2022-12-19, Robert, Philippe A., Akbar, Rahmad, Frank, Robert, Pavlović, Milena, Widrich, Michael, Snapkov, Igor, Slabodkin, Andrei, Chernigovskaya, Maria, Scheffer, Lonneke, Smorodina, Eva, Rawat, Puneet, Mehta, Brij Bhushan, Vu, Mai Ha, Mathisen, Ingvild Frøberg, Prósz, Aurél, Abram, Krzysztof, Olar, Alex, Miho, Enkelejda, Haug, Dag Trygve Tryslew, Lund-Johansen, Fridtjof, Hochreiter, Sepp, Haff, Ingrid Hobæk, Klambauer, Günter, Sandve, Geir Kjetil, Greiff, Victor

Machine learning (ML) is a key technology for accurate prediction of antibody–antigen binding. Two orthogonal problems hinder the application of ML to antibody-specificity prediction and the benchmarking thereof: the lack of a unified ML formalization of immunological antibody-specificity prediction problems and the unavailability of large-scale synthetic datasets to benchmark real-world relevant ML methods and dataset design. Here we developed the Absolut! software suite that enables parameter-based unconstrained generation of synthetic lattice-based three-dimensional antibody–antigen-binding structures with ground-truth access to conformational paratope, epitope and affinity. We formalized common immunological antibody-specificity prediction problems as ML tasks and confirmed that for both sequence- and structure-based tasks, accuracy-based rankings of ML methods trained on experimental data hold for ML methods trained on Absolut!-generated data. The Absolut! framework has the potential to enable real-world relevant development and benchmarking of ML strategies for biotherapeutics design.

2022-08-05, Cascino, Pasquale, Nevone, Alice, Piscitelli, Maggie, Scopelliti, Claudia, Girelli, Maria, Mazzini, Giulia, Caminito, Serena, Russo, Giancarlo, Milani, Paolo, Basset, Marco, Foli, Andrea, Fazio, Francesca, Casarini, Simona, Massa, Margherita, Bozzola, Margherita, Ripepi, Jessica, Sesta, Melania Antonietta, Acquafredda, Gloria, De Cicco, Marica, Moretta, Antonia, Rognoni, Paola, Milan, Enrico, Ricagno, Stefano, Lavatelli, Francesca, Petrucci, Maria Teresa, Miho, Enkelejda, Klersy, Catherine, Merlini, Giampaolo, Palladini, Giovanni, Nuvolone, Mario

2019-03-21, Miho, Enkelejda

The architecture of mouse and human antibody repertoires is defined by the sequence similarity networks of the clones that compose them. The major principles that define the architecture of antibody repertoires have remained largely unknown. Here, we establish a high-performance computing platform to construct large-scale networks from comprehensive human and murine antibody repertoire sequencing datasets (>100,000 unique sequences). Leveraging a network-based statistical framework, we identify three fundamental principles of antibody repertoire architecture: reproducibility, robustness and redundancy. Antibody repertoire networks are highly reproducible across individuals despite high antibody sequence dissimilarity. The architecture of antibody repertoires is robust to the removal of up to 50–90% of randomly selected clones, but fragile to the removal of public clones shared among individuals. Finally, repertoire architecture is intrinsically redundant. Our analysis provides guidelines for the large-scale network analysis of immune repertoires and may be used in the future to define disease-associated and synthetic repertoires.

2019, Brown, Alex J., Snapkov, Igor, Akbar, Rahmad, Pavlović, Milena, Miho, Enkelejda, Sandve, Geir K., Greiff, Victor

