Biology subjects

Ideker, T.

Publications and source records attributed to Ideker, T..

At least 19 recordsLinked to original sources

bioRxiv2026

HyperMap: An Efficient Framework for Transferring Perturbation Responses Across Diverse Biological Contexts

Recent perturbation atlases profile transcriptional responses to thousands of targeted perturbations in a reference cell type. Generalising these datasets across lineages and individuals has been problematic, however, as similar baseline transcriptomes can yield highly divergent responses. To address this challenge, we present HyperMap, a meta-learning framework that translates existing atlases to predict perturbation responses in new biological contexts using a small number of perturbation "seeds." Applied to CRISPR gene knockdowns in induced pluripotent stem cells, HyperMap accurately captures responses of new iPSC donors. It generalises to additional cell lines, perturbations by small-molecule drugs, and knockdowns not yet performed in any context. HyperMap is highly efficient, obtaining best-in-class predictions with one-eighth the parameters of typical foundation models. Integrating across atlases yields HyperMapDB, a complete 18x19,036 (cell-line x perturbation) matrix expanding current data by 27-fold. HyperMap enables predictive maps spanning the combinatorial space of biological contexts, gene knockdowns and drugs.

systems biology↗

bioRxiv2025

The DREAM complex links somatic mutation, lifespan, and disease

The DREAM complex has emerged as a central repressor of DNA repair, raising questions as to whether such repression exerts long-term effects on human health. Here we establish that DREAM activity significantly impacts lifetime somatic mutation burden, and that such effects are linked to altered lifespan and age-related disease pathology. First, joint profiling of DREAM activity and somatic mutations across a single-cell atlas of 21 mouse tissues shows that cellular niches with lower DREAM activity have decreased mutation rates. Second, DREAM activity predicts the varied lifespans observed across 92 mammals, with low activity marking longer-lived species. Third, reduced DREAM activity in Alzheimers patients predicts late disease onset and decreased risk for severe neuropathology. Finally, we show DREAM knockout protects against mutation accumulation in vivo, reducing single-base substitutions by 4.2% and insertion/deletions by 19.6% in brains of mice. These findings position DREAM as a key regulator of aging.

bioinformatics↗

bioRxiv2025

Redefining Parkinson's Disease by Dysregulated Genetic Networks in Distinct Cell Types

Parkinsons disease (PD) is classically linked to dopaminergic neuron loss, but emerging evidence suggests broader cellular involvement. Here we show that PD risk variants converge on distinct molecular networks across specific brain cell types, enabling stratification of patients into six subgroups: dopaminergic, oligodendrocyte progenitor cells (O), excitatory (E), dopaminergic/excitatory, dopaminergic/oligodendrocyte and other. While all subgroups exhibit motor symptoms, the E-group individuals also display more severe non-motor symptoms, including dementia, hyposmia, and REM sleep behavior disorder. The O-group individuals exhibit reduced myelin integrity, as demonstrated by diffusion tensor imaging, implicating NRG6 (formerly C1orf56), a previously uncharacterized high-risk PD gene. We show that NRG6 encodes a conserved epidermal growth factor-like domain structurally and functionally analogous to neuregulin-1, which is critical for oligodendrocyte development and myelination. These findings redefine the cellular architecture of PD vulnerability and identify neuregulin-like signaling in oligodendrocytes as a potential contributor to non-motor symptoms.

neuroscience↗

bioRxiv2025

Translating clinical gene sequencing into a foundational representation of tumor subtype

While gene sequencing is routine in cancer care, translating sequences into treatment decisions remains a challenge. Here we introduce MutationProjector, an AI foundation model that transforms tumor mutation profiles into a compact representation of cancer subtype, with broad implications for diagnosis and therapy. MutationProjector is pre-trained by integrating genomic alterations from >30,000 tumors with extensive molecular knowledge, yielding a model that accurately reconstructs held-out genetic profiles (demonstrating strong generalization) and determines subtype representations from altered molecular pathways (enabling model interpretability). We evaluate MutationProjector in independent tasks related to prediction of immunotherapy response, prediction of chemotherapy response, and classification of metastasis, recording leading performance in all areas. Each task identifies key biomarkers of interest, including KMT2A and KRAS-STK11 alterations which govern immunotherapy response.

