1st ASCS: Expanding the ISCB Student Council Symposia to Asia.

Since 2004, the ISCB Student Council (ISCB-SC) has successfully organized Student Council Symposia across several continents, including North America, Latin America, Europe, and Africa, as well as local events led by more than 25 Regional Student Groups (RSG) across the world. The ISCB-SC Symposia provide students and early career researchers the chance to showcase their work at an international venue in a format that includes keynote talks, round table discussions, workshops, and more. After several efforts spanning several years to build enough critical mass in the region, we have successfully organized the first Asian Student Council Symposium (1st ASCS). This article discusses the organizational details of this unprecedented event, the challenges faced, and the lessons learned.

ISCB Student Council Symposium 2021, a virtual global venue: challenges and lessons learned.

Since 2004, the ISCB Student Council has been organizing different symposia worldwide, gathering together the community of young computational biologists. Due to the coronavirus disease 2019 (COVID-19) pandemic situation, the world scientific community was forced to cancel in-person meetings for almost two years, imposing the adoption of virtual formats instead. After the successful editions of our continental symposia in 2020 in the USA, Latin America, and Europe, we organized our flagship global event, the Student Council Symposium (SCS) 2021, trying to apply all previous lessons learned and to exploit the advantages that virtuality has to offer.

MHCAttnNet: predicting MHC-peptide bindings for MHC alleles classes I and II using an attention-based deep neural model.

MOTIVATION: Accurate prediction of binding between a major histocompatibility complex (MHC) allele and a peptide plays a major role in the synthesis of personalized cancer vaccines. The immune system struggles to distinguish between a cancerous and a healthy cell. In a patient suffering from cancer who has a particular MHC allele, only those peptides that bind with the MHC allele with high affinity, help the immune system recognize the cancerous cells. RESULTS: MHCAttnNet is a deep neural model that uses an attention mechanism to capture the relevant subsequences of the amino acid sequences of peptides and MHC alleles. It then uses this to accurately predict the MHC-peptide binding. MHCAttnNet achieves an AUC-PRC score of 94.18% with 161 class I MHC alleles, which outperforms the state-of-the-art models for this task. MHCAttnNet also achieves a better F1-score in comparison to the state-of-the-art models while covering a larger number of class II MHC alleles. The attention mechanism used by MHCAttnNet provides a heatmap over the amino acids thus indicating the important subsequences present in the amino acid sequence. This approach also allows us to focus on a much smaller number of relevant trigrams corresponding to the amino acid sequence of an MHC allele, from 9251 possible trigrams to about 258. This significantly reduces the number of amino acid subsequences that need to be clinically tested. AVAILABILITY AND IMPLEMENTATION: The data and source code are available at https://github.com/gopuvenkat/MHCAttnNet.