iiinova — where your digital self keeps evolving

Alessandra Carbone @alecarbone.bsky.social · 06/08/2026

What if protein language model embeddings could collaborate to reveal what proteins do and which residues determine their function? Applied to thioredoxins, visual opsins, cold-shock proteins from environmental diatoms in #TaraOceans. In bioRxiv: lnkd.in/eaAFAYJW #ProteinScience #MarineGenomics

052

Alessandra Carbone @alecarbone.bsky.social · 24/07/2026

Our new results on PPI reconstructions are out! X-PAIR: an ultrafast multitask framework for proteome-scale reconstruction of PPI networks and partner-specific interfaces from sequence biorxiv.org/content/10.6... Retweet it. Great work with Sara Rescalli.

020

Alessandra Carbone @alecarbone.bsky.social · 28/09/2025

We connected molecular signatures of selection with their mechanistic and functional relevance opening new ways of guiding experimental assays without requiring exhaustive testing of tens or hundreds of candidates. Read in Molecular Biology and Evolution: academic.oup.com/mbe/advance-...

052

Alessandra Carbone @alecarbone.bsky.social · 06/05/2025

PRESCOTT online in Genome Biology! see how it works on differentiating mutational effects across isoforms, on unique genetic heritage, recessive and dominant inheritance modes, gain-of-function mutations at link.springer.com/article/10.1.... Work done with M.Tekpinar T.Henry L.David

link.springer.com

PRESCOTT: a population aware, epistatic, and structural model accurately predicts missense effects - Genome Biology

Predicting the functional impact of point mutations is a critical challenge in genomics. PRESCOTT reconstructs complete mutational landscapes, identifies mutation-sensitive regions, and categorizes mi...

000

Alessandra Carbone @alecarbone.bsky.social · 20/02/2025

Designing a functional switch? We recoded a function of Chlamydomonas reinhardtii thioredoxin type-h into a photosynthetic type-f by switching selectivity determinants. Soon out in Frontiers in Plant Science: lnkd.in/emVPNHHa with Julien Henri, Stephane Lemaire, Gianluca Lombardi and Andrea Mancini.

010

Alessandra Carbone @alecarbone.bsky.social · 08/02/2025

Diversifying disorders by distinguishing intrinsic and soft disorders, improves our understanding of proteins. See our new preprint on "LoRA-DR-suite: adapted embeddings predict intrinsic and soft disorder from protein sequences" - lnkd.in/esSD3qxq work done with Beatriz Seoane and Gianluca Lombardi

010

Alessandra Carbone @alecarbone.bsky.social · 01/02/2025

Postdoc position on Al-Driven Discovery of Next-Gen Antibiotics. Join my team! Please, forward it. hashtag#AI hashtag#MachineLearningandAI hashtag#Artificialintelligence hashtag#MachineLearning hashtag#protein

030