Biomedical subjects

Georgios A Pavlopoulos

Publications and source records attributed to Georgios A Pavlopoulos.

3 recordsLinked to original sources

PubMed2026

Accelerating inference in genomic and proteomic foundation models via speculative decoding.

MOTIVATION: Genomic and protein foundation models (GFMs and PFMs) have demonstrated strong performance in learning the language of DNA and proteins, but their use in large-scale sequence generation is limited by the latency of autoregressive decoding. Because every token triggers a forward pass of a large Transformer, whose inference is relatively slow, long-sequence generation quickly becomes costly. RESULTS: In this work we adapt speculative decoding to a representative GFM: the DNA model DNAGPT and two representative PFMs: ProGen2 and ProtGPT2. We implement a probabilistic variant of speculative decoding, in which a lightweight draft model proposes short token spans and a larger target model verifies or corrects them in parallel, while preserving the target model's sampling distribution. Across all three models we systematically study the effect of speculation window length, temperature, draft architecture and prompt length, and we benchmark tokens per second over multiple runs per configuration. Speculative decoding yields consistent speedups over standard key-value cached decoding, with maximum observed speedup reaching 100% increase, while average gains across models ranging between 20% and 40% (e.g. 1.2×-1.4×), without changing the underlying target model predictions. Our results show that speculative decoding is a practical and model-agnostic strategy for accelerating genomic and proteomic sequence generation without sacrificing prediction quality. AVAILABILITY AND IMPLEMENTATION: All code and results are freely available at https://github.com/Georgakopoulos-Soares-lab/BioSpecDec.

Genomics↗

PubMed2025

MAFin: motif detection in multiple alignment files.

MOTIVATION: Whole Genome and Proteome Alignments, represented by the multiple alignment file format, have become a standard approach in comparative genomics and proteomics. These often require identifying conserved motifs, which is crucial for understanding functional and evolutionary relationships. However, current approaches lack a direct method for motif detection within MAF files. We present MAFin, a novel tool that enables efficient motif detection and conservation analysis in MAF files to address this gap, streamlining genomic and proteomic research. RESULTS: We developed MAFin, the first motif detection tool for Multiple Alignment Format files. MAFin enables the multithreaded search of conserved motifs using three approaches: (i) using user-specified k-mers to search the sequences. (ii) with regular expressions, in which case one or more patterns are searched, and (iii) with predefined Position Weight Matrices. Once the motif has been found, MAFin detects the motif instances and calculates the conservation across the aligned sequences. MAFin also calculates a conservation percentage, which provides information about the conservation levels of each motif across the aligned sequences, based on the number of matches relative to the length of the motif. A set of statistics enables the interpretation of each motif's conservation level, and the detected motifs are exported in JSON and CSV files for downstream analyses. AVAILABILITY AND IMPLEMENTATION: MAFin is offered as a Python package under the GPL license as a multi-platform application and is available at: https://github.com/Georgakopoulos-Soares-lab/MAFin.

Software↗

PubMed2025

APNet, an explainable sparse deep learning model to discover differentially active drivers of severe COVID-19.

MOTIVATION: Computational analyses of bulk and single-cell omics provide translational insights into complex diseases, such as COVID-19, by revealing molecules, cellular phenotypes, and signalling patterns that contribute to unfavourable clinical outcomes. Current in silico approaches dovetail differential abundance, biostatistics, and machine learning, but often overlook nonlinear proteomic dynamics, like post-translational modifications, and provide limited biological interpretability beyond feature ranking. RESULTS: We introduce APNet, a novel computational pipeline that combines differential activity analysis based on SJARACNe co-expression networks with PASNet, a biologically informed sparse deep learning model, to perform explainable predictions for COVID-19 severity. The APNet driver-pathway network ingests SJARACNe co-regulation and classification weights to aid result interpretation and hypothesis generation. APNet outperforms alternative models in patient classification across three COVID-19 proteomic datasets, identifying predictive drivers and pathways, including some confirmed in single-cell omics and highlighting under-explored biomarker circuitries in COVID-19. AVAILABILITY AND IMPLEMENTATION: APNet's R, Python scripts, and Cytoscape methodologies are available at https://github.com/BiodataAnalysisGroup/APNet.

COVID-19↗