systems biology↗

bioRxiv2025

An adversarial scheme for integrating multi-modal data on protein function

In order to begin to decipher the structure of the cell, we need to integrate multiple types of data of different scales on subcellular organization. Such integration requires dealing with multiple data modalities and with missing data. To this end, we developed MIRAGE, a multi-modal generative model for integrating protein sequence, protein-protein interaction and protein localization data. Our approach successfully learns a joint embedding space that captures the complex relationships between these diverse modalities. We evaluate our models performance against existing methods, obtaining superior performance in several key tasks, including protein function prediction and module detection. MIRAGE source code is available at https://github.com/raminass/MIRAGE.

bioinformatics↗

bioRxiv2024

scLong: A Billion-Parameter Foundation Model for Capturing Long-Range Gene Context in Single-Cell Transcriptomics

Single-cell RNA sequencing (scRNA-seq) has revolutionized the study of cellular heterogeneity by providing gene expression data at single-cell resolution, uncovering insights into rare cell populations, cell-cell interactions, and gene regulation. Foundation models pretrained on large-scale scRNA-seq datasets have shown great promise in analyzing such data, but existing approaches are often limited to modeling a small subset of highly expressed genes and lack the integration of external genespecific knowledge. To address these limitations, we present sc-Long, a billion-parameter foundation model pretrained on 48 million cells. sc-Long performs self-attention across the entire set of 28,000 genes in the human genome. This enables the model to capture long-range dependencies between all genes, including lowly expressed ones, which often play critical roles in cellular processes but are typically excluded by existing foundation models. Additionally, sc-Long integrates gene knowledge from the Gene Ontology using a graph convolutional network, enriching its contextual understanding of gene functions and relationships. In extensive evaluations, sc-Long surpasses both stateof-the-art scRNA-seq foundation models and task-specific models across diverse tasks, including predicting transcriptional responses to genetic and chemical perturbations, forecasting cancer drug responses, and inferring gene regulatory networks.

bioinformatics↗

bioRxiv2024

A PERTURBATION CELL ATLAS OF HUMAN INDUCED PLURIPOTENT STEM CELLS

Towards comprehensively investigating the genotype-phenotype relationships governing the human pluripotent stem cell state, we generated an expressed genome-scale CRISPRi Perturbation Cell Atlas in KOLF2.1J human induced pluripotent stem cells (hiPSCs) mapping transcriptional and fitness phenotypes associated with 11,739 targeted genes. Using the transcriptional phenotypes, we created a minimum distortion embedding map of the pluripotent state, demonstrating rich recapitulation of protein complexes, such as strong co-clustering of MRPL, BAF, SAGA, and Ragulator family members. Additionally, we uncovered transcriptional regulators that are uncoupled from cell fitness, discovering potential novel pluripotency (JOSD1, RNF7) and metabolic factors (ZBTB41). We validated these findings via phenotypic, protein-interaction, and metabolic tracing assays. Finally, we propose a contrastive human-cell engineering framework (CHEF), a machine learning architecture that learns from perturbation cell atlases to predict perturbation recipes that achieve desired transcriptional states. Taken together, our study presents a comprehensive resource for interrogating the regulatory networks governing pluripotency.

