Decoding functional proteome information in model organisms using protein language models.
Ontology highlight
ABSTRACT:
SUBMITTER: Barrios-Nunez I
PROVIDER: S-EPMC11217674 | biostudies-literature | 2024 Sep
REPOSITORIES: biostudies-literature
Publications
Decoding functional proteome information in model organisms using protein language models.
Barrios-Núñez Israel I Martínez-Redondo Gemma I GI Medina-Burgos Patricia P Cases Ildefonso I Fernández Rosa R Rojas Ana M AM
NAR genomics and bioinformatics 20240702 3
Protein language models have been tested and proved to be reliable when used on curated datasets but have not yet been applied to full proteomes. Accordingly, we tested how two different machine learning-based methods performed when decoding functional information from the proteomes of selected model organisms. We found that protein language models are more precise and informative than deep learning methods for all the species tested and across the three gene ontologies studied, and that they be ...[more]
Similar Datasets
Project description:Protein-protein interaction (PPI) networks are a fundamental resource for modeling cellular and molecular function, and a large and sophisticated toolbox has been developed to leverage their structure and topological organization to predict the functional roles of under-studied genes, proteins, and pathways. However, the overwhelming majority of experimentally-determined interactions from which such networks are constructed come from a small number of well-studied model organisms. Indeed, most species lack even a single experimentally-determined interaction in these databases, much less a network to enable the analysis of cellular function, and methods for computational PPI prediction are too noisy to apply directly. We introduce PHILHARMONIC, a novel computational approach that couples deep learning de novo network inference with robust unsupervised spectral clustering algorithms to uncover functional relationships and high-level organization in non-model organisms. Our clustering approach allows us to de-noise the predicted network, producing highly informative functional modules. We also develop a novel algorithm called ReCIPE, which aims to reconnect disconnected clusters, increasing functional enrichment and biological interpretability. We perform remote homology-based functional annotation by leveraging hmmscan and GODomainMiner to assign initial functions to proteins at large evolutionary distances. Our clusters enable us to newly assign functions to uncharacterized proteins through "function by association." We demonstrate the ability of PHILHARMONIC to recover clusters with significant functional coherence in the reef-building coral P. damicornis, its algal symbiont C. goreaui, and the well-annotated fruit fly D. melanogaster. We perform a deeper analysis of the P. damicornis network, where we show that PHILHARMONIC clusters correlate strongly with gene co-expression and investigate several clusters that participate in temperature regulation in the coral, including the first putative functional annotation of several previously uncharacterized proteins. Easy to run end-to-end and requiring only a sequenced proteome, PHILHARMONIC is an engine for biological hypothesis generation and discovery in non-model organisms. PHILHARMONIC is available at https://github.com/samsledje/philharmonic.
| S-EPMC11565725 | biostudies-literature
Project description:Machine learning algorithms are becoming increasingly popular for decoding psychological constructs based on neural data. However, as a step towards bridging the gap between theory-driven cognitive neuroscience and data-driven decoding approaches, there is a need for methods that allow to interpret trained decoding models. The present study demonstrates grouped model reliance as a model-agnostic permutation-based approach to this problem. Grouped model reliance indicates the extent to which a trained model relies on conceptually related groups of variables, such as frequency bands or regions of interest in electroencephalographic (EEG) data. As a case study to demonstrate the method, random forest and support vector machine models were trained on within-participant single-trial EEG data from a Sternberg working memory task. Participants were asked to memorize a sequence of digits (0-9), varying randomly in length between one, four and seven digits, where EEG recordings for working memory load estimation were taken from a 3-second retention interval. The present results confirm previous findings insofar as both random forest and support vector machine models relied on alpha-band activity in most subjects. However, as revealed by further analyses, patterns in frequency and topography varied considerably between individuals, pointing to more pronounced inter-individual differences than previously reported.
