Biology subjects

Kanduri, C.

Publications and source records attributed to Kanduri, C..

11 recordsLinked to original sources

bioRxiv2026

What Do Generative Models Learn About Adaptive Immune Receptor Repertoires? A Benchmark Study

Generative models are increasingly used to model adaptive immune receptor repertoire (AIRR) sequence distributions, promising to decode the sequence diversity shaping immune responses and accelerate the design of therapeutic antibodies and T-cell receptors. Yet it remains unclear whether these models produce biologically meaningful outputs or merely capture surface-level sequence statistics while missing features driven by receptor generation and selection. Rigorous evaluation is needed, but the field lacks established standards, as existing machine learning metrics do not all translate directly to the AIRR domain, given the complex structure of the data and the lack of biological ground truth. Consequently, researchers face difficulties in evaluating the models and selecting appropriate ones, which can critically affect downstream clinical applications. Here, we apply a suite of evaluation metrics tailored to AIRR sequence data and present a systematic comparison of popular generative model families proposed for the AIRR field, including variational autoencoders, long short-term memory networks, antibody language models, selection models, and simple statistical baselines. We focus specifically on the task of learning individual-specific immune receptor repertoires, a clinically relevant challenge with direct implications for personalized immunotherapy, disease monitoring, and vaccine response studies. By analyzing the sequences generated by each model, we identify memorization risks, innovation capabilities, and sensitivity to hyperparameter tuning. Taken together, these results advance the understanding of how current generative models reproduce the biology of individual immune repertoires and lay the groundwork for more principled model development and evaluation.

immunology↗

bioRxiv2026

Unsupervised Machine Learning for Adaptive Immune Receptors with immuneML

Machine learning (ML) enables adaptive immune receptor repertoires (AIRRs) analyses for biomarker identification and therapeutic development. With the majority of AIRR data partially or imperfectly labeled, unsupervised ML is essential for motif discovery, biologically meaningful clustering, and generation of novel receptor sequences. However, no unified framework for unsupervised ML exists in the AIRR field, hindering the assessment of model robustness and generalizability. Here, we present an immuneML release advancing unsupervised ML in the AIRR field through unified clustering workflows, interpretable generative modeling, integration with protein language model embeddings, dimensionality reduction, and visualization. We demonstrate immuneMLs utility in three use cases: (i) benchmarking generative models for epitope-specific sequence generation, assessing specificity and novelty, (ii) systematic evaluation of clustering approaches on experimental receptor sequences against biological properties, such as epitope specificity and MHC, and (iii) unsupervised analysis of an experimental AIRR dataset to examine potential confounding, a practice widespread in related fields but unexplored in AIRR analyses.

bioinformatics↗

bioRxiv2025

Retroviral insertions contributed to the divergence of human and chimpanzee brains

Over the past 5-7 million years, humans and chimpanzees have diverged in brain size, structural complexity, and cognitive abilities despite high conservation of protein-coding genes. Notably, the endogenization and proliferation of retroviral infections within host genomes has introduced numerous species-specific regulatory elements that have the potential to influence gene regulation. However, the role of these endogenous retroviruses in hominoid brain evolution remains unclear. A burst of lineage-specific PTERV1 retroviruses recently invaded the chimpanzee genome but are absent in humans. We conducted an epigenomic analysis of PTERV1 insertions in chimpanzee neural organoids and found that they are heavily covered by DNA methylation, representing more than 150 species-specific heterochromatin domains with the capacity to influence gene regulatory networks. We identified one such chimpanzee-specific PTERV1 insertion on chromosome 19 that blocks the expression of the long noncoding RNA LINC00662, via DNA methylation spread to the adjacent genomic region. The expression of LINC00662 was restored in chimpanzee induced pluripotent stem cells when we deleted the PTERV1 insertion using CRISPR editing. We found that LINC00662, a human-specific RNA, is highly expressed in the developing brain and plays an important role in the posttranscriptional control of neuronal maturation, axon outgrowth, and neural organoid development. In summary, our findings describe how endogenous retroviral insertions contributed to the functional divergence of the human and chimpanzee brains. This provides a new mechanism by which retroviral pandemics influenced primate brain speciation.

evolutionary biology↗

bioRxiv2023

Simulation of adaptive immune receptors and repertoires with complex immune information to guide the development and benchmarking of AIRR machine learning

