| 1. |
- Shrine, N, et al.
(författare)
-
Multi-ancestry genome-wide association analyses improve resolution of genes and pathways influencing lung function and chronic obstructive pulmonary disease risk
- 2023
-
Ingår i: Nature genetics. - : Springer Science and Business Media LLC. - 1546-1718 .- 1061-4036. ; 55:3, s. 410-
-
Tidskriftsartikel (refereegranskat)abstract
- Lung-function impairment underlies chronic obstructive pulmonary disease (COPD) and predicts mortality. In the largest multi-ancestry genome-wide association meta-analysis of lung function to date, comprising 580,869 participants, we identified 1,020 independent association signals implicating 559 genes supported by ≥2 criteria from a systematic variant-to-gene mapping framework. These genes were enriched in 29 pathways. Individual variants showed heterogeneity across ancestries, age and smoking groups, and collectively as a genetic risk score showed strong association with COPD across ancestry groups. We undertook phenome-wide association studies for selected associated variants as well as trait and pathway-specific genetic risk scores to infer possible consequences of intervening in pathways underlying lung function. We highlight new putative causal variants, genes, proteins and pathways, including those targeted by existing drugs. These findings bring us closer to understanding the mechanisms underlying lung function and COPD, and should inform functional genomics experiments and potentially future COPD therapies.
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
- Wang, Qiang, et al.
(författare)
-
Dexterous robotic manipulation using deep reinforcement learning and knowledge transfer for complex sparse reward-based tasks
- 2023
-
Ingår i: Expert systems (Print). - : Wiley. - 0266-4720 .- 1468-0394. ; 40:6
-
Tidskriftsartikel (refereegranskat)abstract
- This paper describes a deep reinforcement learning (DRL) approach that won Phase 1 of the Real Robot Challenge (RRC) 2021, and then extends this method to a more difficult manipulation task. The RRC consisted of using a TriFinger robot to manipulate a cube along a specified positional trajectory, but with no requirement for the cube to have any specific orientation. We used a relatively simple reward function, a combination of a goal-based sparse reward and a distance reward, in conjunction with Hindsight Experience Replay (HER) to guide the learning of the DRL agent (Deep Deterministic Policy Gradient [DDPG]). Our approach allowed our agents to acquire dexterous robotic manipulation strategies in simulation. These strategies were then deployed on the real robot and outperformed all other competition submissions, including those using more traditional robotic control techniques, in the final evaluation stage of the RRC. Here we extend this method, by modifying the task of Phase 1 of the RRC to require the robot to maintain the cube in a particular orientation, while the cube is moved along the required positional trajectory. The requirement to also orient the cube makes the agent less able to learn the task through blind exploration due to increased problem complexity. To circumvent this issue, we make novel use of a Knowledge Transfer (KT) technique that allows the strategies learned by the agent in the original task (which was agnostic to cube orientation) to be transferred to this task (where orientation matters). KT allowed the agent to learn and perform the extended task in the simulator, which improved the average positional deviation from 0.134 to 0.02 m, and average orientation deviation from 142° to 76° during evaluation. This KT concept shows good generalization properties and could be applied to any actor-critic learning algorithm.
|
|