| S-EPMC6964974 | biostudies-literature
Project description: Not available
| S-EPMC10782804 | biostudies-literature
Project description:Epstein-Barr virus (EBV), a member of the gamma herpesvirus, is the first identified human oncovirus and is associated with various malignancies. Understanding the intricate interactions between EBV antigens and cellular pathways is crucial to unraveling the molecular mechanisms in EBV-mediated diseases. However, fully elucidating EBV-host interactions and the associated pathogenesis remains a significant challenge. In this study, we employed large language models (LLMs) to screen 36,105 EBV-relevant scientific publications and summarize the current literature landscape on various EBV-associated diseases like Burkitt lymphoma (BL), diffuse large B-cell lymphoma (DLBCL), nasopharyngeal carcinoma (NPC), and so on. LLM-generated data indicate that the most-studied EBV-associated pathways are enriched in immune response, apoptosis, cell growth, and replication. The analyses of protein-protein interactions (PPIs) reveal three principal EBV-related protein clusters: TP53-centered apoptotic factors, EBV-associated transcription factors, and immune response elements. Utilizing our dataset and public databases, we demonstrated that BLLF3-targeted TLR2-associated factors are effective diagnostic markers for DLBCL. Next, we confirmed the co-expression of LMP1-targeted calcium pathway factors in BL. Finally, we demonstrated the correlation and co-expression of LMP1-induced PARP1, HIF1A, HK2, and key glycolysis-related factors, further suggesting that LMP1 actively regulates the glycolysis pathway. Therefore, our study presents a comprehensive functional encyclopedia of the interactions between EBV antigens and host signaling pathways across various EBV-associated diseases, providing valuable insights for the development of therapeutic strategies.
| S-EPMC11598986 | biostudies-literature
Project description:Adapting classifiers for the purpose of brain signal decoding is a major challenge in brain-computer-interface (BCI) research. In a previous study we showed in principle that hidden Markov models (HMM) are a suitable alternative to the well-studied static classifiers. However, since we investigated a rather straightforward task, advantages from modeling of the signal could not be assessed.Here, we investigate a more complex data set in order to find out to what extent HMMs, as a dynamic classifier, can provide useful additional information. We show for a visual decoding problem that besides category information, HMMs can simultaneously decode picture duration without an additional training required. This decoding is based on a strong correlation that we found between picture duration and the behavior of the Viterbi paths.Decoding accuracies of up to 80% could be obtained for category and duration decoding with a single classifier trained on category information only.The extraction of multiple types of information using a single classifier enables the processing of more complex problems, while preserving good training results even on small databases. Therefore, it provides a convenient framework for online real-life BCI utilizations.
| S-EPMC4871607 | biostudies-literature
Project description:Deep-learning language models have shown promise in various biotechnological applications, including protein design and engineering. Here we describe ProGen, a language model that can generate protein sequences with a predictable function across large protein families, akin to generating grammatically and semantically correct natural language sentences on diverse topics. The model was trained on 280 million protein sequences from >19,000 families and is augmented with control tags specifying protein properties. ProGen can be further fine-tuned to curated sequences and tags to improve controllable generation performance of proteins from families with sufficient homologous samples. Artificial proteins fine-tuned to five distinct lysozyme families showed similar catalytic efficiencies as natural lysozymes, with sequence identity to natural proteins as low as 31.4%. ProGen is readily adapted to diverse protein families, as we demonstrate with chorismate mutase and malate dehydrogenase.
| S-EPMC10400306 | biostudies-literature
Project description:BackgroundInjuries pose a significant global health challenge due to their high incidence and mortality rates. Although injury surveillance is essential for prevention, it is resource-intensive. This study aimed to develop and validate locally deployable large language models (LLMs) to extract core injury-related information from Emergency Department (ED) clinical notes.MethodsWe conducted a diagnostic study using retrospectively collected data from January 2014 to December 2020 from two urban academic tertiary hospitals. One served as the derivation cohort and the other as the external test cohort. Adult patients presenting to the ED with injury-related complaints were included. Primary outcomes included classification accuracies for information extraction tasks related to injury mechanism, place of occurrence, activity, intent, and severity. We fine-tuned a single generalizable Llama-2 model and five distinct Bidirectional Encoder Representations from Transformers (BERT) models for each task to extract information from initial ED physician notes. The Llama-2 model was able to perform different tasks by modifying the instruction prompt. Data recorded in injury registries provided the gold standard labels. Model performance was assessed using accuracy and macro-average F1 scores.ResultsThe derivation and external test cohorts comprised 36,346 and 32,232 patients, respectively. In the derivation cohort's test set, the Llama-2 model achieved accuracies (95% confidence intervals) of 0.899 (0.889-0.909) for injury mechanism, 0.774 (0.760-0.789) for place of occurrence, 0.679 (0.665-0.694) for activity, 0.972 (0.967-0.977) for intent, and 0.935 (0.926-0.943) for severity. The Llama-2 model outperformed the BERT models in accuracy and macro-average F1 scores across all tasks in both cohorts. Imposing constraints on the Llama-2 model to avoid uncertain predictions further improved its accuracy.ConclusionLocally deployable LLMs, trained to extract core injury-related information from free-text ED clinical notes, demonstrated good performance. Generative LLMs can serve as versatile solutions for various injury-related information extraction tasks.
