Biology subjects

Fisicaro, C.

Publications and source records attributed to Fisicaro, C..

4 recordsLinked to original sources

bioRxiv2025

Advancing Protein Ensemble Predictions Across the Order-Disorder Continuum

While deep learning has transformed structure prediction for ordered proteins, intrinsically disordered proteins remain poorly predicted due to systematic underrepresentation in training data, despite constituting approximately 30% of eukaryotic proteomes. We introduce PeptoneBench, the first benchmark to enable systematic assessment of ensemble generators for both ordered and disordered proteins, integrating diverse experimental observables. Our analysis reveals that existing evaluation metrics exhibit systematic bias toward the structured spectrum of the proteome. Assessment of popular predictors (AlphaFold2, ESMFlow, Boltz2) confirms high accuracy on ordered proteins but shows performance degradation with increasing disorder. We further present PepTron, a flow-matching ensemble generator trained on data augmented with synthetic disordered protein ensembles. On our benchmark PepTron matches BioEmu on disordered regions while maintaining competitive accuracy on ordered protein benchmarks. Our data augmentation approach demonstrates that targeted training strategies can approach the performance of computationally expensive simulation-based methods, establishing a generalizable framework applicable to other protein generative models. All datasets, models, and code are openly available.

biophysics↗

bioRxiv2025

MYC-induced oncogenesis is dependent on acidic patches within its N-terminal intrinsically disordered domain.

MYC is one of the most enticing therapeutic targets for cancer but clinical-grade inhibitors are still lacking. By site-saturation mutagenesis screening, we identified several evolutionarily conserved acidic patches within the intrinsically-disordered MYC N-terminus that were confirmed to be functionally essential in different cell models and in vivo. Beyond modulating MYCs global transcriptional activity, these negatively charged patches regulate the interaction with chromatin-modifying complexes including those with histone acetyl-transferase activity. One of the key interactions is established with the co-factor TRRAP, a subunit shared between several Histone Acetyl-Transferase complexes. The protein-protein binding between MYC and TRRAP predominantly relies on two of the N-terminal negative clusters that are located outside MYC-Box-II (MBII) and drive oncogenesis. Our work identifies a new multivalent MYC subdomain that presents new therapeutic vulnerabilities providing invaluable insights for the development of new therapeutic approaches.

cancer biology↗

bioRxiv2024

Improving Inverse Folding models at Protein Stability Prediction without additional Training or Data

Deep learning protein sequence models have shown outstanding performance at de novo protein design and variant effect prediction. We substantially improve performance without further training or use of additional experimental data by introducing a second term derived from the models themselves which align outputs for the task of stability prediction. On a task to predict variants which increase protein stability the absolute success probabilities of PO_SCPLOWROTEINC_SCPLOWMPNN and ESMO_SCPLOWIFC_SCPLOW are improved by 11% and 5% respectively. We term these models PO_SCPLOWROTEINC_SCPLOWMPNN-O_SCPLOWDDC_SCPLOWG and ESMO_SCPLOWIFC_SCPLOW-O_SCPLOWDDC_SCPLOWG.

biophysics↗

bioRxiv2022

ADOPT: intrinsic protein disorder prediction through deep bidirectional transformers

Intrinsically disordered proteins (IDP) are important for a broad range of biological functions and are involved in many diseases. An understanding of intrinsic disorder is key to develop compounds that target IDPs. Experimental characterization of IDPs is hindered by the very fact that they are highly dynamic. Computational methods that predict disorder from the amino acid sequence have been proposed. Here, we present ADOPT, a new predictor of protein disorder. ADOPT is composed of a self-supervised encoder and a supervised disorder predictor. The former is based on a deep bidirectional transformer, which extracts dense residue level representations from Facebooks Evolutionary Scale Modeling (ESM) library. The latter uses a database of NMR chemical shifts, constructed to ensure balanced amounts of disordered and ordered residues, as a training and test dataset for protein disorder. ADOPT predicts whether a protein or a specific region is disordered with better performance than the best existing predictors and faster than most other proposed methods (a few seconds per sequence). We identify the features which are relevant for the prediction performance and show that good performance can already gained with less than 100 features. ADOPT is available as a standalone package at https://github.com/PeptoneLtd/ADOPT.

bioinformatics↗