Biology subjects

Tosatto, S.

Publications and source records attributed to Tosatto, S..

3 recordsLinked to original sources

bioRxiv2026

emb2dis: a novel protein disorder prediction tool based on ResNets, dilated convolutions & protein language models

Intrinsically disordered proteins (IDPs) play an important role in a wide range of biological functions and are linked to several diseases. Due to technical difficulties and the high cost of experimental determination of disorder in proteins, combined with the exponential increase of unannotated protein sequences, the development of computational methods for disorder prediction became an active area of research in the last few decades. In this work, we present emb2dis, a deep learning model that uses protein language models (pLMs) to predict disorder from sequence. The emb2dis tool is a pre-trained model that receives as input a protein sequence, calculates its pLM embedding and passes it to a deep learning model. In contrast to existing approaches, emb2dis integrates informative sequence representations with a novel architecture that combines residual networks (ResNets) and dilated convolutions. This design effectively enlarges the receptive field of the convolution operation, enabling the model to better capture an extended context of each amino acid. At the output, emb2dis assigns a disorder propensity score to each residue in the sequence. The model was evaluated on datasets from the latest CAID3 blind benchmark for disorder prediction, where it achieved first place in the Disorder-PDB category, exhibiting strong performance with high AUC and Fmax scores. Additionally, it ranked among the top ten methods on the Disorder-NOX dataset. We provide a freely available web-demo for emb2dis and a source code repository for local installation. Weblink for the toolhttps://sinc.unl.edu.ar/web-demo/emb2dis/ The importance of the emb2dis tool is that it provides a new deep learning approach and significant improvements in the prediction of protein disorder, with a simple web interface and graphical output detailing per-residue disorder.

bioinformatics↗

bioRxiv2025

Mathematical Modeling and Simulation of Tumor-Induced Angiogenesis in Retinal Hemangioblastoma

Retinal Hemangioblastoma (RH) is the most frequent manifestation of the von Hippel-Lindau syndrome (VHL), a rare disease associated with the germline mutation of the von Hippel-Lindau protein (pVHL). An emblematic feature of RH is the high vascularity, which is explained by the overexpression of angiogenic factors (AFs) arising from the pVHL impairment. The introduction of Optical Coherence Tomography Angiography (OCTA) allowed observing this feature with exceptional detail. Here, we combine OCTA images and a mechanistic model to investigate tumor growth and vascular development in a patient-specific way. We derived our model from the agreed pathology for RH and focused on the earliest stages of tumor-induced angiogenesis. Our simulations closely resemble the medical images, proving the capability of our model to recapitulate vascular patterning in actual patients. Our results also suggest that angiogenesis in RH occurs upon reaching a critical dimension (around 200 m), followed by the rapid formation of stable vascular networks. These findings open a new perspective on the crucial role of time in antiangiogenic therapy in RH, which has resulted in ineffective control. Indeed, it might be that when RH is diagnosed, angiogenesis is already too advanced to be effectively targeted with any effective means. Moreover, our simulations suggest that vascularization in RH is not a continuous process but an inconstant development with long, stable phases and rapid episodes of vascular sprouting. AUTHOR SUMMARYTumor-induced angiogenesis is a survival strategy commonly exploited by solid tumors to access further nutrients and sustain their growth. The recent introduction of Optical Coherence Tomography Angiography (OCTA) enables scientists and physicians to observe vascular patterning in the retina, non-invasively and with unprecedented detail. Here, we exploit direct observations on a vascular retinal tumor, Retinal Hemangioblastoma (RH), and a mathematical model to investigate the earliest stages of tumor-induced angiogenesis. Our simulations closely match reality and provide critical insights into the role of time in anti-angiogenic therapy for this neoplasm.

bioengineering↗

bioRxiv2022

3D-Beacons: Decreasing the gap between protein sequences and structures through a federated network of protein structure data resources

While scientists can often infer the biological function of proteins from their 3-dimensional quaternary structures, the gap between the number of known protein sequences and their experimentally determined structures keeps increasing. A potential solution to this problem is presented by ever more sophisticated computational protein modelling approaches. While often powerful on their own, most methods have strengths and weaknesses. Therefore, it benefits researchers to examine models from various model providers and perform comparative analysis to identify what models can best address their specific use cases. To make data from a large array of model providers more easily accessible to the broader scientific community, we established 3D-Beacons, a collaborative initiative to create a federated network with unified data access mechanisms. The 3D-Beacons Network allows researchers to collate coordinate files and metadata for experimentally determined and theoretical protein models from state-of-the-art and specialist model providers and also from the Protein Data Bank.

bioinformatics↗