerous and healthy regions, but the accompanying text might only specify that this image is a cancer slide, lacking the nuanced details needed for in-depth analysis. In this study, we introduce STimage-1K4M, a novel dataset designed to bridge this gap by providing genomic features for sub-tile images. STimage-1K4M contains 1,149 images derived from spatial transcriptomics data, which captures gene expression information at the level of individual spatial spots within a pathology image. Specifically, each image in the dataset is broken down into smaller sub-image tiles, with each tile paired with 15,000-30,000 dimensional gene expressions. With 4,293,195 pairs of sub-tile images and gene expressions, STimage-1K4M offers unprecedented granularity, paving the way for a wide range of advanced research in multi-modal data analysis an innovative applications in computational pathology, and beyond.
- [63] arXiv:2406.06479 (replaced) [pdf, html, other]
-
Title: Graph-Based Bidirectional Transformer Decision Threshold Adjustment Algorithm for Class-Imbalanced Molecular DataSubjects: Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
Data sets with imbalanced class sizes, often where one class size is much smaller than that of others, occur extremely often in various applications, including those with biological foundations, such as drug discovery and disease diagnosis. Thus, it is extremely important to be able to identify data elements of classes of various sizes, as a failure to detect can result in heavy costs. However, many data classification algorithms do not perform well on imbalanced data sets as they often fail to detect elements belonging to underrepresented classes. In this paper, we propose the BTDT-MBO algorithm, incorporating Merriman-Bence-Osher (MBO) techniques and a bidirectional transformer, as well as distance correlation and decision threshold adjustments, for data classification problems on highly imbalanced molecular data sets, where the sizes of the classes vary greatly. The proposed method not only integrates adjustments in the classification threshold for the MBO algorithm in order to help deal with the class imbalance, but also uses a bidirectional transformer model based on an attention mechanism for self-supervised learning. Additionally, the method implements distance correlation as a weight function for the similarity graph-based framework on which the adjusted MBO algorithm operates. The proposed model is validated using six molecular data sets, and we also provide a thorough comparison to other competing algorithms. The computational experiments show that the proposed method performs better than competing techniques even when the class imbalance ratio is very high.
- [64] arXiv:2406.12808 (replaced) [pdf, html, other]
-
Title: Graph Neural Networks in Histopathology: Emerging Trends and Future DirectionsSubjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Tissues and Organs (q-bio.TO)
Histopathological analysis of Whole Slide Images (WSIs) has seen a surge in the utilization of deep learning methods, particularly Convolutional Neural Networks (CNNs). However, CNNs often fall short in capturing the intricate spatial dependencies inherent in WSIs. Graph Neural Networks (GNNs) present a promising alternative, adept at directly modeling pairwise interactions and effectively discerning the topological tissue and cellular structures within WSIs. Recognizing the pressing need for deep learning techniques that harness the topological structure of WSIs, the application of GNNs in histopathology has experienced rapid growth. In this comprehensive review, we survey GNNs in histopathology, discuss their applications, and explore emerging trends that pave the way for future advancements in the field. We begin by elucidating the fundamentals of GNNs and their potential applications in histopathology. Leveraging quantitative literature analysis, we identify four emerging trends: Hierarchical GNNs, Adaptive Graph Structure Learning, Multimodal GNNs, and Higher-order GNNs. Through an in-depth exploration of these trends, we offer insights into the evolving landscape of GNNs in histopathological analysis. Based on our findings, we propose future directions to propel the field forward. Our analysis serves to guide researchers and practitioners towards innovative approaches and methodologies, fostering advancements in histopathological analysis through the lens of graph neural networks.