Tommaso Mazza
@irongraft
Followers
130
Following
2K
Media
125
Statuses
1K
Computer Science Engineer | #Bioinformatics | #Computationalbiology | Fondazione Policlinico Universitario A. Gemelli, IRCCS
Roma
Joined April 2012
🎉 Huge congrats to the OpenFold Consortium on releasing the latest OpenFold3 model checkpoint! ⚡️Scale your discoveries instantly. We’re thrilled to release this new checkpoint as an optimized NVIDIA NIM microservice, delivering an average 1.53x speedup for predictions on
3
51
257
AF2BIND: a logistic regression model that predicts small-molecule binding site residues in proteins. https://t.co/vPx1GOz6Km
nature.com
Nature Methods - AF2BIND is a logistic regression model trained on AlphaFold2 pair features to predict small-molecule binding-site residues in proteins, without multiple sequence alignments,...
1
19
132
NetMD is a computational framework that synchronizes and analyzes MD trajectories by integrating graph-based representations with dynamic time warping. Check it out at: https://t.co/4jJrr7eeSN GitHub: https://t.co/7Iwn1eHCl3
#bioinformatics #structuralbiology #simulation
github.com
NetMD is a computational method for identifying consensus behaviors across multiple molecular dynamics simulations - mazzalab/NetMD
0
0
0
New preprint out: nAPOGEE, a machine-learning platform for clinically actionable pathogenicity prediction of #mitochondrial #noncoding variants. Using interpretable models, we improve how noncoding #mtDNA changes are assessed for clinical relevance.
biorxiv.org
Mitochondrial noncoding variants, particularly those in tRNA and rRNA genes, pose significant challenges for clinical interpretation due to heteroplasmy, broad phenotypic heterogeneity where symptoms...
0
0
0
What's new in mitochondrial genetics? MitoPhen v2 characterizes phenotypes in primary mitochondrial diseases and expands disease-gene relationships https://t.co/uJq1a2Akp4
1
8
26
See you at the Microbiome Throughout Life 2026 Conference! The call for abstracts is open! Don’t miss the chance to showcase your work on the main stage! 📅 SUBMIT YOUR ABSTRACT BY NOVEMBER 3, 2025 👉
microbiometolife.com
Instructions for writing abstracts (Oral/Poster) Abstract Submission The submission period has now ended. The results of the review process will be communicated via email. Abstract Topics Computati...
0
2
4
XIX Congress of the Italian Proteomics Association (ItPA), organized in collaboration with the Serbian Proteomics Association (SePA) and the Hellenic Proteomics Society (HPS)- Rome , 3rd – 5th December 2025
0
0
0
Presenting my talk "Decoding the Non-Coding: Clinical-Grade Prediction of Pathogenic Variants in Mitochondrial tRNAs and rRNAs with nAPOGEE" at SIGU2025 in Rimini. #SIGU2025 #Bioinformatics #MitochondrialGenomics #AIinGenetics #nAPOGEE #PoliclinicoGemelli
0
0
0
NeuralTSNE: A Python Package for the Dimensionality Reduction of Molecular Dynamics Data Using Neural Networks #MolecularDynamics #DeepLearning
https://t.co/VQbx0fqcze
@JakubRydzewski
#JCIM Vol65 Issue14 #ApplicationNote
pubs.acs.org
Unsupervised machine learning has recently gained much attention in the field of molecular dynamics (MD). Particularly, dimensionality reduction techniques have been regularly employed to analyze...
1
15
69
Ready our preprint: NetMD: Unsupervised Synchronization of Molecular Dynamics Trajectories via Graph Embedding and Time Warping https://t.co/BJy4ohveUf
#moleculardynamics #structuralbiology #Bioinformatics #fpg #netmd #graph #embedding
biorxiv.org
Molecular dynamics (MD) simulations yield detailed atomistic views of biomolecular processes, yet comparing independent trajectories is hindered by stochastic divergence. Here, we introduce NetMD, a...
0
2
6
New fastest shortest-path algorithm in 41 years! Tsinghua researchers broke Dijkstra’s 1984 “sorting barrier,” achieving O(m log^(2/3) n) time. This means faster route planning, less traffic, cheaper deliveries, and more efficient networks - and a CS curriculum revamp =)
338
3K
30K
MD-LLM-1: A Large Language Model for Molecular Dynamics 1. Researchers have developed MD-LLM-1, a novel framework that leverages large language models (LLMs) to simulate molecular dynamics. This approach enables the prediction of protein conformational states not seen during
2
20
127
Towards universal modeling of transcript isoform expression levels https://t.co/eK245WDeTM
#biorxiv_bioinfo
biorxiv.org
A holy grail in computational biology is accurate modeling of transcript expression levels using epigenetic features, which would provide a quantitative way to study gene regulation in normal and...
0
4
14
Tommaso Mazza presents nAPOGEE: a new tool to predict the pathogenicity of non-coding mtDNA variants in tRNAs and rRNAs her at #BITS2025
@irongraft
0
4
5
Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀
48
406
2K
We are pleased to announce the release of the MITOMAP track for hg38/hg19. MITOMAP is a human mitochondrial genome database. This release includes the MITOMAP Control and Coding Variants track & the MITOMAP Disease Mutations track. Learn more at https://t.co/zcDDaYyJsd.
0
6
31
PUBMED is down. disaster !! We don’t have the organization to replace it. (EuroPMC is great but not a replacement) It is crystal clear that we cannot depend on critical systems from a single provider. European reaction has to include science and science infrastructures.
8
61
160
Topological embedding and directional feature importance in ensemble classifiers for multi-class classification. Read the article here: https://t.co/f9ILlwhTOq
0
1
0
RNA-protein interaction prediction without high-throughput data: An overview and benchmark of in silico tools. Read the article here: https://t.co/Sy3qKHXo0W
0
1
0
Another year of fun and successes behind us. Here's to a #newyear with new exciting #challenges and joyful #moments. #HappyNewYear #Bioinformatics #research
0
6
6