bioengineering↗

bioRxiv2024

Mechanistic genotype-phenotype translation using hierarchical transformers

Genome-wide association studies have linked millions of genetic variants to biomedical phenotypes, but their utility has been limited by lack of mechanistic understanding and widespread epistatic interactions. Recently, Transformer models have emerged as powerful machine learning architectures with potential to address these and other challenges. Here we introduce the Genotype-to-Phenotype Transformer (G2PT), a framework for modeling hierarchical information flow among variants, genes, multigenic systems, and phenotypes. As proof-of-concept, we train G2PT to model the genetics of metabolic traits including insulin resistance (serum triglycerides-to-HDL ratio), LDL and type-2 diabetes. G2PT predicts these traits with accuracy exceeding state-of-the-art and, unlike other polygenic models, extends to distinct populations not used for training. Predictions of insulin resistance are based on >1,395 variants within 20 systems and include epistatic interactions among variants, e.g. between APOA4 and CETP in phospholipid transfer. This work positions hierarchical graph transformers as a next-generation approach to polygenic risk.

bioinformatics↗

bioRxiv2024

ProteinAligner: A Multi-modal Pretraining Framework for Protein Foundation Models

Protein foundation models, particularly protein language models, have demonstrated strong success in learning meaningful representations of proteins using transformer architectures pretrained on large-scale protein datasets with self-supervised learning. These representations have been highly effective for downstream tasks such as predicting protein functions and properties. However, most current protein foundation models focus on pretraining with amino acid sequences, often neglecting additional modalities like protein structures and related literature, both of which provide valuable insights. To address this gap, we propose a multi-modal pretraining approach that integrates three key modalities - protein sequences, structures, and literature text. In our framework, the protein sequence modality serves as the anchor, with the other two modalities aligned to it, enhancing the models capacity to capture more comprehensive protein information. ProteinAligner out-performed state-of-the-art protein foundation models in predicting protein functions and properties across diverse down-stream tasks.

bioinformatics↗

bioRxiv2024

Multi-Modal Large Language Model Enables All-Purpose Prediction of Drug Mechanisms and Properties

Accurately predicting the mechanisms and properties of potential drug molecules is essential for advancing drug discovery. However, traditional methods often require the development of specialized models for each specific prediction task, resulting in inefficiencies in both model training and integration into work-flows. Moreover, these approaches are typically limited to predicting pharmaceutical attributes represented as discrete categories, and struggle with predicting complex attributes that are best described in free-form texts. To address these challenges, we introduce DrugChat, a multi-modal large language model (LLM) designed to provide comprehensive predictions of molecule mechanisms and properties within a unified framework. DrugChat analyzes the structure of an input molecule along with users queries to generate comprehensive, free-form predictions on drug indications, pharmacodynamics, and mechanisms of action. Moreover, DrugChat supports multi-turn dialogues with users, facilitating interactive and in-depth exploration of the same molecule. Our extensive evaluation, including assessments by human experts, demonstrates that DrugChat significantly outperforms GPT-4 and other leading LLMs in generating accurate free-form predictions, and exceeds state-of-the-art specialized prediction models.

pharmacology and toxicology↗

bioRxiv2024

Multi-Modal Large Language Model Enables Protein Function Prediction

Predicting the functions of proteins can greatly accelerate biological discovery and applications, where deep learning methods have recently shown great potential. However, these methods predominantly predict protein functions as discrete categories, which fails to capture the nuanced and complex nature of protein functions. Furthermore, existing methods require the development of separate models for each prediction task, a process that can be both resource-heavy and time-consuming. Here, we present ProteinChat, a versatile, multi-modal large language model that takes a proteins amino acid sequence as input and generates comprehensive narratives describing its function. ProteinChat is trained using over 1,500,000 (protein, prompt, answer) triplets curated from the Swiss-Prot dataset, covering diverse functions. This novel model can universally predict a wide range of protein functions, all within a single, unified framework. Furthermore, ProteinChat supports interactive dialogues with human users, allowing for iterative refinement of predictions and deeper exploration of protein functions. Our experimental results, evaluated through both human expert assessment and automated metrics, demonstrate that ProteinChat outperforms general-purpose LLMs like GPT-4, one of the flagship LLMs, by over ten-fold. In addition, ProteinChat exceeds or matches the performance of task-specific prediction models.

