Varun Ullanat

We introduce 🌿 MINT (Multimer Interaction Transformer) – a Protein Language Model (PLM) trained on 96M protein-protein interactions (PPIs) to predict binding affinity, mutational impacts, & antibody interactions better than existing PLMs. 🔗Code: github.com/VarunUllanat/m… 🧵👇

Predicting clinical outcomes of drug combinations from preclinical data is a major challenge @YepHuang We know a drug works in the lab. But will it work in patients? 🔬 ➡️ 🏥 This is key for safe and effective therapies and it's one of the hardest challenges in medicine. MADRIGAL is a multimodal AI model that predicts clinical outcomes of drug combinations from preclinical data 🧵 Why does this matter? Combo therapies can improve efficacy and reduce side effects, but identifying safe and effective pairs is difficult. The search space is enormous, pharmacological interactions are complex, and many compounds lack complete preclinical data The missing data problem Most AI models struggle when key drug data is missing. MADRIGAL learns from incomplete datasets at both training and inference, making it capable of predicting clinical outcomes even for drugs with sparse data What is MADRIGAL? A multimodal AI model that integrates 21,842 compounds and predicts 953 clinical outcomes to assess: ✔️ New drug combinations ✔️ Drug safety and toxicity across organs ✔️ Personalized response using patient genomic data Led by a stellar PhD student @YepHuang with a team of fantastic collaborators @xiaorui_su, Varun Ullanat, Ivy Liang, Lindsay Clegg, Damilola Olabode, Nicholas Ho, Bino John, Megan Gibbs @HarvardDBMI @Harvard @harvardmed @broadinstitute @KempnerInst @harvard_data

Happy to share our work on dynamics of coupled cellular decision-making feedback loops in @BiosciencesOf @IAScBng, led by @kishorehari139 & @PradyumnaVH @BSSE_IISc, with contributions from Aditi & @VUllanat (BTech students @RvceUpdates), @TheAviatorFrame. link.springer.com/article/10.100…

PriSM (precision for integrative structural models) is now in press. It is an efficient method to annotate high and low-precision regions in integrative models. @VUllanat and @n_kasukurthi did all the hard work, moving fast and breaking things! academic.oup.com/bioinformatics…

This week in #MathOnco 1⃣9⃣4⃣: <life histories, network models of plasticity, model-informed precision dosing, coordination games, Hawk-Dove control theory, and more> thisweekmathonco.substack.com/p/this-week-in… Cover art by: @TheAviatorFrame & @kishorehari139 💯😎

Excited to share our preprint on how "teams" of epithelial & mesenchymal drivers inhibiting each other drive the landscape of large regulatory networks, thus driving canalisation of cell phenotypes biorxiv.org/content/10.110… Plz check out the thread (1/6) @MenonBioPhysics @rikdrprof