The adaptive immune system is a natural diagnostic sensor and therapeutic. It recognizes threats earlier than clinical symptoms manifest and neutralizes antigens with exquisite specificity. Recognition specificity and broad reactivity are enabled via adaptive B- and T-cell receptors: the immune receptor repertoire. The human immune system, however, is not omnipotent. Our natural defense system sometimes loses the battle to parasites and microbes and even turns against us in the case of cancer and (autoimmune) inflammatory disease. A long-standing dream of immunoengineers has been, therefore, to mechanistically understand how the immune system “sees”, “reacts” and “remembers” (auto)antigens. Only very recently, experimental and computational methods have achieved sufficient quantitative resolution to start querying and engineering adaptive immunity with high precision. Specifically, these innovations have been applied with the greatest fervency and success in immunotherapy, autoimmunity and vaccine design. The work here highlights advances, challenges and future directions of quantitative approaches which seek to advance the fundamental understanding of immunological phenomena, and reverse engineer the immune system to produce auspicious biopharmaceutical drugs and immunodiagnostics. Our review shows how the merger of fundamental immunology, computational immunology and (digital) biotechnology advances both immunological knowledge and immunoengineering methodologies.

2022-12-19, Robert, Philippe A., Akbar, Rahmad, Pavlović, Milena, Widrich, Michael, Snapkov, Igor, Slabodkin, Andrei, Chernigovskaya, Maria, Scheffer, Lonneke, Smorodina, Eva, Rawat, Puneet, Mehta, Brij Bhushan, Vu, Mai Ha, Mathisen, Ingvild Frøberg, Prósz, Aurél, Abram, Krzysztof, Olar, Axel, Miho, Enkelejda, Haug, Dag Trygve Tryslew, Lund-Johansen, Fridtjof, Hochreiter, Sepp, Hobæk Haff, Ingrid, Klambauer, Günter, Sandve, Geir Kjetil, Greiff, Victor

Machine learning (ML) is a key technology for accurate prediction of antibody–antigen binding. Two orthogonal problems hinder the application of ML to antibody-specificity prediction and the benchmarking thereof: the lack of a unified ML formalization of immunological antibody-specificity prediction problems and the unavailability of large-scale synthetic datasets to benchmark real-world relevant ML methods and dataset design. Here we developed the Absolut! software suite that enables parameter-based unconstrained generation of synthetic lattice-based three-dimensional antibody–antigen-binding structures with ground-truth access to conformational paratope, epitope and affinity. We formalized common immunological antibody-specificity prediction problems as ML tasks and confirmed that for both sequence- and structure-based tasks, accuracy-based rankings of ML methods trained on experimental data hold for ML methods trained on Absolut!-generated data. The Absolut! framework has the potential to enable real-world relevant development and benchmarking of ML strategies for biotherapeutics design.

2019-12-24, Smakaj, Erand, Babrak, Lmar, Tosoni, Deniz David, Galli, Christa, Miho, Enkelejda

2019-01-28, Miho, Enkelejda

2022-08-23, Cascino, Pasquale, Nevone, Alice, Piscitelli, Maggie, Scopelliti, Claudia, Girelli, Maria, Mazzini, Giulia, Caminito, Serena, Russo, Giancarlo, Milani, Paolo, Basset, Marco, Foli, Andrea, Fazio, Francesca, Casarini, Simona, Massa, Margherita, Bozzola, Margherita, Ripepi, Jessica, Sesta, Melania Antonietta, Acquafredda, Gloria, De Cicco, Marica, Moretta, Antonia, Rognoni, Paola, Milan, Enrico, Ricagno, Stefano, Lavatelli, Francesca, Petrucci, Maria Teresa, Klersy, Catherine, Merlini, Giampaolo, Palladini, Giovanni, Nuvolone, Mario, Miho, Enkelejda

Each patient with a monoclonal gammopathy has a unique monoclonal (M) protein, whose sequence can be used as a tumoral fingerprint to track the presence of the B cell or plasma cell (PC) clone itself. Moreover, the M protein can directly cause potentially life-threatening organ damage, which is dictated by the specific, patient's unique clonal light and/or heavy chain amino acid sequence, as in patients affected by immunoglobulin light chain (AL) amyloidosis.1 However, patients' specific M protein sequences remain mostly undefined and molecular mechanisms underlying M protein-related clinical manifestations are largely obscure.

2019-09-17, Miho, Enkelejda

2019-01-17, Miho, Enkelejda