bioinformatics↗

bioRxiv2024

Global siRNA Screen Reveals Critical Human Host Factors of SARS-CoV-2 Multicycle Replication

Defining the subset of cellular factors governing SARS-CoV-2 replication can provide critical insights into viral pathogenesis and identify targets for host-directed antiviral therapies. While a number of genetic screens have previously reported SARS-CoV-2 host dependency factors, these approaches relied on utilizing pooled genome-scale CRISPR libraries, which are biased towards the discovery of host proteins impacting early stages of viral replication. To identify host factors involved throughout the SARS-CoV-2 infectious cycle, we conducted an arrayed genome-scale siRNA screen. Resulting data were integrated with published datasets to reveal pathways supported by orthogonal datasets, including transcriptional regulation, epigenetic modifications, and MAPK signalling. The identified proviral host factors were mapped into the SARS-CoV-2 infectious cycle, including 27 proteins that were determined to impact assembly and release. Additionally, a subset of proteins were tested across other coronaviruses revealing 17 potential pan-coronavirus targets. Further studies illuminated a role for the heparan sulfate proteoglycan perlecan in SARS-CoV-2 viral entry, and found that inhibition of the non-canonical NF-kB pathway through targeting of BIRC2 restricts SARS-CoV-2 replication both in vitro and in vivo. These studies provide critical insight into the landscape of virus-host interactions driving SARS-CoV-2 replication as well as valuable targets for host-directed antivirals.

systems biology↗

bioRxiv2024

Cell Maps for Artificial Intelligence: AI-Ready Maps of Human Cell Architecture from Disease-Relevant Cell Lines

This article describes the Cell Maps for Artificial Intelligence (CM4AI) project and its goals, methods, standards, current datasets, software tools, status, and future directions. CM4AI is the Functional Genomics Data Generation Project in the U.S. National Institute of Healths (NIH) Bridge2AI program. Its overarching mission is to produce ethical, AI-ready datasets of cell architecture, inferred from multimodal data collected for human cell lines, to enable transformative biomedical AI research.

systems biology↗

bioRxiv2024

State of the Interactomes: an evaluation of molecular networks for generating biological insights

Advancements in genomic and proteomic technologies have powered the use of gene and protein networks ("interactomes") for understanding genotype-phenotype translation. However, the proliferation of interactomes complicates the selection of networks for specific applications. Here, we present a comprehensive evaluation of 46 current human interactomes, encompassing protein-protein interactions as well as gene regulatory, signaling, colocalization, and genetic interaction networks. Our analysis shows that large composite networks such as HumanNet, STRING, and FunCoup are most effective for identifying disease genes, while smaller networks such as DIP and SIGNOR demonstrate strong interaction prediction performance. These findings provide a benchmark for interactomes across diverse network biology applications and clarify factors that influence network performance. Furthermore, our evaluation pipeline paves the way for continued assessment of emerging and updated interaction networks in the future.

bioinformatics↗

bioRxiv2024

Rare and Common Variants Associated with Alcohol Consumption Identify a Conserved Molecular Network