Machine learning (ML) has shown great potential in the adaptive immune receptor repertoire (AIRR) field. However, there is a lack of large-scale ground-truth experimental AIRR data suitable for AIRR-ML-based disease diagnostics and therapeutics discovery. Simulated ground-truth AIRR data are required to complement the development and benchmarking of robust and interpretable AIRR-ML methods where experimental data is currently inaccessible or insufficient. The challenge for simulated data to be useful is incorporating key features observed in experimental repertoires. These features, such as antigen or disease-associated immune information, cause AIRR-ML problems to be challenging. Here, we introduce LIgO, a software suite, which simulates AIRR data for the development and benchmarking of AIRR-ML methods. LIgO incorporates different types of immune information both on the receptor and the repertoire level and preserves native-like generation probability distribution. Additionally, LIgO assists users in determining the computational feasibility of their simulations. We show two examples where LIgO supports the development and validation of AIRR-ML methods: (1) how individuals carrying out-of-distribution immune information impacts receptor-level prediction performance and (2) how immune information co-occurring in the same AIRs impacts the performance of conventional receptor-level encoding and repertoire-level classification approaches. LIgO guides the advancement and assessment of interpretable AIRR-ML methods.

bioinformatics↗

bioRxiv2023

PITAR, a DNA damage-inducible Cancer/Testis long noncoding RNA, inactivates p53 by binding and stabilizing TRIM28 mRNA

In tumors with WT p53, alternate mechanisms of p53 inactivation are reported. Here, we have identified a long noncoding RNA, PITAR (p53 Inactivating TRIM28 associated RNA), as an inhibitor of p53. PITAR is an oncogenic Cancer/testis lncRNA and is highly expressed in glioblastoma (GBM) and glioma stem-like cells (GSC). We establish that TRIM28 mRNA, which encodes a p53-specific E3 ubiquitin ligase, is a direct target of PITAR. PITAR interaction with TRIM28 RNA stabilized TRIM28 mRNA, which resulted in increased TRIM28 protein levels and reduced p53 steady-state levels due to enhanced p53 ubiquitination. DNA damage activated PITAR, in addition to p53, in a p53-independent manner, thus creating an incoherent feedforward loop to inhibit the DNA damage response by p53. While PITAR silencing inhibited the growth of WT p53 containing GSCs in vitro and reduced glioma tumor growth in vivo, its overexpression enhanced the tumor growth in a TRIM28-dependent manner and promoted resistance to Temozolomide. Thus, we establish an alternate way of p53 inactivation by PITAR, which maintains low p53 levels in normal cells and attenuates the DNA damage response by p53. Finally, we propose PITAR as a potential GBM therapeutic target.

cancer biology↗

bioRxiv2022

BioNumPy: Fast and easy analysis of biological data with Python

Python is a popular and widespread programming language for scientific computing, in large part due to the powerful array programming library NumPy, which makes it easy to write clean, vectorized and efficient code for handling large datasets. A challenge with using array programming for biological data is that the data is often non-numeric and variable-length (such as DNA sequences), inhibiting out-of-the-box use of standard array programming techniques. Thus, a tradition in bioinformatics has been to use low-level languages like C and C++ to write efficient code. This makes the tools less transparent to the average computational biologist - making them harder to understand, modify and contribute to. We here present a new Python package BioNumPy, which adds a layer on top of NumPy in order to enable intuitive array programming on biological datasets. BioNumPy is able to efficiently load biological datasets (e.g. FASTQ-files, BED-files and BAM-files) into NumPy-like data structures, so that NumPy operations like indexing, vectorized functions and reductions can be applied to the data. We show that BioNumPy is considerably faster than vanilla Python and other Python packages for common bioinformatics tasks, and in many cases as fast as tools written in C/C++. BioNumPy thus bridges a long-lasting gap in bioinformatics, allowing the same programming language (Python) to be used across the full spectrum from quick and simple scripts to computationally efficient processing of large-scale data.

bioinformatics↗

bioRxiv2021

Profiling the baseline performance and limits of machine learning models for adaptive immune receptor repertoire classification

BackgroundMachine learning (ML) methodology development for classification of immune states in adaptive immune receptor repertoires (AIRR) has seen a recent surge of interest. However, so far, there does not exist a systematic evaluation of scenarios where classical ML methods (such as penalized logistic regression) already perform adequately for AIRR classification. This hinders investigative reorientation to those scenarios where further method development of more sophisticated ML approaches may be required. ResultsTo identify those scenarios where a baseline method is able to perform well for AIRR classification, we generated a collection of synthetic benchmark datasets encompassing a wide range of dataset architecture-associated and immune state-associated sequence pattern (signal) complexity. We trained {approx}1300 ML models with varying assumptions regarding immune signal on{approx}850 datasets with a total of {approx}210000 repertoires containing {approx}42 billion TCR{beta} CDR3 amino acid sequences, thereby surpassing the sample sizes of current state-of-the-art AIRR ML setups by two orders of magnitude. We found that L1-penalized logistic regression achieved high prediction accuracy even when the immune signal occurs only in 1 out of 50000 AIR sequences. ConclusionsWe provide a reference benchmark to guide new AIRR ML classification methodology by: (i) identifying those scenarios characterised by immune signal and dataset complexity, where baseline methods already achieve high prediction accuracy and (ii) facilitating realistic expectations of the performance of AIRR ML models given training dataset properties and assumptions. Our study serves as a template for defining specialized AIRR benchmark datasets for comprehensive benchmarking of AIRR ML methods.

