Biology subjects

Dumitrescu, A.

Publications and source records attributed to Dumitrescu, A..

7 recordsLinked to original sources

bioRxiv2026

Peptide-HLA II interaction prediction for post-translationally modified peptides

CD4+ T cells recognize peptides presented by human leukocyte antigen (HLA) II, implementing a fundamental mediation mechanism of the adaptive immune system. Although post-translational modifications (PTMs) alter immune responses, PTM-peptide-HLA interaction prediction remains challenging due to data scarcity resulting from substoichiometric levels of PTMs. To overcome this, we developed PepChem, a deep learning model utilizing novel, molecular-level peptide representations that enable predictions for sidechain modifications. Using monoallelic datasets that we reanalyze for PTMs of interest, we show accurate predictions on PTMs that were unseen during training. Furthermore, we introduce a novel training protocol that improves PTM-peptide generalization compared to conventional methods. We predict and experimentally validate citrullination-induced binding increase of rheumatoid arthritis (RA)-linked peptides to HLA II risk allele DRB1*04:01. This framework bridges the critical gap in PTM-aware immune recognition prediction, with immediate applications in autoimmunity, cancer, and infectious disease.

bioinformatics↗

bioRxiv2026

PepCABO: Latent-space Bayesian optimization for peptide-MHC binding using contrastive alignment

MotivationOptimizing peptide sequences for binding to specific MHC class I alleles is a central challenge in immunotherapy and vaccine design. The combinatorial size of peptide space, the nonlinear nature of peptide- MHC interactions, and limited experimental budgets make efficient optimization difficult. Latent-space Bayesian optimization (LSBO) provides a framework by embedding discrete sequences into a continuous space where Bayesian optimization can be applied. However, existing LSBO methods do not effectively leverage binding data from related alleles and often rely on inefficient random initialization. ResultsWe propose PepCABO, an LSBO framework for peptide-MHC binding using contrastive alignment, which utilizes a dual variational autoencoder framework that jointly learns peptide-allele alignment and a Gaussian process surrogate prior to Bayesian optimization. This simultaneous training induces a latent geometry that reflects the binding landscape and enables structured knowledge transfer across alleles. The pretrained model shapes a structured latent space in which peptides with high objective values regarding a specific MHC allele are geometrically organized, while the jointly trained Gaussian process defines an informative prior over the objective in this space, enabling principled and efficient exploration of promising regions during subsequent optimization. Across 12 target alleles without prior binding data and under both low- and high-budget settings, PepCABO consistently outperforms various baselines. We observe faster convergence, improved area under the optimization curve, and stronger best-found binding affinities, suggesting improved sample efficiency under experimentally constrained scenarios. Code availabilityThe source code is available at https://github.com/mohsen-g/PepCABO

bioinformatics↗

bioRxiv2023

EPIC-TRACE: predicting TCR binding to unseen epitopes using attention and contextualized embeddings

T cells play an essential role in adaptive immune system to fight pathogens and cancer but may also give rise to autoimmune diseases. The recognition of a peptide-MHC (pMHC) complex by a T cell receptor (TCR) is required to elicit an immune response. Many machine learning models have been developed to predict the binding, but generalizing predictions to pMHCs outside the training data remains challenging. We have developed a new machine learning model that utilizes information about the TCR from both and {beta} chains, epitope sequence, and MHC. Our method uses ProtBERT embeddings for the amino acid sequences of both chains and the epitope, as well as convolution and multi-head attention architectures. We show the importance of each input feature as well as the benefit of including epitopes with only a few TCRs to the training data. We evaluate our model on existing databases and show that it compares favorably against other state-of-the-art models.

immunology↗

bioRxiv2022

TSignal: A transformer model for signal peptide prediction

Signal peptides are short amino acid segments present at the N-terminus of newly synthesized proteins that facilitate protein translocation into the lumen of the endoplasmic reticulum, after which they are cleaved off. Specific regions of signal peptides influence the efficiency of protein translocation, and small changes in their primary structure can abolish protein secretion altogether. The lack of conserved motifs across signal peptides, sensitivity to mutations, and variability in the length of the peptides, make signal peptide prediction a challenging task that has been extensively pursued over the years. We introduce TSignal, a deep transformer-based neural network architecture that utilizes BERT language models (LMs) and dot-product attention techniques. TSignal predicts the presence of signal peptides (SPs) and the cleavage site between the SP and the translocated mature protein. We show improved accuracy in terms of cleavage site and SP presence prediction for most of the SP types and organism groups. We further illustrate that our fully data-driven trained model identifies useful biological information on heterogeneous test sequences.

bioinformatics↗

bioRxiv2022

Predicting recognition between T cell receptors and epitopes using contextualized motifs

We introduce TCRconv, a deep learning model for predicting recognition between T-cell receptors and epitopes. TCRconv uses a deep protein language model and convolutions to extract contextualized motifs and provides state-of-the-art TCR-epitope prediction accuracy. Using TCR repertoires from COVID-19 patients, we demonstrate that TCRconv can provide insight into T-cell dynamics and phenotypes during the disease.

bioinformatics↗

bioRxiv2020

Intrinsic/extrinsic duality of large-scale neural functional integration in the human brain

Human brain activity is not merely responsive to environmental context but includes intrinsic dynamics, as suggested by the discovery of functionally meaningful neural networks at rest, i.e., even without explicit engagement of the corresponding function. Yet, the neurophysiological coupling mechanisms distinguishing intrinsic (i.e., task-invariant) from extrinsic (i.e., task-dependent) brain networks remain indeterminate. Here, we investigated functional brain integration using magnetoencephalography throughout rest and various tasks recruiting different functional systems and modulating perceptual/cognitive loads. We demonstrated that two distinct modes of neural communication continually operate in parallel: extrinsic coupling supported by phase synchronization and intrinsic integration encoded in amplitude correlation. Intrinsic integration also contributes to phase synchronization, especially over short (second-long) timescales, through modulatory effects of amplitude correlation. Our study establishes the foundations of a novel conceptual framework for human brain function that fundamentally relies on electrophysiological features of functional integration. This framework blurs the boundary between resting-state and task-related neuroimaging.

neuroscience↗

bioRxiv2020

A calibrated optogenetic toolbox of stable zebrafish opsin lines

Optogenetic actuators with diverse spectral tuning, ion selectivity and kinetics are constantly being engineered providing powerful tools for controlling neural activity with subcellular resolution and millisecond precision. Achieving reliable and interpretable in vivo optogenetic manipulations requires reproducible actuator expression and calibration of photocurrents in target neurons. Here, we developed nine transgenic zebrafish lines for stable opsin expression and calibrated their efficacy in vivo. We first used high-throughput behavioural assays to compare opsin ability to elicit or silence neural activity. Next, we performed in vivo whole-cell electrophysiological recordings to quantify the amplitude and kinetics of photocurrents and test opsin ability to precisely control spiking. We observed substantial variation in efficacy, associated with differences in both opsin expression level and photocurrent characteristics, and identified conditions for optimal use of the most efficient opsins. Overall, our calibrated optogenetic toolkit will facilitate the design of controlled optogenetic circuit manipulations.

neuroscience↗