Overview
Philippe Herman is Chief Executive Officer of immunochem, a role he has held since December 2019. He is based in Chaumont-Gistoux and works in antibody engineering and bioinformatics.
Between April 2019 and July 2021 he was a project manager at Ansers Analytical Services. Before that he spent a year as a postdoctoral researcher at ETH Zürich, from April 2018 to April 2019, and completed a postgraduate degree in protein engineering at the ETH Department of Biosystems Science and Engineering over the same period.
His earlier career was at the Université catholique de Louvain, where he carried out his master's thesis from September 2011 to September 2012, completed a PhD in biophysics on the force nanoscopy of staphylococcal adhesion between October 2012 and April 2016, and then undertook postdoctoral studies in biophysics until April 2018. He holds a bachelor's and a master's degree in bioengineering and biomedical engineering from the same university. In October 2021 he took a course in GMP basics and pharmaceutical design at aptaskil.
Career history
In the news
- Great news! IMMUNOCHEM has been approved by the NVIDIA Inception Program 🎖️ 💫 We received this : « WELCOME TO NVIDIA INCEPTION! We're pleased to inform you that Immunochem's NVIDIA Inception Program application was approved. Congratulations on joining an elite group of startups leading change across industries and around the world. » Being part of this program is a reminder that the vision is right. I'm grateful. And ready for what's next! 🫶 Phil. PS: I've launched EVOBody™, a unique platform allowing biotech leaders to
- Generating single-domain antibody from scratch in 2026 is a quick and ideal way to address your targets. 👉Follow the guide. I put together a quick 5-step guide that walks you through the full process of single-domain antibody (aka #nanobody or VHH) generation, from target definition, VHH design and generation, to validation. Two things that surprise Scientists the most: ✅ The AI step reduces weeks of experimental screening to a few days ✅You don't need a full immunology team to get started! Keep it rational. Phil. PS: I've launched
- 4 weeks. The quicker time we got for VHHs generation from scratch That's our record at IMMUNOCHEM. The fastest we've ever generated functional VHHs from scratch. When I told this to the client, his reaction was immediate: "Philippe… I did not believe we would succeed." I understood the skepticism because for decades, antibody generation has been synonymous with 6 to 12-month timelines. So when someone tells you 4 weeks, it sounds like a magic trick. 🎩 But it is magic. It is process. Here's what made it possible: 1️⃣
- Good job! All three AI-designed nanobodies beat our lab-validated benchmark! (🎥 Designing nanobody Ep10 ) This episode closes the design campaign I opened nine posts ago. Here's the final comparison : 🚩 On one side, the 8SKJ crystal structure, the real, experimentally resolved binding mode we started from. 🚩 On the other, our three finalists, the survivors of 14,000 designs, 362 candidates, 123 shortlisted, and 100 nanoseconds of molecular dynamics each! Results : ✅ All three maintain a truly deep, buried interface with the V5
- Three things keep me showing up every morning. Of course one of them is science. 🫶 Running a biotech startup asks a lot of you. Here's what actually keeps me going. 👩🔬 The science is genuinely exciting We're working at a frontier that didn't exist a couple of years, even months, ago. AI-designed antibodies. Computational protein engineering. It's a real shift, and we get to be inside it. 🧙♂️ The people Working with passionate scientists who care about what they build changes the energy of every single day. That's rare, and
- Molecular Dymanics must be the last filter in your pipeline (🎥 Designing nanobody Ep9 ) Out of our 123 candidates, for this example, we selected just 3, the top of our funnel, for this final Molecular Dynamics (MD) validation step 💪 Every step so far has been AI: diffusion, inverse folding, ESM2Fold, Boltz2X. MD is not, it's grounded in the physical world, meaning that it simulates physics. ✅ MD is a toolbox that resolves Newtonian equations. ✅ There's no model guessing here We run each of the 3 designs for 100 nanoseconds of
- How convergence separates good designs from lucky ones. (🎥 Designing nanobody Ep8 ) After the multi-seed REC8 screen, we were left with 362 candidates. It is good enough to survive noise, but not good enough to trust with a wet lab budget yet 🙃 For this next cut, let's bring in a second, independent model: Boltz2X, alongside ESM2Fold, and we'll run convergence between the two. We keep the same multi-seed logic as before, no single lucky fold saves a candidate here! 📈 The bar goes up too. Where the first pass only asked for 3
- Learning to sell a vision to people who will probably never handle a pipette. Years ago, my first investor pitch, I opened with twelve slides… on mechanism of action 😅 CDR loops. Binding kinetics. A full slide dedicated to epitope mapping strategy. OUAW, I was so proud of that slide! 😎 Ten minutes in, one of the investors gently stopped me saying : "Philippe, I don't need to understand the biology. I need to understand why this makes money, and why you're the one who can make it happen." I remember the silence after that
This page shows public professional information only, each fact cited. Is this you? send a correction, or ask for removal within 24 hours, no questions asked.