bioinformatics↗

bioRxiv2021

immuneML: an ecosystem for machine learning analysis of adaptive immune receptor repertoires

Adaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. To date, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency, and interoperability. immuneML (immuneml.uio.no) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (i) reproducing a large-scale study on immune state prediction, (ii) developing, integrating, and applying a novel method for antigen specificity prediction, and (iii) showcasing streamlined interpretability-focused benchmarking of AIRR ML.

bioinformatics↗

bioRxiv2020

PPM1D is a neuroblastoma oncogene and therapeutic target in childhood neural tumors.

Majority of cancers harbor alterations of the tumor suppressor TP53. However, childhood cancers, including unfavorable neuroblastoma, often lack TP53 mutations despite frequent loss of p53 function, suggesting alternative p53 inactivating mechanisms. Here we show that p53-regulating PPM1D at chromosome 17q22.3 is linked to aggressive tumors and poor prognosis in neuroblastoma. We identified that WIP1-phosphatase encoded by PPM1D, is activated by frequent segmental 17q-gain further accumulated during clonal evolution, gene-amplifications, gene-fusions or gain-of-function somatic and germline mutations. Pharmacological and genetic manipulation established WIP1 as a druggable target in neuroblastoma. Genome-scale CRISPR-Cas9 screening demonstrated PPM1D genetic dependency in TP53 wild-type neuroblastoma cell lines, and shRNA PPM1D knockdown significantly delayed in vivo tumor formation. Establishing a transgenic mouse model overexpressing PPM1D showed that these mice develop cancers phenotypically and genetically similar to tumors arising in mice with dysfunctional p53 when subjected to low-dose irradiation. Tumors include T-cell lymphomas harboring Notch1-mutations, Pten-deletions and p53-accumulation, adenocarcinomas and PHOX2B-expressing neuroblastomas establishing PPM1D as a bona fide oncogene in wtTP53 cancer and childhood neuroblastoma. Pharmacological inhibition of WIP1 suppressed the growth of neural tumors in nude mice proposing WIP1 as a therapeutic target in neural childhood tumors.

cancer biology↗

bioRxiv2018

Mind your gaps: Overlooking assembly gaps confounds statistical testing in genome analysis

BackgroundThe difficulties associated with sequencing and assembling some regions of the DNA sequence result in gaps in the reference genomes that are typically represented as stretches of Ns. Although the presence of assembly gaps causes a slight reduction in the mapping rate in many experimental settings, that does not invalidate the typical statistical testing comparing read count distributions across experimental conditions. However, we hypothesize that not handling assembly gaps in the null model may confound statistical testing of co-localization of genomic features.\n\nResultsFirst, we performed a series of explorative analyses to understand whether and how the public genomic tracks intersect the assembly gaps track (hg19). The findings rightly confirm that the genomic regions in public genomic tracks intersect very little with assembly gaps and the intersection was observed only at the beginning and end regions of the assembly gaps rather than covering the whole gap sizes. Further, we simulated a set of query and reference genomic tracks in a way that nullified any dependence between them to test our hypothesis that not avoiding assembly gaps in the null model would result in spurious inflation of statistical significance. We then contrasted the distributions of test statistics and p-values of Monte Carlo simulation-based permutation tests that either avoided or not avoided assembly gaps in the null model when testing for significant co-localization between a pair of query and reference tracks. We observed that the statistical tests that did not account for the assembly gaps in the null model resulted in a distribution of the test statistic that is shifted to the right and a distribu tion of p-values that is shifted to the left (leading to inflated significance).\n\nConclusionOur results shows that not accounting for assembly gaps in statistical testing of co-localization analysis may lead to false positives and over-optimistic findings.

bioinformatics↗

bioRxiv2017

Genome Build Information Is An Essential Part Of Genomic Track Files

Genomic locations are represented as coordinates on a specific genome build version, but the build information is frequently missing when coordinates are provided. It is essential to correctly interpret and analyse the genomic intervals contained in genomic track files. Here, we demonstrate that this crucial metadatum (or rather datum) is often isolated from the genomic track files in public repositories and journal articles, which could be a major time thief. We propose best practices to ensure that genome build version is always carried along with genomic track files. Although not a substitute to the best practices, we also provide a tool to predict the genome build version of genomic track files.

bioinformatics↗