Samad Amini

Boltz-2 has enabled accurate binding affinity prediction by leveraging co-folded protein–ligand structures, but the absence of a public training recipe has limited its use in active drug discovery projects, where new experimental measurements and congeneric ligand series continually arrive during lead optimization. We present an open framework for affinity fine-tuning of Boltz-2, showing that adapting only the affinity prediction components with project-specific experimental data can make the model substantially more useful for lead optimization. We evaluate the approach in two internal studies: a multi-target retrospective benchmark against physics-based and machine learning baselines, and a large single-target study with up to 1,700 ligands. In both settings, fine-tuned Boltz-2 improves correlation over the off-the-shelf model, and in some cases reaches performance competitive with free energy perturbation (FEP) methods. By releasing this framework, we aim to enable the community to adapt Boltz-2 to the specific targets and data of their own drug discovery campaigns. The code is available at: https://github.com/molecularinformatics/Boltz2_affinity

1. Monoclonal antibodies (mAbs) have emerged as one of the most successful classes of biotherapeutics, with over 200 FDA-approved antibodies currently in clinical use.1,2 Their high specificity and...

INTRODUCTION: Identification of individuals with mild cognitive impairment (MCI) who are at risk of developing Alzheimer's disease (AD) is crucial for early intervention and selection of clinical trials.METHODS: We applied natural language processing techniques along with machine learning methods to develop a method for automated prediction of progression to AD within 6 years using speech. The study design was evaluated on the neuropsychological test interviews of n = 166 participants from the Framingham Heart Study, comprising 90 progressive MCI and 76 stable MCI cases.RESULTS: Our best models, which used features generated from speech data, as well as age, sex, and education level, achieved an accuracy of 78.5% and a sensitivity of 81.1% to predict MCI‐to‐AD progression within 6 years.DISCUSSION: The proposed method offers a fully automated procedure, providing an opportunity to develop an inexpensive, broadly accessible, and easy‐to‐administer screening tool for MCI‐to‐AD progression prediction, facilitating development of remote assessment.Highlights: Voice recordings from neuropsychological exams coupled with basic demographics can lead to strong predictive models of progression to dementia from mild cognitive impairment. The study leveraged AI methods for speech recognition and processed the resulting text using language models. The developed AI‐powered pipeline can lead to fully automated assessment that could enable remote and cost‐effective screening and prognosis for Alzehimer's disease.

Background: Widespread early dementia detection could drastically increase clinical trial candidates and enable early interventions. Since the Clock Drawing Test (CDT) can be potentially used for diagnosing dementia related diseases, it can be leveraged to devise a computer-aided screening tool. Objective: This work aims to develop an online screening tool by leveraging Artificial Intelligence and the CDT. Methods: Images of an analog clock drawn by 3, 263 cognitively intact and 160 impaired subjects were used. First, we processed the images from the CDT by a deep learning algorithm to obtain dementia scores. Then, individuals were classified as belonging to either category by combining CDT image scores with the participant’s age. Results: We have evaluated the performance of the developed models by applying 5-fold cross validation on 20% of the dataset. The deep learning model generates dementia scores for the CDT images with an Area Under the ROC Curve (AUC) of 81.3% ± 4.3%. A composite logistic regression model using age and the generated dementia scores, yielded an average AUC and average weighted F1 score of 92% ± 0.8% and 94.4% ± 0.7%, respectively. Discussion: CDT images were subjected to distortion consistent with an image drawn on paper and photographed by a cell phone. The model offers a cost-effective and easily deployable mechanism for detecting cognitive impairment online, without the need to visit a clinic.