Mirko Torrisi

Mirko Torrisi

Senior AI Engineer

Openchip

Biography

I am the technical lead for Sustainable AI at Openchip in Barcelona, where I drive sustainable AI initiatives, maintaining a holistic perspective while leading the definition and assessment of resource-aware solutions. Previously, I focused on characterizing molecular interactions and omics data at Bristol Myers Squibb through the application of deep learning techniques. I am deeply fascinated by the potential of representation learning to effectively decipher the continually expanding body of human knowledge and, in turn, advance it.

During my PhD with Dr. Gianluca Pollastri, I focused on Predicting Protein Structural Annotations by Deep and Shallow Learning at University College Dublin, Ireland. I visited Dr. Pierre Baldi’s lab at the University of California, Irvine in 2018. I hold a BSc in Informatics with the highest honour from Università degli Studi di Catania, Italy.

Beyond my research endeavours, I am also passionate about topics related to environmental sustainability, and enjoy hiking, snowboarding, and cycling.

Interests

  • Deep Learning
  • Bioinformatics
  • Sustainability
  • Climbing
  • Snowboarding

Education

  • PhD in Computer Science, 2020

    University College Dublin, Ireland

  • Visiting Scholar, 2018

    University of California, Irvine, US

  • BSc in Informatics, 2015

    University of Catania, Italy

Recent Publications

Quickly discover relevant content by filtering publications.

Do chemical language models provide a better compound representation?

In recent years, several chemical language models have been developed, inspired by the success of protein language models and …
PDF DOI

Improving the assessment of deep learning models in the context of drug-target interaction prediction

Machine Learning techniques have been widely adopted to predict drug-target interactions, a central area of research in early drug …
PDF DOI

Protein profiles: Biases and protocols

The use of evolutionary profiles to predict protein secondary structure, as well as other protein structural features, has been …
PDF Code DOI

Brewery: Deep Learning and deeper profiles for the prediction of 1D protein structure annotations

Motivation: Protein Structural Annotations are essential abstractions to deal with the prediction of Protein Structures. Many …
PDF Code DOI

Deep learning methods in protein structure prediction

Protein Structure Prediction is a central topic in Structural Bioinformatics. Since the ’60s statistical methods, followed by …
PDF DOI
See all publications

Software

EVALpro

Evaluate the accuracy of a profile-based predictor as a function of the max cosine similarity between training and test profiles.

Brewery

State-of-the-art ab initio prediction of 1D protein structure annotations

Porter

State-of-the-art ab initio prediction of protein secondary structure

Contact