Genome-wide association studies (GWAS) have identified hundreds of common variants associated with alcohol consumption. In contrast, rare variants have only begun to be studied for their role in alcohol consumption. No studies have examined whether common and rare variants implicate the same genes and molecular networks. To address this knowledge gap, we used publicly available alcohol consumption GWAS summary statistics (GSCAN, N=666,978) and whole exome sequencing data (Genebass, N=393,099) to identify a set of common and rare variants for alcohol consumption. Gene-based analysis of each dataset have implicated 294 (common variants) and 35 (rare variants) genes, including ethanol metabolizing genes ADH1B and ADH1C, which were identified by both analyses, and ANKRD12, GIGYF1, KIF21B, and STK31, which were identified only by rare variant analysis, but have been associated with related psychiatric traits. We then used a network colocalization procedure to propagate the common and rare gene sets onto a shared molecular network, revealing significant overlap. The shared network identified gene families that function in alcohol metabolism, including ADH, ALDH, CYP, and UGT. 74 of the genes in the network were previously implicated in comorbid psychiatric or substance use disorders, but had not previously been identified for alcohol-related behaviors, including EXOC2, EPM2A, CACNB3, and CACNG4. Differential gene expression analysis showed enrichment in the liver and several brain regions supporting the role of network genes in alcohol consumption. Thus, genes implicated by common and rare variants identify shared functions relevant to alcohol consumption, which also underlie psychiatric traits and substance use disorders that are comorbid with alcohol use.

genetics↗

bioRxiv2023

Somatic mutation as an explanation for epigenetic aging

DNA methylation marks have recently been used to build models known as "epigenetic clocks" which predict calendar age. As methylation of cytosine promotes C-to-T mutations, we hypothesized that the methylation changes observed with age should reflect the accrual of somatic mutations, and the two should yield analogous aging estimates. In analysis of multimodal data from 9,331 human individuals, we find that CpG mutations indeed coincide with changes in methylation, not only at the mutated site but also with pervasive remodeling of the methylome out to {+/-}10 kilobases. This one-to-many mapping enables mutation-based predictions of age that agree with epigenetic clocks, including which individuals are aging faster or slower than expected. Moreover, genomic loci where mutations accumulate with age also tend to have methylation patterns that are especially predictive of age. These results suggest a close coupling between the accumulation of sporadic somatic mutations and the widespread changes in methylation observed over the course of life.

genomics↗

bioRxiv2023

A foundational atlas of autism protein interactions reveals molecular convergence

Translating high-confidence (hc) autism spectrum disorder (ASD) genes into viable treatment targets remains elusive. We constructed a foundational protein-protein interaction (PPI) network in HEK293T cells involving 100 hcASD risk genes, revealing over 1,800 PPIs (87% novel). Interactors, expressed in the human brain and enriched for ASD but not schizophrenia genetic risk, converged on protein complexes involved in neurogenesis, tubulin biology, transcriptional regulation, and chromatin modification. A PPI map of 54 patient-derived missense variants identified differential physical interactions, and we leveraged AlphaFold-Multimer predictions to prioritize direct PPIs and specific variants for interrogation in Xenopus tropicalis and human forebrain organoids. A mutation in the transcription factor FOXP1 led to reconfiguration of DNA binding sites and altered development of deep cortical layer neurons in forebrain organoids. This work offers new insights into molecular mechanisms underlying ASD and describes a powerful platform to develop and test therapeutic strategies for many genetically-defined conditions.

systems biology↗

bioRxiv2023

Desmosome mutations impact the tumor microenvironment to promote melanoma proliferation

Desmosomes are transmembrane protein complexes that contribute to cell-cell adhesion in epithelia and other tissues. Here, we report the discovery of frequent genetic alterations in the desmosome in human cancers, with the strongest signal seen in cutaneous melanoma where desmosomes are mutated in >70% of cases. In primary but not metastatic melanoma biopsies, the burden of coding mutations in desmosome genes associates with a strong reduction in desmosome gene expression. Analysis by spatial transcriptomics and protein immunofluorescence suggests that these expression decreases occur in keratinocytes in the microenvironment rather than in primary melanoma cells. In further support of a microenvironmental origin, we find that desmosome gene knockdown in keratinocytes yields markedly increased proliferation of adjacent melanoma cells in keratinocyte/melanoma co-cultures. Similar increases in melanoma proliferation are observed in media preconditioned by desmosome-deficient keratinocytes. Thus, gradual accumulation of desmosome mutations in neighboring cells may prime melanoma cells for neoplastic transformation.

systems biology↗