| S-EPMC11611659 | biostudies-literature
Project description:BackgroundA vast amount of potentially useful information such as description of patient symptoms, family, and social history is recorded as free-text notes in electronic health records (EHRs) but is difficult to reliably extract at scale, limiting their utility in research. This study aims to assess whether an "out of the box" implementation of open-source large language models (LLMs) without any fine-tuning can accurately extract social determinants of health (SDoH) data from free-text clinical notes.MethodsWe conducted a cross-sectional study using EHR data from the Mass General Brigham (MGB) system, analyzing free-text notes for SDoH information. We selected a random sample of 200 patients and manually labeled nine SDoH aspects. Eight advanced open-source LLMs were evaluated against a baseline pattern-matching model. Two human reviewers provided the manual labels, achieving 93% inter-annotator agreement. LLM performance was assessed using accuracy metrics for overall, mentioned, and non-mentioned SDoH, and macro F1 scores.ResultsLLMs outperformed the baseline pattern-matching approach, particularly for explicitly mentioned SDoH, achieving up to 40% higher Accuracymentioned. openchat_3.5 was the best-performing model, surpassing the baseline in overall accuracy across all nine SDoH aspects. The refined pipeline with prompt engineering reduced hallucinations and improved accuracy.ConclusionsOpen-source LLMs are effective and scalable tools for extracting SDoH from unstructured EHRs, surpassing traditional pattern-matching methods. Further refinement and domain-specific training could enhance their utility in clinical research and predictive analytics, improving healthcare outcomes and addressing health disparities.
| S-EPMC11773977 | biostudies-literature
Project description:Natural products have long been a rich source of diverse and clinically effective drug candidates. Non-ribosomal peptides (NRPs), polyketides (PKs), and NRP-PK hybrids are three classes of natural products that display a broad range of bioactivities, including antibiotic, antifungal, anticancer, and immunosuppressant activities. However, discovering these compounds through traditional bioactivity-guided techniques is costly and time-consuming, often resulting in the rediscovery of known molecules. Consequently, genome mining has emerged as a high-throughput strategy to screen hundreds of thousands of microbial genomes to identify their potential to produce novel natural products. Adenylation domains play a key role in the biosynthesis of NRPs and NRP-PKs by recruiting substrates to incrementally build the final structure. We propose MASPR, a machine learning method that leverages protein language models for accurate and interpretable predictions of A-domain substrate specificities. MASPR demonstrates superior accuracy and generalization over existing methods and is capable of predicting substrates not present in its training data, or zero-shot classification. We use MASPR to develop Seq2Hybrid, an efficient algorithm to predict the structure of hybrid NRP-PK natural products from microbial genomes. Using Seq2Hybrid, we propose putative biosynthetic gene clusters for the orphan natural products Octaminomycin A, Dityromycin, SW-163B, and JBIR-39.
| S-EPMC11761653 | biostudies-literature
Project description:Organisms have evolved sensory mechanisms to extract pertinent information from their environment, enabling them to assess their situation and act accordingly. For social organisms travelling in groups, like the fish in a school or the birds in a flock, sharing information can further improve their situational awareness and reaction times. Data on the benefits and costs of social coordination, however, have largely allowed our understanding of why collective behaviours have evolved to outpace our mechanistic knowledge of how they arise. Recent studies have begun to correct this imbalance through fine-scale analyses of group movement data. One approach that has received renewed attention is the use of information theoretic (IT) tools like mutual information, transfer entropy and causation entropy, which can help identify causal interactions in the type of complex, dynamical patterns often on display when organisms act collectively. Yet, there is a communications gap between studies focused on the ecological constraints and solutions of collective action with those demonstrating the promise of IT tools in this arena. We attempt to bridge this divide through a series of ecologically motivated examples designed to illustrate the benefits and challenges of using IT tools to extract deeper insights into the interaction patterns governing group-level dynamics. We summarize some of the approaches taken thus far to circumvent existing challenges in this area and we conclude with an optimistic, yet cautionary perspective.
| S-EPMC7115225 | biostudies-literature