←
caithmac320 posts
caithmac avatar

caithmac

@caithmac

I will build in public! What tho? My life. PhD Computer Science (ongoing) Computer Vision,ML/DL, Philosophy,History.

◷ Joined March 2024▧ 109 Photos and videos
caithmac avatar
caithmac@caithmac·Apr 2

We just published our work on an explainable active learning framework for ligand–protein binding affinity prediction in Digital Discovery. 🔗 pubs.rsc.org/en/content/arti… Here’s a quick breakdown of what we did and why 👇

caithmac avatar
caithmac@caithmac·Apr 2

SHAP analysis revealed chemically meaningful features driving predictions. The model learns to focus on SAR-relevant motifs over time. We identified key fragments for high affinity (e.g., halogens for TYK2).

Post attachment
caithmac avatar
caithmac@caithmac·Apr 2

Big thanks to all collaborators and reviewers who helped improve the work. @gorantlarohan @ppxasjsm If you’re working on: • drug discovery • active learning • explainable ML we’d love to hear your thoughts!

caithmac avatar
caithmac@caithmac·Apr 2

This is not a final solution, but a step toward: • More transparent ML models • Better human–AI collaboration in science • Active learning systems that scientists can actually trust

caithmac avatar
caithmac@caithmac·Apr 2

Why this matters: In real drug discovery workflows, every experiment is costly. If we can select better data points and explain why, we reduce both cost and uncertainty.

caithmac avatar
caithmac@caithmac·Apr 2

One interesting observation: The samples selected by our method are not just “uncertain” they often correspond to meaningful interaction patterns. This gives more confidence in the active learning loop.

caithmac avatar
caithmac@caithmac·Apr 2

We evaluate the framework across multiple settings and compare against standard baselines. Key takeaway: We can maintain (or improve) performance while gaining explainability.

caithmac avatar
caithmac@caithmac·Apr 2

Instead of just predicting affinity, the model provides insight into: 👉 Which parts of the ligand and protein matter 👉 Why a sample is selected during active learning This helps move from “prediction” → “understanding”.

caithmac avatar
caithmac@caithmac·Apr 2

Our goal was simple: 👉 Build an active learning framework that is not only effective 👉 But also explainable So that model decisions can be inspected, trusted, and potentially acted upon.

caithmac avatar
caithmac@caithmac·Apr 2

Most active learning methods are black boxes. They may pick good samples, but don’t tell us why those samples are useful. In drug discovery, that lack of interpretability is a real limitation.

caithmac avatar
caithmac@caithmac·Apr 2

Predicting binding affinity is central to drug discovery, but data is expensive. Active learning helps by selecting which experiments to run next, instead of blindly collecting more data. But there’s a problem…

bioRxiv Biophysics avatar
⟳ caithmac retweeted
bioRxiv Biophysics@biorxiv_biophys·20 Dec 2025

Explainable Active Learning Framework for Ligand BindingAffinity Prediction biorxiv.org/content/10.64898… #biorxiv_biophys

caithmac avatar
caithmac@caithmac·7 Dec 2025

As soon as I tell Gemini that this was my paper. I get praised instead of criticism. Lol!

Post attachment